fix: surface actionable error when DuckDuckGo web search is rate-limited

Non-Anthropic / non-codex providers (minimax, kimi, generic OpenAI-compatible)
fell through to the DDG adapter when no paid search key was configured. DDG's
scraper is blocked on most IPs, so web_search surfaced an opaque "anomaly in
the request" error. Catch that response in the DDG provider and rethrow with
the exact env vars that would unblock the tool, or the option to switch to a
native-search provider.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

.dockerignore

@@ -0,0 +1,16 @@
+node_modules
+dist
+.git
+.gitignore
+.env
+.env.*
+!.env.example
+coverage
+reports
+vscode-extension
+python
+docs
+*.md
+!README.md
+.github
+.tsbuildinfo

.env.example

@@ -225,6 +225,30 @@ ANTHROPIC_API_KEY=sk-ant-your-key-here
 # GOOGLE_CLOUD_PROJECT=your-gcp-project-id
 
 
+# -----------------------------------------------------------------------------
+# Option 9: NVIDIA NIM
+# -----------------------------------------------------------------------------
+# NVIDIA NIM provides hosted inference endpoints for NVIDIA models.
+# Get your API key from https://build.nvidia.com/
+#
+# CLAUDE_CODE_USE_OPENAI=1
+# NVIDIA_API_KEY=nvapi-your-key-here
+# OPENAI_BASE_URL=https://integrate.api.nvidia.com/v1
+# OPENAI_MODEL=nvidia/llama-3.1-nemotron-70b-instruct
+
+
+# -----------------------------------------------------------------------------
+# Option 10: MiniMax
+# -----------------------------------------------------------------------------
+# MiniMax API provides text generation models.
+# Get your API key from https://platform.minimax.io/
+#
+# CLAUDE_CODE_USE_OPENAI=1
+# MINIMAX_API_KEY=your-minimax-key-here
+# OPENAI_BASE_URL=https://api.minimax.io/v1
+# OPENAI_MODEL=MiniMax-M2.5
+
+
 # =============================================================================
 # OPTIONAL TUNING
 # =============================================================================
@@ -243,6 +267,11 @@ ANTHROPIC_API_KEY=sk-ant-your-key-here
 # Disable "Co-authored-by" line in git commits made by OpenClaude
 # OPENCLAUDE_DISABLE_CO_AUTHORED_BY=1
 
+# Disable strict tool schema normalization for non-Gemini providers
+# Useful when MCP tools with complex optional params (e.g. list[dict])
+# trigger "Extra required key ... supplied" errors from OpenAI-compatible endpoints
+# OPENCLAUDE_DISABLE_STRICT_TOOLS=1
+
 # Custom timeout for API requests in milliseconds (default: varies)
 # API_TIMEOUT_MS=60000
 

.github/workflows/release.yml

@@ -11,6 +11,7 @@ concurrency:
 
 jobs:
   release-please:
+    if: ${{ github.repository == 'Gitlawb/openclaude' }}
     name: Release Please
     runs-on: ubuntu-latest
     permissions:
@@ -86,3 +87,58 @@ jobs:
             echo "- npm: https://www.npmjs.com/package/@gitlawb/openclaude"
             echo "- GitHub: https://github.com/Gitlawb/openclaude/releases/tag/${{ needs.release-please.outputs.tag_name }}"
           } >> "$GITHUB_STEP_SUMMARY"
+
+  docker:
+    name: Build & Push Docker Image
+    needs: release-please
+    if: ${{ needs.release-please.outputs.release_created == 'true' }}
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+    steps:
+      - name: Checkout release tag
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        with:
+          ref: ${{ needs.release-please.outputs.tag_name }}
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
+
+      - name: Log in to GitHub Container Registry
+        uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata
+        id: meta
+        uses: docker/metadata-action@902fa8ec7d6ecbf8d84d538b9b233a880e428804 # v5.7.0
+        with:
+          images: ghcr.io/${{ github.repository }}
+          tags: |
+            type=semver,pattern={{version}},value=${{ needs.release-please.outputs.version }}
+            type=semver,pattern={{major}}.{{minor}},value=${{ needs.release-please.outputs.version }}
+            type=raw,value=latest
+
+      - name: Build and load locally
+        uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
+        with:
+          context: .
+          load: true
+          tags: openclaude:smoke
+          cache-from: type=gha
+
+      - name: Smoke test
+        run: docker run --rm openclaude:smoke --version
+
+      - name: Build and push
+        uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
+        with:
+          context: .
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max

.gitignore

@@ -7,6 +7,8 @@ dist/
 .openclaude-profile.json
 reports/
 GEMINI.md
+CLAUDE.md
 package-lock.json
 /.claude
 coverage/
+agent.log

.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "0.2.2"
+  ".": "0.6.0"
 }

CHANGELOG.md

@@ -1,5 +1,120 @@
 # Changelog
 
+## [0.6.0](https://github.com/Gitlawb/openclaude/compare/v0.5.2...v0.6.0) (2026-04-22)
+
+
+### Features
+
+* add model caching and benchmarking utilities ([#671](https://github.com/Gitlawb/openclaude/issues/671)) ([2b15e16](https://github.com/Gitlawb/openclaude/commit/2b15e16421f793f954a92c53933a07094544b29d))
+* add thinking token extraction ([#798](https://github.com/Gitlawb/openclaude/issues/798)) ([268c039](https://github.com/Gitlawb/openclaude/commit/268c0398e4bf1ab898069c61500a2b3c226a0322))
+* **api:** compress old tool_result content for small-context providers ([#801](https://github.com/Gitlawb/openclaude/issues/801)) ([a6a3de5](https://github.com/Gitlawb/openclaude/commit/a6a3de5ac155fe9d00befbfcab98d439314effd8))
+* **api:** improve local provider reliability with readiness and self-healing ([#738](https://github.com/Gitlawb/openclaude/issues/738)) ([4cb963e](https://github.com/Gitlawb/openclaude/commit/4cb963e660dbd6ee438c04042700db05a9d32c59))
+* **api:** smart model routing primitive (cheap-for-simple, strong-for-hard) ([#785](https://github.com/Gitlawb/openclaude/issues/785)) ([e908864](https://github.com/Gitlawb/openclaude/commit/e908864da7e7c987a98053ac5d18d702e192db2b))
+* enable 15 additional feature flags in open build ([#667](https://github.com/Gitlawb/openclaude/issues/667)) ([6a62e3f](https://github.com/Gitlawb/openclaude/commit/6a62e3ff76ba9ba446b8e20cf2bb139ee76a9387))
+* native Anthropic API mode for Claude models on GitHub Copilot ([#579](https://github.com/Gitlawb/openclaude/issues/579)) ([fdef4a1](https://github.com/Gitlawb/openclaude/commit/fdef4a1b4ce218ded4937ca83b30acce7c726472))
+* **provider:** expose Atomic Chat in /provider picker with autodetect ([#810](https://github.com/Gitlawb/openclaude/issues/810)) ([ee19159](https://github.com/Gitlawb/openclaude/commit/ee19159c17b3de3b4a8b4a4541a6569f4261d54e))
+* **provider:** zero-config autodetection primitive ([#784](https://github.com/Gitlawb/openclaude/issues/784)) ([a5bfcbb](https://github.com/Gitlawb/openclaude/commit/a5bfcbbadf8e9a1fd42f3e103d295524b8da64b0))
+
+
+### Bug Fixes
+
+* **api:** ensure strict role sequence and filter empty assistant messages after interruption ([#745](https://github.com/Gitlawb/openclaude/issues/745) regression) ([#794](https://github.com/Gitlawb/openclaude/issues/794)) ([06e7684](https://github.com/Gitlawb/openclaude/commit/06e7684eb56df8e694ac784575e163641931c44c))
+* Collapse all-text arrays to string for DeepSeek compatibility ([#806](https://github.com/Gitlawb/openclaude/issues/806)) ([761924d](https://github.com/Gitlawb/openclaude/commit/761924daa7e225fe8acf41651408c7cae639a511))
+* **model:** codex/nvidia-nim/minimax now read OPENAI_MODEL env ([#815](https://github.com/Gitlawb/openclaude/issues/815)) ([4581208](https://github.com/Gitlawb/openclaude/commit/458120889f6ce54cc9f0b287461d5e38eae48a20))
+* **provider:** saved profile ignored when stale CLAUDE_CODE_USE_* in shell ([#807](https://github.com/Gitlawb/openclaude/issues/807)) ([13de4e8](https://github.com/Gitlawb/openclaude/commit/13de4e85df7f5fadc8cd15a76076374dc112360b))
+* rename .claude.json to .openclaude.json with legacy fallback ([#582](https://github.com/Gitlawb/openclaude/issues/582)) ([4d4fb28](https://github.com/Gitlawb/openclaude/commit/4d4fb2880e4d0e3a62d8715e1ec13d932e736279))
+* replace discontinued gemini-2.5-pro-preview-03-25 with stable gemini-2.5-pro ([#802](https://github.com/Gitlawb/openclaude/issues/802)) ([64582c1](https://github.com/Gitlawb/openclaude/commit/64582c119d5d0278195271379da4a68d59a89c1f)), closes [#398](https://github.com/Gitlawb/openclaude/issues/398)
+* **security:** harden project settings trust boundary + MCP sanitization ([#789](https://github.com/Gitlawb/openclaude/issues/789)) ([ae3b723](https://github.com/Gitlawb/openclaude/commit/ae3b723f3b297b49925cada4728f3174aee8bf12))
+* **test:** autoCompact floor assertion is flag-sensitive ([#816](https://github.com/Gitlawb/openclaude/issues/816)) ([c13842e](https://github.com/Gitlawb/openclaude/commit/c13842e91c7227246520955de6ae0636b30def9a))
+* **ui:** prevent provider manager lag by deferring sync I/O ([#803](https://github.com/Gitlawb/openclaude/issues/803)) ([85eab27](https://github.com/Gitlawb/openclaude/commit/85eab2751e7d351bb0ed6a3fe0e15461d241c9cb))
+
+## [0.5.2](https://github.com/Gitlawb/openclaude/compare/v0.5.1...v0.5.2) (2026-04-20)
+
+
+### Bug Fixes
+
+* **api:** replace phrase-based reasoning sanitizer with tag-based filter ([#779](https://github.com/Gitlawb/openclaude/issues/779)) ([336ddcc](https://github.com/Gitlawb/openclaude/commit/336ddcc50d59d79ebff50993f2673652aecb0d7d))
+
+## [0.5.1](https://github.com/Gitlawb/openclaude/compare/v0.5.0...v0.5.1) (2026-04-20)
+
+
+### Bug Fixes
+
+* enforce Bash path constraints after sandbox allow ([#777](https://github.com/Gitlawb/openclaude/issues/777)) ([7002cb3](https://github.com/Gitlawb/openclaude/commit/7002cb302b78ea2a19da3f26226de24e2903fa1d))
+* enforce MCP OAuth callback state before errors ([#775](https://github.com/Gitlawb/openclaude/issues/775)) ([739b8d1](https://github.com/Gitlawb/openclaude/commit/739b8d1f40fde0e401a5cbd2b9a55d88bd5124ad))
+* require trusted approval for sandbox override ([#778](https://github.com/Gitlawb/openclaude/issues/778)) ([aab4890](https://github.com/Gitlawb/openclaude/commit/aab489055c53dd64369414116fe93226d2656273))
+
+## [0.5.0](https://github.com/Gitlawb/openclaude/compare/v0.4.0...v0.5.0) (2026-04-20)
+
+
+### Features
+
+* add OPENCLAUDE_DISABLE_STRICT_TOOLS env var to opt out of strict MCP tool schema normalization ([#770](https://github.com/Gitlawb/openclaude/issues/770)) ([e6e8d9a](https://github.com/Gitlawb/openclaude/commit/e6e8d9a24897e4c9ef08b72df20fabbf8ef27f38))
+* mask provider api key input ([#772](https://github.com/Gitlawb/openclaude/issues/772)) ([13e9f22](https://github.com/Gitlawb/openclaude/commit/13e9f22a83a2b0f85f557b1e12c9442ba61241e4))
+
+
+### Bug Fixes
+
+* allow provider recovery during startup ([#765](https://github.com/Gitlawb/openclaude/issues/765)) ([f828171](https://github.com/Gitlawb/openclaude/commit/f828171ef1ab94e2acf73a28a292799e4e26cc0d))
+* **api:** drop orphan tool results to satisfy strict role sequence ([#745](https://github.com/Gitlawb/openclaude/issues/745)) ([b786b76](https://github.com/Gitlawb/openclaude/commit/b786b765f01f392652eaf28ed3579a96b7260a53))
+* **help:** prevent /help tab crash from undefined descriptions ([#732](https://github.com/Gitlawb/openclaude/issues/732)) ([3d1979f](https://github.com/Gitlawb/openclaude/commit/3d1979ff066db32415e0c8321af916d81f5f2621))
+* **mcp:** sync required array with properties in tool schemas ([#754](https://github.com/Gitlawb/openclaude/issues/754)) ([002a8f1](https://github.com/Gitlawb/openclaude/commit/002a8f1f6de2fcfc917165d828501d3047bad61f))
+* remove cached mcpClient in diagnostic tracking to prevent stale references ([#727](https://github.com/Gitlawb/openclaude/issues/727)) ([2c98be7](https://github.com/Gitlawb/openclaude/commit/2c98be700274a4241963b5f43530bf3bd8f8963f))
+* use raw context window for auto-compact percentage display ([#748](https://github.com/Gitlawb/openclaude/issues/748)) ([55c5f26](https://github.com/Gitlawb/openclaude/commit/55c5f262a9a5a8be0aa9ae8dc6c7dafc465eb2c6))
+
+## [0.4.0](https://github.com/Gitlawb/openclaude/compare/v0.3.0...v0.4.0) (2026-04-17)
+
+
+### Features
+
+* add Alibaba Coding Plan (DashScope) provider support ([#509](https://github.com/Gitlawb/openclaude/issues/509)) ([43ac6db](https://github.com/Gitlawb/openclaude/commit/43ac6dba75537282da1e2ad8f855082bc4e25f1e))
+* add NVIDIA NIM and MiniMax provider support ([#552](https://github.com/Gitlawb/openclaude/issues/552)) ([51191d6](https://github.com/Gitlawb/openclaude/commit/51191d61326e1f8319d70b3a3c0d9229e185a564))
+* add ripgrep to Dockerfile for faster file searching ([#688](https://github.com/Gitlawb/openclaude/issues/688)) ([12dd375](https://github.com/Gitlawb/openclaude/commit/12dd3755c619cc27af3b151ae8fdb9d425a7b9a2))
+* **api:** classify openai-compatible provider failures ([#708](https://github.com/Gitlawb/openclaude/issues/708)) ([80a00ac](https://github.com/Gitlawb/openclaude/commit/80a00acc2c6dc4657a78de7366f7a9ebc920bfbb))
+* **vscode:** add full chat interface to OpenClaude extension ([#608](https://github.com/Gitlawb/openclaude/issues/608)) ([fbcd928](https://github.com/Gitlawb/openclaude/commit/fbcd928f7f8511da795aea3ad318bddf0ab9a1a7))
+
+
+### Bug Fixes
+
+* focus "Done" option after completing provider manager actions ([#718](https://github.com/Gitlawb/openclaude/issues/718)) ([d6f5130](https://github.com/Gitlawb/openclaude/commit/d6f5130c204d8ffe582212466768706cd7fd6774))
+* **models:** prevent /models crash from non-string saved model values ([#691](https://github.com/Gitlawb/openclaude/issues/691)) ([6b2121d](https://github.com/Gitlawb/openclaude/commit/6b2121da12189fa7ce1f33394d18abd24cf8a01b))
+* prevent crash in commands tab when description is undefined ([#730](https://github.com/Gitlawb/openclaude/issues/730)) ([eed77e6](https://github.com/Gitlawb/openclaude/commit/eed77e6579866a98384dcc948a0ad6406614ede3))
+* strip comments before scanning for missing imports ([#676](https://github.com/Gitlawb/openclaude/issues/676)) ([a00b792](https://github.com/Gitlawb/openclaude/commit/a00b7928de9662ffb7ef6abd8cd040afe6f4f122))
+* **ui:** show correct endpoint URL in intro screen for custom Anthropic endpoints ([#735](https://github.com/Gitlawb/openclaude/issues/735)) ([3424663](https://github.com/Gitlawb/openclaude/commit/34246635fb9a09499047a52e7f96ca9b36c8a85a))
+
+## [0.3.0](https://github.com/Gitlawb/openclaude/compare/v0.2.3...v0.3.0) (2026-04-14)
+
+
+### Features
+
+* activate coordinator mode in open build ([#647](https://github.com/Gitlawb/openclaude/issues/647)) ([99a1714](https://github.com/Gitlawb/openclaude/commit/99a17144ee285b892a0801acb6abcc9af68879af))
+* activate local-only team memory in open build ([#648](https://github.com/Gitlawb/openclaude/issues/648)) ([24d485f](https://github.com/Gitlawb/openclaude/commit/24d485f42f5b1405d2fab13f2f497d5edd3b5300))
+* activate message actions in open build ([#632](https://github.com/Gitlawb/openclaude/issues/632)) ([252808b](https://github.com/Gitlawb/openclaude/commit/252808bbd0a12a6ccf97e2cb09752a0212ea3acd))
+* add allowBypassPermissionsMode setting ([#658](https://github.com/Gitlawb/openclaude/issues/658)) ([31be66d](https://github.com/Gitlawb/openclaude/commit/31be66d7645ea3473334c9ce89ea1a5095b8df6e))
+* add Docker image build and push to GHCR on release ([#656](https://github.com/Gitlawb/openclaude/issues/656)) ([658d076](https://github.com/Gitlawb/openclaude/commit/658d076909e14eb0459bcb98aee9aa0472118265))
+* implement /loop command with fixed and dynamic scheduling ([#621](https://github.com/Gitlawb/openclaude/issues/621)) ([64298a6](https://github.com/Gitlawb/openclaude/commit/64298a663f1391b16aa1f5a49e8a877e1d3742f2))
+* implement Monitor tool for streaming shell output ([#649](https://github.com/Gitlawb/openclaude/issues/649)) ([b818dd5](https://github.com/Gitlawb/openclaude/commit/b818dd5958f4e8428566ce25a1a6be5fd4fe66f8))
+* local feature flag overrides via ~/.claude/feature-flags.json ([#639](https://github.com/Gitlawb/openclaude/issues/639)) ([0e48884](https://github.com/Gitlawb/openclaude/commit/0e48884f56c6c008f047a7926d3b2cb924170625))
+* open useful USER_TYPE-gated features to all users ([#644](https://github.com/Gitlawb/openclaude/issues/644)) ([c1beea9](https://github.com/Gitlawb/openclaude/commit/c1beea98676a413c54152a45a6b9fbe7fb9ed028))
+
+
+### Bug Fixes
+
+* bump axios 1.14.0 → 1.15.0 (Dependabot [#4](https://github.com/Gitlawb/openclaude/issues/4), [#5](https://github.com/Gitlawb/openclaude/issues/5)) ([#670](https://github.com/Gitlawb/openclaude/issues/670)) ([a07e5ef](https://github.com/Gitlawb/openclaude/commit/a07e5ef990a5ed01a72e83fdbd1fcab36f515a08))
+* extend provider guard to protect anthropic profiles from cross-terminal override ([#641](https://github.com/Gitlawb/openclaude/issues/641)) ([03e0b06](https://github.com/Gitlawb/openclaude/commit/03e0b06e0784e4ea46945b3950840b10b6e3ca49))
+* improve fetch diagnostics for bootstrap and session requests ([#646](https://github.com/Gitlawb/openclaude/issues/646)) ([df2b9f2](https://github.com/Gitlawb/openclaude/commit/df2b9f2b7b4c661ee3d9ed5dc58b3064de0599d1))
+* **openai-shim:** preserve tool result images and local token caps ([#659](https://github.com/Gitlawb/openclaude/issues/659)) ([30c866d](https://github.com/Gitlawb/openclaude/commit/30c866d31ad8538496460667d86ed5efbd4a8547))
+* replace broken bun:bundle shim with source pre-processing ([#657](https://github.com/Gitlawb/openclaude/issues/657)) ([adbe391](https://github.com/Gitlawb/openclaude/commit/adbe391e63721918b5d147f4f845111c1a3143db))
+* resolve 12 bugs across API, MCP, agent tools, web search, and context overflow ([#674](https://github.com/Gitlawb/openclaude/issues/674)) ([25ce2ca](https://github.com/Gitlawb/openclaude/commit/25ce2ca7bff8937b0b79ad7f85c6dc1c68432069))
+* route OpenAI Codex shortcuts to correct endpoint ([#566](https://github.com/Gitlawb/openclaude/issues/566)) ([7c8bdcc](https://github.com/Gitlawb/openclaude/commit/7c8bdcc3e2ac1ecb98286c705c85671044be3d6b))
+
+## [0.2.3](https://github.com/Gitlawb/openclaude/compare/v0.2.2...v0.2.3) (2026-04-12)
+
+
+### Bug Fixes
+
+* prevent infinite auto-compact loop for unknown 3P models ([#635](https://github.com/Gitlawb/openclaude/issues/635)) ([#636](https://github.com/Gitlawb/openclaude/issues/636)) ([aeaa658](https://github.com/Gitlawb/openclaude/commit/aeaa658f776fb8df95721e8b8962385f8b00f66a))
+
 ## [0.2.2](https://github.com/Gitlawb/openclaude/compare/v0.2.1...v0.2.2) (2026-04-12)
 
 

Dockerfile

@@ -0,0 +1,46 @@
+# ---- build stage ----
+FROM node:22-slim AS build
+
+# Install Bun
+RUN npm install -g bun@1.3.11
+
+WORKDIR /app
+
+# Copy dependency manifests first for better layer caching
+COPY package.json bun.lock ./
+
+# Install all dependencies (including devDependencies for build)
+RUN bun install --frozen-lockfile
+
+# Copy source code
+COPY src/ src/
+COPY scripts/ scripts/
+COPY bin/ bin/
+COPY tsconfig.json ./
+
+# Build the CLI bundle
+RUN bun run build
+
+# Prune devDependencies
+RUN rm -rf node_modules && bun install --frozen-lockfile --production
+
+# ---- runtime stage ----
+FROM node:22-slim
+
+WORKDIR /app
+
+# Copy only what's needed to run
+COPY --from=build /app/dist/cli.mjs dist/cli.mjs
+COPY --from=build /app/bin/ bin/
+COPY --from=build /app/node_modules/ node_modules/
+COPY --from=build /app/package.json package.json
+COPY README.md ./
+
+# Install git and ripgrep — many CLI tool operations depend on them
+RUN apt-get update && apt-get install -y --no-install-recommends git ripgrep \
+    && rm -rf /var/lib/apt/lists/*
+
+# Run as non-root user
+USER node
+
+ENTRYPOINT ["node", "/app/dist/cli.mjs"]

README.md

@@ -2,7 +2,7 @@
 
 OpenClaude is an open-source coding-agent CLI for cloud and local model providers.
 
-Use OpenAI-compatible APIs, Gemini, GitHub Models, Codex, Ollama, Atomic Chat, and other supported backends while keeping one terminal-first workflow: prompts, tools, agents, MCP, slash commands, and streaming output.
+Use OpenAI-compatible APIs, Gemini, GitHub Models, Codex OAuth, Codex, Ollama, Atomic Chat, and other supported backends while keeping one terminal-first workflow: prompts, tools, agents, MCP, slash commands, and streaming output.
 
 [![PR Checks](https://github.com/Gitlawb/openclaude/actions/workflows/pr-checks.yml/badge.svg?branch=main)](https://github.com/Gitlawb/openclaude/actions/workflows/pr-checks.yml)
 [![Release](https://img.shields.io/github/v/tag/Gitlawb/openclaude?label=release&color=0ea5e9)](https://github.com/Gitlawb/openclaude/tags)
@@ -10,13 +10,20 @@ Use OpenAI-compatible APIs, Gemini, GitHub Models, Codex, Ollama, Atomic Chat, a
 [![Security Policy](https://img.shields.io/badge/security-policy-0f766e)](SECURITY.md)
 [![License](https://img.shields.io/badge/license-MIT-2563eb)](LICENSE)
 
+OpenClaude is also mirrored to GitLawb:
+[gitlawb.com/node/repos/z6MkqDnb/openclaude](https://gitlawb.com/node/repos/z6MkqDnb/openclaude)
+
 [Quick Start](#quick-start) | [Setup Guides](#setup-guides) | [Providers](#supported-providers) | [Source Build](#source-build-and-local-development) | [VS Code Extension](#vs-code-extension) | [Community](#community)
 
+## Star History
+
+[![Star History Chart](https://api.star-history.com/chart?repos=gitlawb/openclaude&type=date&legend=top-left)](https://www.star-history.com/?repos=gitlawb%2Fopenclaude&type=date&legend=top-left)
+
 ## Why OpenClaude
 
 - Use one CLI across cloud APIs and local model backends
 - Save provider profiles inside the app with `/provider`
-- Run with OpenAI-compatible services, Gemini, GitHub Models, Codex, Ollama, Atomic Chat, and other supported providers
+- Run with OpenAI-compatible services, Gemini, GitHub Models, Codex OAuth, Codex, Ollama, Atomic Chat, and other supported providers
 - Keep coding-agent workflows in one place: bash, file tools, grep, glob, agents, tasks, MCP, and web tools
 - Use the bundled VS Code extension for launch integration and theme support
 
@@ -85,6 +92,16 @@ $env:OPENAI_MODEL="qwen2.5-coder:7b"
 openclaude
 ```
 
+### Using Ollama's launch command
+
+If you have [Ollama](https://ollama.com) installed, you can skip the env var setup entirely:
+
+```bash
+ollama launch openclaude --model qwen2.5-coder:7b
+```
+
+This automatically sets `ANTHROPIC_BASE_URL`, model routing, and auth so all API traffic goes through your local Ollama instance. Works with any model you have pulled — local or cloud.
+
 ## Setup Guides
 
 Beginner-friendly guides:
@@ -105,9 +122,10 @@ Advanced and source-build guides:
 | OpenAI-compatible | `/provider` or env vars | Works with OpenAI, OpenRouter, DeepSeek, Groq, Mistral, LM Studio, and other compatible `/v1` servers |
 | Gemini | `/provider` or env vars | Supports API key, access token, or local ADC workflow on current `main` |
 | GitHub Models | `/onboard-github` | Interactive onboarding with saved credentials |
-| Codex | `/provider` | Uses existing Codex credentials when available |
-| Ollama | `/provider` or env vars | Local inference with no API key |
-| Atomic Chat | advanced setup | Local Apple Silicon backend |
+| Codex OAuth | `/provider` | Opens ChatGPT sign-in in your browser and stores Codex credentials securely |
+| Codex | `/provider` | Uses existing Codex CLI auth, OpenClaude secure storage, or env credentials |
+| Ollama | `/provider`, env vars, or `ollama launch` | Local inference with no API key |
+| Atomic Chat | `/provider`, env vars, or `bun run dev:atomic-chat` | Local Model Provider; auto-detects loaded models |
 | Bedrock / Vertex / Foundry | env vars | Additional provider integrations for supported environments |
 
 ## What Works
@@ -313,7 +331,8 @@ For larger changes, open an issue first so the scope is clear before implementat
 - `bun run build`
 - `bun run test:coverage`
 - `bun run smoke`
-- focused `bun test ...` runs for touched areas
+- focused `bun test ...` runs for files and flows you changed
+
 
 ## Disclaimer
 

bun.lock

@@ -30,7 +30,7 @@
         "@opentelemetry/semantic-conventions": "1.40.0",
         "ajv": "8.18.0",
         "auto-bind": "5.0.1",
-        "axios": "1.14.0",
+        "axios": "1.15.0",
         "bidi-js": "1.0.3",
         "chalk": "5.6.2",
         "chokidar": "4.0.3",
@@ -479,7 +479,7 @@
 
     "auto-bind": ["auto-bind@5.0.1", "", {}, "sha512-ooviqdwwgfIfNmDwo94wlshcdzfO64XV0Cg6oDsDYBJfITDz1EngD2z7DkbvCWn+XIMsIqW27sEVF6qcpJrRcg=="],
 
-    "axios": ["axios@1.14.0", "", { "dependencies": { "follow-redirects": "^1.15.11", "form-data": "^4.0.5", "proxy-from-env": "^2.1.0" } }, "sha512-3Y8yrqLSwjuzpXuZ0oIYZ/XGgLwUIBU3uLvbcpb0pidD9ctpShJd43KSlEEkVQg6DS0G9NKyzOvBfUtDKEyHvQ=="],
+    "axios": ["axios@1.15.0", "", { "dependencies": { "follow-redirects": "^1.15.11", "form-data": "^4.0.5", "proxy-from-env": "^2.1.0" } }, "sha512-wWyJDlAatxk30ZJer+GeCWS209sA42X+N5jU2jy6oHTp7ufw8uzUTVFBX9+wTfAlhiJXGS0Bq7X6efruWjuK9Q=="],
 
     "base64-js": ["base64-js@1.5.1", "", {}, "sha512-AKpaYlHn8t4SVbOHCy+b5+KKgvR4vrsD8vbvrbiQJps7fKDTkjkDry6ji0rUJjC0kzbNePLwzxq8iypo41qeWA=="],
 
@@ -1151,6 +1151,8 @@
 
     "@emnapi/runtime/tslib": ["tslib@2.8.1", "", {}, "sha512-oJFu94HQb+KVduSUQL7wnpmqnfmLsOA/nAh6b6EH0wCEoK0/mPeXU6c3wKDV83MkOuHPRHtSXKKU99IBazS/2w=="],
 
+    "@mendable/firecrawl-js/axios": ["axios@1.14.0", "", { "dependencies": { "follow-redirects": "^1.15.11", "form-data": "^4.0.5", "proxy-from-env": "^2.1.0" } }, "sha512-3Y8yrqLSwjuzpXuZ0oIYZ/XGgLwUIBU3uLvbcpb0pidD9ctpShJd43KSlEEkVQg6DS0G9NKyzOvBfUtDKEyHvQ=="],
+
     "@opentelemetry/exporter-trace-otlp-grpc/@opentelemetry/core": ["@opentelemetry/core@1.30.1", "", { "dependencies": { "@opentelemetry/semantic-conventions": "1.28.0" }, "peerDependencies": { "@opentelemetry/api": ">=1.0.0 <1.10.0" } }, "sha512-OOCM2C/QIURhJMuKaekP3TRBxBKxG/TWWA0TL2J6nXUtDnuCtccy49LUJF8xPFXMX+0LMcxFpCo8M9cGY1W6rQ=="],
 
     "@opentelemetry/exporter-trace-otlp-grpc/@opentelemetry/otlp-exporter-base": ["@opentelemetry/otlp-exporter-base@0.57.2", "", { "dependencies": { "@opentelemetry/core": "1.30.1", "@opentelemetry/otlp-transformer": "0.57.2" }, "peerDependencies": { "@opentelemetry/api": "^1.3.0" } }, "sha512-XdxEzL23Urhidyebg5E6jZoaiW5ygP/mRjxLHixogbqwDy2Faduzb5N0o/Oi+XTIJu+iyxXdVORjXax+Qgfxag=="],
@@ -1377,6 +1379,8 @@
 
     "cliui/wrap-ansi": ["wrap-ansi@7.0.0", "", { "dependencies": { "ansi-styles": "^4.0.0", "string-width": "^4.1.0", "strip-ansi": "^6.0.0" } }, "sha512-YVGIj2kamLSTxw6NsZjoBxfSwsn0ycdesmc4p+Q21c5zPuZ1pl+NfxVdxPtdHvmNVOQ6XSYG4AUtyt/Fi7D16Q=="],
 
+    "firecrawl/axios": ["axios@1.14.0", "", { "dependencies": { "follow-redirects": "^1.15.11", "form-data": "^4.0.5", "proxy-from-env": "^2.1.0" } }, "sha512-3Y8yrqLSwjuzpXuZ0oIYZ/XGgLwUIBU3uLvbcpb0pidD9ctpShJd43KSlEEkVQg6DS0G9NKyzOvBfUtDKEyHvQ=="],
+
     "form-data/mime-types": ["mime-types@2.1.35", "", { "dependencies": { "mime-db": "1.52.0" } }, "sha512-ZDY+bPm5zTTF+YpCrAU9nK0UgICYPT0QtT1NZWFv4s++TNkcgVaT0g6+4R2uI4MjQjzysHB1zxuWL50hzaeXiw=="],
 
     "gaxios/is-stream": ["is-stream@2.0.1", "", {}, "sha512-hFoiJiTl63nn+kstHGBtewWSKnQLpyb155KHheA1l39uvtO9nWIop1p3udqPcUd/xbF1VLMO4n7OI6p7RbngDg=="],

docs/advanced-setup.md

@@ -48,6 +48,8 @@ export OPENAI_MODEL=gpt-4o
 `codexplan` maps to GPT-5.4 on the Codex backend with high reasoning.
 `codexspark` maps to GPT-5.3 Codex Spark for faster loops.
 
+If you use the in-app provider wizard, choose `Codex OAuth` to open ChatGPT sign-in in your browser and let OpenClaude store Codex credentials securely.
+
 If you already use the Codex CLI, OpenClaude reads `~/.codex/auth.json` automatically. You can also point it elsewhere with `CODEX_AUTH_JSON_PATH` or override the token directly with `CODEX_API_KEY`.
 
 ```bash
@@ -82,6 +84,16 @@ OpenRouter model availability changes over time. If a model stops working, try a
 
 ### Ollama
 
+Using `ollama launch` (recommended if you have Ollama installed):
+
+```bash
+ollama launch openclaude --model llama3.3:70b
+```
+
+This handles all environment setup automatically — no env vars needed. Works with any local or cloud model available in your Ollama instance.
+
+Using environment variables manually:
+
 ```bash
 ollama pull llama3.3:70b
 

docs/hook-chains.md

@@ -0,0 +1,333 @@
+# Hook Chains (Self-Healing Agent Mesh MVP)
+
+Hook Chains provide an event-driven recovery layer for important workflow failures.
+When a matching hook event occurs, OpenClaude evaluates declarative rules and can dispatch remediation actions such as:
+
+- `spawn_fallback_agent`
+- `notify_team`
+- `warm_remote_capacity`
+
+## Disabled-By-Default Rollout
+
+> **Rollout recommendation:** keep Hook Chains disabled until you validate rules in your environment.
+>
+> - Set top-level config to `"enabled": false` initially.
+> - Enable per environment when ready.
+> - Dispatch is gated by `feature('HOOK_CHAINS')`.
+> - Env gate defaults to off unless `CLAUDE_CODE_ENABLE_HOOK_CHAINS=1` is set.
+
+This keeps existing workflows unchanged while you tune guard windows and action behavior.
+
+## Feature Overview
+
+Hook Chains are loaded from a deterministic config file and evaluated on dispatched hook events.
+
+MVP runtime trigger wiring:
+
+- `PostToolUseFailure` hooks dispatch Hook Chains with outcome `failed`.
+- `TaskCompleted` hooks dispatch Hook Chains with outcome:
+  - `success` when completion hooks did not block.
+  - `failed` when completion hooks returned blocking errors or prevented continuation.
+
+Default config path:
+
+- `.openclaude/hook-chains.json`
+
+Override path:
+
+- `CLAUDE_CODE_HOOK_CHAINS_CONFIG_PATH=/abs/or/relative/path/to/hook-chains.json`
+
+Global gate:
+
+- `feature('HOOK_CHAINS')` must be enabled in the build
+- `CLAUDE_CODE_ENABLE_HOOK_CHAINS=0|1` (defaults to disabled when unset)
+
+## Safety Guarantees
+
+The runtime is intentionally conservative:
+
+- **Depth guard:** chain dispatch is blocked when `chainDepth >= maxChainDepth`.
+- **Rule cooldown:** each rule can only re-fire after cooldown expires.
+- **Dedup window:** identical event/action combinations are suppressed for a window.
+- **Abort-safe behavior:** if the current signal is aborted, actions skip safely.
+- **Policy-aware remote warm:** `warm_remote_capacity` skips when remote sessions are policy denied.
+- **Bridge inactive no-op:** `warm_remote_capacity` safely skips when no active bridge handle exists.
+- **Missing team context safety:** `notify_team` skips with structured reason if no team context/team file is available.
+- **Fallback launcher safety:** `spawn_fallback_agent` fails with a structured reason when launch permissions/context are unavailable.
+
+## Configuration Schema Reference
+
+Top-level object:
+
+```json
+{
+  "version": 1,
+  "enabled": true,
+  "maxChainDepth": 2,
+  "defaultCooldownMs": 30000,
+  "defaultDedupWindowMs": 30000,
+  "rules": []
+}
+```
+
+### Top-Level Fields
+
+| Field | Type | Required | Notes |
+|---|---|---:|---|
+| `version` | `1` | No | Defaults to `1`. |
+| `enabled` | `boolean` | No | Global feature switch for this config file. |
+| `maxChainDepth` | `integer` | No | Global depth guard (default `2`, max `10`). |
+| `defaultCooldownMs` | `integer` | No | Default rule cooldown in ms (default `30000`). |
+| `defaultDedupWindowMs` | `integer` | No | Default action dedup window in ms (default `30000`). |
+| `rules` | `HookChainRule[]` | No | Defaults to `[]`. May be omitted or empty; when no rules are present, dispatch is a no-op and returns `enabled: false`. |
+
+> **Note:** An empty ruleset is valid and can be used to keep Hook Chains configured but effectively disabled until rules are added.
+### Rule Object (`HookChainRule`)
+
+```json
+{
+  "id": "task-failure-recovery",
+  "enabled": true,
+  "trigger": {
+    "event": "TaskCompleted",
+    "outcome": "failed"
+  },
+  "condition": {
+    "toolNames": ["Edit"],
+    "taskStatuses": ["failed"],
+    "errorIncludes": ["timeout", "permission denied"],
+    "eventFieldEquals": {
+      "meta.source": "scheduler"
+    }
+  },
+  "cooldownMs": 60000,
+  "dedupWindowMs": 30000,
+  "maxDepth": 2,
+  "actions": []
+}
+```
+
+| Field | Type | Required | Notes |
+|---|---|---:|---|
+| `id` | `string` | Yes | Stable identifier used in telemetry/guards. |
+| `enabled` | `boolean` | No | Per-rule switch. |
+| `trigger.event` | `HookEvent` | Yes | Event name to match. |
+| `trigger.outcome` | `"success"|"failed"|"timeout"|"unknown"` | No | Single outcome matcher. |
+| `trigger.outcomes` | `Outcome[]` | No | Multi-outcome matcher. Use either `outcome` or `outcomes`. |
+| `condition` | `object` | No | Optional extra matching constraints. |
+| `cooldownMs` | `integer` | No | Overrides global cooldown for this rule. |
+| `dedupWindowMs` | `integer` | No | Overrides global dedup for this rule. |
+| `maxDepth` | `integer` | No | Per-rule depth cap. |
+| `actions` | `HookChainAction[]` | Yes | One or more actions to execute in order. |
+
+### Condition Fields
+
+| Field | Type | Notes |
+|---|---|---|
+| `toolNames` | `string[]` | Matches `tool_name` / `toolName` in event payload. |
+| `taskStatuses` | `string[]` | Matches `task_status` / `taskStatus` / `status`. |
+| `errorIncludes` | `string[]` | Case-insensitive substring match against `error` / `reason` / `message`. |
+| `eventFieldEquals` | `Record<string, string\|number\|boolean>` | Dot-path equality against payload (example: `"meta.source": "scheduler"`). |
+
+### Actions
+
+#### `spawn_fallback_agent`
+
+```json
+{
+  "type": "spawn_fallback_agent",
+  "id": "fallback-1",
+  "enabled": true,
+  "dedupWindowMs": 30000,
+  "description": "Fallback recovery for failed task",
+  "promptTemplate": "Recover task ${TASK_SUBJECT}. Event=${EVENT_NAME}, outcome=${OUTCOME}, error=${ERROR}. Payload=${PAYLOAD_JSON}",
+  "agentType": "general-purpose",
+  "model": "sonnet"
+}
+```
+
+#### `notify_team`
+
+```json
+{
+  "type": "notify_team",
+  "id": "notify-ops",
+  "enabled": true,
+  "dedupWindowMs": 30000,
+  "teamName": "mesh-team",
+  "recipients": ["*"],
+  "summary": "Hook chain ${RULE_ID} fired",
+  "messageTemplate": "Event=${EVENT_NAME} outcome=${OUTCOME}\nTask=${TASK_ID}\nError=${ERROR}\nPayload=${PAYLOAD_JSON}"
+}
+```
+
+#### `warm_remote_capacity`
+
+```json
+{
+  "type": "warm_remote_capacity",
+  "id": "warm-bridge",
+  "enabled": true,
+  "dedupWindowMs": 60000,
+  "createDefaultEnvironmentIfMissing": false
+}
+```
+
+## Complete Example Configs
+
+### 1) Retry via Fallback Agent
+
+```json
+{
+  "version": 1,
+  "enabled": true,
+  "maxChainDepth": 2,
+  "defaultCooldownMs": 30000,
+  "defaultDedupWindowMs": 30000,
+  "rules": [
+    {
+      "id": "retry-task-via-fallback",
+      "trigger": {
+        "event": "TaskCompleted",
+        "outcome": "failed"
+      },
+      "cooldownMs": 60000,
+      "actions": [
+        {
+          "type": "spawn_fallback_agent",
+          "id": "spawn-retry-agent",
+          "description": "Retry failed task with fallback agent",
+          "promptTemplate": "A task failed. Recover it safely.\nTask=${TASK_SUBJECT}\nDescription=${TASK_DESCRIPTION}\nError=${ERROR}\nPayload=${PAYLOAD_JSON}",
+          "agentType": "general-purpose",
+          "model": "sonnet"
+        }
+      ]
+    }
+  ]
+}
+```
+
+### 2) Notify Only
+
+```json
+{
+  "version": 1,
+  "enabled": true,
+  "maxChainDepth": 2,
+  "defaultCooldownMs": 30000,
+  "defaultDedupWindowMs": 30000,
+  "rules": [
+    {
+      "id": "notify-on-tool-failure",
+      "trigger": {
+        "event": "PostToolUseFailure",
+        "outcome": "failed"
+      },
+      "condition": {
+        "toolNames": ["Edit", "Write", "Bash"]
+      },
+      "actions": [
+        {
+          "type": "notify_team",
+          "id": "notify-team-failure",
+          "recipients": ["*"],
+          "summary": "Tool failure detected",
+          "messageTemplate": "Tool failure detected.\nEvent=${EVENT_NAME} outcome=${OUTCOME}\nError=${ERROR}\nPayload=${PAYLOAD_JSON}"
+        }
+      ]
+    }
+  ]
+}
+```
+
+### 3) Combined Fallback + Notify + Bridge Warm
+
+```json
+{
+  "version": 1,
+  "enabled": true,
+  "maxChainDepth": 2,
+  "defaultCooldownMs": 45000,
+  "defaultDedupWindowMs": 30000,
+  "rules": [
+    {
+      "id": "full-recovery-chain",
+      "trigger": {
+        "event": "TaskCompleted",
+        "outcomes": ["failed", "timeout"]
+      },
+      "condition": {
+        "errorIncludes": ["timeout", "capacity", "connection"]
+      },
+      "cooldownMs": 90000,
+      "actions": [
+        {
+          "type": "spawn_fallback_agent",
+          "id": "fallback-agent",
+          "description": "Recover failed task execution",
+          "promptTemplate": "Recover failed task and produce a concise fix summary.\nTask=${TASK_SUBJECT}\nError=${ERROR}\nPayload=${PAYLOAD_JSON}"
+        },
+        {
+          "type": "notify_team",
+          "id": "notify-team",
+          "recipients": ["*"],
+          "summary": "Recovery chain triggered",
+          "messageTemplate": "Recovery chain ${RULE_ID} fired.\nOutcome=${OUTCOME}\nTask=${TASK_SUBJECT}\nError=${ERROR}"
+        },
+        {
+          "type": "warm_remote_capacity",
+          "id": "warm-capacity",
+          "createDefaultEnvironmentIfMissing": false
+        }
+      ]
+    }
+  ]
+}
+```
+
+## Template Variables
+
+The following placeholders are supported by `promptTemplate`, `summary`, and `messageTemplate`:
+
+- `${EVENT_NAME}`
+- `${OUTCOME}`
+- `${RULE_ID}`
+- `${TASK_SUBJECT}`
+- `${TASK_DESCRIPTION}`
+- `${TASK_ID}`
+- `${ERROR}`
+- `${PAYLOAD_JSON}`
+
+## Troubleshooting
+
+### Rule never triggers
+
+- Verify `trigger.event` and `trigger.outcome`/`trigger.outcomes` exactly match dispatched event data.
+- Check `condition` filters (especially `toolNames` and `eventFieldEquals` dot-path keys).
+- Confirm the config file is valid JSON and schema-valid.
+
+### Actions show as skipped
+
+Common skip reasons:
+
+- `action disabled`
+- `rule cooldown active ...`
+- `dedup window active ...`
+- `max chain depth reached ...`
+- `No team context is available ...`
+- `Team file not found ...`
+- `Remote sessions are blocked by policy`
+- `Bridge is not active; warm_remote_capacity is a safe no-op`
+- `No fallback agent launcher is registered in runtime context`
+
+### Config changes not reflected
+
+- Loader uses memoization by file mtime/size.
+- Ensure your editor writes the file fully and updates mtime.
+- If needed, force reload from the caller side with `forceReloadConfig: true`.
+
+### Existing workflows changed unexpectedly
+
+- Set `"enabled": false` at top-level.
+- Or globally disable with `CLAUDE_CODE_ENABLE_HOOK_CHAINS=0`.
+- Re-enable gradually after validating one rule at a time.

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@gitlawb/openclaude",
-  "version": "0.2.2",
+  "version": "0.6.0",
   "description": "Claude Code opened to any LLM — OpenAI, Gemini, DeepSeek, Ollama, and 200+ models",
   "type": "module",
   "bin": {
@@ -76,7 +76,7 @@
     "@opentelemetry/semantic-conventions": "1.40.0",
     "ajv": "8.18.0",
     "auto-bind": "5.0.1",
-    "axios": "1.14.0",
+    "axios": "1.15.0",
     "bidi-js": "1.0.3",
     "chalk": "5.6.2",
     "chokidar": "4.0.3",

scripts/build.ts

@@ -8,7 +8,8 @@
  * - src/ path aliases
  */
 
-import { readFileSync } from 'fs'
+import { readFileSync, readdirSync, writeFileSync } from 'fs'
+import { join } from 'path'
 import { noTelemetryPlugin } from './no-telemetry-plugin'
 
 const pkg = JSON.parse(readFileSync('./package.json', 'utf-8'))
@@ -18,31 +19,106 @@ const version = pkg.version
 // Most Anthropic-internal features stay off; open-build features can be
 // selectively enabled here when their full source exists in the mirror.
 const featureFlags: Record<string, boolean> = {
-  VOICE_MODE: false,
-  PROACTIVE: false,
-  KAIROS: false,
-  BRIDGE_MODE: false,
-  DAEMON: false,
-  AGENT_TRIGGERS: false,
-  MONITOR_TOOL: false,
-  ABLATION_BASELINE: false,
-  DUMP_SYSTEM_PROMPT: false,
-  CACHED_MICROCOMPACT: false,
-  COORDINATOR_MODE: false,
-  CONTEXT_COLLAPSE: false,
-  COMMIT_ATTRIBUTION: false,
-  TEAMMEM: false,
-  UDS_INBOX: false,
-  BG_SESSIONS: false,
-  AWAY_SUMMARY: false,
-  TRANSCRIPT_CLASSIFIER: false,
-  WEB_BROWSER_TOOL: false,
-  MESSAGE_ACTIONS: false,
-  BUDDY: true,
-  CHICAGO_MCP: false,
-  COWORKER_TYPE_TELEMETRY: false,
+  // ── Disabled: require Anthropic infrastructure or missing source ─────
+  VOICE_MODE: false,              // Push-to-talk STT via claude.ai OAuth endpoint
+  PROACTIVE: false,               // Autonomous agent mode (missing proactive/ module)
+  KAIROS: false,                  // Persistent assistant/session mode (cloud backend)
+  BRIDGE_MODE: false,             // Remote desktop bridge via CCR infrastructure
+  DAEMON: false,                  // Background daemon process (stubbed in open build)
+  AGENT_TRIGGERS: false,          // Scheduled remote agent triggers
+  ABLATION_BASELINE: false,       // A/B testing harness for eval experiments
+  CONTEXT_COLLAPSE: false,        // Context collapsing optimization (stubbed)
+  COMMIT_ATTRIBUTION: false,      // Co-Authored-By metadata in git commits
+  UDS_INBOX: false,               // Unix Domain Socket inter-session messaging
+  BG_SESSIONS: false,             // Background sessions via tmux (stubbed)
+  WEB_BROWSER_TOOL: false,        // Built-in browser automation (source not mirrored)
+  CHICAGO_MCP: false,             // Computer-use MCP (native Swift modules stubbed)
+  COWORKER_TYPE_TELEMETRY: false, // Telemetry for agent/coworker type classification
+
+  // ── Enabled: upstream defaults ──────────────────────────────────────
+  COORDINATOR_MODE: true,             // Multi-agent coordinator with worker delegation
+  BUILTIN_EXPLORE_PLAN_AGENTS: true,  // Built-in Explore/Plan specialized subagents
+  BUDDY: true,                        // Buddy mode for paired programming
+  MONITOR_TOOL: true,                 // MCP server monitoring/streaming tool
+  TEAMMEM: true,                      // Team memory management
+  MESSAGE_ACTIONS: true,              // Message action buttons in the UI
+
+  // ── Enabled: new activations ────────────────────────────────────────
+  DUMP_SYSTEM_PROMPT: true,           // --dump-system-prompt CLI flag for debugging
+  CACHED_MICROCOMPACT: true,          // Cache-aware tool result truncation optimization
+  AWAY_SUMMARY: true,                 // "While you were away" recap after 5min blur
+  TRANSCRIPT_CLASSIFIER: true,        // Auto-approval classifier for safe tool uses
+  ULTRATHINK: true,                   // Deep thinking mode — type "ultrathink" to boost reasoning
+  TOKEN_BUDGET: true,                 // Token budget tracking with usage warnings
+  HISTORY_PICKER: true,               // Enhanced interactive prompt history picker
+  QUICK_SEARCH: true,                 // Ctrl+G quick search across prompts
+  SHOT_STATS: true,                   // Shot distribution stats in session summary
+  EXTRACT_MEMORIES: true,             // Auto-extract durable memories from conversations
+  FORK_SUBAGENT: true,                // Implicit context-forking when omitting subagent_type
+  VERIFICATION_AGENT: true,           // Built-in read-only agent for test/verification
+  MCP_SKILLS: true,                   // Discover skills dynamically from MCP server resources
+  PROMPT_CACHE_BREAK_DETECTION: true, // Detect & log unexpected prompt cache invalidations
+  HOOK_PROMPTS: true,                 // Allow tools to request interactive user prompts
 }
 
+// ── Pre-process: replace feature() calls with boolean literals ──────
+// Bun v1.3.9+ resolves `import { feature } from 'bun:bundle'` natively
+// before plugins can intercept it via onResolve. The bun: namespace is
+// handled by Bun's C++ resolver which runs before the JS plugin phase,
+// so the previous onResolve/onLoad shim was silently ineffective — ALL
+// feature() calls evaluated to false regardless of the featureFlags map.
+//
+// Fix: pre-process source files to strip the bun:bundle import and
+// replace feature('FLAG') calls with their boolean literal. Files are
+// modified in-place before Bun.build() and restored in a finally block.
+
+// Match feature('FLAG') calls, including multi-line: feature(\n  'FLAG',\n)
+const featureCallRe = /\bfeature\(\s*['"](\w+)['"][,\s]*\)/gs
+const featureImportRe = /import\s*\{[^}]*\bfeature\b[^}]*\}\s*from\s*['"]bun:bundle['"];?\s*\n?/g
+const modifiedFiles = new Map<string, string>() // path → original content
+
+function preProcessFeatureFlags(dir: string) {
+  for (const ent of readdirSync(dir, { withFileTypes: true })) {
+    const full = join(dir, ent.name)
+    if (ent.isDirectory()) { preProcessFeatureFlags(full); continue }
+    if (!/\.(ts|tsx)$/.test(ent.name)) continue
+
+    const raw = readFileSync(full, 'utf-8')
+    if (!raw.includes('feature(')) continue
+
+    let contents = raw
+    contents = contents.replace(featureImportRe, '')
+    contents = contents.replace(featureCallRe, (_match, name) =>
+      String((featureFlags as Record<string, boolean>)[name] ?? false),
+    )
+
+    if (contents !== raw) {
+      modifiedFiles.set(full, raw)
+      writeFileSync(full, contents)
+    }
+  }
+}
+
+function restoreModifiedFiles() {
+  for (const [path, original] of modifiedFiles) {
+    writeFileSync(path, original)
+  }
+  modifiedFiles.clear()
+}
+
+preProcessFeatureFlags(join(import.meta.dir, '..', 'src'))
+const numModified = modifiedFiles.size
+
+// Restore source files on abrupt termination (Ctrl+C, kill, etc.)
+for (const signal of ['SIGINT', 'SIGTERM'] as const) {
+  process.on(signal, () => {
+    restoreModifiedFiles()
+    process.exit(signal === 'SIGINT' ? 130 : 143)
+  })
+}
+
+try {
+
 const result = await Bun.build({
   entrypoints: ['./src/entrypoints/cli.tsx'],
   outdir: './dist',
@@ -103,18 +179,11 @@ export async function handleBgFlag() { throw new Error("Background sessions are
           ],
         ] as const)
 
-        // Resolve `import { feature } from 'bun:bundle'` to a shim
-        build.onResolve({ filter: /^bun:bundle$/ }, () => ({
-          path: 'bun:bundle',
-          namespace: 'bun-bundle-shim',
-        }))
-        build.onLoad(
-          { filter: /.*/, namespace: 'bun-bundle-shim' },
-          () => ({
-            contents: `const featureFlags = ${JSON.stringify(featureFlags)};\nexport function feature(name) { return featureFlags[name] ?? false; }`,
-            loader: 'js',
-          }),
-        )
+        // bun:bundle feature() replacement is handled by the source
+        // pre-processing step above (see preProcessFeatureFlags).
+        // The previous onResolve/onLoad shim was ineffective in Bun
+        // v1.3.9+ because the bun: namespace is resolved natively
+        // before the JS plugin phase runs.
 
         build.onResolve(
           { filter: /^\.\.\/(daemon\/workerRegistry|daemon\/main|cli\/bg|cli\/handlers\/templateJobs|environment-runner\/main|self-hosted-runner\/main)\.js$/ },
@@ -274,16 +343,7 @@ export const SeverityNumber = {};
 
         // Scan source to find imports that can't resolve
         function scanForMissingImports() {
-          function walk(dir: string) {
-            for (const ent of fs.readdirSync(dir, { withFileTypes: true })) {
-              const full = pathMod.join(dir, ent.name)
-              if (ent.isDirectory()) { walk(full); continue }
-              if (!/\.(ts|tsx)$/.test(ent.name)) continue
-              const code: string = fs.readFileSync(full, 'utf-8')
-              // Collect all imports
-              for (const m of code.matchAll(/import\s+(?:\{([^}]*)\}|(\w+))?\s*(?:,\s*\{([^}]*)\})?\s*from\s+['"](.*?)['"]/g)) {
-                const specifier = m[4]
-                const namedPart = m[1] || m[3] || ''
+          function checkAndRegister(specifier: string, fileDir: string, namedPart: string) {
                 const names = namedPart.split(',')
                   .map((s: string) => s.trim().replace(/^type\s+/, ''))
                   .filter((s: string) => s && !s.startsWith('type '))
@@ -303,8 +363,7 @@ export const SeverityNumber = {};
                 }
                 // Check relative .js imports
                 else if (specifier.endsWith('.js') && (specifier.startsWith('./') || specifier.startsWith('../'))) {
-                  const dir2 = pathMod.dirname(full)
-                  const resolved = pathMod.resolve(dir2, specifier)
+                  const resolved = pathMod.resolve(fileDir, specifier)
                   const tsVariant = resolved.replace(/\.js$/, '.ts')
                   const tsxVariant = resolved.replace(/\.js$/, '.tsx')
                   if (!fs.existsSync(resolved) && !fs.existsSync(tsVariant) && !fs.existsSync(tsxVariant)) {
@@ -317,6 +376,38 @@ export const SeverityNumber = {};
                   if (!missingModuleExports.has(specifier)) missingModuleExports.set(specifier, new Set())
                   for (const n of names) missingModuleExports.get(specifier)!.add(n)
                 }
+          }
+
+          function walk(dir: string) {
+            for (const ent of fs.readdirSync(dir, { withFileTypes: true })) {
+              const full = pathMod.join(dir, ent.name)
+              if (ent.isDirectory()) { walk(full); continue }
+              if (!/\.(ts|tsx)$/.test(ent.name)) continue
+              const rawCode: string = fs.readFileSync(full, 'utf-8')
+              const fileDir = pathMod.dirname(full)
+
+              // Strip comments before scanning for imports/requires.
+              // The regex scanner matches require()/import() patterns
+              // inside JSDoc comments, causing false-positive missing
+              // module detection that breaks the build with noop stubs.
+              const code = rawCode
+                .replace(/\/\*[\s\S]*?\*\//g, '')  // block comments
+                .replace(/\/\/.*$/gm, '')           // line comments
+
+              // Collect static imports: import { X } from '...'
+              for (const m of code.matchAll(/import\s+(?:\{([^}]*)\}|(\w+))?\s*(?:,\s*\{([^}]*)\})?\s*from\s+['"](.*?)['"]/g)) {
+                checkAndRegister(m[4], fileDir, m[1] || m[3] || '')
+              }
+
+              // Collect dynamic requires: require('...') — these are used
+              // behind feature() gates and become live when flags are enabled.
+              for (const m of code.matchAll(/require\(\s*['"](\.\.?\/[^'"]+)['"]\s*\)/g)) {
+                checkAndRegister(m[1], fileDir, '')
+              }
+
+              // Collect dynamic imports: import('...')
+              for (const m of code.matchAll(/import\(\s*['"](\.\.?\/[^'"]+)['"]\s*\)/g)) {
+                checkAndRegister(m[1], fileDir, '')
               }
             }
           }
@@ -389,7 +480,13 @@ if (!result.success) {
   for (const log of result.logs) {
     console.error(log)
   }
-  process.exit(1)
+  process.exitCode = 1
+} else {
+  console.log(`✓ Built openclaude v${version} → dist/cli.mjs`)
 }
 
-console.log(`✓ Built openclaude v${version} → dist/cli.mjs`)
+} finally {
+  // Always restore source files, even if Bun.build() throws
+  restoreModifiedFiles()
+  console.log(`  🔄 feature-flags: pre-processed ${numModified} files (restored)`)
+}

scripts/no-telemetry-growthbook-stub.test.ts

@@ -0,0 +1,163 @@
+import { afterAll, beforeEach, describe, expect, test } from 'bun:test'
+import { mkdirSync, readFileSync, rmSync, unlinkSync, writeFileSync } from 'node:fs'
+import { join } from 'node:path'
+import { tmpdir } from 'node:os'
+
+// ---------------------------------------------------------------------------
+// Setup: extract the growthbook stub from no-telemetry-plugin.ts, write it to
+// a temp .mjs file, and dynamically import it so we can test the real code
+// that gets bundled.
+// ---------------------------------------------------------------------------
+
+const pluginSource = readFileSync(join(__dirname, 'no-telemetry-plugin.ts'), 'utf-8')
+const stubMatch = pluginSource.match(/'services\/analytics\/growthbook': `([\s\S]*?)`/)
+if (!stubMatch) throw new Error('Could not extract growthbook stub from no-telemetry-plugin.ts')
+
+const testDir = join(tmpdir(), `growthbook-stub-test-${process.pid}`)
+const stubFile = join(testDir, 'growthbook-stub.mjs')
+const flagsFile = join(testDir, 'test-flags.json')
+
+mkdirSync(testDir, { recursive: true })
+writeFileSync(stubFile, stubMatch[1])
+
+// Point the stub at our test flags file (checked by _loadFlags on first access)
+process.env.CLAUDE_FEATURE_FLAGS_FILE = flagsFile
+
+const stub = await import(stubFile)
+
+// ---------------------------------------------------------------------------
+// Tests
+// ---------------------------------------------------------------------------
+
+describe('growthbook stub — local feature flag overrides', () => {
+  beforeEach(() => {
+    stub.resetGrowthBook()
+    try { unlinkSync(flagsFile) } catch { /* may not exist */ }
+  })
+
+  afterAll(() => {
+    rmSync(testDir, { recursive: true, force: true })
+    delete process.env.CLAUDE_FEATURE_FLAGS_FILE
+  })
+
+  // ── File absent ──────────────────────────────────────────────────
+
+  test('returns defaultValue when flags file is absent', () => {
+    expect(stub.getFeatureValue_CACHED_MAY_BE_STALE('tengu_foo', 42)).toBe(42)
+  })
+
+  test('getAllGrowthBookFeatures returns {} when file is absent', () => {
+    expect(stub.getAllGrowthBookFeatures()).toEqual({})
+  })
+
+  // ── Open-build defaults (_openBuildDefaults) ────────────────────
+
+  test('returns open-build default when flags file is absent', () => {
+    // tengu_passport_quail is in _openBuildDefaults as true; without a
+    // flags file the stub should return the open-build override, not
+    // the call-site defaultValue.
+    expect(stub.getFeatureValue_CACHED_MAY_BE_STALE('tengu_passport_quail', false)).toBe(true)
+    expect(stub.getFeatureValue_CACHED_MAY_BE_STALE('tengu_coral_fern', false)).toBe(true)
+  })
+
+  test('flags file overrides open-build defaults', () => {
+    // User-provided feature-flags.json takes priority over _openBuildDefaults.
+    writeFileSync(flagsFile, JSON.stringify({ tengu_passport_quail: false }))
+
+    expect(stub.getFeatureValue_CACHED_MAY_BE_STALE('tengu_passport_quail', true)).toBe(false)
+  })
+
+  // ── Valid JSON object ────────────────────────────────────────────
+
+  test('loads and returns values from a valid JSON file', () => {
+    writeFileSync(flagsFile, JSON.stringify({ tengu_foo: true, tengu_bar: 'hello' }))
+
+    expect(stub.getFeatureValue_CACHED_MAY_BE_STALE('tengu_foo', false)).toBe(true)
+    expect(stub.getFeatureValue_CACHED_MAY_BE_STALE('tengu_bar', 'default')).toBe('hello')
+  })
+
+  test('returns defaultValue for keys not present in the file', () => {
+    writeFileSync(flagsFile, JSON.stringify({ tengu_foo: true }))
+
+    expect(stub.getFeatureValue_CACHED_MAY_BE_STALE('tengu_missing', 99)).toBe(99)
+  })
+
+  test('getAllGrowthBookFeatures returns the full flags object', () => {
+    const flags = { tengu_a: true, tengu_b: false, tengu_c: 42 }
+    writeFileSync(flagsFile, JSON.stringify(flags))
+
+    expect(stub.getAllGrowthBookFeatures()).toEqual(flags)
+  })
+
+  // ── Malformed / non-object JSON ──────────────────────────────────
+
+  test('falls back to defaults on malformed JSON', () => {
+    writeFileSync(flagsFile, '{not valid json!!!')
+
+    expect(stub.getFeatureValue_CACHED_MAY_BE_STALE('tengu_foo', 'fallback')).toBe('fallback')
+  })
+
+  test('falls back to defaults when JSON is a primitive (true)', () => {
+    writeFileSync(flagsFile, 'true')
+
+    expect(stub.getFeatureValue_CACHED_MAY_BE_STALE('tengu_foo', 'fallback')).toBe('fallback')
+  })
+
+  test('falls back to defaults when JSON is an array', () => {
+    writeFileSync(flagsFile, '["a", "b"]')
+
+    expect(stub.getFeatureValue_CACHED_MAY_BE_STALE('tengu_foo', 'fallback')).toBe('fallback')
+  })
+
+  // ── Cache invalidation ───────────────────────────────────────────
+
+  test('resetGrowthBook clears cache so the file is re-read', () => {
+    writeFileSync(flagsFile, JSON.stringify({ tengu_foo: 'first' }))
+    expect(stub.getFeatureValue_CACHED_MAY_BE_STALE('tengu_foo', 'x')).toBe('first')
+
+    // Update the file — cached value is still 'first'
+    writeFileSync(flagsFile, JSON.stringify({ tengu_foo: 'second' }))
+    expect(stub.getFeatureValue_CACHED_MAY_BE_STALE('tengu_foo', 'x')).toBe('first')
+
+    // After reset, the new value is picked up
+    stub.resetGrowthBook()
+    expect(stub.getFeatureValue_CACHED_MAY_BE_STALE('tengu_foo', 'x')).toBe('second')
+  })
+
+  test('refreshGrowthBookFeatures clears cache', async () => {
+    writeFileSync(flagsFile, JSON.stringify({ tengu_foo: 'v1' }))
+    expect(stub.getFeatureValue_CACHED_MAY_BE_STALE('tengu_foo', 'x')).toBe('v1')
+
+    writeFileSync(flagsFile, JSON.stringify({ tengu_foo: 'v2' }))
+    await stub.refreshGrowthBookFeatures()
+    expect(stub.getFeatureValue_CACHED_MAY_BE_STALE('tengu_foo', 'x')).toBe('v2')
+  })
+
+  // ── Multiple getter variants ─────────────────────────────────────
+
+  test('all getter functions read from local flags', async () => {
+    writeFileSync(flagsFile, JSON.stringify({ tengu_gate: true, tengu_config: { a: 1 } }))
+
+    expect(await stub.getFeatureValue_DEPRECATED('tengu_gate', false)).toBe(true)
+    stub.resetGrowthBook()
+    expect(stub.getFeatureValue_CACHED_WITH_REFRESH('tengu_gate', false)).toBe(true)
+    stub.resetGrowthBook()
+    expect(stub.checkStatsigFeatureGate_CACHED_MAY_BE_STALE('tengu_gate')).toBe(true)
+    stub.resetGrowthBook()
+    expect(await stub.checkGate_CACHED_OR_BLOCKING('tengu_gate')).toBe(true)
+    stub.resetGrowthBook()
+    expect(await stub.getDynamicConfig_BLOCKS_ON_INIT('tengu_config', {})).toEqual({ a: 1 })
+    stub.resetGrowthBook()
+    expect(stub.getDynamicConfig_CACHED_MAY_BE_STALE('tengu_config', {})).toEqual({ a: 1 })
+  })
+
+  // ── Security gate ────────────────────────────────────────────────
+
+  test('checkSecurityRestrictionGate always returns false regardless of flags', async () => {
+    writeFileSync(flagsFile, JSON.stringify({
+      tengu_disable_bypass_permissions_mode: true,
+    }))
+
+    expect(await stub.checkSecurityRestrictionGate()).toBe(false)
+  })
+})

scripts/no-telemetry-plugin.ts

@@ -34,28 +34,201 @@ export function _resetForTesting() {}
 `,
 
 	'services/analytics/growthbook': `
+import _fs from 'node:fs';
+import _path from 'node:path';
+import _os from 'node:os';
+
+let _flags = undefined;
+
+// ── Open-build GrowthBook overrides ───────────────────────────────────
+// Override upstream defaultValue for runtime gates tied to build-time
+// features. Only keys that DIFFER from upstream belong here — the
+// catalog below is pure documentation and does NOT affect resolution.
+//
+// Priority: ~/.claude/feature-flags.json > _openBuildDefaults > defaultValue
+//
+// To override at runtime, create ~/.claude/feature-flags.json:
+//   { "tengu_some_flag": true }
+const _openBuildDefaults = {
+  'tengu_sedge_lantern': true,  // AWAY_SUMMARY — "while you were away" recap (upstream: false)
+  'tengu_hive_evidence': true,  // VERIFICATION_AGENT — read-only test/verification agent (upstream: false)
+  'tengu_passport_quail': true, // EXTRACT_MEMORIES — enable memory extraction (upstream: false)
+  'tengu_coral_fern': true,     // EXTRACT_MEMORIES — enable memory search in past context (upstream: false)
+};
+
+/* ── Known runtime feature keys (reference only) ───────────────────────
+ * This catalog does NOT participate in flag resolution. It documents
+ * the known GrowthBook keys and their upstream default values, scraped
+ * from src/ call sites. It is NOT exhaustive — new keys may be added
+ * upstream between catalog updates.
+ *
+ * Some keys have different defaults at different call sites — this is
+ * intentional upstream (the server unifies the value at runtime).
+ *
+ * To activate any of these, add them to ~/.claude/feature-flags.json
+ * or to _openBuildDefaults above.
+ *
+ * ── Reasoning & thinking ──────────────────────────────────────────────
+ *   tengu_turtle_carbon            = true       ULTRATHINK deep thinking runtime gate
+ *   tengu_thinkback                = gate       /thinkback replay command
+ *
+ * ── Agents & orchestration ────────────────────────────────────────────
+ *   tengu_amber_flint              = true       Agent swarms coordination
+ *   tengu_amber_stoat              = true       Built-in agent availability (Explore, Plan, etc.)
+ *   tengu_agent_list_attach        = true       Attach file context to agent list
+ *   tengu_auto_background_agents   = false      Auto-spawn background agents
+ *   tengu_slim_subagent_claudemd   = true       Lighter ClaudeMD for subagents
+ *   tengu_hive_evidence            = false      Verification agent / evidence tracking (4 call sites)
+ *   tengu_ultraplan_model          = model cfg  ULTRAPLAN model selection (dynamic config)
+ *
+ * ── Memory & context ──────────────────────────────────────────────────
+ *   tengu_passport_quail           = false      EXTRACT_MEMORIES main gate (isExtractModeActive)
+ *   tengu_coral_fern               = false      EXTRACT_MEMORIES search in past context
+ *   tengu_slate_thimble            = false      Memory dir paths (non-interactive sessions)
+ *   tengu_herring_clock            = true/false Team memory paths (varies by call site)
+ *   tengu_bramble_lintel           = null       Extract memories throttle (null → every turn)
+ *   tengu_sedge_lantern            = false      AWAY_SUMMARY "while you were away" recap
+ *   tengu_session_memory           = false      Session memory service
+ *   tengu_sm_config                = {}         Session memory config (dynamic)
+ *   tengu_sm_compact_config        = {}         Session memory compaction config (dynamic)
+ *   tengu_cobalt_raccoon           = false      Reactive compaction (suppress auto-compact)
+ *   tengu_pebble_leaf_prune        = false      Session storage pruning
+ *
+ * ── Kairos & cron ─────────────────────────────────────────────────────
+ *   tengu_kairos_brief             = false      Brief layout mode (KAIROS)
+ *   tengu_kairos_brief_config      = {}         Brief config (dynamic)
+ *   tengu_kairos_cron              = true       Cron scheduler enable
+ *   tengu_kairos_cron_durable      = true       Durable (disk-persistent) cron tasks
+ *   tengu_kairos_cron_config       = {}         Cron jitter config (dynamic)
+ *
+ * ── Bridge & remote (require Anthropic infra) ─────────────────────────
+ *   tengu_ccr_bridge               = false      CCR bridge connection
+ *   tengu_ccr_bridge_multi_session = gate       Multi-session spawn mode
+ *   tengu_ccr_mirror               = false      CCR session mirroring
+ *   tengu_ccr_bundle_seed_enabled  = gate       Git bundle seeding for CCR
+ *   tengu_ccr_bundle_max_bytes     = null       Bundle size limit (null → default)
+ *   tengu_bridge_repl_v2           = false      Environment-less REPL bridge v2
+ *   tengu_bridge_repl_v2_cse_shim_enabled = true CSE→Session tag retag shim
+ *   tengu_bridge_min_version       = {min:'0'}  Min CLI version for bridge (dynamic)
+ *   tengu_bridge_initial_history_cap = 200      Initial history cap for bridge
+ *   tengu_bridge_system_init       = false      Bridge system initialization
+ *   tengu_cobalt_harbor            = false      Auto-connect CCR at startup
+ *   tengu_cobalt_lantern           = false      Remote setup preconditions
+ *   tengu_remote_backend           = false      Remote TUI backend
+ *   tengu_surreal_dali             = false      Remote agent tasks / triggers
+ *
+ * ── Prompt & API ──────────────────────────────────────────────────────
+ *   tengu_attribution_header       = true       Attribution header in API requests
+ *   tengu_basalt_3kr               = true       MCP instructions delta
+ *   tengu_slate_prism              = true/false Message formatting (varies by call site)
+ *   tengu_amber_prism              = false      Message content formatting
+ *   tengu_amber_json_tools         = false      JSON format for tool schemas
+ *   tengu_fgts                     = false      API feature gates
+ *   tengu_otk_slot_v1              = false      One-time key slots for API auth
+ *   tengu_cicada_nap_ms            = 0          Background GrowthBook refresh throttle (ms)
+ *   tengu_miraculo_the_bard        = false      Service initialization gate
+ *   tengu_immediate_model_command  = false      Immediate /model command execution
+ *   tengu_chomp_inflection         = false      Prompt suggestions after responses
+ *   tengu_tool_pear                = gate       API betas for tool use
+ *   tengu-off-switch               = {act:false} Service kill switch (dynamic; uses dash)
+ *
+ * ── Permissions & security ────────────────────────────────────────────
+ *   tengu_birch_trellis            = true       Bash auto-mode permissions config
+ *   tengu_auto_mode_config         = {}         Auto-mode configuration (dynamic, many call sites)
+ *   tengu_iron_gate_closed         = true       Permission iron gate (with refresh)
+ *   tengu_destructive_command_warning = false    Warning for destructive bash commands
+ *   tengu_disable_bypass_permissions_mode = security Security killswitch (always false in open build)
+ *
+ * ── UI & UX ───────────────────────────────────────────────────────────
+ *   tengu_willow_mode              = 'off'      REPL rendering mode
+ *   tengu_terminal_panel           = false      Terminal panel keybinding
+ *   tengu_terminal_sidebar         = false      Terminal sidebar in REPL/config
+ *   tengu_marble_sandcastle        = false      Fast mode gate
+ *   tengu_jade_anvil_4             = false      Rate limit options UI ordering
+ *   tengu_collage_kaleidoscope     = true       Native clipboard image paste (macOS)
+ *   tengu_lapis_finch              = false      Plugin/hint recommendation
+ *   tengu_lodestone_enabled        = false      Deep links claude-cli:// protocol
+ *   tengu_copper_panda             = false      Skill improvement suggestions
+ *   tengu_desktop_upsell           = {}         Desktop app upsell config (dynamic)
+ *   tengu-top-of-feed-tip          = {}         Emergency tip of feed (dynamic; uses dash)
+ *
+ * ── File operations ───────────────────────────────────────────────────
+ *   tengu_quartz_lantern           = false      File read/write dedup optimization
+ *   tengu_moth_copse               = false      Attachments handling (variant A)
+ *   tengu_marble_fox               = false      Attachments handling (variant B)
+ *   tengu_scratch                  = gate       Scratchpad filesystem access / coordinator
+ *
+ * ── MCP & plugins ─────────────────────────────────────────────────────
+ *   tengu_harbor                   = false      MCP channel allowlist verification
+ *   tengu_harbor_permissions       = false      MCP channel permissions enforcement
+ *   tengu_copper_bridge            = false      Chrome MCP bridge
+ *   tengu_chrome_auto_enable       = false      Auto-enable Chrome MCP on startup
+ *   tengu_glacier_2xr              = false      Enhanced tool search / ToolSearchTool
+ *   tengu_malort_pedway            = {}         Computer-use (Chicago) config (dynamic)
+ *
+ * ── VSCode / IDE ──────────────────────────────────────────────────────
+ *   tengu_quiet_fern               = false      VSCode browser support
+ *   tengu_vscode_cc_auth           = false      VSCode in-band OAuth via claude_authenticate
+ *   tengu_vscode_review_upsell     = gate       VSCode review upsell
+ *   tengu_vscode_onboarding        = gate       VSCode onboarding experience
+ *
+ * ── Voice ─────────────────────────────────────────────────────────────
+ *   tengu_amber_quartz_disabled    = false      VOICE_MODE kill-switch (false = voice allowed)
+ *
+ * ── Auto-updater (stubbed in open build) ──────────────────────────────
+ *   tengu_version_config           = {min:'0'}  Min version enforcement (dynamic)
+ *   tengu_max_version_config       = {}         Max version / deprecation config (dynamic)
+ *
+ * ── Telemetry & tracing ───────────────────────────────────────────────
+ *   tengu_trace_lantern            = false      Beta session tracing
+ *   tengu_chair_sermon             = gate       Analytics / message formatting gate
+ *   tengu_strap_foyer              = false      Settings sync to cloud
+ */
+
+function _loadFlags() {
+  if (_flags !== undefined) return;
+  try {
+    const flagsPath = process.env.CLAUDE_FEATURE_FLAGS_FILE
+      || _path.join(_os.homedir(), '.claude', 'feature-flags.json');
+    const parsed = JSON.parse(_fs.readFileSync(flagsPath, 'utf-8'));
+    _flags = (parsed && typeof parsed === 'object' && !Array.isArray(parsed)) ? parsed : null;
+  } catch {
+    _flags = null;
+  }
+}
+
+function _getFlagValue(key, defaultValue) {
+  _loadFlags();
+  if (_flags != null && Object.hasOwn(_flags, key)) return _flags[key];
+  if (Object.hasOwn(_openBuildDefaults, key)) return _openBuildDefaults[key];
+  return defaultValue;
+}
+
 const noop = () => {};
 export function onGrowthBookRefresh() { return noop; }
 export function hasGrowthBookEnvOverride() { return false; }
-export function getAllGrowthBookFeatures() { return {}; }
+export function getAllGrowthBookFeatures() { _loadFlags(); return _flags || {}; }
 export function getGrowthBookConfigOverrides() { return {}; }
 export function setGrowthBookConfigOverride() {}
 export function clearGrowthBookConfigOverrides() {}
 export function getApiBaseUrlHost() { return undefined; }
 export const initializeGrowthBook = async () => null;
-export async function getFeatureValue_DEPRECATED(feature, defaultValue) { return defaultValue; }
-export function getFeatureValue_CACHED_MAY_BE_STALE(feature, defaultValue) { return defaultValue; }
-export function getFeatureValue_CACHED_WITH_REFRESH(feature, defaultValue) { return defaultValue; }
-export function checkStatsigFeatureGate_CACHED_MAY_BE_STALE() { return false; }
-export async function checkSecurityRestrictionGate() { return false; }
-export async function checkGate_CACHED_OR_BLOCKING() { return false; }
+export async function getFeatureValue_DEPRECATED(feature, defaultValue) { return _getFlagValue(feature, defaultValue); }
+export function getFeatureValue_CACHED_MAY_BE_STALE(feature, defaultValue) { return _getFlagValue(feature, defaultValue); }
+export function getFeatureValue_CACHED_WITH_REFRESH(feature, defaultValue) { return _getFlagValue(feature, defaultValue); }
+export function checkStatsigFeatureGate_CACHED_MAY_BE_STALE(gate) { return Boolean(_getFlagValue(gate, false)); }
+// Security killswitch — always false in the open build. Anthropic uses this
+// gate to remotely disable bypassPermissions mode; exposing it via local flags
+// would let users accidentally lock themselves out of --dangerously-skip-permissions.
+export async function checkSecurityRestrictionGate(gate) { return false; }
+export async function checkGate_CACHED_OR_BLOCKING(gate) { return Boolean(_getFlagValue(gate, false)); }
 export function refreshGrowthBookAfterAuthChange() {}
-export function resetGrowthBook() {}
-export async function refreshGrowthBookFeatures() {}
+export function resetGrowthBook() { _flags = undefined; }
+export async function refreshGrowthBookFeatures() { _flags = undefined; }
 export function setupPeriodicGrowthBookRefresh() {}
 export function stopPeriodicGrowthBookRefresh() {}
-export async function getDynamicConfig_BLOCKS_ON_INIT(configName, defaultValue) { return defaultValue; }
-export function getDynamicConfig_CACHED_MAY_BE_STALE(configName, defaultValue) { return defaultValue; }
+export async function getDynamicConfig_BLOCKS_ON_INIT(configName, defaultValue) { return _getFlagValue(configName, defaultValue); }
+export function getDynamicConfig_CACHED_MAY_BE_STALE(configName, defaultValue) { return _getFlagValue(configName, defaultValue); }
 `,
 
 	'services/analytics/sink': `

scripts/system-check.test.ts

@@ -20,6 +20,23 @@ describe('formatReachabilityFailureDetail', () => {
     )
   })
 
+  test('redacts credentials and sensitive query parameters in endpoint details', () => {
+    const detail = formatReachabilityFailureDetail(
+      'http://user:pass@localhost:11434/v1/models?token=abc123&mode=test',
+      502,
+      'bad gateway',
+      {
+        transport: 'chat_completions',
+        requestedModel: 'llama3.1:8b',
+        resolvedModel: 'llama3.1:8b',
+      },
+    )
+
+    expect(detail).toBe(
+      'Unexpected status 502 from http://redacted:redacted@localhost:11434/v1/models?token=redacted&mode=test. Body: bad gateway',
+    )
+  })
+
   test('adds alias/entitlement hint for codex model support 400s', () => {
     const detail = formatReachabilityFailureDetail(
       'https://chatgpt.com/backend-api/codex/responses',

scripts/system-check.ts

@@ -7,6 +7,11 @@ import {
   resolveProviderRequest,
   isLocalProviderUrl as isProviderLocalUrl,
 } from '../src/services/api/providerConfig.js'
+import {
+  getLocalOpenAICompatibleProviderLabel,
+  probeOllamaGenerationReadiness,
+} from '../src/utils/providerDiscovery.js'
+import { redactUrlForDisplay } from '../src/utils/urlRedaction.js'
 
 type CheckResult = {
   ok: boolean
@@ -69,7 +74,7 @@ export function formatReachabilityFailureDetail(
   },
 ): string {
   const compactBody = responseBody.trim().replace(/\s+/g, ' ').slice(0, 240)
-  const base = `Unexpected status ${status} from ${endpoint}.`
+  const base = `Unexpected status ${status} from ${redactUrlForDisplay(endpoint)}.`
   const bodySuffix = compactBody ? ` Body: ${compactBody}` : ''
 
   if (request.transport !== 'codex_responses' || status !== 400) {
@@ -255,7 +260,7 @@ function checkOpenAIEnv(): CheckResult[] {
     results.push(pass('OPENAI_MODEL', process.env.OPENAI_MODEL))
   }
 
-  results.push(pass('OPENAI_BASE_URL', request.baseUrl))
+  results.push(pass('OPENAI_BASE_URL', redactUrlForDisplay(request.baseUrl)))
 
   if (request.transport === 'codex_responses') {
     const credentials = resolveCodexApiCredentials(process.env)
@@ -308,7 +313,7 @@ async function checkBaseUrlReachability(): Promise<CheckResult> {
     return pass('Provider reachability', 'Skipped (OpenAI-compatible mode disabled).')
   }
 
-  if (useGithub) {
+  if (useGithub && !useOpenAI) {
     return pass(
       'Provider reachability',
       'Skipped for GitHub Models (inference endpoint differs from OpenAI /models probe).',
@@ -326,6 +331,7 @@ async function checkBaseUrlReachability(): Promise<CheckResult> {
   const endpoint = request.transport === 'codex_responses'
     ? `${request.baseUrl}/responses`
     : `${request.baseUrl}/models`
+  const redactedEndpoint = redactUrlForDisplay(endpoint)
 
   const controller = new AbortController()
   const timeout = setTimeout(() => controller.abort(), 4000)
@@ -375,7 +381,10 @@ async function checkBaseUrlReachability(): Promise<CheckResult> {
     })
 
     if (response.status === 200 || response.status === 401 || response.status === 403) {
-      return pass('Provider reachability', `Reached ${endpoint} (status ${response.status}).`)
+      return pass(
+        'Provider reachability',
+        `Reached ${redactedEndpoint} (status ${response.status}).`,
+      )
     }
 
     const responseBody = await response.text().catch(() => '')
@@ -391,12 +400,100 @@ async function checkBaseUrlReachability(): Promise<CheckResult> {
     )
   } catch (error) {
     const message = error instanceof Error ? error.message : String(error)
-    return fail('Provider reachability', `Failed to reach ${endpoint}: ${message}`)
+    return fail(
+      'Provider reachability',
+      `Failed to reach ${redactedEndpoint}: ${message}`,
+    )
   } finally {
     clearTimeout(timeout)
   }
 }
 
+async function checkProviderGenerationReadiness(): Promise<CheckResult> {
+  const useGemini = isTruthy(process.env.CLAUDE_CODE_USE_GEMINI)
+  const useOpenAI = isTruthy(process.env.CLAUDE_CODE_USE_OPENAI)
+  const useGithub = isTruthy(process.env.CLAUDE_CODE_USE_GITHUB)
+  const useMistral = isTruthy(process.env.CLAUDE_CODE_USE_MISTRAL)
+
+  if (!useGemini && !useOpenAI && !useGithub && !useMistral) {
+    return pass('Provider generation readiness', 'Skipped (OpenAI-compatible mode disabled).')
+  }
+
+  if (useGithub && !useOpenAI) {
+    return pass(
+      'Provider generation readiness',
+      'Skipped for GitHub Models (runtime generation uses a different endpoint flow).',
+    )
+  }
+
+  if (useGemini || useMistral) {
+    return pass(
+      'Provider generation readiness',
+      'Skipped for managed provider mode.',
+    )
+  }
+
+  if (!useOpenAI) {
+    return pass('Provider generation readiness', 'Skipped (OpenAI-compatible mode disabled).')
+  }
+
+  const request = resolveProviderRequest({
+    model: process.env.OPENAI_MODEL,
+    baseUrl: process.env.OPENAI_BASE_URL,
+  })
+
+  if (request.transport === 'codex_responses') {
+    return pass(
+      'Provider generation readiness',
+      'Skipped for Codex responses (reachability probe already performs a lightweight generation request).',
+    )
+  }
+
+  if (!isLocalBaseUrl(request.baseUrl)) {
+    return pass('Provider generation readiness', 'Skipped for non-local provider URL.')
+  }
+
+  const localProviderLabel = getLocalOpenAICompatibleProviderLabel(request.baseUrl)
+  if (localProviderLabel !== 'Ollama') {
+    return pass(
+      'Provider generation readiness',
+      `Skipped for ${localProviderLabel} (no provider-specific generation probe).`,
+    )
+  }
+
+  const readiness = await probeOllamaGenerationReadiness({
+    baseUrl: request.baseUrl,
+    model: request.requestedModel,
+  })
+
+  if (readiness.state === 'ready') {
+    return pass(
+      'Provider generation readiness',
+      `Generated a test response with ${readiness.probeModel ?? request.requestedModel}.`,
+    )
+  }
+
+  if (readiness.state === 'unreachable') {
+    return fail(
+      'Provider generation readiness',
+      `Could not reach Ollama at ${redactUrlForDisplay(request.baseUrl)}.`,
+    )
+  }
+
+  if (readiness.state === 'no_models') {
+    return fail(
+      'Provider generation readiness',
+      'Ollama is reachable, but no installed models were found. Pull a model first (for example: ollama pull qwen2.5-coder:7b).',
+    )
+  }
+
+  const detailSuffix = readiness.detail ? ` Detail: ${readiness.detail}.` : ''
+  return fail(
+    'Provider generation readiness',
+    `Ollama is reachable, but generation failed for ${readiness.probeModel ?? request.requestedModel}.${detailSuffix}`,
+  )
+}
+
 function isAtomicChatUrl(baseUrl: string): boolean {
   try {
     const parsed = new URL(baseUrl)
@@ -567,6 +664,7 @@ async function main(): Promise<void> {
   results.push(checkBuildArtifacts())
   results.push(...checkOpenAIEnv())
   results.push(await checkBaseUrlReachability())
+  results.push(await checkProviderGenerationReadiness())
   results.push(checkOllamaProcessorMode())
 
   if (!options.json) {

src/Tool.ts

@@ -249,6 +249,11 @@ export type ToolUseContext = {
   /** When true, canUseTool must always be called even when hooks auto-approve.
    *  Used by speculation for overlay file path rewriting. */
   requireCanUseTool?: boolean
+  /**
+   * Optional callback used by hook-chain fallback actions that launch
+   * AgentTool from hook runtime paths.
+   */
+  hookChainsCanUseTool?: CanUseToolFn
   messages: Message[]
   fileReadingLimits?: {
     maxTokens?: number

src/__tests__/bugfixes.test.ts

@@ -0,0 +1,282 @@
+/**
+ * Tests for Bug Fixes applied to openclaude.
+ *
+ * Covers:
+ * 1. Gemini `store: false` rejection fix
+ * 2. Session timeout / 500 error fix (stream idle timeout)
+ * 3. Agent loop continuation nudge
+ * 4. Web search result count improvements
+ */
+
+import { describe, test, expect } from 'bun:test'
+import { resolve } from 'path'
+
+const SRC = resolve(import.meta.dir, '..')
+const file = (relative: string) => Bun.file(resolve(SRC, relative))
+
+// ---------------------------------------------------------------------------
+// Fix 1: Gemini `store: false` rejection
+// ---------------------------------------------------------------------------
+describe('Gemini store field fix', () => {
+  test('isGeminiMode is imported and used in openaiShim', async () => {
+    const content = await file('services/api/openaiShim.ts').text()
+
+    // Verify the fix: store deletion should check for Gemini mode
+    expect(content).toContain('isGeminiMode()')
+    expect(content).toContain("mistral and gemini don't recognize body.store")
+    // Ensure the delete body.store is guarded for both Mistral and Gemini
+    expect(content).toMatch(/isMistral\s*\|\|\s*isGeminiMode\(\)/)
+  })
+
+  test('store: false is still set by default (OpenAI needs it)', async () => {
+    const content = await file('services/api/openaiShim.ts').text()
+
+    // The body should still have store: false by default
+    expect(content).toMatch(/store:\s*false/)
+    // But it should be deleted for non-OpenAI providers
+    expect(content).toMatch(/delete body\.store/)
+  })
+})
+
+// ---------------------------------------------------------------------------
+// Fix 2: Session timeout — stream idle timeout
+// ---------------------------------------------------------------------------
+describe('Session timeout fix', () => {
+  test('openaiShim has idle timeout for SSE streams', async () => {
+    const content = await file('services/api/openaiShim.ts').text()
+
+    expect(content).toContain('STREAM_IDLE_TIMEOUT_MS')
+    expect(content).toContain('readWithTimeout')
+    expect(content).toMatch(/readWithTimeout\(\)/)
+  })
+
+  test('codexShim has idle timeout for SSE streams', async () => {
+    const content = await file('services/api/codexShim.ts').text()
+
+    expect(content).toContain('STREAM_IDLE_TIMEOUT_MS')
+    expect(content).toContain('readWithTimeout')
+    expect(content).toMatch(/readWithTimeout\(\)/)
+  })
+
+  test('idle timeout is set to a reasonable value (>= 60s)', async () => {
+    const content = await file('services/api/openaiShim.ts').text()
+
+    // Extract the timeout value (supports numeric separators like 120_000)
+    const match = content.match(/STREAM_IDLE_TIMEOUT_MS\s*=\s*([\d_]+)/)
+    expect(match).not.toBeNull()
+    const timeoutMs = parseInt(match![1].replace(/_/g, ''), 10)
+    expect(timeoutMs).toBeGreaterThanOrEqual(60_000)
+  })
+})
+
+// ---------------------------------------------------------------------------
+// Fix 3: Agent loop continuation nudge
+// ---------------------------------------------------------------------------
+describe('Agent loop continuation nudge', () => {
+  test('query.ts has continuation signal detection', async () => {
+    const content = await file('query.ts').text()
+
+    expect(content).toContain('continuationSignals')
+    expect(content).toContain('Continuation nudge triggered')
+    expect(content).toContain('continuation_nudge')
+  })
+
+  test('continuation signals include tightened patterns', async () => {
+    const content = await file('query.ts').text()
+
+    // Should detect tightened patterns requiring explicit action verbs
+    expect(content).toMatch(/so now \(i\|let me\|we\)/)
+    expect(content).toContain('completionMarkers')
+    expect(content).toContain('MAX_CONTINUATION_NUDGES')
+    // Verify the nudge counter guard exists
+    expect(content).toMatch(/continuationNudgeCount\s*<\s*MAX_CONTINUATION_NUDGES/)
+  })
+
+  test('nudge creates a meta user message to continue', async () => {
+    const content = await file('query.ts').text()
+
+    expect(content).toContain(
+      'Continue with the task. Use the appropriate tools to proceed.',
+    )
+  })
+})
+
+// ---------------------------------------------------------------------------
+// Fix 4: Web search result count improvements
+// ---------------------------------------------------------------------------
+describe('Web search result count improvements', () => {
+  test('Bing provider requests at least 15 results', async () => {
+    const content = await file(
+      'tools/WebSearchTool/providers/bing.ts',
+    ).text()
+
+    expect(content).toMatch(/count.*['"]15['"]/)
+  })
+
+  test('Tavily provider requests at least 15 results', async () => {
+    const content = await file(
+      'tools/WebSearchTool/providers/tavily.ts',
+    ).text()
+
+    expect(content).toMatch(/max_results:\s*15/)
+  })
+
+  test('Exa provider requests at least 15 results', async () => {
+    const content = await file(
+      'tools/WebSearchTool/providers/exa.ts',
+    ).text()
+
+    expect(content).toMatch(/numResults:\s*15/)
+  })
+
+  test('Firecrawl provider requests at least 15 results', async () => {
+    const content = await file(
+      'tools/WebSearchTool/providers/firecrawl.ts',
+    ).text()
+
+    expect(content).toMatch(/limit:\s*15/)
+  })
+
+  test('Mojeek provider requests at least 10 results', async () => {
+    const content = await file(
+      'tools/WebSearchTool/providers/mojeek.ts',
+    ).text()
+
+    // Mojeek uses 't' param for result count — verify it's set to 10
+    expect(content).toMatch(/searchParams\.set\('t',\s*'10'\)/)
+  })
+
+  test('You.com provider requests at least 10 results', async () => {
+    const content = await file(
+      'tools/WebSearchTool/providers/you.ts',
+    ).text()
+
+    expect(content).toMatch(/num_web_results.*['"]10['"]/)
+  })
+
+  test('Jina provider requests at least 10 results', async () => {
+    const content = await file(
+      'tools/WebSearchTool/providers/jina.ts',
+    ).text()
+
+    expect(content).toMatch(/count.*['"]10['"]/)
+  })
+
+  test('Native Anthropic web search max_uses increased to 15', async () => {
+    const content = await file(
+      'tools/WebSearchTool/WebSearchTool.ts',
+    ).text()
+
+    expect(content).toMatch(/max_uses:\s*15/)
+  })
+})
+
+// ---------------------------------------------------------------------------
+// Fix 5: MCP tool timeout fix
+// ---------------------------------------------------------------------------
+describe('MCP tool timeout fix', () => {
+  test('default MCP tool timeout is reasonable (not 27 hours)', async () => {
+    const content = await file('services/mcp/client.ts').text()
+
+    // Should NOT have the old ~27.8 hour default
+    expect(content).not.toContain('100_000_000')
+    // Should have a reasonable timeout (5 minutes = 300_000ms)
+    expect(content).toMatch(/DEFAULT_MCP_TOOL_TIMEOUT_MS\s*=\s*300_000/)
+  })
+
+  test('MCP tools/list has retry logic', async () => {
+    const content = await file('services/mcp/client.ts').text()
+
+    expect(content).toContain('tools/list failed (attempt')
+    expect(content).toContain('Retrying...')
+  })
+
+  test('MCP URL elicitation checks abort signal', async () => {
+    const content = await file('services/mcp/client.ts').text()
+
+    expect(content).toContain('signal.aborted')
+    expect(content).toContain('Tool call aborted during URL elicitation')
+  })
+
+  test('MCP tool error messages include server and tool name in telemetry', async () => {
+    const content = await file('services/mcp/client.ts').text()
+
+    // Telemetry message should include context like "MCP tool [serverName] toolName: error"
+    // The human-readable message stays unchanged to avoid breaking error consumers
+    expect(content).toContain('MCP tool [${name}] ${tool}:')
+  })
+})
+
+// ---------------------------------------------------------------------------
+// Cross-cutting: verify no regressions
+// ---------------------------------------------------------------------------
+describe('Regression checks', () => {
+  test('store field is still set for OpenAI (not deleted unconditionally)', async () => {
+    const content = await file('services/api/openaiShim.ts').text()
+
+    // store: false should exist in body construction
+    expect(content).toMatch(/store:\s*false/)
+    // But delete body.store should be conditional (guarded by if)
+    const deleteLines = content.split('\n').filter(l => l.includes('delete body.store'))
+    expect(deleteLines.length).toBeGreaterThan(0)
+    // Verify the delete is inside a conditional block by checking surrounding context
+    for (const line of deleteLines) {
+      const trimmed = line.trim()
+      // Should be either inside an if block (indented delete) or a comment
+      expect(
+        trimmed.startsWith('delete') && !trimmed.includes('// unconditional'),
+      ).toBe(true)
+    }
+  })
+})
+
+// ---------------------------------------------------------------------------
+// Fix 6: SendMessageTool race condition guard
+// ---------------------------------------------------------------------------
+describe('SendMessageTool race condition fix', () => {
+  test('SendMessageTool has double-check for concurrent resume', async () => {
+    const content = await file('tools/SendMessageTool/SendMessageTool.ts').text()
+
+    // Should have a second status check before resuming to prevent race
+    expect(content).toContain('was concurrently resumed')
+    // The freshTask check should re-read from getAppState
+    expect(content).toMatch(/const freshTask = context\.getAppState\(\)\.tasks\[agentId\]/)
+  })
+})
+
+// ---------------------------------------------------------------------------
+// Fix 7: AgentTool dump state cleanup
+// ---------------------------------------------------------------------------
+describe('AgentTool cleanup fix', () => {
+  test('backgrounded agent always cleans up dump state', async () => {
+    const content = await file('tools/AgentTool/AgentTool.tsx').text()
+
+    // The backgrounded agent's finally block should clean up regardless
+    // of whether the agent crashed or completed normally
+    expect(content).toContain('Defensive cleanup: wrap each call so one failure')
+    // Verify cleanup is wrapped in try/catch for defensive execution
+    expect(content).toMatch(/try\s*\{\s*clearInvokedSkillsForAgent/)
+    expect(content).toMatch(/try\s*\{\s*clearDumpState/)
+  })
+})
+
+// ---------------------------------------------------------------------------
+// Fix 8: Context overflow 500 error handling
+// ---------------------------------------------------------------------------
+describe('Context overflow 500 fix', () => {
+  test('errors.ts has handler for context overflow 500 errors', async () => {
+    const content = await file('services/api/errors.ts').text()
+
+    expect(content).toContain('500 errors caused by context overflow')
+    expect(content).toContain('too many tokens')
+    expect(content).toContain('The conversation has grown too large')
+  })
+
+  test('query.ts has circuit breaker safety net for oversized context', async () => {
+    const content = await file('query.ts').text()
+
+    expect(content).toContain('Safety net: when auto-compact')
+    expect(content).toContain('circuit breaker has tripped')
+    expect(content).toContain('automatic compaction has failed')
+  })
+})

src/__tests__/providerCounts.test.ts

@@ -0,0 +1,55 @@
+/**
+ * Tests for Web Search Provider result count configurations.
+ */
+
+import { describe, test, expect } from 'bun:test'
+import { resolve } from 'path'
+
+const SRC = resolve(import.meta.dir, '..', 'tools', 'WebSearchTool', 'providers')
+const file = (name: string) => Bun.file(resolve(SRC, name))
+
+describe('Provider result counts', () => {
+  const providers = [
+    'bing.ts',
+    'tavily.ts',
+    'exa.ts',
+    'firecrawl.ts',
+    'mojeek.ts',
+    'you.ts',
+    'jina.ts',
+    'duckduckgo.ts',
+    // linkup.ts excluded — uses depth param, not a result count field
+  ]
+
+  for (const name of providers) {
+    test(`${name} exists and is readable`, async () => {
+      const f = file(name)
+      expect(await f.exists()).toBe(true)
+      const content = await f.text()
+      expect(content.length).toBeGreaterThan(100)
+    })
+  }
+
+  test('No provider hardcodes a limit below 10', async () => {
+    const suspiciousPatterns = [
+      /count['":\s]*['"]([1-9])['"]/i,
+      /limit['":\s]*([1-9])\b/,
+      /max_results['":\s]*([1-9])\b/,
+      /numResults['":\s]*([1-9])\b/,
+    ]
+
+    for (const name of providers) {
+      const content = await file(name).text()
+      for (const pattern of suspiciousPatterns) {
+        const match = content.match(pattern)
+        if (match) {
+          const num = parseInt(match[1], 10)
+          expect(num).toBeGreaterThanOrEqual(
+            10,
+            `${name} has suspiciously low result count: ${match[0]}`,
+          )
+        }
+      }
+    }
+  })
+})

src/__tests__/security-hardening.test.ts

@@ -0,0 +1,191 @@
+/**
+ * Security hardening regression tests.
+ *
+ * Covers:
+ * 1. MCP tool result Unicode sanitization
+ * 2. Sandbox settings source filtering (exclude projectSettings)
+ * 3. Plugin git clone/pull hooks disabled
+ * 4. ANTHROPIC_FOUNDRY_API_KEY removed from SAFE_ENV_VARS
+ * 5. WebFetch SSRF protection via ssrfGuardedLookup
+ */
+
+import { describe, test, expect } from 'bun:test'
+import { resolve } from 'path'
+
+const SRC = resolve(import.meta.dir, '..')
+const file = (relative: string) => Bun.file(resolve(SRC, relative))
+
+// ---------------------------------------------------------------------------
+// Fix 1: MCP tool result Unicode sanitization
+// ---------------------------------------------------------------------------
+describe('MCP tool result sanitization', () => {
+  test('transformResultContent sanitizes text content', async () => {
+    const content = await file('services/mcp/client.ts').text()
+    // Tool definitions are already sanitized (line ~1798)
+    expect(content).toContain('recursivelySanitizeUnicode(result.tools)')
+    // Tool results must also be sanitized
+    expect(content).toMatch(
+      /case 'text':[\s\S]*?recursivelySanitizeUnicode\(resultContent\.text\)/,
+    )
+  })
+
+  test('resource text content is also sanitized', async () => {
+    const content = await file('services/mcp/client.ts').text()
+    expect(content).toMatch(
+      /recursivelySanitizeUnicode\(\s*`\$\{prefix\}\$\{resource\.text\}`/,
+    )
+  })
+})
+
+// ---------------------------------------------------------------------------
+// Fix 2: Sandbox settings source filtering
+// ---------------------------------------------------------------------------
+describe('Sandbox settings trust boundary', () => {
+  test('getSandboxEnabledSetting does not use getSettings_DEPRECATED', async () => {
+    const content = await file('utils/sandbox/sandbox-adapter.ts').text()
+    // Extract the getSandboxEnabledSetting function body
+    const fnMatch = content.match(
+      /function getSandboxEnabledSetting\(\)[^{]*\{([\s\S]*?)\n\}/,
+    )
+    expect(fnMatch).not.toBeNull()
+    const fnBody = fnMatch![1]
+    // Must NOT use getSettings_DEPRECATED (reads all sources including project)
+    expect(fnBody).not.toContain('getSettings_DEPRECATED')
+    // Must use getSettingsForSource for individual trusted sources
+    expect(fnBody).toContain("getSettingsForSource('userSettings')")
+    expect(fnBody).toContain("getSettingsForSource('policySettings')")
+    // Must NOT read from projectSettings
+    expect(fnBody).not.toContain("'projectSettings'")
+  })
+})
+
+// ---------------------------------------------------------------------------
+// Fix 3: Plugin git hooks disabled
+// ---------------------------------------------------------------------------
+describe('Plugin git operations disable hooks', () => {
+  test('gitClone includes core.hooksPath=/dev/null', async () => {
+    const content = await file('utils/plugins/marketplaceManager.ts').text()
+    // The clone args must disable hooks
+    const cloneSection = content.slice(
+      content.indexOf('export async function gitClone('),
+      content.indexOf('export async function gitClone(') + 2000,
+    )
+    expect(cloneSection).toContain("'core.hooksPath=/dev/null'")
+  })
+
+  test('gitPull includes core.hooksPath=/dev/null', async () => {
+    const content = await file('utils/plugins/marketplaceManager.ts').text()
+    const pullSection = content.slice(
+      content.indexOf('export async function gitPull('),
+      content.indexOf('export async function gitPull(') + 2000,
+    )
+    expect(pullSection).toContain("'core.hooksPath=/dev/null'")
+  })
+
+  test('gitSubmoduleUpdate includes core.hooksPath=/dev/null', async () => {
+    const content = await file('utils/plugins/marketplaceManager.ts').text()
+    const subSection = content.slice(
+      content.indexOf('async function gitSubmoduleUpdate('),
+      content.indexOf('async function gitSubmoduleUpdate(') + 1000,
+    )
+    expect(subSection).toContain("'core.hooksPath=/dev/null'")
+  })
+})
+
+// ---------------------------------------------------------------------------
+// Fix 4: ANTHROPIC_FOUNDRY_API_KEY not in SAFE_ENV_VARS
+// ---------------------------------------------------------------------------
+describe('SAFE_ENV_VARS excludes credentials', () => {
+  test('ANTHROPIC_FOUNDRY_API_KEY is not in SAFE_ENV_VARS', async () => {
+    const content = await file('utils/managedEnvConstants.ts').text()
+    // Extract the SAFE_ENV_VARS set definition
+    const safeStart = content.indexOf('export const SAFE_ENV_VARS')
+    const safeEnd = content.indexOf('])', safeStart)
+    const safeSection = content.slice(safeStart, safeEnd)
+    expect(safeSection).not.toContain('ANTHROPIC_FOUNDRY_API_KEY')
+  })
+})
+
+// ---------------------------------------------------------------------------
+// Fix 5: WebFetch SSRF protection
+// ---------------------------------------------------------------------------
+describe('WebFetch SSRF guard', () => {
+  test('getWithPermittedRedirects uses ssrfGuardedLookup', async () => {
+    const content = await file('tools/WebFetchTool/utils.ts').text()
+    expect(content).toContain(
+      "import { ssrfGuardedLookup } from '../../utils/hooks/ssrfGuard.js'",
+    )
+    // The axios.get call in getWithPermittedRedirects must include lookup
+    const fnSection = content.slice(
+      content.indexOf('export async function getWithPermittedRedirects('),
+      content.indexOf('export async function getWithPermittedRedirects(') +
+        1000,
+    )
+    expect(fnSection).toContain('lookup: ssrfGuardedLookup')
+  })
+})
+
+// ---------------------------------------------------------------------------
+// Fix 6: Swarm permission file polling removed (security hardening)
+// ---------------------------------------------------------------------------
+describe('Swarm permission file polling removed', () => {
+  test('useSwarmPermissionPoller hook no longer exists', async () => {
+    const content = await file(
+      'hooks/useSwarmPermissionPoller.ts',
+    ).text()
+    // The file-based polling hook must not exist — it read from an
+    // unauthenticated resolved/ directory where any local process could
+    // forge approval files.
+    expect(content).not.toContain('function useSwarmPermissionPoller(')
+    // The file-based processResponse must not exist
+    expect(content).not.toContain('function processResponse(')
+  })
+
+  test('poller does not import from permissionSync', async () => {
+    const content = await file(
+      'hooks/useSwarmPermissionPoller.ts',
+    ).text()
+    // Must not import anything from permissionSync — all file-based
+    // functions have been removed from this module's dependencies
+    expect(content).not.toContain('permissionSync')
+  })
+
+  test('file-based permission functions are marked deprecated', async () => {
+    const content = await file(
+      'utils/swarm/permissionSync.ts',
+    ).text()
+    // All file-based functions must have @deprecated JSDoc
+    const deprecatedFns = [
+      'writePermissionRequest',
+      'readPendingPermissions',
+      'readResolvedPermission',
+      'resolvePermission',
+      'pollForResponse',
+      'removeWorkerResponse',
+    ]
+    for (const fn of deprecatedFns) {
+      // Find the function and check that @deprecated appears before it
+      const fnIndex = content.indexOf(`export async function ${fn}(`)
+      if (fnIndex === -1) continue // submitPermissionRequest is a const, not async function
+      const preceding = content.slice(Math.max(0, fnIndex - 500), fnIndex)
+      expect(preceding).toContain('@deprecated')
+    }
+  })
+
+  test('mailbox-based functions are NOT deprecated', async () => {
+    const content = await file(
+      'utils/swarm/permissionSync.ts',
+    ).text()
+    // These are the active path — must not be deprecated
+    const activeFns = [
+      'sendPermissionRequestViaMailbox',
+      'sendPermissionResponseViaMailbox',
+    ]
+    for (const fn of activeFns) {
+      const fnIndex = content.indexOf(`export async function ${fn}(`)
+      expect(fnIndex).not.toBe(-1)
+      const preceding = content.slice(Math.max(0, fnIndex - 300), fnIndex)
+      expect(preceding).not.toContain('@deprecated')
+    }
+  })
+})

src/bootstrap/state.ts

@@ -1562,29 +1562,8 @@ export function clearInvokedSkillsForAgent(agentId: string): void {
   }
 }
 
-// Slow operations tracking for dev bar
-const MAX_SLOW_OPERATIONS = 10
-const SLOW_OPERATION_TTL_MS = 10000
-
-export function addSlowOperation(operation: string, durationMs: number): void {
-  if (process.env.USER_TYPE !== 'ant') return
-  // Skip tracking for editor sessions (user editing a prompt file in $EDITOR)
-  // These are intentionally slow since the user is drafting text
-  if (operation.includes('exec') && operation.includes('claude-prompt-')) {
-    return
-  }
-  const now = Date.now()
-  // Remove stale operations
-  STATE.slowOperations = STATE.slowOperations.filter(
-    op => now - op.timestamp < SLOW_OPERATION_TTL_MS,
-  )
-  // Add new operation
-  STATE.slowOperations.push({ operation, durationMs, timestamp: now })
-  // Keep only the most recent operations
-  if (STATE.slowOperations.length > MAX_SLOW_OPERATIONS) {
-    STATE.slowOperations = STATE.slowOperations.slice(-MAX_SLOW_OPERATIONS)
-  }
-}
+// Slow operations tracking removed (was internal-only).
+// Functions kept as no-ops to avoid breaking callers.
 
 const EMPTY_SLOW_OPERATIONS: ReadonlyArray<{
   operation: string
@@ -1592,32 +1571,17 @@ const EMPTY_SLOW_OPERATIONS: ReadonlyArray<{
   timestamp: number
 }> = []
 
+export function addSlowOperation(
+  _operation: string,
+  _durationMs: number,
+): void {}
+
 export function getSlowOperations(): ReadonlyArray<{
   operation: string
   durationMs: number
   timestamp: number
 }> {
-  // Most common case: nothing tracked. Return a stable reference so the
-  // caller's setState() can bail via Object.is instead of re-rendering at 2fps.
-  if (STATE.slowOperations.length === 0) {
-    return EMPTY_SLOW_OPERATIONS
-  }
-  const now = Date.now()
-  // Only allocate a new array when something actually expired; otherwise keep
-  // the reference stable across polls while ops are still fresh.
-  if (
-    STATE.slowOperations.some(op => now - op.timestamp >= SLOW_OPERATION_TTL_MS)
-  ) {
-    STATE.slowOperations = STATE.slowOperations.filter(
-      op => now - op.timestamp < SLOW_OPERATION_TTL_MS,
-    )
-    if (STATE.slowOperations.length === 0) {
-      return EMPTY_SLOW_OPERATIONS
-    }
-  }
-  // Safe to return directly: addSlowOperation() reassigns STATE.slowOperations
-  // before pushing, so the array held in React state is never mutated.
-  return STATE.slowOperations
+  return EMPTY_SLOW_OPERATIONS
 }
 
 export function getMainThreadAgentType(): string | undefined {

src/bridge/bridgeConfig.ts

@@ -14,21 +14,14 @@
 import { getOauthConfig } from '../constants/oauth.js'
 import { getClaudeAIOAuthTokens } from '../utils/auth.js'
 
-/** Ant-only dev override: CLAUDE_BRIDGE_OAUTH_TOKEN, else undefined. */
+/** Dev override: CLAUDE_BRIDGE_OAUTH_TOKEN, else undefined. */
 export function getBridgeTokenOverride(): string | undefined {
-  return (
-    (process.env.USER_TYPE === 'ant' &&
-      process.env.CLAUDE_BRIDGE_OAUTH_TOKEN) ||
-    undefined
-  )
+  return process.env.CLAUDE_BRIDGE_OAUTH_TOKEN || undefined
 }
 
-/** Ant-only dev override: CLAUDE_BRIDGE_BASE_URL, else undefined. */
+/** Dev override: CLAUDE_BRIDGE_BASE_URL, else undefined. */
 export function getBridgeBaseUrlOverride(): string | undefined {
-  return (
-    (process.env.USER_TYPE === 'ant' && process.env.CLAUDE_BRIDGE_BASE_URL) ||
-    undefined
-  )
+  return process.env.CLAUDE_BRIDGE_BASE_URL || undefined
 }
 
 /**

src/bridge/bridgeMain.ts

@@ -2194,14 +2194,10 @@ export async function bridgeMain(args: string[]): Promise<void> {
 
   // Session ingress URL for WebSocket connections. In production this is the
   // same as baseUrl (Envoy routes /v1/session_ingress/* to session-ingress).
-  // Locally, session-ingress runs on a different port (9413) than the
-  // contain-provide-api (8211), so CLAUDE_BRIDGE_SESSION_INGRESS_URL must be
-  // set explicitly. Ant-only, matching CLAUDE_BRIDGE_BASE_URL.
+  // Locally, session-ingress may run on a different port, so
+  // CLAUDE_BRIDGE_SESSION_INGRESS_URL can override the default.
   const sessionIngressUrl =
-    process.env.USER_TYPE === 'ant' &&
-    process.env.CLAUDE_BRIDGE_SESSION_INGRESS_URL
-      ? process.env.CLAUDE_BRIDGE_SESSION_INGRESS_URL
-      : baseUrl
+    process.env.CLAUDE_BRIDGE_SESSION_INGRESS_URL || baseUrl
 
   const { getBranch, getRemoteUrl, findGitRoot } = await import(
     '../utils/git.js'
@@ -2851,10 +2847,7 @@ export async function runBridgeHeadless(
     )
   }
   const sessionIngressUrl =
-    process.env.USER_TYPE === 'ant' &&
-    process.env.CLAUDE_BRIDGE_SESSION_INGRESS_URL
-      ? process.env.CLAUDE_BRIDGE_SESSION_INGRESS_URL
-      : baseUrl
+    process.env.CLAUDE_BRIDGE_SESSION_INGRESS_URL || baseUrl
 
   const { getBranch, getRemoteUrl, findGitRoot } = await import(
     '../utils/git.js'

src/bridge/createSession.ts

@@ -217,25 +217,39 @@ export async function getBridgeSession(
   }
 
   const url = `${opts?.baseUrl ?? getOauthConfig().BASE_API_URL}/v1/sessions/${sessionId}`
+  const timeoutMs = 10_000
   logForDebugging(`[bridge] Fetching session ${sessionId}`)
 
   let response
   try {
     response = await axios.get<{ environment_id?: string; title?: string }>(
       url,
-      { headers, timeout: 10_000, validateStatus: s => s < 500 },
+      { headers, timeout: timeoutMs, validateStatus: s => s < 500 },
     )
   } catch (err: unknown) {
-    logForDebugging(
-      `[bridge] Session fetch request failed: ${errorMessage(err)}`,
-    )
+    if (axios.isAxiosError(err)) {
+      const status = err.response?.status ?? 'no-response'
+      const code = err.code ?? 'unknown-code'
+      const requestUrl = err.config?.url ?? url
+      const method = err.config?.method?.toUpperCase() ?? 'GET'
+      const message = err.message ?? errorMessage(err)
+      const timeout = err.config?.timeout ?? timeoutMs
+
+      logForDebugging(
+        `[bridge] Session fetch request failed: status=${status} code=${code} method=${method} url=${requestUrl} timeout=${timeout} message=${message}`,
+      )
+    } else {
+      logForDebugging(
+        `[bridge] Session fetch request failed: url=${url} timeout=${timeoutMs} message=${errorMessage(err)}`,
+      )
+    }
     return null
   }
 
   if (response.status !== 200) {
     const detail = extractErrorDetail(response.data)
     logForDebugging(
-      `[bridge] Session fetch failed with status ${response.status}${detail ? `: ${detail}` : ''}`,
+      `[bridge] Session fetch failed with status ${response.status} url=${url}${detail ? `: ${detail}` : ''}`,
     )
     return null
   }

src/bridge/initReplBridge.ts

@@ -465,10 +465,7 @@ export async function initReplBridge(
   const branch = await getBranch()
   const gitRepoUrl = await getRemoteUrl()
   const sessionIngressUrl =
-    process.env.USER_TYPE === 'ant' &&
-    process.env.CLAUDE_BRIDGE_SESSION_INGRESS_URL
-      ? process.env.CLAUDE_BRIDGE_SESSION_INGRESS_URL
-      : baseUrl
+    process.env.CLAUDE_BRIDGE_SESSION_INGRESS_URL || baseUrl
 
   // Assistant-mode sessions advertise a distinct worker_type so the web UI
   // can filter them into a dedicated picker. KAIROS guard keeps the

src/cli/handlers/mcp.tsx

@@ -11,7 +11,12 @@ import { MCPServerDesktopImportDialog } from '../../components/MCPServerDesktopI
 import { render } from '../../ink.js';
 import { KeybindingSetup } from '../../keybindings/KeybindingProviderSetup.js';
 import { type AnalyticsMetadata_I_VERIFIED_THIS_IS_NOT_CODE_OR_FILEPATHS, logEvent } from '../../services/analytics/index.js';
-import { clearMcpClientConfig, clearServerTokensFromLocalStorage, readClientSecret, saveMcpClientSecret } from '../../services/mcp/auth.js';
+import {
+  clearMcpClientConfig,
+  clearServerTokensFromSecureStorage,
+  readClientSecret,
+  saveMcpClientSecret,
+} from '../../services/mcp/auth.js'
 import { doctorAllServers, doctorServer, type McpDoctorReport, type McpDoctorScopeFilter } from '../../services/mcp/doctor.js';
 import { connectToServer, getMcpServerConnectionBatchSize } from '../../services/mcp/client.js';
 import { addMcpConfig, getAllMcpConfigs, getMcpConfigByName, getMcpConfigsByScope, removeMcpConfig } from '../../services/mcp/config.js';

src/cli/print.ts

@@ -362,15 +362,9 @@ const proactiveModule =
   feature('PROACTIVE') || feature('KAIROS')
     ? (require('../proactive/index.js') as typeof import('../proactive/index.js'))
     : null
-const cronSchedulerModule = feature('AGENT_TRIGGERS')
-  ? (require('../utils/cronScheduler.js') as typeof import('../utils/cronScheduler.js'))
-  : null
-const cronJitterConfigModule = feature('AGENT_TRIGGERS')
-  ? (require('../utils/cronJitterConfig.js') as typeof import('../utils/cronJitterConfig.js'))
-  : null
-const cronGate = feature('AGENT_TRIGGERS')
-  ? (require('../tools/ScheduleCronTool/prompt.js') as typeof import('../tools/ScheduleCronTool/prompt.js'))
-  : null
+const cronSchedulerModule = require('../utils/cronScheduler.js') as typeof import('../utils/cronScheduler.js')
+const cronJitterConfigModule = require('../utils/cronJitterConfig.js') as typeof import('../utils/cronJitterConfig.js')
+const cronGate = require('../tools/ScheduleCronTool/prompt.js') as typeof import('../tools/ScheduleCronTool/prompt.js')
 const extractMemoriesModule = feature('EXTRACT_MEMORIES')
   ? (require('../services/extractMemories/extractMemories.js') as typeof import('../services/extractMemories/extractMemories.js'))
   : null
@@ -2701,11 +2695,7 @@ function runHeadlessStreaming(
   // the end of run() picks up the queued command.
   let cronScheduler: import('../utils/cronScheduler.js').CronScheduler | null =
     null
-  if (
-    feature('AGENT_TRIGGERS') &&
-    cronSchedulerModule &&
-    cronGate?.isKairosCronEnabled()
-  ) {
+  if (cronGate.isKairosCronEnabled()) {
     cronScheduler = cronSchedulerModule.createCronScheduler({
       onFire: prompt => {
         if (inputClosed) return
@@ -2727,8 +2717,8 @@ function runHeadlessStreaming(
         void run()
       },
       isLoading: () => running || inputClosed,
-      getJitterConfig: cronJitterConfigModule?.getCronJitterConfig,
-      isKilled: () => !cronGate?.isKairosCronEnabled(),
+      getJitterConfig: cronJitterConfigModule.getCronJitterConfig,
+      isKilled: () => !cronGate.isKairosCronEnabled(),
     })
     cronScheduler.start()
   }
@@ -4592,7 +4582,7 @@ function handleSetPermissionMode(
           subtype: 'error',
           request_id: requestId,
           error:
-            'Cannot set permission mode to bypassPermissions because the session was not launched with --dangerously-skip-permissions',
+            'Cannot set permission mode to bypassPermissions. Enable it with --allow-dangerously-skip-permissions or set permissions.allowBypassPermissionsMode in settings.json',
         },
       })
       return toolPermissionContext

src/commands.test.ts

@@ -0,0 +1,30 @@
+import { formatDescriptionWithSource } from './commands.js'
+
+describe('formatDescriptionWithSource', () => {
+  test('returns empty text for prompt commands missing a description', () => {
+    const command = {
+      name: 'example',
+      type: 'prompt',
+      source: 'builtin',
+      description: undefined,
+    } as any
+
+    expect(formatDescriptionWithSource(command)).toBe('')
+  })
+
+  test('formats plugin commands with missing description safely', () => {
+    const command = {
+      name: 'example',
+      type: 'prompt',
+      source: 'plugin',
+      description: undefined,
+      pluginInfo: {
+        pluginManifest: {
+          name: 'MyPlugin',
+        },
+      },
+    } as any
+
+    expect(formatDescriptionWithSource(command)).toBe('(MyPlugin) ')
+  })
+})

src/commands.ts

@@ -740,23 +740,23 @@ export function getCommand(commandName: string, commands: Command[]): Command {
  */
 export function formatDescriptionWithSource(cmd: Command): string {
   if (cmd.type !== 'prompt') {
-    return cmd.description
+    return cmd.description ?? ''
   }
 
   if (cmd.kind === 'workflow') {
-    return `${cmd.description} (workflow)`
+    return `${cmd.description ?? ''} (workflow)`
   }
 
   if (cmd.source === 'plugin') {
     const pluginName = cmd.pluginInfo?.pluginManifest.name
     if (pluginName) {
-      return `(${pluginName}) ${cmd.description}`
+      return `(${pluginName}) ${cmd.description ?? ''}`
     }
-    return `${cmd.description} (plugin)`
+    return `${cmd.description ?? ''} (plugin)`
   }
 
   if (cmd.source === 'builtin' || cmd.source === 'mcp') {
-    return cmd.description
+    return cmd.description ?? ''
   }
 
   if (cmd.source === 'bundled') {

src/commands/benchmark.ts

@@ -0,0 +1,56 @@
+import type { ToolUseContext } from '../Tool.js'
+import type { Command } from '../types/command.js'
+import {
+  benchmarkModel,
+  benchmarkMultipleModels,
+  formatBenchmarkResults,
+  isBenchmarkSupported,
+} from '../utils/model/benchmark.js'
+import { getOllamaModelOptions } from '../utils/model/ollamaModels.js'
+
+async function runBenchmark(
+  model?: string,
+  context?: ToolUseContext,
+): Promise<void> {
+  if (!isBenchmarkSupported()) {
+    context?.stdout?.write(
+      'Benchmark not supported for this provider.\n' +
+        'Supported: OpenAI-compatible endpoints (Ollama, NVIDIA NIM, MiniMax)\n',
+    )
+    return
+  }
+
+  let modelsToBenchmark: string[]
+
+  if (model) {
+    modelsToBenchmark = [model]
+  } else {
+    const ollamaModels = getOllamaModelOptions()
+    modelsToBenchmark = ollamaModels.slice(0, 3).map((m) => m.value)
+  }
+
+  context?.stdout?.write(`Benchmarking ${modelsToBenchmark.length} model(s)...\n`)
+
+  const results = await benchmarkMultipleModels(
+    modelsToBenchmark,
+    (completed, total, result) => {
+      context?.stdout?.write(
+        `[${completed}/${total}] ${result.model}: ` +
+          `${result.success ? result.tokensPerSecond.toFixed(1) + ' tps' : 'FAILED'}\n`,
+      )
+    },
+  )
+
+  context?.stdout?.write('\n' + formatBenchmarkResults(results) + '\n')
+}
+
+export const benchmark: Command = {
+  name: 'benchmark',
+
+  async onExecute(context: ToolUseContext): Promise<void> {
+    const args = context.args ?? {}
+    const model = args.model as string | undefined
+
+    await runBenchmark(model, context)
+  },
+}

src/commands/insights.ts

@@ -1,17 +1,12 @@
 import { execFileSync } from 'child_process'
 import { diffLines } from 'diff'
-import { constants as fsConstants } from 'fs'
 import {
-  copyFile,
   mkdir,
-  mkdtemp,
   readdir,
   readFile,
-  rm,
   unlink,
   writeFile,
 } from 'fs/promises'
-import { tmpdir } from 'os'
 import { extname, join } from 'path'
 import type { Command } from '../commands.js'
 import { queryWithModel } from '../services/api/claude.js'
@@ -22,7 +17,6 @@ import {
 import type { LogOption } from '../types/logs.js'
 import { getClaudeConfigHomeDir } from '../utils/envUtils.js'
 import { toError } from '../utils/errors.js'
-import { execFileNoThrow } from '../utils/execFileNoThrow.js'
 import { logError } from '../utils/log.js'
 import { extractTextContent } from '../utils/messages.js'
 import { getDefaultOpusModel } from '../utils/model/model.js'
@@ -47,180 +41,6 @@ function getInsightsModel(): string {
   return getDefaultOpusModel()
 }
 
-// ============================================================================
-// Homespace Data Collection
-// ============================================================================
-
-type RemoteHostInfo = {
-  name: string
-  sessionCount: number
-}
-
-/* eslint-disable custom-rules/no-process-env-top-level */
-const getRunningRemoteHosts: () => Promise<string[]> =
-  process.env.USER_TYPE === 'ant'
-    ? async () => {
-        const { stdout, code } = await execFileNoThrow(
-          'coder',
-          ['list', '-o', 'json'],
-          { timeout: 30000 },
-        )
-        if (code !== 0) return []
-        try {
-          const workspaces = jsonParse(stdout) as Array<{
-            name: string
-            latest_build?: { status?: string }
-          }>
-          return workspaces
-            .filter(w => w.latest_build?.status === 'running')
-            .map(w => w.name)
-        } catch {
-          return []
-        }
-      }
-    : async () => []
-
-const getRemoteHostSessionCount: (hs: string) => Promise<number> =
-  process.env.USER_TYPE === 'ant'
-    ? async (homespace: string) => {
-        const { stdout, code } = await execFileNoThrow(
-          'ssh',
-          [
-            `${homespace}.coder`,
-            'find /root/.claude/projects -name "*.jsonl" 2>/dev/null | wc -l',
-          ],
-          { timeout: 30000 },
-        )
-        if (code !== 0) return 0
-        return parseInt(stdout.trim(), 10) || 0
-      }
-    : async () => 0
-
-const collectFromRemoteHost: (
-  hs: string,
-  destDir: string,
-) => Promise<{ copied: number; skipped: number }> =
-  process.env.USER_TYPE === 'ant'
-    ? async (homespace: string, destDir: string) => {
-        const result = { copied: 0, skipped: 0 }
-
-        // Create temp directory
-        const tempDir = await mkdtemp(join(tmpdir(), 'claude-hs-'))
-
-        try {
-          // SCP the projects folder
-          const scpResult = await execFileNoThrow(
-            'scp',
-            ['-rq', `${homespace}.coder:/root/.claude/projects/`, tempDir],
-            { timeout: 300000 },
-          )
-          if (scpResult.code !== 0) {
-            // SCP failed
-            return result
-          }
-
-          const projectsDir = join(tempDir, 'projects')
-          let projectDirents: Awaited<ReturnType<typeof readdir>>
-          try {
-            projectDirents = await readdir(projectsDir, { withFileTypes: true })
-          } catch {
-            return result
-          }
-
-          // Merge into destination (parallel per project directory)
-          await Promise.all(
-            projectDirents.map(async dirent => {
-              const projectName = dirent.name
-              const projectPath = join(projectsDir, projectName)
-
-              // Skip if not a directory
-              if (!dirent.isDirectory()) return
-
-              const destProjectName = `${projectName}__${homespace}`
-              const destProjectPath = join(destDir, destProjectName)
-
-              try {
-                await mkdir(destProjectPath, { recursive: true })
-              } catch {
-                // Directory may already exist
-              }
-
-              // Copy session files (skip existing)
-              let files: Awaited<ReturnType<typeof readdir>>
-              try {
-                files = await readdir(projectPath, { withFileTypes: true })
-              } catch {
-                return
-              }
-              await Promise.all(
-                files.map(async fileDirent => {
-                  const fileName = fileDirent.name
-                  if (!fileName.endsWith('.jsonl')) return
-
-                  const srcFile = join(projectPath, fileName)
-                  const destFile = join(destProjectPath, fileName)
-
-                  try {
-                    await copyFile(srcFile, destFile, fsConstants.COPYFILE_EXCL)
-                    result.copied++
-                  } catch {
-                    // EEXIST from COPYFILE_EXCL means dest already exists
-                    result.skipped++
-                  }
-                }),
-              )
-            }),
-          )
-        } finally {
-          try {
-            await rm(tempDir, { recursive: true, force: true })
-          } catch {
-            // Ignore cleanup errors
-          }
-        }
-
-        return result
-      }
-    : async () => ({ copied: 0, skipped: 0 })
-
-const collectAllRemoteHostData: (destDir: string) => Promise<{
-  hosts: RemoteHostInfo[]
-  totalCopied: number
-  totalSkipped: number
-}> =
-  process.env.USER_TYPE === 'ant'
-    ? async (destDir: string) => {
-        const rHosts = await getRunningRemoteHosts()
-        const result: RemoteHostInfo[] = []
-        let totalCopied = 0
-        let totalSkipped = 0
-
-        // Collect from all hosts in parallel (SCP per host can take seconds)
-        const hostResults = await Promise.all(
-          rHosts.map(async hs => {
-            const sessionCount = await getRemoteHostSessionCount(hs)
-            if (sessionCount > 0) {
-              const { copied, skipped } = await collectFromRemoteHost(
-                hs,
-                destDir,
-              )
-              return { name: hs, sessionCount, copied, skipped }
-            }
-            return { name: hs, sessionCount, copied: 0, skipped: 0 }
-          }),
-        )
-
-        for (const hr of hostResults) {
-          result.push({ name: hr.name, sessionCount: hr.sessionCount })
-          totalCopied += hr.copied
-          totalSkipped += hr.skipped
-        }
-
-        return { hosts: result, totalCopied, totalSkipped }
-      }
-    : async () => ({ hosts: [], totalCopied: 0, totalSkipped: 0 })
-/* eslint-enable custom-rules/no-process-env-top-level */
-
 // ============================================================================
 // Types
 // ============================================================================
@@ -2659,7 +2479,6 @@ export type InsightsExport = {
     claude_code_version: string
     date_range: { start: string; end: string }
     session_count: number
-    remote_hosts_collected?: string[]
   }
   aggregated_data: AggregatedData
   insights: InsightResults
@@ -2680,14 +2499,9 @@ export function buildExportData(
   data: AggregatedData,
   insights: InsightResults,
   facets: Map<string, SessionFacets>,
-  remoteStats?: { hosts: RemoteHostInfo[]; totalCopied: number },
 ): InsightsExport {
   const version = typeof MACRO !== 'undefined' ? MACRO.VERSION : 'unknown'
 
-  const remote_hosts_collected = remoteStats?.hosts
-    .filter(h => h.sessionCount > 0)
-    .map(h => h.name)
-
   const facets_summary = {
     total: facets.size,
     goal_categories: {} as Record<string, number>,
@@ -2725,10 +2539,6 @@ export function buildExportData(
       claude_code_version: version,
       date_range: data.date_range,
       session_count: data.total_sessions,
-      ...(remote_hosts_collected &&
-        remote_hosts_collected.length > 0 && {
-          remote_hosts_collected,
-        }),
     },
     aggregated_data: data,
     insights,
@@ -2793,24 +2603,12 @@ async function scanAllSessions(): Promise<LiteSessionInfo[]> {
 // Main Function
 // ============================================================================
 
-export async function generateUsageReport(options?: {
-  collectRemote?: boolean
-}): Promise<{
+export async function generateUsageReport(): Promise<{
   insights: InsightResults
   htmlPath: string
   data: AggregatedData
-  remoteStats?: { hosts: RemoteHostInfo[]; totalCopied: number }
   facets: Map<string, SessionFacets>
 }> {
-  let remoteStats: { hosts: RemoteHostInfo[]; totalCopied: number } | undefined
-
-  // Optionally collect data from remote hosts first (internal-only)
-  if (process.env.USER_TYPE === 'ant' && options?.collectRemote) {
-    const destDir = join(getClaudeConfigHomeDir(), 'projects')
-    const { hosts, totalCopied } = await collectAllRemoteHostData(destDir)
-    remoteStats = { hosts, totalCopied }
-  }
-
   // Phase 1: Lite scan — filesystem metadata only (no JSONL parsing)
   const allScannedSessions = await scanAllSessions()
   const totalSessionsScanned = allScannedSessions.length
@@ -3017,7 +2815,6 @@ export async function generateUsageReport(options?: {
     insights,
     htmlPath,
     data: aggregated,
-    remoteStats,
     facets: substantiveFacets,
   }
 }
@@ -3043,31 +2840,8 @@ const usageReport: Command = {
   contentLength: 0, // Dynamic content
   progressMessage: 'analyzing your sessions',
   source: 'builtin',
-  async getPromptForCommand(args) {
-    let collectRemote = false
-    let remoteHosts: string[] = []
-    let hasRemoteHosts = false
-
-    if (process.env.USER_TYPE === 'ant') {
-      // Parse --homespaces flag
-      collectRemote = args?.includes('--homespaces') ?? false
-
-      // Check for available remote hosts
-      remoteHosts = await getRunningRemoteHosts()
-      hasRemoteHosts = remoteHosts.length > 0
-
-      // Show collection message if collecting
-      if (collectRemote && hasRemoteHosts) {
-        // biome-ignore lint/suspicious/noConsole: intentional
-        console.error(
-          `Collecting sessions from ${remoteHosts.length} homespace(s): ${remoteHosts.join(', ')}...`,
-        )
-      }
-    }
-
-    const { insights, htmlPath, data, remoteStats } = await generateUsageReport(
-      { collectRemote },
-    )
+  async getPromptForCommand(_args) {
+    const { insights, htmlPath, data } = await generateUsageReport()
 
     let reportUrl = `file://${htmlPath}`
     let uploadHint = ''
@@ -3085,20 +2859,6 @@ const usageReport: Command = {
       `${data.git_commits} commits`,
     ].join(' · ')
 
-    // Build remote host info (internal-only)
-    let remoteInfo = ''
-    if (process.env.USER_TYPE === 'ant') {
-      if (remoteStats && remoteStats.totalCopied > 0) {
-        const hsNames = remoteStats.hosts
-          .filter(h => h.sessionCount > 0)
-          .map(h => h.name)
-          .join(', ')
-        remoteInfo = `\n_Collected ${remoteStats.totalCopied} new sessions from: ${hsNames}_\n`
-      } else if (!collectRemote && hasRemoteHosts) {
-        // Suggest using --homespaces if they have remote hosts but didn't use the flag
-        remoteInfo = `\n_Tip: Run \`/insights --homespaces\` to include sessions from your ${remoteHosts.length} running homespace(s)_\n`
-      }
-    }
 
     // Build markdown summary from insights
     const atAGlance = insights.at_a_glance
@@ -3118,7 +2878,6 @@ ${atAGlance.ambitious_workflows ? `**Ambitious workflows:** ${atAGlance.ambitiou
 
 ${stats}
 ${data.date_range.start} to ${data.date_range.end}
-${remoteInfo}
 `
 
     const userSummary = `${header}${summaryText}

src/commands/provider/provider.test.tsx

@@ -1,20 +1,28 @@
 import { PassThrough } from 'node:stream'
 
-import { expect, test } from 'bun:test'
+import { afterEach, expect, mock, test } from 'bun:test'
 import React from 'react'
 import stripAnsi from 'strip-ansi'
 
 import { createRoot, render, useApp } from '../../ink.js'
 import { AppStateProvider } from '../../state/AppState.js'
 import {
+  applySavedProfileToCurrentSession,
+  buildCodexOAuthProfileEnv,
   buildCurrentProviderSummary,
   buildProfileSaveMessage,
   getProviderWizardDefaults,
+  ProviderWizard,
   TextEntryDialog,
 } from './provider.js'
+import { createProfileFile } from '../../utils/providerProfile.js'
 
 const SYNC_START = '\x1B[?2026h'
 const SYNC_END = '\x1B[?2026l'
+const ORIGINAL_SIMPLE_ENV = process.env.CLAUDE_CODE_SIMPLE
+const ORIGINAL_CODEX_API_KEY = process.env.CODEX_API_KEY
+const ORIGINAL_CHATGPT_ACCOUNT_ID = process.env.CHATGPT_ACCOUNT_ID
+const ORIGINAL_CODEX_ACCOUNT_ID = process.env.CODEX_ACCOUNT_ID
 
 function extractLastFrame(output: string): string {
   let lastFrame: string | null = null
@@ -60,6 +68,51 @@ async function renderFinalFrame(node: React.ReactNode): Promise<string> {
   return stripAnsi(extractLastFrame(getOutput()))
 }
 
+async function waitForOutput(
+  getOutput: () => string,
+  predicate: (output: string) => boolean,
+  timeoutMs = 2500,
+): Promise<string> {
+  const startedAt = Date.now()
+
+  while (Date.now() - startedAt < timeoutMs) {
+    const output = stripAnsi(extractLastFrame(getOutput()))
+    if (predicate(output)) {
+      return output
+    }
+    await Bun.sleep(10)
+  }
+
+  throw new Error('Timed out waiting for ProviderWizard test output')
+}
+
+async function renderProviderWizardFrame(): Promise<string> {
+  const { stdout, stdin, getOutput } = createTestStreams()
+  const root = await createRoot({
+    stdout: stdout as unknown as NodeJS.WriteStream,
+    stdin: stdin as unknown as NodeJS.ReadStream,
+    patchConsole: false,
+  })
+
+  root.render(
+    <AppStateProvider>
+      <ProviderWizard onDone={() => {}} />
+    </AppStateProvider>,
+  )
+
+  try {
+    return await waitForOutput(
+      getOutput,
+      output => output.includes('Set up a provider profile'),
+    )
+  } finally {
+    root.unmount()
+    stdin.end()
+    stdout.end()
+    await Bun.sleep(0)
+  }
+}
+
 function createTestStreams(): {
   stdout: PassThrough
   stdin: PassThrough & {
@@ -94,6 +147,34 @@ function createTestStreams(): {
   }
 }
 
+afterEach(() => {
+  mock.restore()
+
+  if (ORIGINAL_SIMPLE_ENV === undefined) {
+    delete process.env.CLAUDE_CODE_SIMPLE
+  } else {
+    process.env.CLAUDE_CODE_SIMPLE = ORIGINAL_SIMPLE_ENV
+  }
+
+  if (ORIGINAL_CODEX_API_KEY === undefined) {
+    delete process.env.CODEX_API_KEY
+  } else {
+    process.env.CODEX_API_KEY = ORIGINAL_CODEX_API_KEY
+  }
+
+  if (ORIGINAL_CHATGPT_ACCOUNT_ID === undefined) {
+    delete process.env.CHATGPT_ACCOUNT_ID
+  } else {
+    process.env.CHATGPT_ACCOUNT_ID = ORIGINAL_CHATGPT_ACCOUNT_ID
+  }
+
+  if (ORIGINAL_CODEX_ACCOUNT_ID === undefined) {
+    delete process.env.CODEX_ACCOUNT_ID
+  } else {
+    process.env.CODEX_ACCOUNT_ID = ORIGINAL_CODEX_ACCOUNT_ID
+  }
+})
+
 function StepChangeHarness(): React.ReactNode {
   const { exit } = useApp()
   const [step, setStep] = React.useState<'api' | 'model'>('api')
@@ -233,6 +314,167 @@ test('buildProfileSaveMessage describes Gemini access token / ADC mode clearly',
   expect(message).not.toContain('AIza')
 })
 
+test('buildProfileSaveMessage reflects immediate Codex activation for existing credentials', () => {
+  const message = buildProfileSaveMessage(
+    'codex',
+    {
+      OPENAI_MODEL: 'codexplan',
+      OPENAI_BASE_URL: 'https://chatgpt.com/backend-api/codex',
+      CHATGPT_ACCOUNT_ID: 'acct_codex',
+    },
+    'D:/codings/Opensource/openclaude/.openclaude-profile.json',
+    {
+      activatedInSession: true,
+    },
+  )
+
+  expect(message).toContain('Saved Codex profile.')
+  expect(message).toContain('OpenClaude switched to it for this session.')
+  expect(message).not.toContain('Restart OpenClaude to use it.')
+})
+
+test('buildProfileSaveMessage reflects immediate Codex OAuth activation when the session switched successfully', () => {
+  const message = buildProfileSaveMessage(
+    'codex',
+    {
+      OPENAI_MODEL: 'codexplan',
+      OPENAI_BASE_URL: 'https://chatgpt.com/backend-api/codex',
+      CHATGPT_ACCOUNT_ID: 'acct_codex',
+      CODEX_CREDENTIAL_SOURCE: 'oauth',
+    },
+    'D:/codings/Opensource/openclaude/.openclaude-profile.json',
+    {
+      activatedInSession: true,
+    },
+  )
+
+  expect(message).toContain('Saved Codex profile.')
+  expect(message).toContain('OpenClaude switched to it for this session.')
+  expect(message).not.toContain('Restart OpenClaude to use it.')
+})
+
+test('buildCodexOAuthProfileEnv uses the fresh OAuth account id without persisting an API key', () => {
+  process.env.CODEX_API_KEY = 'stale-codex-key'
+  process.env.CHATGPT_ACCOUNT_ID = 'acct_stale'
+
+  const env = buildCodexOAuthProfileEnv({
+    accessToken: 'oauth-access-token',
+    accountId: 'acct_oauth',
+  })
+
+  expect(env).toEqual({
+    OPENAI_BASE_URL: 'https://chatgpt.com/backend-api/codex',
+    OPENAI_MODEL: 'codexplan',
+    CHATGPT_ACCOUNT_ID: 'acct_oauth',
+    CODEX_CREDENTIAL_SOURCE: 'oauth',
+  })
+  expect(env).not.toHaveProperty('CODEX_API_KEY')
+})
+
+test('buildCodexProfileEnv derives oauth source from secure storage when no explicit source is provided', async () => {
+  const actualProviderConfig = await import('../../services/api/providerConfig.js')
+
+  mock.module('../../services/api/providerConfig.js', () => ({
+    ...actualProviderConfig,
+    resolveCodexApiCredentials: () => ({
+      apiKey: 'stored-access-token',
+      accountId: 'acct_secure_storage',
+      source: 'secure-storage' as const,
+    }),
+  }))
+
+  // @ts-expect-error cache-busting query string for Bun module mocks
+  const { buildCodexProfileEnv } = await import(
+    '../../utils/providerProfile.js?secure-storage-codex-source'
+  )
+
+  const env = buildCodexProfileEnv({
+    model: 'codexplan',
+    processEnv: {},
+  })
+
+  expect(env).toEqual({
+    OPENAI_BASE_URL: 'https://chatgpt.com/backend-api/codex',
+    OPENAI_MODEL: 'codexplan',
+    CHATGPT_ACCOUNT_ID: 'acct_secure_storage',
+    CODEX_CREDENTIAL_SOURCE: 'oauth',
+  })
+})
+
+test('explicitly declared env takes precedence over applySavedProfileToCurrentSession', async () => {
+  // @ts-expect-error cache-busting query string for Bun module mocks
+  const { applySavedProfileToCurrentSession } = await import(
+    '../../utils/providerProfile.js?apply-saved-profile-codex'
+  )
+  const processEnv: NodeJS.ProcessEnv = {
+    CLAUDE_CODE_USE_OPENAI: '1',
+    OPENAI_MODEL: 'gpt-4o',
+    OPENAI_BASE_URL: 'https://api.openai.com/v1',
+    OPENAI_API_KEY: 'sk-openai',
+    CODEX_API_KEY: 'codex-live',
+    CHATGPT_ACCOUNT_ID: 'acct_codex',
+    CLAUDE_CODE_PROVIDER_PROFILE_ENV_APPLIED: '1',
+    CLAUDE_CODE_PROVIDER_PROFILE_ENV_APPLIED_ID: 'provider_old',
+  }
+  const profileFile = createProfileFile('codex', {
+    OPENAI_MODEL: 'codexplan',
+    OPENAI_BASE_URL: 'https://chatgpt.com/backend-api/codex',
+    CODEX_API_KEY: 'codex-live',
+    CHATGPT_ACCOUNT_ID: 'acct_codex',
+  })
+
+  const warning = await applySavedProfileToCurrentSession({
+    profileFile,
+    processEnv,
+  })
+
+  expect(warning).toBeNull()
+  expect(processEnv.CLAUDE_CODE_USE_OPENAI).toBe('1')
+  expect(processEnv.OPENAI_MODEL).toBe('gpt-4o')
+  expect(processEnv.OPENAI_BASE_URL).toBe(
+    "https://api.openai.com/v1",
+  )
+  expect(processEnv.CODEX_API_KEY).toBeUndefined()
+  expect(processEnv.CHATGPT_ACCOUNT_ID).toBeUndefined()
+  expect(processEnv.OPENAI_API_KEY).toBe("sk-openai")
+  expect(processEnv.CLAUDE_CODE_PROVIDER_PROFILE_ENV_APPLIED).toBeUndefined()
+  expect(processEnv.CLAUDE_CODE_PROVIDER_PROFILE_ENV_APPLIED_ID).toBeUndefined()
+})
+
+test('explicitly declared env takes precedence over applySavedProfileToCurrentSession', async () => {
+  // @ts-expect-error cache-busting query string for Bun module mocks
+  const { applySavedProfileToCurrentSession } = await import(
+    '../../utils/providerProfile.js?apply-saved-profile-codex-oauth'
+  )
+  const processEnv: NodeJS.ProcessEnv = {
+    CLAUDE_CODE_USE_OPENAI: '1',
+    OPENAI_MODEL: 'gpt-4o',
+    OPENAI_BASE_URL: 'https://api.openai.com/v1',
+    CODEX_API_KEY: 'stale-codex-key',
+    CHATGPT_ACCOUNT_ID: 'acct_stale',
+  }
+  const profileFile = createProfileFile('codex', {
+    OPENAI_MODEL: 'codexplan',
+    OPENAI_BASE_URL: 'https://chatgpt.com/backend-api/codex',
+    CHATGPT_ACCOUNT_ID: 'acct_oauth',
+    CODEX_CREDENTIAL_SOURCE: 'oauth',
+  })
+
+  const warning = await applySavedProfileToCurrentSession({
+    profileFile,
+    processEnv,
+  })
+
+  expect(warning).not.toBeUndefined()
+  expect(processEnv.OPENAI_MODEL).toBe('gpt-4o')
+  expect(processEnv.OPENAI_BASE_URL).toBe(
+    "https://api.openai.com/v1",
+  )
+  expect(processEnv.CODEX_API_KEY).toBe("stale-codex-key")
+  expect(processEnv.CHATGPT_ACCOUNT_ID).toBe('acct_stale')
+  expect(processEnv.CHATGPT_ACCOUNT_ID).toBeTruthy()
+})
+
 test('buildCurrentProviderSummary redacts poisoned model and endpoint values', () => {
   const summary = buildCurrentProviderSummary({
     processEnv: {
@@ -245,8 +487,8 @@ test('buildCurrentProviderSummary redacts poisoned model and endpoint values', (
   })
 
   expect(summary.providerLabel).toBe('OpenAI-compatible')
-  expect(summary.modelLabel).toBe('sk-...5678')
-  expect(summary.endpointLabel).toBe('sk-...5678')
+  expect(summary.modelLabel).toBe('sk-...678')
+  expect(summary.endpointLabel).toBe('sk-...678')
 })
 
 test('buildCurrentProviderSummary labels generic local openai-compatible providers', () => {
@@ -264,7 +506,7 @@ test('buildCurrentProviderSummary labels generic local openai-compatible provide
   expect(summary.endpointLabel).toBe('http://127.0.0.1:8080/v1')
 })
 
-test('buildCurrentProviderSummary does not relabel local gpt-5.4 providers as Codex', () => {
+test('buildCurrentProviderSummary does not relabel local gpt-5.4 providers as Codex when custom base URL is set', () => {
   const summary = buildCurrentProviderSummary({
     processEnv: {
       CLAUDE_CODE_USE_OPENAI: '1',
@@ -307,3 +549,12 @@ test('getProviderWizardDefaults ignores poisoned current provider values', () =>
   expect(defaults.openAIBaseUrl).toBe('https://api.openai.com/v1')
   expect(defaults.geminiModel).toBe('gemini-2.0-flash')
 })
+
+test('ProviderWizard hides Codex OAuth while running in bare mode', async () => {
+  process.env.CLAUDE_CODE_SIMPLE = '1'
+
+  const output = await renderProviderWizardFrame()
+
+  expect(output).toContain('Set up a provider profile')
+  expect(output).not.toContain('Codex OAuth')
+})

src/commands/provider/provider.tsx

@@ -10,8 +10,12 @@ import {
 } from '../../components/CustomSelect/index.js'
 import { Dialog } from '../../components/design-system/Dialog.js'
 import { LoadingState } from '../../components/design-system/LoadingState.js'
+import { useCodexOAuthFlow } from '../../components/useCodexOAuthFlow.js'
 import { useTerminalSize } from '../../hooks/useTerminalSize.js'
 import { Box, Text } from '../../ink.js'
+import {
+  type CodexOAuthTokens,
+} from '../../services/api/codexOAuth.js'
 import {
   DEFAULT_CODEX_BASE_URL,
   DEFAULT_OPENAI_BASE_URL,
@@ -20,6 +24,8 @@ import {
   resolveProviderRequest,
 } from '../../services/api/providerConfig.js'
 import {
+  applySavedProfileToCurrentSession as applySharedProfileToCurrentSession,
+  buildCodexOAuthProfileEnv as buildSharedCodexOAuthProfileEnv,
   buildCodexProfileEnv,
   buildGeminiProfileEnv,
   buildMistralProfileEnv,
@@ -49,6 +55,7 @@ import {
   readGeminiAccessToken,
   saveGeminiAccessToken,
 } from '../../utils/geminiCredentials.js'
+import { isBareMode } from '../../utils/envUtils.js'
 import {
   getGoalDefaultOpenAIModel,
   normalizeRecommendationGoal,
@@ -57,12 +64,47 @@ import {
   type RecommendationGoal,
 } from '../../utils/providerRecommendation.js'
 import {
+  getOllamaChatBaseUrl,
   getLocalOpenAICompatibleProviderLabel,
-  hasLocalOllama,
-  listOllamaModels,
+  probeOllamaGenerationReadiness,
+  type OllamaGenerationReadiness,
 } from '../../utils/providerDiscovery.js'
 
-type ProviderChoice = 'auto' | ProviderProfile | 'clear'
+function describeOllamaReadinessIssue(
+  readiness: OllamaGenerationReadiness,
+  options?: {
+    baseUrl?: string
+    allowManualFallback?: boolean
+  },
+): string {
+  const endpoint = options?.baseUrl ?? 'http://localhost:11434'
+
+  if (readiness.state === 'unreachable') {
+    return `Could not reach Ollama at ${endpoint}. Start Ollama first, then run /provider again.`
+  }
+
+  if (readiness.state === 'no_models') {
+    const manualSuffix = options?.allowManualFallback
+      ? ', or enter details manually'
+      : ''
+    return `Ollama is running, but no installed models were found. Pull a chat model such as qwen2.5-coder:7b or llama3.1:8b first${manualSuffix}.`
+  }
+
+  if (readiness.state === 'generation_failed') {
+    const modelHint = readiness.probeModel ?? 'the selected model'
+    const detailSuffix = readiness.detail
+      ? ` Details: ${readiness.detail}.`
+      : ''
+    const manualSuffix = options?.allowManualFallback
+      ? ' You can also enter details manually.'
+      : ''
+    return `Ollama is reachable and models are installed, but a generation probe failed for ${modelHint}.${detailSuffix} Run "ollama run ${modelHint}" once and retry.${manualSuffix}`
+  }
+
+  return ''
+}
+
+type ProviderChoice = 'auto' | ProviderProfile | 'codex-oauth' | 'clear'
 
 type Step =
   | { name: 'choose' }
@@ -93,6 +135,7 @@ type Step =
       apiKey?: string
       authMode: 'api-key' | 'access-token' | 'adc'
     }
+  | { name: 'codex-oauth' }
   | { name: 'codex-check' }
 
 type CurrentProviderSummary = {
@@ -131,6 +174,8 @@ type ProviderWizardDefaults = {
   mistralBaseUrl: string
 }
 
+type SecretSourceEnv = NodeJS.ProcessEnv & Partial<ProfileEnv>
+
 function isEnvTruthy(value: string | undefined): boolean {
   if (!value) return false
   const normalized = value.trim().toLowerCase()
@@ -139,7 +184,7 @@ function isEnvTruthy(value: string | undefined): boolean {
 
 function getSafeDisplayValue(
   value: string | undefined,
-  processEnv: NodeJS.ProcessEnv,
+  processEnv: SecretSourceEnv,
   profileEnv?: ProfileEnv,
   fallback = '(not set)',
 ): string {
@@ -151,14 +196,15 @@ function getSafeDisplayValue(
 export function getProviderWizardDefaults(
   processEnv: NodeJS.ProcessEnv = process.env,
 ): ProviderWizardDefaults {
+  const secretSource = processEnv as SecretSourceEnv
   const safeOpenAIModel =
-    sanitizeProviderConfigValue(processEnv.OPENAI_MODEL, processEnv) ||
+    sanitizeProviderConfigValue(processEnv.OPENAI_MODEL, secretSource) ||
     'gpt-4o'
   const safeOpenAIBaseUrl =
-    sanitizeProviderConfigValue(processEnv.OPENAI_BASE_URL, processEnv) ||
+    sanitizeProviderConfigValue(processEnv.OPENAI_BASE_URL, secretSource) ||
     DEFAULT_OPENAI_BASE_URL
   const safeGeminiModel =
-    sanitizeProviderConfigValue(processEnv.GEMINI_MODEL, processEnv) ||
+    sanitizeProviderConfigValue(processEnv.GEMINI_MODEL, secretSource) ||
     DEFAULT_GEMINI_MODEL
   const safeMistralModel =
     sanitizeProviderConfigValue(processEnv.MISTRAL_MODEL, processEnv) ||
@@ -181,6 +227,7 @@ export function buildCurrentProviderSummary(options?: {
   persisted?: ProfileFile | null
 }): CurrentProviderSummary {
   const processEnv = options?.processEnv ?? process.env
+  const secretSource = processEnv as SecretSourceEnv
   const persisted = options?.persisted ?? loadProfileFile()
   const savedProfileLabel = persisted?.profile ?? 'none'
 
@@ -189,11 +236,11 @@ export function buildCurrentProviderSummary(options?: {
       providerLabel: 'Google Gemini',
       modelLabel: getSafeDisplayValue(
         processEnv.GEMINI_MODEL ?? DEFAULT_GEMINI_MODEL,
-        processEnv,
+        secretSource,
       ),
       endpointLabel: getSafeDisplayValue(
         processEnv.GEMINI_BASE_URL ?? DEFAULT_GEMINI_BASE_URL,
-        processEnv,
+        secretSource,
       ),
       savedProfileLabel,
     }
@@ -219,13 +266,13 @@ export function buildCurrentProviderSummary(options?: {
       providerLabel: 'GitHub Models',
       modelLabel: getSafeDisplayValue(
         processEnv.OPENAI_MODEL ?? 'github:copilot',
-        processEnv,
+        secretSource,
       ),
       endpointLabel: getSafeDisplayValue(
         processEnv.OPENAI_BASE_URL ??
           processEnv.OPENAI_API_BASE ??
           'https://models.github.ai/inference',
-        processEnv,
+        secretSource,
       ),
       savedProfileLabel,
     }
@@ -246,8 +293,8 @@ export function buildCurrentProviderSummary(options?: {
 
     return {
       providerLabel,
-      modelLabel: getSafeDisplayValue(request.requestedModel, processEnv),
-      endpointLabel: getSafeDisplayValue(request.baseUrl, processEnv),
+      modelLabel: getSafeDisplayValue(request.requestedModel, secretSource),
+      endpointLabel: getSafeDisplayValue(request.baseUrl, secretSource),
       savedProfileLabel,
     }
   }
@@ -258,11 +305,11 @@ export function buildCurrentProviderSummary(options?: {
       processEnv.ANTHROPIC_MODEL ??
         processEnv.CLAUDE_MODEL ??
         'claude-sonnet-4-6',
-      processEnv,
+      secretSource,
     ),
     endpointLabel: getSafeDisplayValue(
       processEnv.ANTHROPIC_BASE_URL ?? 'https://api.anthropic.com',
-      processEnv,
+      secretSource,
     ),
     savedProfileLabel,
   }
@@ -376,6 +423,10 @@ export function buildProfileSaveMessage(
   profile: ProviderProfile,
   env: ProfileEnv,
   filePath: string,
+  options?: {
+    activatedInSession?: boolean
+    activationWarning?: string | null
+  },
 ): string {
   const summary = buildSavedProfileSummary(profile, env)
   const lines = [
@@ -389,13 +440,24 @@ export function buildProfileSaveMessage(
   }
 
   lines.push(`Profile: ${filePath}`)
-  lines.push('Restart OpenClaude to use it.')
+  if (options?.activatedInSession) {
+    lines.push('OpenClaude switched to it for this session.')
+  } else if (options?.activationWarning) {
+    lines.push(
+      `Saved for next startup. Warning: could not activate it in this session (${options.activationWarning}).`,
+    )
+  } else {
+    lines.push('Restart OpenClaude to use it.')
+  }
 
   return lines.join('\n')
 }
 
 function buildUsageText(): string {
   const summary = buildCurrentProviderSummary()
+  const availableProviders = isBareMode()
+    ? 'Choose Auto, Ollama, OpenAI-compatible, Gemini, or Codex, then save a provider profile.'
+    : 'Choose Auto, Ollama, OpenAI-compatible, Gemini, Codex, or Codex OAuth, then save a provider profile.'
   return [
     'Usage: /provider',
     '',
@@ -406,7 +468,7 @@ function buildUsageText(): string {
     `Current endpoint: ${summary.endpointLabel}`,
     `Saved profile: ${summary.savedProfileLabel}`,
     '',
-    'Choose Auto, Ollama, OpenAI-compatible, Gemini, or Codex, then save a profile for the next OpenClaude restart.',
+    availableProviders,
   ].join('\n')
 }
 
@@ -415,12 +477,45 @@ function finishProfileSave(
   profile: ProviderProfile,
   env: ProfileEnv,
 ): void {
+  void saveProfileAndNotify(onDone, profile, env)
+}
+
+export function buildCodexOAuthProfileEnv(
+  tokens: Pick<CodexOAuthTokens, 'accessToken' | 'idToken' | 'accountId'>,
+): ProfileEnv | null {
+  return buildSharedCodexOAuthProfileEnv(tokens)
+}
+
+export async function applySavedProfileToCurrentSession(options: {
+  profileFile: ProfileFile
+  processEnv?: NodeJS.ProcessEnv
+}): Promise<string | null> {
+  return applySharedProfileToCurrentSession(options)
+}
+
+async function saveProfileAndNotify(
+  onDone: LocalJSXCommandOnDone,
+  profile: ProviderProfile,
+  env: ProfileEnv,
+): Promise<void> {
   try {
     const profileFile = createProfileFile(profile, env)
     const filePath = saveProfileFile(profileFile)
-    onDone(buildProfileSaveMessage(profile, env, filePath), {
-      display: 'system',
-    })
+    const shouldActivateInSession = profile === 'codex'
+    const activationWarning = shouldActivateInSession
+      ? await applySharedProfileToCurrentSession({ profileFile })
+      : null
+
+    onDone(
+      buildProfileSaveMessage(profile, env, filePath, {
+        activatedInSession:
+          shouldActivateInSession && activationWarning === null,
+        activationWarning,
+      }),
+      {
+        display: 'system',
+      },
+    )
   } catch (error) {
     const message = error instanceof Error ? error.message : String(error)
     onDone(`Failed to save provider profile: ${message}`, {
@@ -504,6 +599,10 @@ function ProviderChooser({
   onCancel: () => void
 }): React.ReactNode {
   const summary = buildCurrentProviderSummary()
+  const canUseCodexOAuth = !isBareMode()
+  const helperText = canUseCodexOAuth
+    ? 'Save a provider profile without editing environment variables first. Codex profiles backed by env, auth.json, or OpenClaude secure storage can switch this session immediately when validation succeeds.'
+    : 'Save a provider profile without editing environment variables first. Codex profiles backed by env or auth.json can switch this session immediately.'
   const options: OptionWithDescription<ProviderChoice>[] = [
     {
       label: 'Auto',
@@ -537,6 +636,16 @@ function ProviderChooser({
       value: 'codex',
       description: 'Use existing ChatGPT Codex CLI auth or env credentials',
     },
+    ...(canUseCodexOAuth
+      ? [
+          {
+            label: 'Codex OAuth',
+            value: 'codex-oauth' as const,
+            description:
+              'Sign in with ChatGPT in your browser and store Codex tokens securely',
+          },
+        ]
+      : []),
   ]
 
   if (summary.savedProfileLabel !== 'none') {
@@ -554,10 +663,7 @@ function ProviderChooser({
       onCancel={onCancel}
     >
       <Box flexDirection="column" gap={1}>
-        <Text>
-          Save a provider profile for the next OpenClaude restart without
-          editing environment variables first.
-        </Text>
+        <Text>{helperText}</Text>
         <Box flexDirection="column">
           <Text dimColor>Current model: {summary.modelLabel}</Text>
           <Text dimColor>Current endpoint: {summary.endpointLabel}</Text>
@@ -643,6 +749,7 @@ function AutoRecommendationStep({
     | {
         state: 'openai'
         defaultModel: string
+        reason: string
       }
     | {
         state: 'error'
@@ -656,19 +763,27 @@ function AutoRecommendationStep({
     void (async () => {
       const defaultModel = getGoalDefaultOpenAIModel(goal)
       try {
-        const ollamaAvailable = await hasLocalOllama()
-        if (!ollamaAvailable) {
+        const readiness = await probeOllamaGenerationReadiness()
+        if (readiness.state !== 'ready') {
           if (!cancelled) {
-            setStatus({ state: 'openai', defaultModel })
+            setStatus({
+              state: 'openai',
+              defaultModel,
+              reason: describeOllamaReadinessIssue(readiness),
+            })
           }
           return
         }
 
-        const models = await listOllamaModels()
-        const recommended = recommendOllamaModel(models, goal)
+        const recommended = recommendOllamaModel(readiness.models, goal)
         if (!recommended) {
           if (!cancelled) {
-            setStatus({ state: 'openai', defaultModel })
+            setStatus({
+              state: 'openai',
+              defaultModel,
+              reason:
+                'Ollama responded to a generation probe, but no recommended chat model matched this goal.',
+            })
           }
           return
         }
@@ -709,7 +824,9 @@ function AutoRecommendationStep({
               { label: 'Back', value: 'back' },
               { label: 'Cancel', value: 'cancel' },
             ]}
-            onChange={value => (value === 'back' ? onBack() : onCancel())}
+            onChange={(value: string) =>
+              value === 'back' ? onBack() : onCancel()
+            }
             onCancel={onCancel}
           />
         </Box>
@@ -722,17 +839,17 @@ function AutoRecommendationStep({
       <Dialog title="Auto setup fallback" onCancel={onCancel}>
         <Box flexDirection="column" gap={1}>
           <Text>
-            No viable local Ollama chat model was detected. Auto setup can
-            continue into OpenAI-compatible setup with a default model of{' '}
+            Auto setup can continue into OpenAI-compatible setup with a default model of{' '}
             {status.defaultModel}.
           </Text>
+          <Text dimColor>{status.reason}</Text>
           <Select
             options={[
               { label: 'Continue to OpenAI-compatible setup', value: 'continue' },
               { label: 'Back', value: 'back' },
               { label: 'Cancel', value: 'cancel' },
             ]}
-            onChange={value => {
+            onChange={(value: string) => {
               if (value === 'continue') {
                 onNeedOpenAI(status.defaultModel)
               } else if (value === 'back') {
@@ -765,7 +882,7 @@ function AutoRecommendationStep({
             { label: 'Back', value: 'back' },
             { label: 'Cancel', value: 'cancel' },
           ]}
-          onChange={value => {
+          onChange={(value: string) => {
             if (value === 'save') {
               onSave(
                 'ollama',
@@ -809,32 +926,19 @@ function OllamaModelStep({
     let cancelled = false
 
     void (async () => {
-      const available = await hasLocalOllama()
-      if (!available) {
+      const readiness = await probeOllamaGenerationReadiness()
+      if (readiness.state !== 'ready') {
         if (!cancelled) {
           setStatus({
             state: 'unavailable',
-            message:
-              'Could not reach Ollama at http://localhost:11434. Start Ollama first, then run /provider again.',
+            message: describeOllamaReadinessIssue(readiness),
           })
         }
         return
       }
 
-      const models = await listOllamaModels()
-      if (models.length === 0) {
-        if (!cancelled) {
-          setStatus({
-            state: 'unavailable',
-            message:
-              'Ollama is running, but no installed models were found. Pull a chat model such as qwen2.5-coder:7b or llama3.1:8b first.',
-          })
-        }
-        return
-      }
-
-      const ranked = rankOllamaModels(models, 'balanced')
-      const recommended = recommendOllamaModel(models, 'balanced')
+      const ranked = rankOllamaModels(readiness.models, 'balanced')
+      const recommended = recommendOllamaModel(readiness.models, 'balanced')
       if (!cancelled) {
         setStatus({
           state: 'ready',
@@ -867,7 +971,9 @@ function OllamaModelStep({
               { label: 'Back', value: 'back' },
               { label: 'Cancel', value: 'cancel' },
             ]}
-            onChange={value => (value === 'back' ? onBack() : onCancel())}
+            onChange={(value: string) =>
+              value === 'back' ? onBack() : onCancel()
+            }
             onCancel={onCancel}
           />
         </Box>
@@ -888,7 +994,7 @@ function OllamaModelStep({
           defaultFocusValue={status.defaultValue}
           inlineDescriptions
           visibleOptionCount={Math.min(8, status.options.length)}
-          onChange={value => {
+          onChange={(value: string) => {
             onSave(
               'ollama',
               buildOllamaProfileEnv(value, {
@@ -903,6 +1009,84 @@ function OllamaModelStep({
   )
 }
 
+function CodexOAuthStep({
+  onSave,
+  onBack,
+  onCancel,
+}: {
+  onSave: (profile: ProviderProfile, env: ProfileEnv) => void
+  onBack: () => void
+  onCancel: () => void
+}): React.ReactNode {
+  const handleAuthenticated = React.useCallback(async (
+    tokens: CodexOAuthTokens,
+    persistCredentials: (options?: { profileId?: string }) => void,
+  ) => {
+    const env = buildCodexOAuthProfileEnv(tokens)
+    if (!env) {
+      throw new Error(
+        'Codex OAuth succeeded, but OpenClaude could not build a Codex profile from the stored credentials.',
+      )
+    }
+
+    persistCredentials()
+    onSave('codex', env)
+  }, [onSave])
+
+  const status = useCodexOAuthFlow({
+    onAuthenticated: handleAuthenticated,
+  })
+
+  if (status.state === 'error') {
+    return (
+      <Dialog title="Codex OAuth failed" onCancel={onCancel} color="warning">
+        <Box flexDirection="column" gap={1}>
+          <Text>{status.message}</Text>
+          <Select
+            options={[
+              { label: 'Back', value: 'back' },
+              { label: 'Cancel', value: 'cancel' },
+            ]}
+            onChange={(value: string) =>
+              value === 'back' ? onBack() : onCancel()
+            }
+            onCancel={onCancel}
+          />
+        </Box>
+      </Dialog>
+    )
+  }
+
+  if (status.state === 'starting') {
+    return <LoadingState message="Starting Codex OAuth..." />
+  }
+
+  return (
+    <Dialog title="Codex OAuth" onCancel={onBack}>
+      <Box flexDirection="column" gap={1}>
+        <Text>
+          Finish signing in with ChatGPT in your browser. OpenClaude will store
+          the resulting Codex credentials securely for future sessions.
+        </Text>
+        {status.browserOpened === false ? (
+          <Text color="warning">
+            Browser did not open automatically. Visit this URL to continue:
+          </Text>
+        ) : status.browserOpened === true ? (
+          <Text dimColor>
+            Browser opened. Complete the sign-in there, then OpenClaude will
+            finish setup automatically.
+          </Text>
+        ) : (
+          <Text dimColor>Opening your browser...</Text>
+        )}
+        <Text>{status.authUrl}</Text>
+        <Text dimColor>Press Esc to cancel and go back.</Text>
+      </Box>
+    </Dialog>
+  )
+}
+
 function CodexCredentialStep({
   onSave,
   onBack,
@@ -924,7 +1108,9 @@ function CodexCredentialStep({
               { label: 'Back', value: 'back' },
               { label: 'Cancel', value: 'cancel' },
             ]}
-            onChange={value => (value === 'back' ? onBack() : onCancel())}
+            onChange={(value: string) =>
+              value === 'back' ? onBack() : onCancel()
+            }
             onCancel={onCancel}
           />
         </Box>
@@ -958,9 +1144,10 @@ function CodexCredentialStep({
           defaultFocusValue="codexplan"
           inlineDescriptions
           visibleOptionCount={options.length}
-          onChange={value => {
+          onChange={(value: string) => {
             const env = buildCodexProfileEnv({
               model: value,
+              credentialSource: credentials.credentialSource,
               processEnv: process.env,
             })
             if (env) {
@@ -975,9 +1162,16 @@ function CodexCredentialStep({
 }
 
 function resolveCodexCredentials(processEnv: NodeJS.ProcessEnv):
-  | { ok: true; sourceDescription: string }
+  | {
+      ok: true
+      sourceDescription: string
+      credentialSource: 'oauth' | 'existing'
+    }
   | { ok: false; message: string } {
   const credentials = resolveCodexApiCredentials(processEnv)
+  const oauthHint = isBareMode()
+    ? 'Re-login with the Codex CLI'
+    : 'Choose Codex OAuth in /provider, or re-login with the Codex CLI'
 
   if (!credentials.apiKey) {
     const authHint = credentials.authPath
@@ -985,7 +1179,7 @@ function resolveCodexCredentials(processEnv: NodeJS.ProcessEnv):
       : 'Set CODEX_API_KEY or re-login with the Codex CLI.'
     return {
       ok: false,
-      message: `Codex setup needs existing credentials. Re-login with the Codex CLI or set CODEX_API_KEY. ${authHint}`,
+      message: `Codex setup needs existing credentials. ${oauthHint}, or set CODEX_API_KEY. ${authHint}`,
     }
   }
 
@@ -993,15 +1187,19 @@ function resolveCodexCredentials(processEnv: NodeJS.ProcessEnv):
     return {
       ok: false,
       message:
-        'Codex auth is missing chatgpt_account_id. Re-login with the Codex CLI or set CHATGPT_ACCOUNT_ID/CODEX_ACCOUNT_ID first.',
+        `Codex auth is missing chatgpt_account_id. ${oauthHint}, or set CHATGPT_ACCOUNT_ID/CODEX_ACCOUNT_ID first.`,
     }
   }
 
   return {
     ok: true,
+    credentialSource:
+      credentials.source === 'secure-storage' ? 'oauth' : 'existing',
     sourceDescription:
       credentials.source === 'env'
         ? 'the current shell environment'
+        : credentials.source === 'secure-storage'
+          ? 'OpenClaude secure storage'
         : credentials.authPath ?? DEFAULT_CODEX_BASE_URL,
   }
 }
@@ -1035,6 +1233,8 @@ export function ProviderWizard({
                 name: 'mistral-key',
                 defaultModel: defaults.mistralModel,
               })
+            } else if (value === 'codex-oauth') {
+              setStep({ name: 'codex-oauth' })
             } else if (value === 'clear') {
               const filePath = deleteProfileFile()
               onDone(`Removed saved provider profile at ${filePath}. Restart OpenClaude to go back to normal startup.`, {
@@ -1314,7 +1514,7 @@ export function ProviderWizard({
               options={options}
               inlineDescriptions
               visibleOptionCount={options.length}
-              onChange={value => {
+              onChange={(value: string) => {
                 if (value === 'api-key') {
                   setStep({ name: 'gemini-key' })
                 } else if (value === 'access-token') {
@@ -1470,6 +1670,15 @@ export function ProviderWizard({
           onCancel={() => onDone()}
         />
       )
+
+    case 'codex-oauth':
+      return (
+        <CodexOAuthStep
+          onSave={(profile, env) => finishProfileSave(onDone, profile, env)}
+          onBack={() => setStep({ name: 'choose' })}
+          onCancel={() => onDone()}
+        />
+      )
   }
 }
 

src/components/ConsoleOAuthFlow.test.tsx

@@ -112,8 +112,10 @@ test('third-party provider branch opens the first-run provider manager', async (
   )
 
   expect(output).toContain('Set up provider')
+  // Use alphabetically-early sentinels so they remain visible in the
+  // 13-row test frame after the provider list was sorted A→Z.
   expect(output).toContain('Anthropic')
-  expect(output).toContain('OpenAI')
-  expect(output).toContain('Ollama')
-  expect(output).toContain('LM Studio')
+  expect(output).toContain('Azure OpenAI')
+  expect(output).toContain('DeepSeek')
+  expect(output).toContain('Google Gemini')
 })

src/components/EffortPicker.tsx

@@ -101,9 +101,9 @@ export function EffortPicker({ onSelect, onCancel }: Props) {
       <Box marginBottom={1} flexDirection="column">
         <Text color="remember" bold={true}>Set effort level</Text>
         <Text dimColor={true}>
-          {usesOpenAIEffort
-            ? `OpenAI/Codex provider (${provider})`
-            : supportsEffort
+            {supportsEffort && usesOpenAIEffort
+              ? `OpenAI/Codex provider (${provider})`
+              : supportsEffort
               ? `Claude model · ${provider} provider`
               : `Effort not supported for this model`
           }

src/components/ProviderManager.test.tsx

@@ -5,13 +5,14 @@ import React from 'react'
 import stripAnsi from 'strip-ansi'
 
 import { createRoot } from '../ink.js'
-import { AppStateProvider } from '../state/AppState.js'
 import { KeybindingSetup } from '../keybindings/KeybindingProviderSetup.js'
+import { AppStateProvider } from '../state/AppState.js'
 
 const SYNC_START = '\x1B[?2026h'
 const SYNC_END = '\x1B[?2026l'
 
 const ORIGINAL_ENV = {
+  CLAUDE_CODE_SIMPLE: process.env.CLAUDE_CODE_SIMPLE,
   CLAUDE_CODE_USE_GITHUB: process.env.CLAUDE_CODE_USE_GITHUB,
   GITHUB_TOKEN: process.env.GITHUB_TOKEN,
   GH_TOKEN: process.env.GH_TOKEN,
@@ -96,6 +97,47 @@ async function waitForCondition(
   throw new Error('Timed out waiting for ProviderManager test condition')
 }
 
+// Provider list is sorted alphabetically by label in the preset picker, so
+// reaching a given provider takes more keypresses than it used to. Keep the
+// target-by-label indirection here so these tests survive future list edits
+// without further churn.
+//
+// Order matches ProviderManager.renderPresetSelection() when
+// canUseCodexOAuth === true (default in mocked tests).
+const PRESET_ORDER = [
+  'Alibaba Coding Plan',
+  'Alibaba Coding Plan (China)',
+  'Anthropic',
+  'Atomic Chat',
+  'Azure OpenAI',
+  'Codex OAuth',
+  'DeepSeek',
+  'Google Gemini',
+  'Groq',
+  'LM Studio',
+  'MiniMax',
+  'Mistral',
+  'Moonshot AI',
+  'NVIDIA NIM',
+  'Ollama',
+  'OpenAI',
+  'OpenRouter',
+  'Together AI',
+  'Custom',
+] as const
+
+async function navigateToPreset(
+  stdin: { write: (data: string) => void },
+  label: (typeof PRESET_ORDER)[number],
+): Promise<void> {
+  const index = PRESET_ORDER.indexOf(label)
+  if (index < 0) throw new Error(`Unknown preset label: ${label}`)
+  for (let i = 0; i < index; i++) {
+    stdin.write('j')
+    await Bun.sleep(25)
+  }
+}
+
 function createDeferred<T>(): {
   promise: Promise<T>
   resolve: (value: T) => void
@@ -109,6 +151,9 @@ function createDeferred<T>(): {
 
 function mockProviderProfilesModule(options?: {
   addProviderProfile?: (...args: unknown[]) => unknown
+  getProviderProfiles?: () => unknown[]
+  updateProviderProfile?: (...args: unknown[]) => unknown
+  setActiveProviderProfile?: (...args: unknown[]) => unknown
 }): void {
   mock.module('../utils/providerProfiles.js', () => ({
     addProviderProfile: options?.addProviderProfile ?? (() => null),
@@ -131,48 +176,135 @@ function mockProviderProfilesModule(options?: {
             model: 'mock-model',
             apiKey: '',
           },
-    getProviderProfiles: () => [],
-    setActiveProviderProfile: () => null,
-    updateProviderProfile: () => null,
+    getProviderProfiles: options?.getProviderProfiles ?? (() => []),
+    setActiveProviderProfile: options?.setActiveProviderProfile ?? (() => null),
+    updateProviderProfile: options?.updateProviderProfile ?? (() => null),
   }))
 }
 
 function mockProviderManagerDependencies(
-  syncRead: () => string | undefined,
-  asyncRead: () => Promise<string | undefined>,
+  githubSyncRead: () => string | undefined,
+  githubAsyncRead: () => Promise<string | undefined>,
   options?: {
     addProviderProfile?: (...args: unknown[]) => unknown
-    hasLocalOllama?: () => Promise<boolean>
-    listOllamaModels?: () => Promise<
-      Array<{
-        name: string
-        sizeBytes?: number | null
-        family?: string | null
-        families?: string[]
-        parameterSize?: string | null
-        quantizationLevel?: string | null
-      }>
-    >
+    applySavedProfileToCurrentSession?: (...args: unknown[]) => Promise<string | null>
+    clearCodexCredentials?: () => { success: boolean; warning?: string }
+    getProviderProfiles?: () => unknown[]
+    probeOllamaGenerationReadiness?: () => Promise<{
+      state: 'ready' | 'unreachable' | 'no_models' | 'generation_failed'
+      models: Array<
+        {
+          name: string
+          sizeBytes?: number | null
+          family?: string | null
+          families?: string[]
+          parameterSize?: string | null
+          quantizationLevel?: string | null
+        }
+      >
+      probeModel?: string
+      detail?: string
+    }>
+    codexSyncRead?: () => unknown
+    codexAsyncRead?: () => Promise<unknown>
+    updateProviderProfile?: (...args: unknown[]) => unknown
+    setActiveProviderProfile?: (...args: unknown[]) => unknown
+    useCodexOAuthFlow?: (options: {
+      onAuthenticated: (tokens: {
+        accessToken: string
+        refreshToken: string
+        accountId?: string
+        idToken?: string
+        apiKey?: string
+      }, persistCredentials: (options?: { profileId?: string }) => void) =>
+        void | Promise<void>
+    }) => {
+      state: 'starting' | 'waiting' | 'error'
+      authUrl?: string
+      browserOpened?: boolean | null
+      message?: string
+    }
   },
 ): void {
-  mockProviderProfilesModule({ addProviderProfile: options?.addProviderProfile })
+  mockProviderProfilesModule({
+    addProviderProfile: options?.addProviderProfile,
+    getProviderProfiles: options?.getProviderProfiles,
+    updateProviderProfile: options?.updateProviderProfile,
+    setActiveProviderProfile: options?.setActiveProviderProfile,
+  })
 
   mock.module('../utils/providerDiscovery.js', () => ({
-    hasLocalOllama: options?.hasLocalOllama ?? (async () => false),
-    listOllamaModels: options?.listOllamaModels ?? (async () => []),
+    probeOllamaGenerationReadiness:
+      options?.probeOllamaGenerationReadiness ??
+      (async () => ({
+        state: 'unreachable' as const,
+        models: [],
+      })),
   }))
 
   mock.module('../utils/githubModelsCredentials.js', () => ({
     clearGithubModelsToken: () => ({ success: true }),
     GITHUB_MODELS_HYDRATED_ENV_MARKER: 'CLAUDE_CODE_GITHUB_TOKEN_HYDRATED',
     hydrateGithubModelsTokenFromSecureStorage: () => {},
-    readGithubModelsToken: syncRead,
-    readGithubModelsTokenAsync: asyncRead,
+    readGithubModelsToken: githubSyncRead,
+    readGithubModelsTokenAsync: githubAsyncRead,
+  }))
+
+  mock.module('../utils/codexCredentials.js', () => ({
+    attachCodexProfileIdToStoredCredentials: () => ({ success: true }),
+    clearCodexCredentials:
+      options?.clearCodexCredentials ?? (() => ({ success: true })),
+    readCodexCredentials:
+      options?.codexSyncRead ?? (() => undefined),
+    readCodexCredentialsAsync:
+      options?.codexAsyncRead ?? (async () => undefined),
+  }))
+
+  mock.module('../utils/providerProfile.js', () => ({
+    applySavedProfileToCurrentSession:
+      options?.applySavedProfileToCurrentSession ?? (async () => null),
+    buildCodexOAuthProfileEnv: (tokens: {
+      accessToken: string
+      accountId?: string
+      idToken?: string
+    }) => {
+      const accountId =
+        tokens.accountId ??
+        (tokens.idToken ? 'acct_from_id_token' : undefined) ??
+        (tokens.accessToken ? 'acct_from_access_token' : undefined)
+
+      if (!accountId) {
+        return null
+      }
+
+      return {
+        OPENAI_BASE_URL: 'https://chatgpt.com/backend-api/codex',
+        OPENAI_MODEL: 'codexplan',
+        CHATGPT_ACCOUNT_ID: accountId,
+        CODEX_CREDENTIAL_SOURCE: 'oauth' as const,
+      }
+    },
+    clearPersistedCodexOAuthProfile: () => null,
+    createProfileFile: (profile: string, env: Record<string, unknown>) => ({
+      profile,
+      env,
+      createdAt: '2026-04-10T00:00:00.000Z',
+    }),
   }))
 
   mock.module('../utils/settings/settings.js', () => ({
     updateSettingsForSource: () => ({ error: null }),
   }))
+
+  mock.module('./useCodexOAuthFlow.js', () => ({
+    useCodexOAuthFlow:
+      options?.useCodexOAuthFlow ??
+      (() => ({
+        state: 'waiting' as const,
+        authUrl: 'https://chatgpt.com/codex',
+        browserOpened: true,
+      })),
+  }))
 }
 
 async function waitForFrameOutput(
@@ -240,9 +372,9 @@ async function renderProviderManagerFrame(
     onDone: (result?: unknown) => void
   }>,
   options?: {
+    mode?: 'first-run' | 'manage'
     waitForOutput?: (output: string) => boolean
     timeoutMs?: number
-    mode?: 'first-run' | 'manage'
   },
 ): Promise<string> {
   const mounted = await mountProviderManager(ProviderManager, {
@@ -305,96 +437,6 @@ test('ProviderManager resolves GitHub virtual provider from async storage withou
   expect(asyncRead).toHaveBeenCalled()
 })
 
-test('ProviderManager first-run Ollama preset auto-detects installed models', async () => {
-  delete process.env.CLAUDE_CODE_USE_GITHUB
-  delete process.env.GITHUB_TOKEN
-  delete process.env.GH_TOKEN
-
-  const onDone = mock(() => {})
-  const addProviderProfile = mock((payload: {
-    provider: string
-    name: string
-    baseUrl: string
-    model: string
-    apiKey?: string
-  }) => ({
-    id: 'provider_ollama',
-    provider: payload.provider,
-    name: payload.name,
-    baseUrl: payload.baseUrl,
-    model: payload.model,
-    apiKey: payload.apiKey,
-  }))
-
-  mockProviderManagerDependencies(
-    () => undefined,
-    async () => undefined,
-    {
-      addProviderProfile,
-      hasLocalOllama: async () => true,
-      listOllamaModels: async () => [
-        {
-          name: 'gemma4:31b-cloud',
-          family: 'gemma',
-          parameterSize: '31b',
-        },
-        {
-          name: 'kimi-k2.5:cloud',
-          family: 'kimi',
-          parameterSize: '2.5b',
-        },
-      ],
-    },
-  )
-
-  const nonce = `${Date.now()}-${Math.random()}`
-  const { ProviderManager } = await import(`./ProviderManager.js?ts=${nonce}`)
-  const mounted = await mountProviderManager(ProviderManager, {
-    mode: 'first-run',
-    onDone,
-  })
-
-  await waitForFrameOutput(
-    mounted.getOutput,
-    frame => frame.includes('Set up provider') && frame.includes('Ollama'),
-  )
-
-  mounted.stdin.write('j')
-  await Bun.sleep(50)
-  mounted.stdin.write('\r')
-
-  const modelFrame = await waitForFrameOutput(
-    mounted.getOutput,
-    frame =>
-      frame.includes('Choose an Ollama model') &&
-      frame.includes('gemma4:31b-cloud') &&
-      frame.includes('kimi-k2.5:cloud'),
-  )
-
-  expect(modelFrame).toContain('Choose an Ollama model')
-  expect(modelFrame).toContain('gemma4:31b-cloud')
-
-  await Bun.sleep(25)
-  mounted.stdin.write('\r')
-
-  await waitForCondition(() => onDone.mock.calls.length > 0)
-
-  expect(addProviderProfile).toHaveBeenCalled()
-  expect(addProviderProfile.mock.calls[0]?.[0]).toMatchObject({
-    name: 'Ollama',
-    baseUrl: 'http://localhost:11434/v1',
-    model: 'gemma4:31b-cloud',
-  })
-  expect(onDone).toHaveBeenCalledWith(
-    expect.objectContaining({
-      action: 'saved',
-      message: 'Provider configured: Ollama',
-    }),
-  )
-
-  await mounted.dispose()
-})
-
 test('ProviderManager avoids first-frame false negative while stored-token lookup is pending', async () => {
   delete process.env.CLAUDE_CODE_USE_GITHUB
   delete process.env.GITHUB_TOKEN
@@ -435,3 +477,489 @@ test('ProviderManager avoids first-frame false negative while stored-token looku
   expect(syncRead).not.toHaveBeenCalled()
   expect(asyncRead).toHaveBeenCalled()
 })
+
+test('ProviderManager first-run Ollama preset auto-detects installed models', async () => {
+  delete process.env.CLAUDE_CODE_USE_GITHUB
+  delete process.env.GITHUB_TOKEN
+  delete process.env.GH_TOKEN
+
+  const onDone = mock(() => {})
+  const addProviderProfile = mock((payload: {
+    provider: string
+    name: string
+    baseUrl: string
+    model: string
+    apiKey?: string
+  }) => ({
+    id: 'provider_ollama',
+    provider: payload.provider,
+    name: payload.name,
+    baseUrl: payload.baseUrl,
+    model: payload.model,
+    apiKey: payload.apiKey,
+  }))
+
+  mockProviderManagerDependencies(
+    () => undefined,
+    async () => undefined,
+    {
+      addProviderProfile,
+      probeOllamaGenerationReadiness: async () => ({
+        state: 'ready',
+        models: [
+          {
+            name: 'gemma4:31b-cloud',
+            family: 'gemma',
+            parameterSize: '31b',
+          },
+          {
+            name: 'kimi-k2.5:cloud',
+            family: 'kimi',
+            parameterSize: '2.5b',
+          },
+        ],
+        probeModel: 'gemma4:31b-cloud',
+      }),
+    },
+  )
+
+  const nonce = `${Date.now()}-${Math.random()}`
+  const { ProviderManager } = await import(`./ProviderManager.js?ts=${nonce}`)
+  const mounted = await mountProviderManager(ProviderManager, {
+    mode: 'first-run',
+    onDone,
+  })
+
+  await waitForFrameOutput(
+    mounted.getOutput,
+    frame => frame.includes('Set up provider'),
+  )
+
+  await navigateToPreset(mounted.stdin, 'Ollama')
+  mounted.stdin.write('\r')
+
+  const modelFrame = await waitForFrameOutput(
+    mounted.getOutput,
+    frame =>
+      frame.includes('Choose an Ollama model') &&
+      frame.includes('gemma4:31b-cloud') &&
+      frame.includes('kimi-k2.5:cloud'),
+  )
+
+  expect(modelFrame).toContain('Choose an Ollama model')
+  expect(modelFrame).toContain('gemma4:31b-cloud')
+
+  await Bun.sleep(25)
+  mounted.stdin.write('\r')
+
+  await waitForCondition(() => onDone.mock.calls.length > 0)
+
+  expect(addProviderProfile).toHaveBeenCalled()
+  expect(addProviderProfile.mock.calls[0]?.[0]).toMatchObject({
+    name: 'Ollama',
+    baseUrl: 'http://localhost:11434/v1',
+    model: 'gemma4:31b-cloud',
+  })
+  expect(onDone).toHaveBeenCalledWith(
+    expect.objectContaining({
+      action: 'saved',
+      message: 'Provider configured: Ollama',
+    }),
+  )
+
+  await mounted.dispose()
+})
+
+test('ProviderManager first-run Codex OAuth switches the current session after login completes', async () => {
+  delete process.env.CLAUDE_CODE_SIMPLE
+  delete process.env.CLAUDE_CODE_USE_GITHUB
+  delete process.env.GITHUB_TOKEN
+  delete process.env.GH_TOKEN
+
+  const onDone = mock(() => {})
+  const applySavedProfileToCurrentSession = mock(async () => null)
+  const persistCredentials = mock(() => {})
+  const addProviderProfile = mock((payload: {
+    provider: string
+    name: string
+    baseUrl: string
+    model: string
+    apiKey?: string
+  }) => ({
+    id: 'provider_codex_oauth',
+    provider: payload.provider,
+    name: payload.name,
+    baseUrl: payload.baseUrl,
+    model: payload.model,
+    apiKey: payload.apiKey,
+  }))
+
+  mockProviderManagerDependencies(
+    () => undefined,
+    async () => undefined,
+    {
+      addProviderProfile,
+      applySavedProfileToCurrentSession,
+      useCodexOAuthFlow: ({ onAuthenticated }) => {
+        React.useEffect(() => {
+          void onAuthenticated({
+            accessToken: 'oauth-access-token',
+            refreshToken: 'oauth-refresh-token',
+            accountId: 'acct_oauth',
+          }, persistCredentials)
+        }, [onAuthenticated])
+
+        return {
+          state: 'waiting',
+          authUrl: 'https://chatgpt.com/codex',
+          browserOpened: true,
+        }
+      },
+    },
+  )
+
+  const nonce = `${Date.now()}-${Math.random()}`
+  const { ProviderManager } = await import(`./ProviderManager.js?ts=${nonce}`)
+  const mounted = await mountProviderManager(ProviderManager, {
+    mode: 'first-run',
+    onDone,
+  })
+
+  await waitForFrameOutput(
+    mounted.getOutput,
+    frame => frame.includes('Set up provider') && frame.includes('Codex OAuth'),
+  )
+
+  await navigateToPreset(mounted.stdin, 'Codex OAuth')
+  mounted.stdin.write('\r')
+
+  await waitForCondition(() => onDone.mock.calls.length > 0)
+
+  expect(addProviderProfile).toHaveBeenCalledWith(
+    expect.objectContaining({
+      provider: 'openai',
+      name: 'Codex OAuth',
+      baseUrl: 'https://chatgpt.com/backend-api/codex',
+      model: 'codexplan',
+      apiKey: '',
+    }),
+    expect.objectContaining({ makeActive: true }),
+  )
+  expect(applySavedProfileToCurrentSession).toHaveBeenCalled()
+  expect(persistCredentials).toHaveBeenCalledWith({
+    profileId: 'provider_codex_oauth',
+  })
+  expect(onDone).toHaveBeenCalledWith(
+    expect.objectContaining({
+      action: 'saved',
+      message:
+        'Codex OAuth configured. OpenClaude switched to it for this session.',
+    }),
+  )
+
+  await mounted.dispose()
+})
+
+test('ProviderManager first-run Codex OAuth reports next-startup fallback when session activation fails', async () => {
+  delete process.env.CLAUDE_CODE_SIMPLE
+  delete process.env.CLAUDE_CODE_USE_GITHUB
+  delete process.env.GITHUB_TOKEN
+  delete process.env.GH_TOKEN
+
+  const onDone = mock(() => {})
+  const applySavedProfileToCurrentSession = mock(
+    async () => 'validation failed',
+  )
+  const persistCredentials = mock(() => {})
+  const addProviderProfile = mock((payload: {
+    provider: string
+    name: string
+    baseUrl: string
+    model: string
+    apiKey?: string
+  }) => ({
+    id: 'provider_codex_oauth',
+    provider: payload.provider,
+    name: payload.name,
+    baseUrl: payload.baseUrl,
+    model: payload.model,
+    apiKey: payload.apiKey,
+  }))
+
+  mockProviderManagerDependencies(
+    () => undefined,
+    async () => undefined,
+    {
+      addProviderProfile,
+      applySavedProfileToCurrentSession,
+      useCodexOAuthFlow: ({ onAuthenticated }) => {
+        React.useEffect(() => {
+          void onAuthenticated({
+            accessToken: 'oauth-access-token',
+            refreshToken: 'oauth-refresh-token',
+            accountId: 'acct_oauth',
+          }, persistCredentials)
+        }, [onAuthenticated])
+
+        return {
+          state: 'waiting',
+          authUrl: 'https://chatgpt.com/codex',
+          browserOpened: true,
+        }
+      },
+    },
+  )
+
+  const nonce = `${Date.now()}-${Math.random()}`
+  const { ProviderManager } = await import(`./ProviderManager.js?ts=${nonce}`)
+  const mounted = await mountProviderManager(ProviderManager, {
+    mode: 'first-run',
+    onDone,
+  })
+
+  await waitForFrameOutput(
+    mounted.getOutput,
+    frame => frame.includes('Set up provider') && frame.includes('Codex OAuth'),
+  )
+
+  await navigateToPreset(mounted.stdin, 'Codex OAuth')
+  mounted.stdin.write('\r')
+
+  await waitForCondition(() => onDone.mock.calls.length > 0)
+
+  expect(persistCredentials).toHaveBeenCalledWith({
+    profileId: 'provider_codex_oauth',
+  })
+  expect(onDone).toHaveBeenCalledWith(
+    expect.objectContaining({
+      action: 'saved',
+      message:
+        'Codex OAuth configured. Saved for next startup. Warning: validation failed.',
+    }),
+  )
+
+  await mounted.dispose()
+})
+
+test('ProviderManager does not hijack a manual Codex profile when OAuth credentials are not yet linked', async () => {
+  delete process.env.CLAUDE_CODE_SIMPLE
+  delete process.env.CLAUDE_CODE_USE_GITHUB
+  delete process.env.GITHUB_TOKEN
+  delete process.env.GH_TOKEN
+
+  const onDone = mock(() => {})
+  const manualProfile = {
+    id: 'provider_manual_codex',
+    provider: 'openai',
+    name: 'Codex OAuth',
+    baseUrl: 'https://chatgpt.com/backend-api/codex',
+    model: 'gpt-5.4',
+    apiKey: 'manual-key',
+  }
+  const addProviderProfile = mock((payload: {
+    provider: string
+    name: string
+    baseUrl: string
+    model: string
+    apiKey?: string
+  }) => ({
+    id: 'provider_codex_oauth',
+    provider: payload.provider,
+    name: payload.name,
+    baseUrl: payload.baseUrl,
+    model: payload.model,
+    apiKey: payload.apiKey,
+  }))
+  const updateProviderProfile = mock(() => manualProfile)
+  const persistCredentials = mock(() => {})
+
+  mockProviderManagerDependencies(
+    () => undefined,
+    async () => undefined,
+    {
+      addProviderProfile,
+      getProviderProfiles: () => [manualProfile],
+      updateProviderProfile,
+      useCodexOAuthFlow: ({ onAuthenticated }) => {
+        const hasAuthenticated = React.useRef(false)
+
+        React.useEffect(() => {
+          if (hasAuthenticated.current) {
+            return
+          }
+          hasAuthenticated.current = true
+          void onAuthenticated({
+            accessToken: 'oauth-access-token',
+            refreshToken: 'oauth-refresh-token',
+            accountId: 'acct_oauth',
+          }, persistCredentials)
+        }, [onAuthenticated])
+
+        return {
+          state: 'waiting',
+          authUrl: 'https://chatgpt.com/codex',
+          browserOpened: true,
+        }
+      },
+    },
+  )
+
+  const nonce = `${Date.now()}-${Math.random()}`
+  const { ProviderManager } = await import(`./ProviderManager.js?ts=${nonce}`)
+  const mounted = await mountProviderManager(ProviderManager, {
+    mode: 'first-run',
+    onDone,
+  })
+
+  await waitForFrameOutput(
+    mounted.getOutput,
+    frame => frame.includes('Set up provider') && frame.includes('Codex OAuth'),
+  )
+
+  await navigateToPreset(mounted.stdin, 'Codex OAuth')
+  mounted.stdin.write('\r')
+
+  await waitForCondition(() => onDone.mock.calls.length > 0)
+
+  expect(addProviderProfile).toHaveBeenCalledTimes(1)
+  expect(updateProviderProfile).not.toHaveBeenCalled()
+  expect(persistCredentials).toHaveBeenCalledWith({
+    profileId: 'provider_codex_oauth',
+  })
+
+  await mounted.dispose()
+})
+
+test('ProviderManager keeps Codex OAuth as next-startup only when activating the session fails from the menu', async () => {
+  delete process.env.CLAUDE_CODE_SIMPLE
+  delete process.env.CLAUDE_CODE_USE_GITHUB
+  delete process.env.GITHUB_TOKEN
+  delete process.env.GH_TOKEN
+
+  const codexProfile = {
+    id: 'provider_codex_oauth',
+    provider: 'openai',
+    name: 'Codex OAuth',
+    baseUrl: 'https://chatgpt.com/backend-api/codex',
+    model: 'codexplan',
+    apiKey: '',
+  }
+
+  const applySavedProfileToCurrentSession = mock(
+    async () => 'validation failed',
+  )
+  const setActiveProviderProfile = mock(() => codexProfile)
+
+  mockProviderManagerDependencies(
+    () => undefined,
+    async () => undefined,
+    {
+      applySavedProfileToCurrentSession,
+      getProviderProfiles: () => [codexProfile],
+      setActiveProviderProfile,
+      codexAsyncRead: async () => ({
+        accessToken: 'oauth-access-token',
+        refreshToken: 'oauth-refresh-token',
+        accountId: 'acct_oauth',
+        profileId: 'provider_codex_oauth',
+      }),
+    },
+  )
+
+  const nonce = `${Date.now()}-${Math.random()}`
+  const { ProviderManager } = await import(`./ProviderManager.js?ts=${nonce}`)
+  const mounted = await mountProviderManager(ProviderManager)
+
+  await waitForFrameOutput(
+    mounted.getOutput,
+    frame =>
+      frame.includes('Provider manager') &&
+      frame.includes('Set active provider') &&
+      frame.includes('Log out Codex OAuth'),
+  )
+
+  mounted.stdin.write('j')
+  await Bun.sleep(25)
+  mounted.stdin.write('\r')
+
+  await waitForFrameOutput(
+    mounted.getOutput,
+    frame => frame.includes('Set active provider') && frame.includes('Codex OAuth'),
+  )
+
+  await Bun.sleep(25)
+  mounted.stdin.write('\r')
+
+  await waitForCondition(() => setActiveProviderProfile.mock.calls.length > 0)
+  await waitForCondition(
+    () => applySavedProfileToCurrentSession.mock.calls.length > 0,
+  )
+  await Bun.sleep(50)
+  const output = stripAnsi(extractLastFrame(mounted.getOutput()))
+
+  expect(output).toContain(
+    'Active provider: Codex OAuth. Saved for next startup. Warning: validation failed.',
+  )
+  expect(applySavedProfileToCurrentSession).toHaveBeenCalled()
+  expect(setActiveProviderProfile).toHaveBeenCalledWith('provider_codex_oauth')
+
+  await mounted.dispose()
+})
+
+test('ProviderManager resolves Codex OAuth state from async storage without sync reads in render flow', async () => {
+  delete process.env.CLAUDE_CODE_SIMPLE
+  delete process.env.CLAUDE_CODE_USE_GITHUB
+  delete process.env.GITHUB_TOKEN
+  delete process.env.GH_TOKEN
+
+  const githubSyncRead = mock(() => undefined)
+  const githubAsyncRead = mock(async () => undefined)
+  const codexSyncRead = mock(() => {
+    throw new Error('sync codex credential read should not run in ProviderManager render flow')
+  })
+  const codexAsyncRead = mock(async () => ({
+    accessToken: 'codex-access-token',
+    refreshToken: 'codex-refresh-token',
+  }))
+
+  mockProviderManagerDependencies(githubSyncRead, githubAsyncRead, {
+    codexSyncRead,
+    codexAsyncRead,
+  })
+
+  const nonce = `${Date.now()}-${Math.random()}`
+  const { ProviderManager } = await import(`./ProviderManager.js?ts=${nonce}`)
+  const output = await renderProviderManagerFrame(ProviderManager, {
+    waitForOutput: frame =>
+      frame.includes('Provider manager') &&
+      frame.includes('Log out Codex OAuth'),
+  })
+
+  expect(output).toContain('Provider manager')
+  expect(output).toContain('Log out Codex OAuth')
+  expect(codexSyncRead).not.toHaveBeenCalled()
+  expect(codexAsyncRead).toHaveBeenCalled()
+})
+
+test('ProviderManager hides Codex OAuth setup in bare mode', async () => {
+  process.env.CLAUDE_CODE_SIMPLE = '1'
+  delete process.env.CLAUDE_CODE_USE_GITHUB
+  delete process.env.GITHUB_TOKEN
+  delete process.env.GH_TOKEN
+
+  const githubSyncRead = mock(() => undefined)
+  const githubAsyncRead = mock(async () => undefined)
+
+  mockProviderManagerDependencies(githubSyncRead, githubAsyncRead)
+
+  const nonce = `${Date.now()}-${Math.random()}`
+  const { ProviderManager } = await import(`./ProviderManager.js?ts=${nonce}`)
+  const output = await renderProviderManagerFrame(ProviderManager, {
+    mode: 'first-run',
+    waitForOutput: frame =>
+      frame.includes('Set up provider') && frame.includes('OpenAI'),
+  })
+
+  expect(output).toContain('Set up provider')
+  expect(output).not.toContain('Codex OAuth')
+})

src/components/Settings/Config.tsx

@@ -281,6 +281,24 @@ export function Config({
         enabled: autoCompactEnabled
       });
     }
+  }, {
+    id: 'toolHistoryCompressionEnabled',
+    label: 'Tool history compression',
+    value: globalConfig.toolHistoryCompressionEnabled,
+    type: 'boolean' as const,
+    onChange(toolHistoryCompressionEnabled: boolean) {
+      saveGlobalConfig(current => ({
+        ...current,
+        toolHistoryCompressionEnabled
+      }));
+      setGlobalConfig({
+        ...getGlobalConfig(),
+        toolHistoryCompressionEnabled
+      });
+      logEvent('tengu_tool_history_compression_setting_changed', {
+        enabled: toolHistoryCompressionEnabled
+      });
+    }
   }, {
     id: 'spinnerTipsEnabled',
     label: 'Show tips',
@@ -1158,6 +1176,9 @@ export function Config({
     if (globalConfig.autoCompactEnabled !== initialConfig.current.autoCompactEnabled) {
       formattedChanges.push(`${globalConfig.autoCompactEnabled ? 'Enabled' : 'Disabled'} auto-compact`);
     }
+    if (globalConfig.toolHistoryCompressionEnabled !== initialConfig.current.toolHistoryCompressionEnabled) {
+      formattedChanges.push(`${globalConfig.toolHistoryCompressionEnabled ? 'Enabled' : 'Disabled'} tool history compression`);
+    }
     if (globalConfig.respectGitignore !== initialConfig.current.respectGitignore) {
       formattedChanges.push(`${globalConfig.respectGitignore ? 'Enabled' : 'Disabled'} respect .gitignore in file picker`);
     }

src/components/StartupScreen.ts

@@ -5,7 +5,7 @@
  * Addresses: https://github.com/Gitlawb/openclaude/issues/55
  */
 
-import { isLocalProviderUrl } from '../services/api/providerConfig.js'
+import { isLocalProviderUrl, resolveProviderRequest } from '../services/api/providerConfig.js'
 import { getLocalOpenAICompatibleProviderLabel } from '../utils/providerDiscovery.js'
 import { getSettings_DEPRECATED } from '../utils/settings/settings.js'
 import { parseUserSpecifiedModel } from '../utils/model/model.js'
@@ -110,39 +110,42 @@ function detectProvider(): { name: string; model: string; baseUrl: string; isLoc
 
   if (useOpenAI) {
     const rawModel = process.env.OPENAI_MODEL || 'gpt-4o'
-    const baseUrl = process.env.OPENAI_BASE_URL || 'https://api.openai.com/v1'
+    const resolvedRequest = resolveProviderRequest({
+      model: rawModel,
+      baseUrl: process.env.OPENAI_BASE_URL,
+    })
+    const baseUrl = resolvedRequest.baseUrl
     const isLocal = isLocalProviderUrl(baseUrl)
     let name = 'OpenAI'
-    if (/deepseek/i.test(baseUrl) || /deepseek/i.test(rawModel))       name = 'DeepSeek'
-    else if (/openrouter/i.test(baseUrl))                             name = 'OpenRouter'
-    else if (/together/i.test(baseUrl))                               name = 'Together AI'
-    else if (/groq/i.test(baseUrl))                                   name = 'Groq'
-    else if (/mistral/i.test(baseUrl) || /mistral/i.test(rawModel))     name = 'Mistral'
-    else if (/azure/i.test(baseUrl))                                  name = 'Azure OpenAI'
-    else if (/llama/i.test(rawModel))                                    name = 'Meta Llama'
-    else if (isLocal)                                                  name = getLocalOpenAICompatibleProviderLabel(baseUrl)
+    if (/nvidia/i.test(baseUrl) || /nvidia/i.test(rawModel) || process.env.NVIDIA_NIM)
+      name = 'NVIDIA NIM'
+    else if (/minimax/i.test(baseUrl) || /minimax/i.test(rawModel) || process.env.MINIMAX_API_KEY)
+      name = 'MiniMax'
+    else if (resolvedRequest.transport === 'codex_responses' || baseUrl.includes('chatgpt.com/backend-api/codex'))
+      name = 'Codex'
+    else if (/moonshot/i.test(baseUrl) || /kimi/i.test(rawModel))
+      name = 'Moonshot (Kimi)'
+    else if (/deepseek/i.test(baseUrl) || /deepseek/i.test(rawModel))
+      name = 'DeepSeek'
+    else if (/openrouter/i.test(baseUrl))
+      name = 'OpenRouter'
+    else if (/together/i.test(baseUrl))
+      name = 'Together AI'
+    else if (/groq/i.test(baseUrl))
+      name = 'Groq'
+    else if (/mistral/i.test(baseUrl) || /mistral/i.test(rawModel))
+      name = 'Mistral'
+    else if (/azure/i.test(baseUrl))
+      name = 'Azure OpenAI'
+    else if (/llama/i.test(rawModel))
+      name = 'Meta Llama'
+    else if (isLocal)
+      name = getLocalOpenAICompatibleProviderLabel(baseUrl)
     
     // Resolve model alias to actual model name + reasoning effort
-    let displayModel = rawModel
-    const codexAliases: Record<string, { model: string; reasoningEffort?: string }> = {
-      codexplan: { model: 'gpt-5.4', reasoningEffort: 'high' },
-      'gpt-5.4': { model: 'gpt-5.4', reasoningEffort: 'high' },
-      'gpt-5.3-codex': { model: 'gpt-5.3-codex', reasoningEffort: 'high' },
-      'gpt-5.3-codex-spark': { model: 'gpt-5.3-codex-spark' },
-      codexspark: { model: 'gpt-5.3-codex-spark' },
-      'gpt-5.2-codex': { model: 'gpt-5.2-codex', reasoningEffort: 'high' },
-      'gpt-5.1-codex-max': { model: 'gpt-5.1-codex-max', reasoningEffort: 'high' },
-      'gpt-5.1-codex-mini': { model: 'gpt-5.1-codex-mini' },
-      'gpt-5.4-mini': { model: 'gpt-5.4-mini', reasoningEffort: 'medium' },
-      'gpt-5.2': { model: 'gpt-5.2', reasoningEffort: 'medium' },
-    }
-    const alias = rawModel.toLowerCase()
-    if (alias in codexAliases) {
-      const resolved = codexAliases[alias]
-      displayModel = resolved.model
-      if (resolved.reasoningEffort) {
-        displayModel = `${displayModel} (${resolved.reasoningEffort})`
-      }
+    let displayModel = resolvedRequest.resolvedModel
+    if (resolvedRequest.reasoning?.effort) {
+      displayModel = `${displayModel} (${resolvedRequest.reasoning.effort})`
     }
     
     return { name, model: displayModel, baseUrl, isLocal }
@@ -152,7 +155,9 @@ function detectProvider(): { name: string; model: string; baseUrl: string; isLoc
   const settings = getSettings_DEPRECATED() || {}
   const modelSetting = settings.model || process.env.ANTHROPIC_MODEL || process.env.CLAUDE_MODEL || 'claude-sonnet-4-6'
   const resolvedModel = parseUserSpecifiedModel(modelSetting)
-  return { name: 'Anthropic', model: resolvedModel, baseUrl: 'https://api.anthropic.com', isLocal: false }
+  const baseUrl = process.env.ANTHROPIC_BASE_URL ?? 'https://api.anthropic.com'
+  const isLocal = isLocalProviderUrl(baseUrl)
+  return { name: 'Anthropic', model: resolvedModel, baseUrl, isLocal }
 }
 
 // ─── Box drawing ──────────────────────────────────────────────────────────────

src/components/TextInput.test.tsx

@@ -6,6 +6,7 @@ import stripAnsi from 'strip-ansi'
 
 import { createRoot } from '../ink.js'
 import { AppStateProvider } from '../state/AppState.js'
+import { maskTextWithVisibleEdges } from '../utils/Cursor.js'
 import TextInput from './TextInput.js'
 import VimTextInput from './VimTextInput.js'
 
@@ -199,6 +200,13 @@ test('TextInput renders typed characters before delayed parent value commits', a
   expect(output).not.toContain('Type here...')
 })
 
+test('maskTextWithVisibleEdges preserves only the first and last three chars', () => {
+  expect(maskTextWithVisibleEdges('sk-secret-12345678', '*')).toBe(
+    'sk-************678',
+  )
+  expect(maskTextWithVisibleEdges('abcdef', '*')).toBe('******')
+})
+
 test('VimTextInput preserves rapid typed characters before delayed parent value commits', async () => {
   const { stdout, stdin, getOutput } = createTestStreams()
   const root = await createRoot({

src/components/memory/memoryFileSelectorPaths.test.ts

@@ -53,17 +53,20 @@ describe('getProjectMemoryPathForSelector', () => {
   })
 
   test('defaults to a new AGENTS.md in the current cwd when no project file is loaded', () => {
-    expect(getProjectMemoryPathForSelector([], '/repo/packages/app')).toBe(
-      '/repo/packages/app/AGENTS.md',
+    const cwd = join('/repo', 'packages', 'app')
+    expect(getProjectMemoryPathForSelector([], cwd)).toBe(
+      join(cwd, 'AGENTS.md'),
     )
   })
 
   test('ignores loaded project instruction files outside the current cwd ancestry', () => {
+    const outsideRepoPath = join('/other-worktree', 'AGENTS.md')
+    const cwd = join('/repo', 'packages', 'app')
     expect(
       getProjectMemoryPathForSelector(
-        [projectFile('/other-worktree/AGENTS.md')],
-        '/repo/packages/app',
+        [projectFile(outsideRepoPath)],
+        cwd,
       ),
-    ).toBe('/repo/packages/app/AGENTS.md')
+    ).toBe(join(cwd, 'AGENTS.md'))
   })
 })

src/components/permissions/MonitorPermissionRequest/MonitorPermissionRequest.tsx

@@ -0,0 +1,173 @@
+import React from 'react'
+import { getOriginalCwd } from '../../../bootstrap/state.js'
+import { Box, Text } from '../../../ink.js'
+import { sanitizeToolNameForAnalytics } from '../../../services/analytics/metadata.js'
+import { env } from '../../../utils/env.js'
+import { shouldShowAlwaysAllowOptions } from '../../../utils/permissions/permissionsLoader.js'
+import { usePermissionRequestLogging } from '../hooks.js'
+import { PermissionDialog } from '../PermissionDialog.js'
+import {
+  PermissionPrompt,
+  type PermissionPromptOption,
+} from '../PermissionPrompt.js'
+import type { PermissionRequestProps } from '../PermissionRequest.js'
+import { PermissionRuleExplanation } from '../PermissionRuleExplanation.js'
+import { logUnaryPermissionEvent } from '../utils.js'
+
+type OptionValue = 'yes' | 'yes-dont-ask-again' | 'no'
+
+export function MonitorPermissionRequest({
+  toolUseConfirm,
+  onDone,
+  onReject,
+  workerBadge,
+}: PermissionRequestProps) {
+  const { command, description } = toolUseConfirm.input as {
+    command?: string
+    description?: string
+  }
+
+  usePermissionRequestLogging(toolUseConfirm, {
+    completion_type: 'tool_use_single',
+    language_name: 'none',
+  })
+
+  const handleSelect = (
+    value: OptionValue,
+    feedback?: string,
+  ) => {
+    switch (value) {
+      case 'yes': {
+        logUnaryPermissionEvent({
+          completion_type: 'tool_use_single',
+          event: 'accept',
+          metadata: {
+            language_name: 'none',
+            message_id: toolUseConfirm.assistantMessage.message.id,
+            platform: env.platform,
+          },
+        })
+        toolUseConfirm.onAllow(toolUseConfirm.input, [], feedback)
+        onDone()
+        break
+      }
+      case 'yes-dont-ask-again': {
+        logUnaryPermissionEvent({
+          completion_type: 'tool_use_single',
+          event: 'accept',
+          metadata: {
+            language_name: 'none',
+            message_id: toolUseConfirm.assistantMessage.message.id,
+            platform: env.platform,
+          },
+        })
+        // Save the rule under 'Bash' toolName because checkPermissions
+        // delegates to bashToolHasPermission which matches rules against
+        // BashTool. Using 'Monitor' here would create a rule that's never
+        // checked. Command-specific prefix (like BashTool's shellRuleMatching).
+        const cmdForRule = command?.trim() || ''
+        const prefix = cmdForRule.split(/\s+/).slice(0, 2).join(' ')
+        toolUseConfirm.onAllow(toolUseConfirm.input, prefix ? [
+          {
+            type: 'addRules',
+            rules: [{ toolName: 'Bash', ruleContent: `${prefix}:*` }],
+            behavior: 'allow',
+            destination: 'localSettings',
+          },
+        ] : [])
+        onDone()
+        break
+      }
+      case 'no': {
+        logUnaryPermissionEvent({
+          completion_type: 'tool_use_single',
+          event: 'reject',
+          metadata: {
+            language_name: 'none',
+            message_id: toolUseConfirm.assistantMessage.message.id,
+            platform: env.platform,
+          },
+        })
+        toolUseConfirm.onReject(feedback)
+        onReject()
+        onDone()
+        break
+      }
+    }
+  }
+
+  const handleCancel = () => {
+    logUnaryPermissionEvent({
+      completion_type: 'tool_use_single',
+      event: 'reject',
+      metadata: {
+        language_name: 'none',
+        message_id: toolUseConfirm.assistantMessage.message.id,
+        platform: env.platform,
+      },
+    })
+    toolUseConfirm.onReject()
+    onReject()
+    onDone()
+  }
+
+  const showAlwaysAllow = shouldShowAlwaysAllowOptions()
+  const originalCwd = getOriginalCwd()
+
+  const options: PermissionPromptOption<OptionValue>[] = [
+    {
+      label: 'Yes',
+      value: 'yes',
+      feedbackConfig: { type: 'accept' },
+    },
+  ]
+
+  if (showAlwaysAllow) {
+    options.push({
+      label: (
+        <Text>
+          Yes, and don&apos;t ask again for{' '}
+          <Text bold>Monitor</Text> commands in{' '}
+          <Text bold>{originalCwd}</Text>
+        </Text>
+      ),
+      value: 'yes-dont-ask-again',
+    })
+  }
+
+  options.push({
+    label: 'No',
+    value: 'no',
+    feedbackConfig: { type: 'reject' },
+  })
+
+  const toolAnalyticsContext = {
+    toolName: sanitizeToolNameForAnalytics(toolUseConfirm.tool.name),
+    isMcp: toolUseConfirm.tool.isMcp ?? false,
+  }
+
+  return (
+    <PermissionDialog title="Monitor" workerBadge={workerBadge}>
+      <Box flexDirection="column" paddingX={2} paddingY={1}>
+        <Text>
+          Monitor({command ?? ''})
+        </Text>
+        {description ? (
+          <Text dimColor>{description}</Text>
+        ) : null}
+      </Box>
+      <Box flexDirection="column">
+        <PermissionRuleExplanation
+          permissionResult={toolUseConfirm.permissionResult}
+          toolType="tool"
+        />
+        <PermissionPrompt
+          options={options}
+          onSelect={handleSelect}
+          onCancel={handleCancel}
+          toolAnalyticsContext={toolAnalyticsContext}
+        />
+      </Box>
+    </PermissionDialog>
+  )
+}

src/components/useCodexOAuthFlow.test.tsx

@@ -0,0 +1,220 @@
+import { PassThrough } from 'node:stream'
+
+import { afterEach, expect, mock, test } from 'bun:test'
+import React from 'react'
+
+import { createRoot, Text } from '../ink.js'
+
+const SYNC_START = '\x1B[?2026h'
+const SYNC_END = '\x1B[?2026l'
+
+function createTestStreams(): {
+  stdout: PassThrough
+  stdin: PassThrough & {
+    isTTY: boolean
+    setRawMode: (mode: boolean) => void
+    ref: () => void
+    unref: () => void
+  }
+  getOutput: () => string
+} {
+  let output = ''
+  const stdout = new PassThrough()
+  const stdin = new PassThrough() as PassThrough & {
+    isTTY: boolean
+    setRawMode: (mode: boolean) => void
+    ref: () => void
+    unref: () => void
+  }
+
+  stdin.isTTY = true
+  stdin.setRawMode = () => {}
+  stdin.ref = () => {}
+  stdin.unref = () => {}
+  ;(stdout as unknown as { columns: number }).columns = 120
+  stdout.on('data', chunk => {
+    output += chunk.toString()
+  })
+
+  return {
+    stdout,
+    stdin,
+    getOutput: () => output,
+  }
+}
+
+async function waitForCondition(
+  predicate: () => boolean,
+  options?: { timeoutMs?: number; intervalMs?: number },
+): Promise<void> {
+  const timeoutMs = options?.timeoutMs ?? 5000
+  const intervalMs = options?.intervalMs ?? 10
+  const startedAt = Date.now()
+
+  while (Date.now() - startedAt < timeoutMs) {
+    if (predicate()) {
+      return
+    }
+    await Bun.sleep(intervalMs)
+  }
+
+  throw new Error('Timed out waiting for useCodexOAuthFlow test condition')
+}
+
+function extractLastFrame(output: string): string {
+  let lastFrame: string | null = null
+  let cursor = 0
+
+  while (cursor < output.length) {
+    const start = output.indexOf(SYNC_START, cursor)
+    if (start === -1) break
+
+    const contentStart = start + SYNC_START.length
+    const end = output.indexOf(SYNC_END, contentStart)
+    if (end === -1) break
+
+    const frame = output.slice(contentStart, end)
+    if (frame.trim().length > 0) {
+      lastFrame = frame
+    }
+    cursor = end + SYNC_END.length
+  }
+
+  return lastFrame ?? output
+}
+
+const TOKENS = {
+  accessToken: 'oauth-access-token',
+  refreshToken: 'oauth-refresh-token',
+  accountId: 'acct_oauth',
+  idToken: 'oauth-id-token',
+  apiKey: 'oauth-api-key',
+}
+
+afterEach(() => {
+  mock.restore()
+})
+
+test('does not persist credentials when downstream setup rejects', async () => {
+  const saveCodexCredentials = mock(() => ({ success: true }))
+  const cleanup = mock(() => {})
+  const onAuthenticated = mock(async () => {
+    throw new Error('profile save failed')
+  })
+  const deps = {
+    createOAuthService: () => ({
+      async startOAuthFlow(
+        onAuthorizationUrl: (authUrl: string) => void | Promise<void>,
+      ) {
+        await onAuthorizationUrl('https://chatgpt.com/codex')
+        return TOKENS
+      },
+      cleanup,
+    }),
+    openBrowser: async () => true,
+    saveCodexCredentials,
+    isBareMode: () => false,
+  }
+
+  const { useCodexOAuthFlow } = await import(
+    `./useCodexOAuthFlow.js?real-reject-${Date.now()}-${Math.random()}`
+  )
+
+  function Harness(): React.ReactNode {
+    const handleAuthenticated = React.useCallback(onAuthenticated, [onAuthenticated])
+    const status = useCodexOAuthFlow({
+      onAuthenticated: handleAuthenticated,
+      deps,
+    })
+
+    return <Text>{status.state === 'error' ? status.message : status.state}</Text>
+  }
+
+  const streams = createTestStreams()
+  const root = await createRoot({
+    stdout: streams.stdout as unknown as NodeJS.WriteStream,
+    stdin: streams.stdin as unknown as NodeJS.ReadStream,
+    patchConsole: false,
+  })
+  root.render(<Harness />)
+
+  try {
+    await waitForCondition(() => onAuthenticated.mock.calls.length === 1)
+    await Bun.sleep(0)
+    await Bun.sleep(0)
+    expect(onAuthenticated).toHaveBeenCalled()
+    expect(saveCodexCredentials).not.toHaveBeenCalled()
+  } finally {
+    root.unmount()
+    streams.stdin.end()
+    streams.stdout.end()
+    await Bun.sleep(0)
+  }
+})
+
+test('persists credentials with profile linkage after downstream setup succeeds', async () => {
+  const saveCodexCredentials = mock(() => ({ success: true }))
+  const onAuthenticated = mock(
+    async (
+      _tokens: typeof TOKENS,
+      persistCredentials: (options?: { profileId?: string }) => void,
+    ) => {
+      persistCredentials({ profileId: 'profile_codex_oauth' })
+    },
+  )
+  const cleanup = mock(() => {})
+  const deps = {
+    createOAuthService: () => ({
+      async startOAuthFlow(
+        onAuthorizationUrl: (authUrl: string) => void | Promise<void>,
+      ) {
+        await onAuthorizationUrl('https://chatgpt.com/codex')
+        return TOKENS
+      },
+      cleanup,
+    }),
+    openBrowser: async () => true,
+    saveCodexCredentials,
+    isBareMode: () => false,
+  }
+
+  const { useCodexOAuthFlow } = await import(
+    `./useCodexOAuthFlow.js?real-persist-${Date.now()}-${Math.random()}`
+  )
+
+  function Harness(): React.ReactNode {
+    const handleAuthenticated = React.useCallback(onAuthenticated, [onAuthenticated])
+    useCodexOAuthFlow({
+      onAuthenticated: handleAuthenticated,
+      deps,
+    })
+    return <Text>waiting</Text>
+  }
+
+  const streams = createTestStreams()
+  const root = await createRoot({
+    stdout: streams.stdout as unknown as NodeJS.WriteStream,
+    stdin: streams.stdin as unknown as NodeJS.ReadStream,
+    patchConsole: false,
+  })
+  root.render(<Harness />)
+
+  try {
+    await waitForCondition(() => onAuthenticated.mock.calls.length === 1)
+    await waitForCondition(() => saveCodexCredentials.mock.calls.length === 1)
+    expect(onAuthenticated).toHaveBeenCalled()
+    expect(saveCodexCredentials).toHaveBeenCalledWith({
+      apiKey: TOKENS.apiKey,
+      accessToken: TOKENS.accessToken,
+      refreshToken: TOKENS.refreshToken,
+      idToken: TOKENS.idToken,
+      accountId: TOKENS.accountId,
+      profileId: 'profile_codex_oauth',
+    })
+  } finally {
+    root.unmount()
+    streams.stdin.end()
+    streams.stdout.end()
+    await Bun.sleep(0)
+  }
+})

src/components/useCodexOAuthFlow.ts

@@ -0,0 +1,134 @@
+import * as React from 'react'
+
+import {
+  CodexOAuthService,
+  type CodexOAuthTokens,
+} from '../services/api/codexOAuth.js'
+import { openBrowser } from '../utils/browser.js'
+import { saveCodexCredentials } from '../utils/codexCredentials.js'
+import { isBareMode } from '../utils/envUtils.js'
+
+export type CodexOAuthFlowStatus =
+  | { state: 'starting' }
+  | {
+      state: 'waiting'
+      authUrl: string
+      browserOpened: boolean | null
+    }
+  | {
+      state: 'error'
+      message: string
+    }
+
+type PersistCodexOAuthCredentials = (options?: {
+  profileId?: string
+}) => void
+
+type CodexOAuthFlowDependencies = {
+  createOAuthService?: () => Pick<
+    CodexOAuthService,
+    'startOAuthFlow' | 'cleanup'
+  >
+  openBrowser?: typeof openBrowser
+  saveCodexCredentials?: typeof saveCodexCredentials
+  isBareMode?: typeof isBareMode
+}
+
+function createDefaultOAuthService(): Pick<
+  CodexOAuthService,
+  'startOAuthFlow' | 'cleanup'
+> {
+  return new CodexOAuthService()
+}
+
+export function useCodexOAuthFlow(options: {
+  onAuthenticated: (
+    tokens: CodexOAuthTokens,
+    persistCredentials: PersistCodexOAuthCredentials,
+  ) => void | Promise<void>
+  deps?: CodexOAuthFlowDependencies
+}): CodexOAuthFlowStatus {
+  const { onAuthenticated } = options
+  const createOAuthService =
+    options.deps?.createOAuthService ?? createDefaultOAuthService
+  const openBrowserFn = options.deps?.openBrowser ?? openBrowser
+  const saveCredentials =
+    options.deps?.saveCodexCredentials ?? saveCodexCredentials
+  const isBareModeFn = options.deps?.isBareMode ?? isBareMode
+  const [status, setStatus] = React.useState<CodexOAuthFlowStatus>({
+    state: 'starting',
+  })
+
+  React.useEffect(() => {
+    if (isBareModeFn()) {
+      setStatus({
+        state: 'error',
+        message:
+          'Codex OAuth is unavailable in --bare because secure storage is disabled.',
+      })
+      return
+    }
+
+    let cancelled = false
+    const oauthService = createOAuthService()
+
+    void oauthService
+      .startOAuthFlow(async authUrl => {
+        if (cancelled) return
+        setStatus({
+          state: 'waiting',
+          authUrl,
+          browserOpened: null,
+        })
+        const browserOpened = await openBrowserFn(authUrl)
+        if (cancelled) return
+        setStatus({
+          state: 'waiting',
+          authUrl,
+          browserOpened,
+        })
+      })
+      .then(async tokens => {
+        if (cancelled) return
+
+        const persistCredentials: PersistCodexOAuthCredentials = options => {
+          const saved = saveCredentials({
+            apiKey: tokens.apiKey,
+            accessToken: tokens.accessToken,
+            refreshToken: tokens.refreshToken,
+            idToken: tokens.idToken,
+            accountId: tokens.accountId,
+            profileId: options?.profileId,
+          })
+          if (!saved.success) {
+            throw new Error(
+              saved.warning ??
+                'Codex OAuth succeeded, but credentials could not be saved securely.',
+            )
+          }
+        }
+
+        await onAuthenticated(tokens, persistCredentials)
+      })
+      .catch(error => {
+        if (cancelled) return
+        setStatus({
+          state: 'error',
+          message: error instanceof Error ? error.message : String(error),
+        })
+      })
+
+    return () => {
+      cancelled = true
+      oauthService.cleanup()
+    }
+  }, [
+    createOAuthService,
+    isBareModeFn,
+    onAuthenticated,
+    openBrowserFn,
+    saveCredentials,
+  ])
+
+  return status
+}

src/constants/promptIdentity.test.ts

@@ -1,5 +1,16 @@
 import { afterEach, expect, test } from 'bun:test'
 
+// MACRO is replaced at build time by Bun.define but not in test mode.
+// Define it globally so tests that import modules using MACRO don't crash.
+;(globalThis as Record<string, unknown>).MACRO = {
+  VERSION: '99.0.0',
+  DISPLAY_VERSION: '0.0.0-test',
+  BUILD_TIME: new Date().toISOString(),
+  ISSUES_EXPLAINER: 'report the issue at https://github.com/anthropics/claude-code/issues',
+  PACKAGE_URL: '@gitlawb/openclaude',
+  NATIVE_PACKAGE_URL: undefined,
+}
+
 import { getSystemPrompt, DEFAULT_AGENT_PROMPT } from './prompts.js'
 import { CLI_SYSPROMPT_PREFIXES, getCLISyspromptPrefix } from './system.js'
 import { CLAUDE_CODE_GUIDE_AGENT } from '../tools/AgentTool/built-in/claudeCodeGuideAgent.js'

src/constants/prompts.ts

@@ -823,6 +823,11 @@ function getFunctionResultClearingSection(model: string): string | null {
     return null
   }
   const config = getCachedMCConfigForFRC()
+  if (!config) {
+    // External/stub builds return null from getCachedMCConfig — abort the
+    // section rather than trying to read .supportedModels off null.
+    return null
+  }
   const isModelSupported = config.supportedModels?.some(pattern =>
     model.includes(pattern),
   )

src/constants/tools.ts

@@ -37,8 +37,6 @@ export const ALL_AGENT_DISALLOWED_TOOLS = new Set([
   TASK_OUTPUT_TOOL_NAME,
   EXIT_PLAN_MODE_V2_TOOL_NAME,
   ENTER_PLAN_MODE_TOOL_NAME,
-  // Allow Agent tool for agents when user is ant (enables nested agents)
-  ...(process.env.USER_TYPE === 'ant' ? [] : [AGENT_TOOL_NAME]),
   ASK_USER_QUESTION_TOOL_NAME,
   TASK_STOP_TOOL_NAME,
   // Prevent recursive workflow execution inside subagents.
@@ -82,9 +80,9 @@ export const IN_PROCESS_TEAMMATE_ALLOWED_TOOLS = new Set([
   SEND_MESSAGE_TOOL_NAME,
   // Teammate-created crons are tagged with the creating agentId and routed to
   // that teammate's pendingUserMessages queue (see useScheduledTasks.ts).
-  ...(feature('AGENT_TRIGGERS')
-    ? [CRON_CREATE_TOOL_NAME, CRON_DELETE_TOOL_NAME, CRON_LIST_TOOL_NAME]
-    : []),
+  CRON_CREATE_TOOL_NAME,
+  CRON_DELETE_TOOL_NAME,
+  CRON_LIST_TOOL_NAME,
 ])
 
 /*

src/coordinator/workerAgent.ts

@@ -0,0 +1,18 @@
+import type { BuiltInAgentDefinition } from '../tools/AgentTool/loadAgentsDir.js'
+import { EXPLORE_AGENT } from '../tools/AgentTool/built-in/exploreAgent.js'
+import { GENERAL_PURPOSE_AGENT } from '../tools/AgentTool/built-in/generalPurposeAgent.js'
+import { PLAN_AGENT } from '../tools/AgentTool/built-in/planAgent.js'
+
+// The coordinator system prompt instructs the model to spawn workers with
+// subagent_type: "worker". This agent definition matches that type so
+// AgentTool.tsx can resolve it. It reuses GENERAL_PURPOSE_AGENT's capabilities.
+const WORKER_AGENT: BuiltInAgentDefinition = {
+  ...GENERAL_PURPOSE_AGENT,
+  agentType: 'worker',
+  whenToUse:
+    'Worker agent for coordinator mode. Executes tasks autonomously — research, implementation, or verification.',
+}
+
+export function getCoordinatorAgents(): BuiltInAgentDefinition[] {
+  return [WORKER_AGENT, GENERAL_PURPOSE_AGENT, EXPLORE_AGENT, PLAN_AGENT]
+}

src/entrypoints/cli.tsx

@@ -5,7 +5,7 @@ import {
 } from '../utils/providerProfile.js'
 import {
   getProviderValidationError,
-  validateProviderEnvOrExit,
+  validateProviderEnvForStartupOrExit,
 } from '../utils/providerValidation.js'
 
 // OpenClaude: polyfill globalThis.File for Node < 20.
@@ -132,7 +132,7 @@ async function main(): Promise<void> {
     hydrateGithubModelsTokenFromSecureStorage()
   }
 
-  await validateProviderEnvOrExit()
+  await validateProviderEnvForStartupOrExit()
 
   // Print the gradient startup screen before the Ink UI loads
   const { printStartupScreen } = await import('../components/StartupScreen.js')

src/entrypoints/mcp.test.ts

@@ -0,0 +1,75 @@
+import { describe, it, expect, mock } from 'bun:test'
+import { getCombinedTools, loadReexposedMcpTools } from './mcp.js'
+import type { Tool as InternalTool } from '../Tool.js'
+import type { MCPServerConnection } from '../services/mcp/types.js'
+import type { Tool } from '@modelcontextprotocol/sdk/types.js'
+
+// Mock the MCP client service to control the tools and connections returned
+const mockGetMcpToolsCommandsAndResources = mock(async (onConnectionAttempt: any) => {})
+mock.module('../services/mcp/client.js', () => ({
+  getMcpToolsCommandsAndResources: mockGetMcpToolsCommandsAndResources
+}))
+
+describe('getCombinedTools', () => {
+  it('deduplicates builtins when mcpTools have the same name, prioritizing mcpTools', () => {
+    const builtinBash = { name: 'Bash', isMcp: false } as unknown as InternalTool
+    const builtinRead = { name: 'Read', isMcp: false } as unknown as InternalTool
+    const mcpBash = { name: 'Bash', isMcp: true } as unknown as InternalTool
+
+    const builtins = [builtinBash, builtinRead]
+    const mcpTools = [mcpBash]
+
+    const result = getCombinedTools(builtins, mcpTools)
+
+    expect(result).toHaveLength(2)
+    expect(result[0]).toBe(mcpBash)
+    expect(result[1]).toBe(builtinRead)
+  })
+})
+
+describe('loadReexposedMcpTools', () => {
+  it('loads tools and clients regardless of connection state (including needs-auth)', async () => {
+    // Setup the mock to simulate yielding a needs-auth server and a connected server
+    mockGetMcpToolsCommandsAndResources.mockImplementation(async (onConnectionAttempt) => {
+      const needsAuthClient = {
+        name: 'auth-server',
+        type: 'needs-auth',
+        config: {}
+      } as MCPServerConnection
+
+      const authTool = {
+        name: 'mcp__auth-server__authenticate',
+        isMcp: true
+      } as unknown as InternalTool
+
+      const connectedClient = {
+        name: 'connected-server',
+        type: 'connected',
+        config: {},
+        client: {}
+      } as MCPServerConnection
+
+      const connectedTool = {
+        name: 'mcp__connected-server__do_thing',
+        isMcp: true
+      } as unknown as InternalTool
+
+      // Simulate the callback behavior
+      onConnectionAttempt({ client: needsAuthClient, tools: [authTool], commands: [] })
+      onConnectionAttempt({ client: connectedClient, tools: [connectedTool], commands: [] })
+    })
+
+    const { mcpClients, mcpTools } = await loadReexposedMcpTools()
+
+    expect(mcpClients).toHaveLength(2)
+    expect(mcpClients[0].type).toBe('needs-auth')
+    expect(mcpClients[1].type).toBe('connected')
+
+    expect(mcpTools).toHaveLength(2)
+    expect(mcpTools[0].name).toBe('mcp__auth-server__authenticate')
+    expect(mcpTools[1].name).toBe('mcp__connected-server__do_thing')
+
+    // Reset mock for other tests
+    mockGetMcpToolsCommandsAndResources.mockReset()
+  })
+})

src/entrypoints/mcp.ts

@@ -7,6 +7,7 @@ process.env.CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS ??= 'true'
 
 import { Server } from '@modelcontextprotocol/sdk/server/index.js'
 import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js'
+import { ZodError } from 'zod'
 import {
   CallToolRequestSchema,
   type CallToolResult,
@@ -17,9 +18,12 @@ import {
 import { getDefaultAppState } from 'src/state/AppStateStore.js'
 import review from '../commands/review.js'
 import type { Command } from '../commands.js'
+import { getMcpToolsCommandsAndResources } from '../services/mcp/client.js'
+import type { MCPServerConnection } from '../services/mcp/types.js'
 import {
   findToolByName,
   getEmptyToolPermissionContext,
+  type Tool as InternalTool,
   type ToolUseContext,
 } from '../Tool.js'
 import { getTools } from '../tools.js'
@@ -39,6 +43,32 @@ type ToolOutput = Tool['outputSchema']
 
 const MCP_COMMANDS: Command[] = [review]
 
+export function getCombinedTools(
+  builtins: InternalTool[],
+  mcpTools: InternalTool[],
+): InternalTool[] {
+  const mcpToolNames = new Set(mcpTools.map(t => t.name))
+  const deduplicatedBuiltins = builtins.filter(t => !mcpToolNames.has(t.name))
+
+  return [...mcpTools, ...deduplicatedBuiltins]
+}
+
+export async function loadReexposedMcpTools(): Promise<{
+  mcpClients: MCPServerConnection[]
+  mcpTools: InternalTool[]
+}> {
+  const mcpClients: MCPServerConnection[] = []
+  const mcpTools: InternalTool[] = []
+
+  // Load configured MCP clients and their tools
+  await getMcpToolsCommandsAndResources(({ client, tools: clientTools }) => {
+    mcpClients.push(client)
+    mcpTools.push(...clientTools)
+  })
+
+  return { mcpClients, mcpTools }
+}
+
 export async function startMCPServer(
   cwd: string,
   debug: boolean,
@@ -63,12 +93,13 @@ export async function startMCPServer(
     },
   )
 
+  const { mcpClients, mcpTools } = await loadReexposedMcpTools()
+
   server.setRequestHandler(
     ListToolsRequestSchema,
     async (): Promise<ListToolsResult> => {
-      // TODO: Also re-expose any MCP tools
       const toolPermissionContext = getEmptyToolPermissionContext()
-      const tools = getTools(toolPermissionContext)
+      const tools = getCombinedTools(getTools(toolPermissionContext), mcpTools)
       return {
         tools: await Promise.all(
           tools.map(async tool => {
@@ -94,7 +125,7 @@ export async function startMCPServer(
                 tools,
                 agents: [],
               }),
-              inputSchema: zodToJsonSchema(tool.inputSchema) as ToolInput,
+              inputSchema: (tool.inputJSONSchema ?? zodToJsonSchema(tool.inputSchema)) as ToolInput,
               outputSchema,
             }
           }),
@@ -107,8 +138,7 @@ export async function startMCPServer(
     CallToolRequestSchema,
     async ({ params: { name, arguments: args } }): Promise<CallToolResult> => {
       const toolPermissionContext = getEmptyToolPermissionContext()
-      // TODO: Also re-expose any MCP tools
-      const tools = getTools(toolPermissionContext)
+      const tools = getCombinedTools(getTools(toolPermissionContext), mcpTools)
       const tool = findToolByName(tools, name)
       if (!tool) {
         throw new Error(`Tool ${name} not found`)
@@ -123,7 +153,7 @@ export async function startMCPServer(
           tools,
           mainLoopModel: getMainLoopModel(),
           thinkingConfig: { type: 'disabled' },
-          mcpClients: [],
+          mcpClients,
           mcpResources: {},
           isNonInteractiveSession: true,
           debug,
@@ -140,13 +170,16 @@ export async function startMCPServer(
         updateAttributionState: () => {},
       }
 
-      // TODO: validate input types with zod
       try {
         if (!tool.isEnabled()) {
           throw new Error(`Tool ${name} is not enabled`)
         }
+
+        // Validate input types with zod
+        const parsedArgs = tool.inputSchema.parse(args ?? {})
+
         const validationResult = await tool.validateInput?.(
-          (args as never) ?? {},
+          (parsedArgs as never) ?? {},
           toolUseContext,
         )
         if (validationResult && !validationResult.result) {
@@ -155,7 +188,7 @@ export async function startMCPServer(
           )
         }
         const finalResult = await tool.call(
-          (args ?? {}) as never,
+          (parsedArgs ?? {}) as never,
           toolUseContext,
           hasPermissionsToUseTool,
           createAssistantMessage({
@@ -163,20 +196,50 @@ export async function startMCPServer(
           }),
         )
 
+        let content: CallToolResult['content']
+        const data = finalResult.data as string | { type: string; text?: string; source?: { type: string; media_type: string; data: string } }[] | unknown
+
+        if (typeof data === 'string') {
+          content = [{ type: 'text', text: data }]
+        } else if (Array.isArray(data)) {
+          content = data.map((block: any) => {
+            if (block.type === 'text') {
+              return { type: 'text', text: block.text || '' }
+            } else if (block.type === 'image' && block.source) {
+              return {
+                type: 'image',
+                data: block.source.data,
+                mimeType: block.source.media_type,
+              }
+            } else {
+              // eslint-disable-next-line custom-rules/no-top-level-side-effects, no-console
+              console.warn(`Unmapped content block type from tool ${name}: ${block.type || 'unknown'}`)
+              return { type: 'text', text: jsonStringify(block) }
+            }
+          }) as CallToolResult['content']
+        } else {
+          content = [{ type: 'text', text: jsonStringify(data) }]
+        }
+
         return {
-          content: [
-            {
-              type: 'text' as const,
-              text:
-                typeof finalResult === 'string'
-                  ? finalResult
-                  : jsonStringify(finalResult.data),
-            },
-          ],
+          content,
+          isError: !!(finalResult as any).isError,
         }
       } catch (error) {
         logError(error)
 
+        if (error instanceof ZodError) {
+          return {
+            isError: true,
+            content: [
+              {
+                type: 'text',
+                text: `Tool ${name} input is invalid:\n${error.errors.map(e => `- ${e.path.join('.')}: ${e.message}`).join('\n')}`,
+              },
+            ],
+          }
+        }
+
         const parts =
           error instanceof Error ? getErrorParts(error) : [String(error)]
         const errorText = parts.filter(Boolean).join('\n').trim() || 'Error'
@@ -201,3 +264,4 @@ export async function startMCPServer(
 
   return await runServer()
 }
+

src/entrypoints/sandboxTypes.ts

@@ -114,8 +114,8 @@ export const SandboxSettingsSchema = lazySchema(() =>
         .boolean()
         .optional()
         .describe(
-          'Allow commands to run outside the sandbox via the dangerouslyDisableSandbox parameter. ' +
-            'When false, the dangerouslyDisableSandbox parameter is completely ignored and all commands must run sandboxed. ' +
+          'Allow trusted, user-initiated commands to run outside the sandbox. ' +
+            'When false, sandbox override requests are ignored and all commands must run sandboxed. ' +
             'Default: true.',
         ),
       network: SandboxNetworkConfigSchema(),

src/hooks/useApiKeyVerification.test.tsx

@@ -0,0 +1,123 @@
+import { PassThrough } from 'node:stream'
+
+import { afterEach, expect, mock, test } from 'bun:test'
+import React from 'react'
+import { createRoot, Text } from '../ink.js'
+
+type AuthState = {
+  anthropicAuthEnabled: boolean
+  claudeSubscriber: boolean
+  key?: string
+  source?: string
+}
+
+function createTestStreams(): {
+  stdout: PassThrough
+  stdin: PassThrough & {
+    isTTY: boolean
+    setRawMode: (mode: boolean) => void
+    ref: () => void
+    unref: () => void
+  }
+} {
+  const stdout = new PassThrough()
+  const stdin = new PassThrough() as PassThrough & {
+    isTTY: boolean
+    setRawMode: (mode: boolean) => void
+    ref: () => void
+    unref: () => void
+  }
+
+  stdin.isTTY = true
+  stdin.setRawMode = () => {}
+  stdin.ref = () => {}
+  stdin.unref = () => {}
+  ;(stdout as unknown as { columns: number }).columns = 120
+
+  return { stdout, stdin }
+}
+
+async function waitForCondition(
+  predicate: () => boolean,
+  timeoutMs = 2000,
+): Promise<void> {
+  const startedAt = Date.now()
+
+  while (Date.now() - startedAt < timeoutMs) {
+    if (predicate()) {
+      return
+    }
+    await Bun.sleep(10)
+  }
+
+  throw new Error('Timed out waiting for useApiKeyVerification test state')
+}
+
+afterEach(() => {
+  mock.restore()
+})
+
+test('useApiKeyVerification resets stale missing status when the session switches to a third-party provider', async () => {
+  const authState: AuthState = {
+    anthropicAuthEnabled: true,
+    claudeSubscriber: false,
+  }
+  const seenStatuses: string[] = []
+
+  mock.module('../utils/auth.js', () => ({
+    getAnthropicApiKeyWithSource: () => ({
+      key: authState.key,
+      source: authState.source,
+    }),
+    getApiKeyFromApiKeyHelper: async () => undefined,
+    isAnthropicAuthEnabled: () => authState.anthropicAuthEnabled,
+    isClaudeAISubscriber: () => authState.claudeSubscriber,
+  }))
+
+  mock.module('../bootstrap/state.js', () => ({
+    getIsNonInteractiveSession: () => false,
+  }))
+
+  mock.module('../services/api/claude.js', () => ({
+    verifyApiKey: async () => true,
+  }))
+
+  // @ts-expect-error cache-busting query string for Bun module mocks
+  const { useApiKeyVerification } = await import(
+    './useApiKeyVerification.ts?switch-to-third-party'
+  )
+
+  function Harness(): React.ReactNode {
+    const { status } = useApiKeyVerification()
+
+    React.useEffect(() => {
+      seenStatuses.push(status)
+    }, [status])
+
+    return <Text>{status}</Text>
+  }
+
+  const { stdout, stdin } = createTestStreams()
+  const root = await createRoot({
+    stdout: stdout as unknown as NodeJS.WriteStream,
+    stdin: stdin as unknown as NodeJS.ReadStream,
+    patchConsole: false,
+  })
+
+  root.render(<Harness />)
+
+  await waitForCondition(() => seenStatuses.includes('missing'))
+
+  authState.anthropicAuthEnabled = false
+  root.render(<Harness />)
+
+  await waitForCondition(() => seenStatuses.includes('valid'))
+
+  root.unmount()
+  stdin.end()
+  stdout.end()
+  await Bun.sleep(0)
+
+  expect(seenStatuses[0]).toBe('missing')
+  expect(seenStatuses).toContain('valid')
+})

src/hooks/useApiKeyVerification.ts

@@ -1,4 +1,4 @@
-import { useCallback, useState } from 'react'
+import { useCallback, useEffect, useState } from 'react'
 import { getIsNonInteractiveSession } from '../bootstrap/state.js'
 import { verifyApiKey } from '../services/api/claude.js'
 import {
@@ -21,24 +21,43 @@ export type ApiKeyVerificationResult = {
   error: Error | null
 }
 
-export function useApiKeyVerification(): ApiKeyVerificationResult {
-  const [status, setStatus] = useState<VerificationStatus>(() => {
-    if (!isAnthropicAuthEnabled() || isClaudeAISubscriber()) {
-      return 'valid'
-    }
-    // Use skipRetrievingKeyFromApiKeyHelper to avoid executing apiKeyHelper
-    // before trust dialog is shown (security: prevents RCE via settings.json)
-    const { key, source } = getAnthropicApiKeyWithSource({
-      skipRetrievingKeyFromApiKeyHelper: true,
-    })
-    // If apiKeyHelper is configured, we have a key source even though we
-    // haven't executed it yet - return 'loading' to indicate we'll verify later
-    if (key || source === 'apiKeyHelper') {
-      return 'loading'
-    }
-    return 'missing'
+function getInitialVerificationStatus(): VerificationStatus {
+  if (!isAnthropicAuthEnabled() || isClaudeAISubscriber()) {
+    return 'valid'
+  }
+  // Use skipRetrievingKeyFromApiKeyHelper to avoid executing apiKeyHelper
+  // before trust dialog is shown (security: prevents RCE via settings.json)
+  const { key, source } = getAnthropicApiKeyWithSource({
+    skipRetrievingKeyFromApiKeyHelper: true,
   })
+  // If apiKeyHelper is configured, we have a key source even though we
+  // haven't executed it yet - return 'loading' to indicate we'll verify later
+  if (key || source === 'apiKeyHelper') {
+    return 'loading'
+  }
+  return 'missing'
+}
+
+export function useApiKeyVerification(): ApiKeyVerificationResult {
+  const [status, setStatus] = useState<VerificationStatus>(
+    getInitialVerificationStatus,
+  )
   const [error, setError] = useState<Error | null>(null)
+  const anthropicVerificationEnabled =
+    isAnthropicAuthEnabled() && !isClaudeAISubscriber()
+
+  useEffect(() => {
+    const nextStatus = anthropicVerificationEnabled
+      ? getInitialVerificationStatus()
+      : 'valid'
+
+    setStatus(currentStatus =>
+      currentStatus === nextStatus ? currentStatus : nextStatus,
+    )
+    if (nextStatus !== 'error') {
+      setError(null)
+    }
+  }, [anthropicVerificationEnabled])
 
   const verify = useCallback(async (): Promise<void> => {
     if (!isAnthropicAuthEnabled() || isClaudeAISubscriber()) {

src/hooks/useOfficialMarketplaceNotification.tsx

@@ -19,7 +19,7 @@ async function _temp() {
     logForDebugging("Showing marketplace config save failure notification");
     notifs.push({
       key: "marketplace-config-save-failed",
-      jsx: <Text color="error">Failed to save marketplace retry info · Check ~/.claude.json permissions</Text>,
+      jsx: <Text color="error">Failed to save marketplace retry info · Check ~/.openclaude.json permissions</Text>,
       priority: "immediate",
       timeoutMs: 10000
     });

src/hooks/usePasteHandler.test.ts

@@ -1,5 +1,8 @@
 import { expect, test } from 'bun:test'
-import { supportsClipboardImageFallback } from './usePasteHandler.ts'
+import {
+  shouldHandleInputAsPaste,
+  supportsClipboardImageFallback,
+} from './usePasteHandler.ts'
 
 test('supports clipboard image fallback on Windows', () => {
   expect(supportsClipboardImageFallback('windows')).toBe(true)
@@ -20,3 +23,42 @@ test('does not support clipboard image fallback on WSL', () => {
 test('does not support clipboard image fallback on unknown platforms', () => {
   expect(supportsClipboardImageFallback('unknown')).toBe(false)
 })
+
+test('does not treat a bracketed paste as pending when no paste handlers are provided', () => {
+  expect(
+    shouldHandleInputAsPaste({
+      hasTextPasteHandler: false,
+      hasImagePasteHandler: false,
+      inputLength: 'kimi-k2.5'.length,
+      pastePending: false,
+      hasImageFilePath: false,
+      isFromPaste: true,
+    }),
+  ).toBe(false)
+})
+
+test('treats bracketed text paste as pending when a text paste handler exists', () => {
+  expect(
+    shouldHandleInputAsPaste({
+      hasTextPasteHandler: true,
+      hasImagePasteHandler: false,
+      inputLength: 'kimi-k2.5'.length,
+      pastePending: false,
+      hasImageFilePath: false,
+      isFromPaste: true,
+    }),
+  ).toBe(true)
+})
+
+test('treats image path paste as pending when only an image handler exists', () => {
+  expect(
+    shouldHandleInputAsPaste({
+      hasTextPasteHandler: false,
+      hasImagePasteHandler: true,
+      inputLength: 'C:\\Users\\jat\\image.png'.length,
+      pastePending: false,
+      hasImageFilePath: true,
+      isFromPaste: false,
+    }),
+  ).toBe(true)
+})

src/hooks/usePasteHandler.ts

@@ -35,6 +35,24 @@ type PasteHandlerProps = {
   ) => void
 }
 
+export function shouldHandleInputAsPaste(options: {
+  hasTextPasteHandler: boolean
+  hasImagePasteHandler: boolean
+  inputLength: number
+  pastePending: boolean
+  hasImageFilePath: boolean
+  isFromPaste: boolean
+}): boolean {
+  return (
+    (options.hasTextPasteHandler &&
+      (options.inputLength > PASTE_THRESHOLD ||
+        options.pastePending ||
+        options.hasImageFilePath ||
+        options.isFromPaste)) ||
+    (options.hasImagePasteHandler && options.hasImageFilePath)
+  )
+}
+
 export function usePasteHandler({
   onPaste,
   onInput,
@@ -236,11 +254,6 @@ export function usePasteHandler({
     // The keypress parser sets isPasted=true for content within bracketed paste.
     const isFromPaste = event.keypress.isPasted
 
-    // If this is pasted content, set isPasting state for UI feedback
-    if (isFromPaste) {
-      setIsPasting(true)
-    }
-
     // Handle large pastes (>PASTE_THRESHOLD chars)
     // Usually we get one or two input characters at a time. If we
     // get more than the threshold, the user has probably pasted.
@@ -268,6 +281,7 @@ export function usePasteHandler({
       canFallbackToClipboardImage &&
       onImagePaste
     ) {
+      setIsPasting(true)
       checkClipboardForImage()
       // Reset isPasting since there's no text content to process
       setIsPasting(false)
@@ -275,14 +289,17 @@ export function usePasteHandler({
     }
 
     // Check if we should handle as paste (from bracketed paste, large input, or continuation)
-    const shouldHandleAsPaste =
-      onPaste &&
-      (input.length > PASTE_THRESHOLD ||
-        pastePendingRef.current ||
-        hasImageFilePath ||
-        isFromPaste)
+    const shouldHandleAsPaste = shouldHandleInputAsPaste({
+      hasTextPasteHandler: Boolean(onPaste),
+      hasImagePasteHandler: Boolean(onImagePaste),
+      inputLength: input.length,
+      pastePending: pastePendingRef.current,
+      hasImageFilePath,
+      isFromPaste,
+    })
 
     if (shouldHandleAsPaste) {
+      setIsPasting(true)
       pastePendingRef.current = true
       setPasteState(({ chunks, timeoutId }) => {
         return {

src/hooks/useReplBridge.tsx

@@ -434,7 +434,7 @@ export function useReplBridge(messages: Message[], setMessages: (action: React.S
                 if (!store.getState().toolPermissionContext.isBypassPermissionsModeAvailable) {
                   return {
                     ok: false,
-                    error: 'Cannot set permission mode to bypassPermissions because the session was not launched with --dangerously-skip-permissions'
+                    error: 'Cannot set permission mode to bypassPermissions. Enable it with --allow-dangerously-skip-permissions or set permissions.allowBypassPermissionsMode in settings.json'
                   };
                 }
               }

src/hooks/useSwarmPermissionPoller.ts

@@ -1,34 +1,23 @@
 /**
- * Swarm Permission Poller Hook
+ * Swarm Permission Callback Registry
  *
- * This hook polls for permission responses from the team leader when running
- * as a worker agent in a swarm. When a response is received, it calls the
- * appropriate callback (onAllow/onReject) to continue execution.
+ * Manages callback registrations for permission requests and responses
+ * in agent swarms. Responses are delivered exclusively via the mailbox
+ * system (useInboxPoller → processMailboxPermissionResponse).
  *
- * This hook should be used in conjunction with the worker-side integration
- * in useCanUseTool.ts, which creates pending requests that this hook monitors.
+ * The legacy file-based polling (resolved/ directory) has been removed
+ * because it created an unauthenticated attack surface — any local process
+ * could forge approval files. The mailbox path is the sole active channel.
  */
 
-import { useCallback, useEffect, useRef } from 'react'
-import { useInterval } from 'usehooks-ts'
 import { logForDebugging } from '../utils/debug.js'
-import { errorMessage } from '../utils/errors.js'
 import {
   type PermissionUpdate,
   permissionUpdateSchema,
 } from '../utils/permissions/PermissionUpdateSchema.js'
-import {
-  isSwarmWorker,
-  type PermissionResponse,
-  pollForResponse,
-  removeWorkerResponse,
-} from '../utils/swarm/permissionSync.js'
-import { getAgentName, getTeamName } from '../utils/teammate.js'
-
-const POLL_INTERVAL_MS = 500
 
 /**
- * Validate permissionUpdates from external sources (mailbox IPC, disk polling).
+ * Validate permissionUpdates from external sources (mailbox IPC).
  * Malformed entries from buggy/old teammate processes are filtered out rather
  * than propagated unchecked into callback.onAllow().
  */
@@ -225,106 +214,9 @@ export function processSandboxPermissionResponse(params: {
   return true
 }
 
-/**
- * Process a permission response by invoking the registered callback
- */
-function processResponse(response: PermissionResponse): boolean {
-  const callback = pendingCallbacks.get(response.requestId)
-
-  if (!callback) {
-    logForDebugging(
-      `[SwarmPermissionPoller] No callback registered for request ${response.requestId}`,
-    )
-    return false
-  }
-
-  logForDebugging(
-    `[SwarmPermissionPoller] Processing response for request ${response.requestId}: ${response.decision}`,
-  )
-
-  // Remove from registry before invoking callback
-  pendingCallbacks.delete(response.requestId)
-
-  if (response.decision === 'approved') {
-    const permissionUpdates = parsePermissionUpdates(response.permissionUpdates)
-    const updatedInput = response.updatedInput
-    callback.onAllow(updatedInput, permissionUpdates)
-  } else {
-    callback.onReject(response.feedback)
-  }
-
-  return true
-}
-
-/**
- * Hook that polls for permission responses when running as a swarm worker.
- *
- * This hook:
- * 1. Only activates when isSwarmWorker() returns true
- * 2. Polls every 500ms for responses
- * 3. When a response is found, invokes the registered callback
- * 4. Cleans up the response file after processing
- */
-export function useSwarmPermissionPoller(): void {
-  const isProcessingRef = useRef(false)
-
-  const poll = useCallback(async () => {
-    // Don't poll if not a swarm worker
-    if (!isSwarmWorker()) {
-      return
-    }
-
-    // Prevent concurrent polling
-    if (isProcessingRef.current) {
-      return
-    }
-
-    // Don't poll if no callbacks are registered
-    if (pendingCallbacks.size === 0) {
-      return
-    }
-
-    isProcessingRef.current = true
-
-    try {
-      const agentName = getAgentName()
-      const teamName = getTeamName()
-
-      if (!agentName || !teamName) {
-        return
-      }
-
-      // Check each pending request for a response
-      for (const [requestId, _callback] of pendingCallbacks) {
-        const response = await pollForResponse(requestId, agentName, teamName)
-
-        if (response) {
-          // Process the response
-          const processed = processResponse(response)
-
-          if (processed) {
-            // Clean up the response from the worker's inbox
-            await removeWorkerResponse(requestId, agentName, teamName)
-          }
-        }
-      }
-    } catch (error) {
-      logForDebugging(
-        `[SwarmPermissionPoller] Error during poll: ${errorMessage(error)}`,
-      )
-    } finally {
-      isProcessingRef.current = false
-    }
-  }, [])
-
-  // Only poll if we're a swarm worker
-  const shouldPoll = isSwarmWorker()
-  useInterval(() => void poll(), shouldPoll ? POLL_INTERVAL_MS : null)
-
-  // Initial poll on mount
-  useEffect(() => {
-    if (isSwarmWorker()) {
-      void poll()
-    }
-  }, [poll])
-}
+// Legacy file-based polling (useSwarmPermissionPoller, processResponse)
+// has been removed. Permission responses are now delivered exclusively
+// via the mailbox system:
+//   Leader: sendPermissionResponseViaMailbox() → writeToMailbox()
+//   Worker: useInboxPoller → processMailboxPermissionResponse()
+// See: fix(security) — remove unauthenticated file-based permission channel

src/ink/termio/osc.test.ts

@@ -11,14 +11,16 @@ const execFileNoThrowMock = mock(
   async () => ({ code: 0, stdout: '', stderr: '' }),
 )
 
-mock.module('../../utils/execFileNoThrow.js', () => ({
-  execFileNoThrow: execFileNoThrowMock,
-  execFileNoThrowWithCwd: execFileNoThrowMock,
-}))
+function installOscMocks(): void {
+  mock.module('../../utils/execFileNoThrow.js', () => ({
+    execFileNoThrow: execFileNoThrowMock,
+    execFileNoThrowWithCwd: execFileNoThrowMock,
+  }))
 
-mock.module('../../utils/tempfile.js', () => ({
-  generateTempFilePath: generateTempFilePathMock,
-}))
+  mock.module('../../utils/tempfile.js', () => ({
+    generateTempFilePath: generateTempFilePathMock,
+  }))
+}
 
 async function importFreshOscModule() {
   return import(`./osc.ts?ts=${Date.now()}-${Math.random()}`)
@@ -45,6 +47,7 @@ async function waitForExecCall(
 
 describe('Windows clipboard fallback', () => {
   beforeEach(() => {
+    installOscMocks()
     execFileNoThrowMock.mockClear()
     generateTempFilePathMock.mockClear()
     process.env = { ...originalEnv }
@@ -62,14 +65,12 @@ describe('Windows clipboard fallback', () => {
     const { setClipboard } = await importFreshOscModule()
 
     await setClipboard('Привет мир')
-    await flushClipboardCopy()
+    const windowsCall = await waitForExecCall('powershell')
 
     expect(execFileNoThrowMock.mock.calls.some(([cmd]) => cmd === 'clip')).toBe(
       false,
     )
-    expect(
-      execFileNoThrowMock.mock.calls.some(([cmd]) => cmd === 'powershell'),
-    ).toBe(true)
+    expect(windowsCall).toBeDefined()
   })
 
   test('passes Windows clipboard text through a UTF-8 temp file instead of stdin', async () => {
@@ -97,6 +98,7 @@ describe('Windows clipboard fallback', () => {
 
 describe('clipboard path behavior remains stable', () => {
   beforeEach(() => {
+    installOscMocks()
     execFileNoThrowMock.mockClear()
     process.env = { ...originalEnv }
     delete process.env['SSH_CONNECTION']

src/ink/termio/osc.ts

@@ -481,16 +481,16 @@ export const CLEAR_TAB_STATUS = osc(
 )
 
 /**
- * Gate for emitting OSC 21337 (tab-status indicator). Ant-only while the
- * spec is unstable. Terminals that don't recognize it discard silently, so
- * emission is safe unconditionally — we don't gate on terminal detection
+ * Gate for emitting OSC 21337 (tab-status indicator). Currently disabled
+ * (spec is unstable). Terminals that don't recognize it discard silently,
+ * so emission is safe unconditionally — we don't gate on terminal detection
  * since support is expected across several terminals.
  *
  * Callers must wrap output with wrapForMultiplexer() so tmux/screen
  * DCS-passthrough carries the sequence to the outer terminal.
  */
 export function supportsTabStatus(): boolean {
-  return process.env.USER_TYPE === 'ant'
+  return false
 }
 
 /**

src/memdir/teamMemPaths.ts

@@ -74,7 +74,7 @@ export function isTeamMemoryEnabled(): boolean {
   if (!isAutoMemoryEnabled()) {
     return false
   }
-  return getFeatureValue_CACHED_MAY_BE_STALE('tengu_herring_clock', false)
+  return getFeatureValue_CACHED_MAY_BE_STALE('tengu_herring_clock', true)
 }
 
 /**

src/migrations/resetAutoModeOptInForDefaultOffer.ts

@@ -12,7 +12,7 @@ import {
  * One-shot migration: clear skipAutoPermissionPrompt for users who accepted
  * the old 2-option AutoModeOptInDialog but don't have auto as their default.
  * Re-surfaces the dialog so they see the new "make it my default mode" option.
- * Guard lives in GlobalConfig (~/.claude.json), not settings.json, so it
+ * Guard lives in GlobalConfig (~/.openclaude.json), not settings.json, so it
  * survives settings resets and doesn't re-arm itself.
  *
  * Only runs when tengu_auto_mode_config.enabled === 'enabled'. For 'opt-in'

src/query.ts

@@ -160,6 +160,7 @@ function* yieldMissingToolResultBlocks(
  * rules, ye will be punished with an entire day of debugging and hair pulling.
  */
 const MAX_OUTPUT_TOKENS_RECOVERY_LIMIT = 3
+const MAX_CONTINUATION_NUDGES = 3
 
 /**
  * Is this a max_output_tokens error message? If so, the streaming loop should
@@ -209,6 +210,10 @@ type State = {
   pendingToolUseSummary: Promise<ToolUseSummaryMessage | null> | undefined
   stopHookActive: boolean | undefined
   turnCount: number
+  // Count of consecutive continuation nudges within the current turn.
+  // Capped at MAX_CONTINUATION_NUDGES to prevent infinite nudge loops
+  // when the model keeps matching continuation signals without tool calls.
+  continuationNudgeCount: number
   // Why the previous iteration continued. Undefined on first iteration.
   // Lets tests assert recovery paths fired without inspecting message contents.
   transition: Continue | undefined
@@ -272,6 +277,7 @@ async function* queryLoop(
     maxOutputTokensRecoveryCount: 0,
     hasAttemptedReactiveCompact: false,
     turnCount: 1,
+    continuationNudgeCount: 0,
     pendingToolUseSummary: undefined,
     transition: undefined,
   }
@@ -645,6 +651,35 @@ async function* queryLoop(
       }
     }
 
+    // Safety net: when auto-compact's circuit breaker has tripped (3+
+    // consecutive failures), the normal blocking check above is gated on
+    // reactiveCompact. If reactiveCompact is also enabled but ALSO fails
+    // (or is disabled), the oversized context goes straight to the API and
+    // gets a 500. This check catches that gap — if compaction is exhausted
+    // and context is still over the autocompact threshold, block immediately
+    // with a clear message instead of burning an API call that will 500.
+    if (
+      tracking?.consecutiveFailures !== undefined &&
+      tracking.consecutiveFailures >= 3 &&
+      isAutoCompactEnabled()
+    ) {
+      const model = toolUseContext.options.mainLoopModel
+      const tokenUsage = tokenCountWithEstimation(messagesForQuery) - snipTokensFreed
+      const { isAboveAutoCompactThreshold } = calculateTokenWarningState(
+        tokenUsage,
+        model,
+      )
+      if (isAboveAutoCompactThreshold) {
+        yield createAssistantAPIErrorMessage({
+          content:
+            'The conversation has exceeded the context limit and automatic compaction has failed. ' +
+            'Press esc twice to go up a few messages and try again, or start a new session with /new.',
+          error: 'invalid_request',
+        })
+        return { reason: 'blocking_limit' }
+      }
+    }
+
     let attemptWithFallback = true
 
     queryCheckpoint('query_api_loop_start')
@@ -1102,6 +1137,7 @@ async function* queryLoop(
               pendingToolUseSummary: undefined,
               stopHookActive: undefined,
               turnCount,
+              continuationNudgeCount: state.continuationNudgeCount,
               transition: {
                 reason: 'collapse_drain_retry',
                 committed: drained.committed,
@@ -1155,6 +1191,7 @@ async function* queryLoop(
             pendingToolUseSummary: undefined,
             stopHookActive: undefined,
             turnCount,
+            continuationNudgeCount: state.continuationNudgeCount,
             transition: { reason: 'reactive_compact_retry' },
           }
           state = next
@@ -1210,6 +1247,7 @@ async function* queryLoop(
             pendingToolUseSummary: undefined,
             stopHookActive: undefined,
             turnCount,
+            continuationNudgeCount: state.continuationNudgeCount,
             transition: { reason: 'max_output_tokens_escalate' },
           }
           state = next
@@ -1238,6 +1276,7 @@ async function* queryLoop(
             pendingToolUseSummary: undefined,
             stopHookActive: undefined,
             turnCount,
+            continuationNudgeCount: state.continuationNudgeCount,
             transition: {
               reason: 'max_output_tokens_recovery',
               attempt: maxOutputTokensRecoveryCount + 1,
@@ -1295,6 +1334,7 @@ async function* queryLoop(
           pendingToolUseSummary: undefined,
           stopHookActive: true,
           turnCount,
+          continuationNudgeCount: state.continuationNudgeCount,
           transition: { reason: 'stop_hook_blocking' },
         }
         state = next
@@ -1331,6 +1371,7 @@ async function* queryLoop(
             pendingToolUseSummary: undefined,
             stopHookActive: undefined,
             turnCount,
+            continuationNudgeCount: state.continuationNudgeCount,
             transition: { reason: 'token_budget_continuation' },
           }
           continue
@@ -1350,6 +1391,77 @@ async function* queryLoop(
         }
       }
 
+      // Continuation nudge: detect when the model signals intent to continue
+      // (e.g., "so now I have to do it", "let me now...", "I'll need to...")
+      // but returned no tool calls. This prevents premature task completion.
+      //
+      // Guard: capped at MAX_CONTINUATION_NUDGES to prevent infinite loops
+      // when the model keeps matching signals without ever calling tools.
+      if (
+        assistantMessages.length > 0 &&
+        turnCount < (maxTurns ?? Infinity) &&
+        state.continuationNudgeCount < MAX_CONTINUATION_NUDGES
+      ) {
+        const lastAssistant = assistantMessages.at(-1)
+        if (lastAssistant?.type === 'assistant') {
+          const lastText = lastAssistant.message.content
+            .filter((b): b is { type: 'text'; text: string } => b.type === 'text')
+            .map(b => b.text)
+            .join(' ')
+            .toLowerCase()
+
+          // Tightened patterns: require explicit action verbs and exclude
+          // common explanatory phrasing to reduce false positives.
+          const continuationSignals = [
+            // Only match "so now I/let me/we" followed by an action verb
+            /\bso now (i|let me|we) (need to|have to|should|must|will) (do|create|write|edit|update|fix|implement|add|run|check|make|build|set up)\b/,
+            // "now I'll" + action (not "now I'll explain" etc.)
+            /\bnow i('ll| will) (do|create|write|edit|update|fix|implement|add|run|check|make|build|set up|go|proceed)\b/,
+            // "let me" + action (not "let me think/explain/show")
+            /\blet me (go ahead and |now )?(do|create|write|edit|update|fix|implement|add|run|check|make|build|set up|proceed)\b/,
+            // "I'll/I need to/I have to" + action, only if message is short (<80 chars)
+            ...(lastText.length < 80
+              ? [/\b(i('ll| will| need to| have to| must) (now )?(do|create|write|edit|update|fix|implement|add|run|check|make|build|set up))\b/]
+              : []),
+            // "time to" + action
+            /\btime to (do|create|write|edit|update|fix|implement|add|run|check|make|build|get started|begin)\b/,
+            // "next, I'll/let me" + action, only if message is short
+            ...(lastText.length < 80
+              ? [/\bnext,?\s+(i('ll| will)|let me|i need to) (do|create|write|edit|update|fix|implement|add|run|check|make|build)\b/]
+              : []),
+          ]
+
+          // Don't nudge if the text contains completion markers
+          const completionMarkers = /\b(done|finished|completed|complete|summary|that's all|that is all|all set|hope this helps|let me know if)\b/
+          if (completionMarkers.test(lastText)) {
+            // Model signaled completion — don't nudge
+          } else if (continuationSignals.some(re => re.test(lastText))) {
+            logForDebugging(
+              `Continuation nudge triggered (${state.continuationNudgeCount + 1}/${MAX_CONTINUATION_NUDGES}): model said "${lastText.slice(-120)}" without tool calls`,
+            )
+            const nudge = createUserMessage({
+              content: 'Continue with the task. Use the appropriate tools to proceed.',
+              isMeta: true,
+            })
+            const next: State = {
+              messages: [...messagesForQuery, ...assistantMessages, nudge],
+              toolUseContext,
+              autoCompactTracking: tracking,
+              maxOutputTokensRecoveryCount: 0,
+              hasAttemptedReactiveCompact: false,
+              maxOutputTokensOverride: undefined,
+              pendingToolUseSummary: undefined,
+              stopHookActive: undefined,
+              turnCount,
+              continuationNudgeCount: state.continuationNudgeCount + 1,
+              transition: { reason: 'continuation_nudge' },
+            }
+            state = next
+            continue
+          }
+        }
+      }
+
       return { reason: 'completed' }
     }
 
@@ -1715,6 +1827,7 @@ async function* queryLoop(
       turnCount: nextTurnCount,
       maxOutputTokensRecoveryCount: 0,
       hasAttemptedReactiveCompact: false,
+      continuationNudgeCount: 0,
       pendingToolUseSummary: nextPendingToolUseSummary,
       maxOutputTokensOverride: undefined,
       stopHookActive,

src/screens/REPL.tsx

@@ -196,7 +196,7 @@ const PROACTIVE_NO_OP_SUBSCRIBE = (_cb: () => void) => () => { };
 const PROACTIVE_FALSE = () => false;
 const SUGGEST_BG_PR_NOOP = (_p: string, _n: string): boolean => false;
 const useProactive = feature('PROACTIVE') || feature('KAIROS') ? require('../proactive/useProactive.js').useProactive : null;
-const useScheduledTasks = feature('AGENT_TRIGGERS') ? require('../hooks/useScheduledTasks.js').useScheduledTasks : null;
+const useScheduledTasks = require('../hooks/useScheduledTasks.js').useScheduledTasks;
 /* eslint-enable @typescript-eslint/no-require-imports */
 import { isAgentSwarmsEnabled } from '../utils/agentSwarmsEnabled.js';
 import { useTaskListWatcher } from '../hooks/useTaskListWatcher.js';
@@ -3873,7 +3873,7 @@ export function REPL({
   // empty to non-empty, not on every length change -- otherwise a render loop
   // (concurrent onQuery thrashing, etc.) spams saveGlobalConfig, which hits
   // ELOCKED under concurrent sessions and falls back to unlocked writes.
-  // That write storm is the primary trigger for ~/.claude.json corruption
+  // That write storm is the primary trigger for ~/.openclaude.json corruption
   // (GH #3117).
   const hasCountedQueueUseRef = useRef(false);
   useEffect(() => {
@@ -4076,21 +4076,13 @@ export function REPL({
   });
 
   // Scheduled tasks from .claude/scheduled_tasks.json (CronCreate/Delete/List)
-  if (feature('AGENT_TRIGGERS')) {
-    // Assistant mode bypasses the isLoading gate (the proactive tick →
-    // Sleep → tick loop would otherwise starve the scheduler).
-    // kairosEnabled is set once in initialState (main.tsx) and never mutated — no
-    // subscription needed. The tengu_kairos_cron runtime gate is checked inside
-    // useScheduledTasks's effect (not here) since wrapping a hook call in a dynamic
-    // condition would break rules-of-hooks.
-    const assistantMode = store.getState().kairosEnabled;
-    // biome-ignore lint/correctness/useHookAtTopLevel: feature() is a compile-time constant
-    useScheduledTasks!({
-      isLoading,
-      assistantMode,
-      setMessages
-    });
-  }
+  // and session-only /loop runs.
+  const assistantMode = store.getState().kairosEnabled;
+  useScheduledTasks({
+    isLoading,
+    assistantMode,
+    setMessages
+  });
 
   // Note: Permission polling is now handled by useInboxPoller
   // - Workers receive permission responses via mailbox messages

src/services/analytics/growthbook.ts

@@ -334,7 +334,7 @@ async function processRemoteEvalPayload(
   // Empty object is truthy — without the length check, `{features: {}}`
   // (transient server bug, truncated response) would pass, clear the maps
   // below, return true, and syncRemoteEvalToDisk would wholesale-write `{}`
-  // to disk: total flag blackout for every process sharing ~/.claude.json.
+  // to disk: total flag blackout for every process sharing ~/.openclaude.json.
   if (!payload?.features || Object.keys(payload.features).length === 0) {
     return false
   }

src/services/api/bootstrap.ts

@@ -116,9 +116,21 @@ async function fetchBootstrapAPI(): Promise<BootstrapResponse | null> {
       return parsed.data
     })
   } catch (error) {
-    logForDebugging(
-      `[Bootstrap] Fetch failed: ${axios.isAxiosError(error) ? (error.response?.status ?? error.code) : 'unknown'}`,
-    )
+    if (axios.isAxiosError(error)) {
+      const status = error.response?.status ?? 'no-response'
+      const code = error.code ?? 'unknown-code'
+      const method = error.config?.method?.toUpperCase() ?? 'UNKNOWN'
+      const requestUrl = error.config?.url ?? 'unknown-url'
+      const message = error.message ?? 'unknown axios error'
+
+      logForDebugging(
+        `[Bootstrap] Fetch failed: status=${status} code=${code} method=${method} url=${requestUrl} message=${message}`,
+      )
+    } else {
+      const message = error instanceof Error ? error.message : String(error)
+      logForDebugging(`[Bootstrap] Fetch failed: ${message}`)
+    }
+
     throw error
   }
 }

src/services/api/claude.ts

@@ -23,6 +23,7 @@ import { randomUUID } from 'crypto'
 import {
   getAPIProvider,
   isFirstPartyAnthropicBaseUrl,
+  isGithubNativeAnthropicMode,
 } from 'src/utils/model/providers.js'
 import {
   getAttributionHeader,
@@ -334,8 +335,13 @@ export function getPromptCachingEnabled(model: string): boolean {
   // Prompt caching is an Anthropic-specific feature. Third-party providers
   // do not understand cache_control blocks and strict backends (e.g. Azure
   // Foundry) reject or flag requests that contain them.
+  //
+  // Exception: when the GitHub provider is configured in native Anthropic API
+  // mode (CLAUDE_CODE_GITHUB_ANTHROPIC_API=1), requests are sent in Anthropic
+  // format, so cache_control blocks are supported.
   const provider = getAPIProvider()
-  if (provider !== 'firstParty' && provider !== 'bedrock' && provider !== 'vertex') {
+  const isNativeGithub = isGithubNativeAnthropicMode(model)
+  if (provider !== 'firstParty' && provider !== 'bedrock' && provider !== 'vertex' && !isNativeGithub) {
     return false
   }
 
@@ -1211,7 +1217,7 @@ async function* queryModel(
     cachedMCEnabled = featureEnabled && modelSupported
     const config = getCachedMCConfig()
     logForDebugging(
-      `Cached MC gate: enabled=${featureEnabled} modelSupported=${modelSupported} model=${options.model} supportedModels=${jsonStringify(config.supportedModels)}`,
+      `Cached MC gate: enabled=${featureEnabled} modelSupported=${modelSupported} model=${options.model} supportedModels=${jsonStringify(config?.supportedModels)}`,
     )
   }
 

src/services/api/client.ts

@@ -14,6 +14,7 @@ import { getSmallFastModel } from 'src/utils/model/model.js'
 import {
   getAPIProvider,
   isFirstPartyAnthropicBaseUrl,
+  isGithubNativeAnthropicMode,
 } from 'src/utils/model/providers.js'
 import { getProxyFetchOptions } from 'src/utils/proxy.js'
 import {
@@ -174,6 +175,25 @@ export async function getAnthropicClient({
       providerOverride,
     }) as unknown as Anthropic
   }
+  // GitHub provider in native Anthropic API mode: send requests in Anthropic
+  // format so cache_control blocks are honoured and prompt caching works.
+  // Requires the GitHub endpoint (OPENAI_BASE_URL) to support Anthropic's
+  // messages API — set CLAUDE_CODE_GITHUB_ANTHROPIC_API=1 to opt in.
+  if (isGithubNativeAnthropicMode(model)) {
+    const githubBaseUrl =
+      process.env.OPENAI_BASE_URL?.replace(/\/$/, '') ??
+      'https://api.githubcopilot.com'
+    const githubToken =
+      process.env.GITHUB_TOKEN ?? process.env.GH_TOKEN ?? ''
+    const nativeArgs: ConstructorParameters<typeof Anthropic>[0] = {
+      ...ARGS,
+      baseURL: githubBaseUrl,
+      authToken: githubToken,
+      // No apiKey — we authenticate via Bearer token (authToken)
+      apiKey: null,
+    }
+    return new Anthropic(nativeArgs)
+  }
   if (
     isEnvTruthy(process.env.CLAUDE_CODE_USE_OPENAI) ||
     isEnvTruthy(process.env.CLAUDE_CODE_USE_GITHUB) ||

src/services/api/codexOAuth.test.ts

@@ -0,0 +1,166 @@
+import { createServer } from 'node:http'
+
+import { afterEach, expect, mock, test } from 'bun:test'
+
+import { CodexOAuthService } from './codexOAuth.js'
+
+const originalFetch = globalThis.fetch
+const originalCallbackPort = process.env.CODEX_OAUTH_CALLBACK_PORT
+const originalClientId = process.env.CODEX_OAUTH_CLIENT_ID
+
+afterEach(() => {
+  mock.restore()
+  globalThis.fetch = originalFetch
+
+  if (originalCallbackPort === undefined) {
+    delete process.env.CODEX_OAUTH_CALLBACK_PORT
+  } else {
+    process.env.CODEX_OAUTH_CALLBACK_PORT = originalCallbackPort
+  }
+
+  if (originalClientId === undefined) {
+    delete process.env.CODEX_OAUTH_CLIENT_ID
+  } else {
+    process.env.CODEX_OAUTH_CLIENT_ID = originalClientId
+  }
+})
+
+async function getFreePort(): Promise<number> {
+  return await new Promise((resolve, reject) => {
+    const server = createServer()
+
+    server.once('error', reject)
+    server.listen(0, '127.0.0.1', () => {
+      const address = server.address()
+      if (!address || typeof address === 'string') {
+        server.close(() => reject(new Error('Failed to allocate test port.')))
+        return
+      }
+
+      const { port } = address
+      server.close(error => {
+        if (error) {
+          reject(error)
+          return
+        }
+        resolve(port)
+      })
+    })
+  })
+}
+
+function buildCallbackRequest(authUrl: string): string {
+  const authorizeUrl = new URL(authUrl)
+  const redirectUri = authorizeUrl.searchParams.get('redirect_uri')
+  const state = authorizeUrl.searchParams.get('state')
+
+  if (!redirectUri || !state) {
+    throw new Error('Codex OAuth test did not receive a valid authorization URL.')
+  }
+
+  const callbackUrl = new URL(redirectUri)
+  callbackUrl.searchParams.set('code', 'auth-code')
+  callbackUrl.searchParams.set('state', state)
+  return callbackUrl.toString()
+}
+
+test('serves updated success copy after a successful Codex OAuth flow', async () => {
+  const callbackPort = await getFreePort()
+  process.env.CODEX_OAUTH_CALLBACK_PORT = String(callbackPort)
+  process.env.CODEX_OAUTH_CLIENT_ID = 'test-client-id'
+
+  globalThis.fetch = mock(async (input, init) => {
+    const url = String(input)
+    if (url.startsWith('http://localhost:')) {
+      return originalFetch(input, init)
+    }
+
+    return new Response(
+      JSON.stringify({
+        access_token: 'access-token',
+        refresh_token: 'refresh-token',
+      }),
+      {
+        status: 200,
+        headers: { 'Content-Type': 'application/json' },
+      },
+    )
+  }) as typeof fetch
+
+  const service = new CodexOAuthService()
+  let callbackResponsePromise!: Promise<Response>
+
+  const flowPromise = service.startOAuthFlow(async authUrl => {
+    callbackResponsePromise = originalFetch(buildCallbackRequest(authUrl))
+  })
+
+  const tokens = await flowPromise
+  const callbackResponse = await callbackResponsePromise
+  const html = await callbackResponse.text()
+
+  expect(tokens.accessToken).toBe('access-token')
+  expect(tokens.refreshToken).toBe('refresh-token')
+  expect(html).toContain('You can return to OpenClaude now.')
+  expect(html).toContain(
+    'OpenClaude will finish activating your new Codex OAuth login.',
+  )
+  expect(html).not.toContain('continue automatically')
+})
+
+test('cancellation during token exchange returns a cancelled page and rejects the flow', async () => {
+  const callbackPort = await getFreePort()
+  process.env.CODEX_OAUTH_CALLBACK_PORT = String(callbackPort)
+  process.env.CODEX_OAUTH_CLIENT_ID = 'test-client-id'
+
+  let resolveFetchStart!: () => void
+  const fetchStarted = new Promise<void>(resolve => {
+    resolveFetchStart = resolve
+  })
+
+  globalThis.fetch = mock((input, init) => {
+    const url = String(input)
+    if (url.startsWith('http://localhost:')) {
+      return originalFetch(input, init)
+    }
+
+    return new Promise<Response>((_resolve, reject) => {
+      resolveFetchStart()
+
+      const signal = init?.signal
+      if (!signal) {
+        return
+      }
+
+      if (signal.aborted) {
+        reject(signal.reason)
+        return
+      }
+
+      signal.addEventListener(
+        'abort',
+        () => {
+          reject(signal.reason)
+        },
+        { once: true },
+      )
+    })
+  }) as typeof fetch
+
+  const service = new CodexOAuthService()
+  let callbackResponsePromise!: Promise<Response>
+
+  const flowPromise = service.startOAuthFlow(async authUrl => {
+    callbackResponsePromise = originalFetch(buildCallbackRequest(authUrl))
+  })
+
+  await fetchStarted
+  service.cleanup()
+
+  await expect(flowPromise).rejects.toThrow('Codex OAuth flow was cancelled.')
+
+  const callbackResponse = await callbackResponsePromise
+  const html = await callbackResponse.text()
+
+  expect(html).toContain('Codex login cancelled')
+  expect(html).toContain('retry in OpenClaude')
+})

src/services/api/codexOAuth.ts

@@ -0,0 +1,307 @@
+import { AuthCodeListener } from '../oauth/auth-code-listener.js'
+import {
+  generateCodeChallenge,
+  generateCodeVerifier,
+  generateState,
+} from '../oauth/crypto.js'
+import {
+  asTrimmedString,
+  CODEX_OAUTH_ISSUER,
+  CODEX_OAUTH_ORIGINATOR,
+  CODEX_OAUTH_SCOPE,
+  escapeHtml,
+  exchangeCodexIdTokenForApiKey,
+  getCodexOAuthCallbackPort,
+  getCodexOAuthClientId,
+  parseChatgptAccountId,
+} from './codexOAuthShared.js'
+
+type CodexOAuthTokenResponse = {
+  id_token?: string
+  access_token?: string
+  refresh_token?: string
+}
+
+export type CodexOAuthTokens = {
+  apiKey?: string
+  accessToken: string
+  refreshToken: string
+  idToken?: string
+  accountId?: string
+}
+
+function buildCodexAuthorizeUrl(options: {
+  port: number
+  codeChallenge: string
+  state: string
+}): string {
+  const redirectUri = `http://localhost:${options.port}/auth/callback`
+  const authUrl = new URL(`${CODEX_OAUTH_ISSUER}/oauth/authorize`)
+
+  authUrl.searchParams.append('response_type', 'code')
+  authUrl.searchParams.append('client_id', getCodexOAuthClientId())
+  authUrl.searchParams.append('redirect_uri', redirectUri)
+  authUrl.searchParams.append('scope', CODEX_OAUTH_SCOPE)
+  authUrl.searchParams.append('code_challenge', options.codeChallenge)
+  authUrl.searchParams.append('code_challenge_method', 'S256')
+  authUrl.searchParams.append('id_token_add_organizations', 'true')
+  authUrl.searchParams.append('codex_cli_simplified_flow', 'true')
+  authUrl.searchParams.append('state', options.state)
+  authUrl.searchParams.append('originator', CODEX_OAUTH_ORIGINATOR)
+
+  return authUrl.toString()
+}
+
+function renderSuccessPage(): string {
+  return `<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="utf-8" />
+    <title>Codex Login Complete</title>
+    <style>
+      body { font-family: sans-serif; padding: 32px; line-height: 1.5; color: #111827; }
+      h1 { margin: 0 0 12px; font-size: 22px; }
+      p { margin: 0 0 10px; }
+    </style>
+  </head>
+  <body>
+    <h1>Codex login complete</h1>
+    <p>You can return to OpenClaude now.</p>
+    <p>OpenClaude will finish activating your new Codex OAuth login.</p>
+  </body>
+</html>`
+}
+
+function renderErrorPage(message: string): string {
+  const safeMessage = escapeHtml(message)
+  return `<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="utf-8" />
+    <title>Codex Login Failed</title>
+    <style>
+      body { font-family: sans-serif; padding: 32px; line-height: 1.5; color: #111827; }
+      h1 { margin: 0 0 12px; font-size: 22px; color: #991b1b; }
+      p { margin: 0 0 10px; }
+    </style>
+  </head>
+  <body>
+    <h1>Codex login failed</h1>
+    <p>${safeMessage}</p>
+    <p>You can close this window and try again in OpenClaude.</p>
+  </body>
+</html>`
+}
+
+function renderCancelledPage(): string {
+  return `<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="utf-8" />
+    <title>Codex Login Cancelled</title>
+    <style>
+      body { font-family: sans-serif; padding: 32px; line-height: 1.5; color: #111827; }
+      h1 { margin: 0 0 12px; font-size: 22px; }
+      p { margin: 0 0 10px; }
+    </style>
+  </head>
+  <body>
+    <h1>Codex login cancelled</h1>
+    <p>You can close this window and retry in OpenClaude.</p>
+  </body>
+</html>`
+}
+
+async function exchangeAuthorizationCode(options: {
+  authorizationCode: string
+  codeVerifier: string
+  port: number
+  signal?: AbortSignal
+}): Promise<CodexOAuthTokens> {
+  const redirectUri = `http://localhost:${options.port}/auth/callback`
+  const body = new URLSearchParams({
+    grant_type: 'authorization_code',
+    code: options.authorizationCode,
+    redirect_uri: redirectUri,
+    client_id: getCodexOAuthClientId(),
+    code_verifier: options.codeVerifier,
+  })
+
+  const response = await fetch(`${CODEX_OAUTH_ISSUER}/oauth/token`, {
+    method: 'POST',
+    headers: {
+      'Content-Type': 'application/x-www-form-urlencoded',
+    },
+    body,
+    signal: options.signal
+      ? AbortSignal.any([options.signal, AbortSignal.timeout(15_000)])
+      : AbortSignal.timeout(15_000),
+  })
+
+  if (!response.ok) {
+    const errorText = await response.text().catch(() => '')
+    throw new Error(
+      errorText.trim()
+        ? `Codex OAuth token exchange failed (${response.status}): ${errorText.trim()}`
+        : `Codex OAuth token exchange failed with status ${response.status}.`,
+    )
+  }
+
+  const payload = (await response.json()) as CodexOAuthTokenResponse
+  const accessToken = asTrimmedString(payload.access_token)
+  const refreshToken = asTrimmedString(payload.refresh_token)
+  if (!accessToken || !refreshToken) {
+    throw new Error(
+      'Codex OAuth completed, but the token response was missing credentials.',
+    )
+  }
+
+  const idToken = asTrimmedString(payload.id_token)
+  const apiKey = idToken
+    ? await exchangeCodexIdTokenForApiKey(idToken).catch(() => undefined)
+    : undefined
+
+  return {
+    apiKey,
+    accessToken,
+    refreshToken,
+    idToken,
+    accountId:
+      parseChatgptAccountId(idToken) ?? parseChatgptAccountId(accessToken),
+  }
+}
+
+export class CodexOAuthService {
+  private authCodeListener: AuthCodeListener | null = null
+  private port: number | null = null
+  private tokenExchangeAbortController: AbortController | null = null
+
+  private buildCancellationError(): Error {
+    return new Error('Codex OAuth flow was cancelled.')
+  }
+
+  async startOAuthFlow(
+    authURLHandler: (authUrl: string) => Promise<void>,
+  ): Promise<CodexOAuthTokens> {
+    const codeVerifier = generateCodeVerifier()
+    const callbackPort = getCodexOAuthCallbackPort()
+    const authCodeListener = new AuthCodeListener('/auth/callback')
+
+    this.authCodeListener = authCodeListener
+    this.port = null
+
+    try {
+      const port = await authCodeListener.start(callbackPort)
+      this.port = port
+
+      const state = generateState()
+      const codeChallenge = await generateCodeChallenge(codeVerifier)
+      const authUrl = buildCodexAuthorizeUrl({
+        port,
+        codeChallenge,
+        state,
+      })
+
+      try {
+        const authorizationCode = await authCodeListener.waitForAuthorization(
+          state,
+          async () => {
+            await authURLHandler(authUrl)
+          },
+        )
+
+        const tokenExchangeAbortController = new AbortController()
+        this.tokenExchangeAbortController = tokenExchangeAbortController
+
+        let tokens: CodexOAuthTokens
+        try {
+          tokens = await exchangeAuthorizationCode({
+            authorizationCode,
+            codeVerifier,
+            port,
+            signal: tokenExchangeAbortController.signal,
+          })
+        } finally {
+          if (
+            this.tokenExchangeAbortController === tokenExchangeAbortController
+          ) {
+            this.tokenExchangeAbortController = null
+          }
+        }
+
+        if (this.authCodeListener !== authCodeListener) {
+          throw this.buildCancellationError()
+        }
+
+        authCodeListener.handleSuccessRedirect([], res => {
+          res.writeHead(200, {
+            'Content-Type': 'text/html; charset=utf-8',
+          })
+          res.end(renderSuccessPage())
+        })
+
+        return tokens
+      } catch (error) {
+        const resolvedError =
+          this.authCodeListener === authCodeListener
+            ? error
+            : this.buildCancellationError()
+
+        if (authCodeListener.hasPendingResponse()) {
+          const isCancellation =
+            resolvedError instanceof Error &&
+            resolvedError.message === 'Codex OAuth flow was cancelled.'
+
+          authCodeListener.handleErrorRedirect(res => {
+            res.writeHead(isCancellation ? 200 : 400, {
+              'Content-Type': 'text/html; charset=utf-8',
+            })
+            res.end(
+              isCancellation
+                ? renderCancelledPage()
+                : renderErrorPage(
+                    resolvedError instanceof Error
+                      ? resolvedError.message
+                      : String(resolvedError),
+                  ),
+            )
+          })
+        }
+        throw resolvedError
+      } finally {
+        this.cleanup()
+      }
+    } catch (error) {
+      const message = error instanceof Error ? error.message : String(error)
+      if (
+        message.includes('EADDRINUSE') ||
+        message.includes(String(callbackPort))
+      ) {
+        throw new Error(
+          `Codex OAuth needs localhost:${callbackPort} for its callback. Close any app already using that port and try again.`,
+        )
+      }
+      throw error
+    }
+  }
+
+  cleanup(): void {
+    const cancellationError = this.buildCancellationError()
+
+    this.tokenExchangeAbortController?.abort(cancellationError)
+    this.tokenExchangeAbortController = null
+
+    if (this.authCodeListener?.hasPendingResponse()) {
+      this.authCodeListener.handleErrorRedirect(res => {
+        res.writeHead(200, {
+          'Content-Type': 'text/html; charset=utf-8',
+        })
+        res.end(renderCancelledPage())
+      })
+    }
+
+    this.authCodeListener?.cancelPendingAuthorization(cancellationError)
+    this.authCodeListener = null
+    this.port = null
+  }
+}

src/services/api/codexOAuthShared.ts

@@ -0,0 +1,139 @@
+export const CODEX_OAUTH_ISSUER = 'https://auth.openai.com'
+export const CODEX_REFRESH_URL = `${CODEX_OAUTH_ISSUER}/oauth/token`
+export const DEFAULT_CODEX_OAUTH_CLIENT_ID = 'app_EMoamEEZ73f0CkXaXp7hrann'
+export const DEFAULT_CODEX_OAUTH_CALLBACK_PORT = 1455
+export const CODEX_OAUTH_SCOPE =
+  'openid profile email offline_access api.connectors.read api.connectors.invoke'
+export const CODEX_OAUTH_ORIGINATOR = 'codex_cli_rs'
+export const CODEX_API_KEY_TOKEN_NAME = 'openai-api-key'
+export const CODEX_ID_TOKEN_SUBJECT_TYPE =
+  'urn:ietf:params:oauth:token-type:id_token'
+export const CODEX_TOKEN_EXCHANGE_GRANT =
+  'urn:ietf:params:oauth:grant-type:token-exchange'
+
+export function asTrimmedString(value: unknown): string | undefined {
+  if (typeof value !== 'string') return undefined
+  const trimmed = value.trim()
+  return trimmed ? trimmed : undefined
+}
+
+export function getCodexOAuthClientId(
+  env: NodeJS.ProcessEnv = process.env,
+): string {
+  return asTrimmedString(env.CODEX_OAUTH_CLIENT_ID) ?? DEFAULT_CODEX_OAUTH_CLIENT_ID
+}
+
+export function getCodexOAuthCallbackPort(
+  env: NodeJS.ProcessEnv = process.env,
+): number {
+  const rawPort = asTrimmedString(env.CODEX_OAUTH_CALLBACK_PORT)
+  if (!rawPort) {
+    return DEFAULT_CODEX_OAUTH_CALLBACK_PORT
+  }
+
+  const parsed = Number.parseInt(rawPort, 10)
+  if (Number.isInteger(parsed) && parsed > 0 && parsed <= 65535) {
+    return parsed
+  }
+
+  return DEFAULT_CODEX_OAUTH_CALLBACK_PORT
+}
+
+export function decodeJwtPayload(
+  token: string,
+): Record<string, unknown> | undefined {
+  const parts = token.split('.')
+  if (parts.length < 2) return undefined
+
+  try {
+    const normalized = parts[1].replace(/-/g, '+').replace(/_/g, '/')
+    const padded = normalized + '='.repeat((4 - (normalized.length % 4)) % 4)
+    const json = Buffer.from(padded, 'base64').toString('utf8')
+    const parsed = JSON.parse(json)
+    return parsed && typeof parsed === 'object'
+      ? (parsed as Record<string, unknown>)
+      : undefined
+  } catch {
+    return undefined
+  }
+}
+
+export function parseChatgptAccountId(
+  token: string | undefined,
+): string | undefined {
+  if (!token) return undefined
+
+  const payload = decodeJwtPayload(token)
+  const nestedAuth =
+    payload?.['https://api.openai.com/auth'] &&
+    typeof payload['https://api.openai.com/auth'] === 'object'
+      ? (payload['https://api.openai.com/auth'] as Record<string, unknown>)
+      : undefined
+
+  return (
+    asTrimmedString(
+      nestedAuth?.chatgpt_account_id ??
+        payload?.['https://api.openai.com/auth.chatgpt_account_id'] ??
+        payload?.chatgpt_account_id,
+    ) ?? undefined
+  )
+}
+
+export function escapeHtml(value: string): string {
+  return value.replace(/[&<>"']/g, char => {
+    switch (char) {
+      case '&':
+        return '&amp;'
+      case '<':
+        return '&lt;'
+      case '>':
+        return '&gt;'
+      case '"':
+        return '&quot;'
+      case '\'':
+        return '&#39;'
+      default:
+        return char
+    }
+  })
+}
+
+export async function exchangeCodexIdTokenForApiKey(
+  idToken: string,
+): Promise<string> {
+  const body = new URLSearchParams({
+    grant_type: CODEX_TOKEN_EXCHANGE_GRANT,
+    client_id: getCodexOAuthClientId(),
+    requested_token: CODEX_API_KEY_TOKEN_NAME,
+    subject_token: idToken,
+    subject_token_type: CODEX_ID_TOKEN_SUBJECT_TYPE,
+  })
+
+  const response = await fetch(CODEX_REFRESH_URL, {
+    method: 'POST',
+    headers: {
+      'Content-Type': 'application/x-www-form-urlencoded',
+    },
+    body,
+    signal: AbortSignal.timeout(15_000),
+  })
+
+  if (!response.ok) {
+    const bodyText = await response.text().catch(() => '')
+    throw new Error(
+      bodyText.trim()
+        ? `Codex API key exchange failed (${response.status}): ${bodyText.trim()}`
+        : `Codex API key exchange failed with status ${response.status}.`,
+    )
+  }
+
+  const payload = (await response.json()) as { access_token?: string }
+  const apiKey = asTrimmedString(payload.access_token)
+  if (!apiKey) {
+    throw new Error(
+      'Codex API key exchange completed, but no API key token was returned.',
+    )
+  }
+
+  return apiKey
+}

src/services/api/codexShim.test.ts

@@ -8,16 +8,13 @@ import {
   convertCodexResponseToAnthropicMessage,
   convertToolsToResponsesTools,
 } from './codexShim.js'
-import {
-  resolveCodexApiCredentials,
-  resolveProviderRequest,
-} from './providerConfig.js'
 
 const tempDirs: string[] = []
 const originalEnv = {
   OPENAI_BASE_URL: process.env.OPENAI_BASE_URL,
   OPENAI_API_BASE: process.env.OPENAI_API_BASE,
   CLAUDE_CODE_USE_GITHUB: process.env.CLAUDE_CODE_USE_GITHUB,
+  OPENAI_MODEL: process.env.OPENAI_MODEL,
 }
 
 afterEach(() => {
@@ -30,6 +27,9 @@ afterEach(() => {
   if (originalEnv.CLAUDE_CODE_USE_GITHUB === undefined) delete process.env.CLAUDE_CODE_USE_GITHUB
   else process.env.CLAUDE_CODE_USE_GITHUB = originalEnv.CLAUDE_CODE_USE_GITHUB
 
+  if (originalEnv.OPENAI_MODEL === undefined) delete process.env.OPENAI_MODEL
+  else process.env.OPENAI_MODEL = originalEnv.OPENAI_MODEL
+
   while (tempDirs.length > 0) {
     const dir = tempDirs.pop()
     if (dir) rmSync(dir, { recursive: true, force: true })
@@ -59,6 +59,10 @@ async function collectStreamEventTypes(responseText: string): Promise<string[]>
   return events
 }
 
+async function importFreshProviderConfigModule() {
+  return import(`./providerConfig.js?ts=${Date.now()}-${Math.random()}`)
+}
+
 describe('Codex provider config', () => {
   const originalOpenaiBaseUrl = process.env.OPENAI_BASE_URL
   const originalOpenaiApiBase = process.env.OPENAI_API_BASE
@@ -75,7 +79,8 @@ describe('Codex provider config', () => {
     else process.env.OPENAI_API_BASE = originalOpenaiApiBase
   })
 
-  test('resolves codexplan alias to Codex transport with reasoning', () => {
+  test('resolves codexplan alias to Codex transport with reasoning', async () => {
+    const { resolveProviderRequest } = await importFreshProviderConfigModule()
     delete process.env.OPENAI_BASE_URL
     delete process.env.OPENAI_API_BASE
     delete process.env.CLAUDE_CODE_USE_GITHUB
@@ -84,9 +89,23 @@ describe('Codex provider config', () => {
     expect(resolved.transport).toBe('codex_responses')
     expect(resolved.resolvedModel).toBe('gpt-5.4')
     expect(resolved.reasoning).toEqual({ effort: 'high' })
+    expect(resolved.baseUrl).toBe('https://chatgpt.com/backend-api/codex')
   })
 
-  test('does not force Codex transport when a local non-Codex base URL is explicit', () => {
+  test('resolves codexspark alias to Codex transport with Codex base URL', async () => {
+    const { resolveProviderRequest } = await importFreshProviderConfigModule()
+    delete process.env.OPENAI_BASE_URL
+    delete process.env.OPENAI_API_BASE
+    delete process.env.CLAUDE_CODE_USE_GITHUB
+
+    const resolved = resolveProviderRequest({ model: 'codexspark' })
+    expect(resolved.transport).toBe('codex_responses')
+    expect(resolved.resolvedModel).toBe('gpt-5.3-codex-spark')
+    expect(resolved.baseUrl).toBe('https://chatgpt.com/backend-api/codex')
+  })
+
+  test('does not force Codex transport when a local non-Codex base URL is explicit', async () => {
+    const { resolveProviderRequest } = await importFreshProviderConfigModule()
     const resolved = resolveProviderRequest({
       model: 'codexplan',
       baseUrl: 'http://127.0.0.1:8080/v1',
@@ -97,7 +116,8 @@ describe('Codex provider config', () => {
     expect(resolved.resolvedModel).toBe('gpt-5.4')
   })
 
-  test('resolves codexplan to Codex transport even when OPENAI_BASE_URL is the string "undefined"', () => {
+  test('resolves codexplan to Codex transport even when OPENAI_BASE_URL is the string "undefined"', async () => {
+    const { resolveProviderRequest } = await importFreshProviderConfigModule()
     // On Windows, env vars can leak as the literal string "undefined" instead of
     // the JS value undefined when not properly unset (issue #336).
     process.env.OPENAI_BASE_URL = 'undefined'
@@ -105,20 +125,57 @@ describe('Codex provider config', () => {
     expect(resolved.transport).toBe('codex_responses')
   })
 
-  test('resolves codexplan to Codex transport even when OPENAI_BASE_URL is an empty string', () => {
+  test('resolves codexplan to Codex transport even when OPENAI_BASE_URL is an empty string', async () => {
+    const { resolveProviderRequest } = await importFreshProviderConfigModule()
     process.env.OPENAI_BASE_URL = ''
     const resolved = resolveProviderRequest({ model: 'codexplan' })
     expect(resolved.transport).toBe('codex_responses')
   })
 
-  test('prefers explicit baseUrl option over env var', () => {
+  test('prefers explicit baseUrl option over env var', async () => {
+    const { resolveProviderRequest } = await importFreshProviderConfigModule()
     process.env.OPENAI_BASE_URL = 'https://example.com/v1'
     const resolved = resolveProviderRequest({ model: 'codexplan', baseUrl: 'https://chatgpt.com/backend-api/codex' })
     expect(resolved.transport).toBe('codex_responses')
     expect(resolved.baseUrl).toBe('https://chatgpt.com/backend-api/codex')
   })
 
-  test('loads Codex credentials from auth.json fallback', () => {
+  test('default gpt-4o uses OpenAI base URL (no regression)', async () => {
+    const { resolveProviderRequest } = await importFreshProviderConfigModule()
+    delete process.env.OPENAI_BASE_URL
+    delete process.env.CLAUDE_CODE_USE_GITHUB
+
+    const resolved = resolveProviderRequest({ model: 'gpt-4o' })
+    expect(resolved.transport).toBe('chat_completions')
+    expect(resolved.baseUrl).toBe('https://api.openai.com/v1')
+    expect(resolved.resolvedModel).toBe('gpt-4o')
+  })
+
+  test('resolves codexplan from env var OPENAI_MODEL to Codex endpoint', async () => {
+    const { resolveProviderRequest } = await importFreshProviderConfigModule()
+    process.env.OPENAI_MODEL = 'codexplan'
+    delete process.env.OPENAI_BASE_URL
+    delete process.env.CLAUDE_CODE_USE_GITHUB
+
+    const resolved = resolveProviderRequest()
+    expect(resolved.transport).toBe('codex_responses')
+    expect(resolved.baseUrl).toBe('https://chatgpt.com/backend-api/codex')
+    expect(resolved.resolvedModel).toBe('gpt-5.4')
+  })
+
+  test('does not override custom base URL for codexplan (e.g., local provider)', async () => {
+    const { resolveProviderRequest } = await importFreshProviderConfigModule()
+    process.env.OPENAI_MODEL = 'codexplan'
+    process.env.OPENAI_BASE_URL = 'http://localhost:11434/v1'
+    delete process.env.CLAUDE_CODE_USE_GITHUB
+
+    const resolved = resolveProviderRequest()
+    expect(resolved.transport).toBe('chat_completions')
+    expect(resolved.baseUrl).toBe('http://localhost:11434/v1')
+  })
+
+  test('loads Codex credentials from auth.json fallback', async () => {
+    const { resolveCodexApiCredentials } = await importFreshProviderConfigModule()
     const authPath = createTempAuthJson({
       tokens: {
         access_token: 'header.payload.signature',
@@ -134,6 +191,31 @@ describe('Codex provider config', () => {
     expect(credentials.accountId).toBe('acct_test')
     expect(credentials.source).toBe('auth.json')
   })
+
+  test('does not treat auth.json id_token as a Codex bearer credential', async () => {
+    const { resolveCodexApiCredentials } = await importFreshProviderConfigModule()
+    const idTokenPayload = Buffer.from(
+      JSON.stringify({
+        'https://api.openai.com/auth': {
+          chatgpt_account_id: 'acct_from_id_token',
+        },
+      }),
+      'utf8',
+    ).toString('base64url')
+    const authPath = createTempAuthJson({
+      tokens: {
+        id_token: `header.${idTokenPayload}.signature`,
+      },
+    })
+
+    const credentials = resolveCodexApiCredentials({
+      CODEX_AUTH_JSON_PATH: authPath,
+    } as NodeJS.ProcessEnv)
+
+    expect(credentials.apiKey).toBe('')
+    expect(credentials.accountId).toBe('acct_from_id_token')
+    expect(credentials.source).toBe('none')
+  })
 })
 
 describe('Codex request translation', () => {
@@ -465,7 +547,7 @@ describe('Codex request translation', () => {
     ])
   })
 
-  test('strips leaked reasoning preamble from completed Codex text responses', () => {
+  test('strips <think> tag block from completed Codex text responses', () => {
     const message = convertCodexResponseToAnthropicMessage(
       {
         id: 'resp_1',
@@ -478,7 +560,7 @@ describe('Codex request translation', () => {
               {
                 type: 'output_text',
                 text:
-                  'The user just said "hey" - a simple greeting. I should respond briefly and friendly.\n\nHey! How can I help you today?',
+                  '<think>user wants a greeting, respond briefly</think>Hey! How can I help you today?',
               },
             ],
           },
@@ -496,6 +578,37 @@ describe('Codex request translation', () => {
     ])
   })
 
+  test('strips unterminated <think> tag at block boundary in Codex completed response', () => {
+    const message = convertCodexResponseToAnthropicMessage(
+      {
+        id: 'resp_1',
+        model: 'gpt-5.4',
+        output: [
+          {
+            type: 'message',
+            role: 'assistant',
+            content: [
+              {
+                type: 'output_text',
+                text:
+                  'Here is the answer.\n<think>wait, let me reconsider the user request',
+              },
+            ],
+          },
+        ],
+        usage: { input_tokens: 12, output_tokens: 4 },
+      },
+      'gpt-5.4',
+    )
+
+    expect(message.content).toEqual([
+      {
+        type: 'text',
+        text: 'Here is the answer.',
+      },
+    ])
+  })
+
   test('translates Codex SSE text stream into Anthropic events', async () => {
     const responseText = [
       'event: response.output_item.added',
@@ -527,7 +640,7 @@ describe('Codex request translation', () => {
     ])
   })
 
-  test('strips leaked reasoning preamble from Codex SSE text stream', async () => {
+  test('strips <think> tag block from Codex SSE text stream', async () => {
     const responseText = [
       'event: response.output_item.added',
       'data: {"type":"response.output_item.added","item":{"id":"msg_1","type":"message","status":"in_progress","content":[],"role":"assistant"},"output_index":0,"sequence_number":0}',
@@ -536,13 +649,13 @@ describe('Codex request translation', () => {
       'data: {"type":"response.content_part.added","content_index":0,"item_id":"msg_1","output_index":0,"part":{"type":"output_text","text":""},"sequence_number":1}',
       '',
       'event: response.output_text.delta',
-      'data: {"type":"response.output_text.delta","content_index":0,"delta":"The user just said \\"hey\\" - a simple greeting. I should respond briefly and friendly.\\n\\nHey! How can I help you today?","item_id":"msg_1","output_index":0,"sequence_number":2}',
+      'data: {"type":"response.output_text.delta","content_index":0,"delta":"<think>user wants a greeting, respond briefly</think>Hey! How can I help you today?","item_id":"msg_1","output_index":0,"sequence_number":2}',
       '',
       'event: response.output_item.done',
-      'data: {"type":"response.output_item.done","item":{"id":"msg_1","type":"message","status":"completed","content":[{"type":"output_text","text":"The user just said \\"hey\\" - a simple greeting. I should respond briefly and friendly.\\n\\nHey! How can I help you today?"}],"role":"assistant"},"output_index":0,"sequence_number":3}',
+      'data: {"type":"response.output_item.done","item":{"id":"msg_1","type":"message","status":"completed","content":[{"type":"output_text","text":"<think>user wants a greeting, respond briefly</think>Hey! How can I help you today?"}],"role":"assistant"},"output_index":0,"sequence_number":3}',
       '',
       'event: response.completed',
-      'data: {"type":"response.completed","response":{"id":"resp_1","status":"completed","model":"gpt-5.4","output":[{"type":"message","role":"assistant","content":[{"type":"output_text","text":"The user just said \\"hey\\" - a simple greeting. I should respond briefly and friendly.\\n\\nHey! How can I help you today?"}]}],"usage":{"input_tokens":2,"output_tokens":1}},"sequence_number":4}',
+      'data: {"type":"response.completed","response":{"id":"resp_1","status":"completed","model":"gpt-5.4","output":[{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<think>user wants a greeting, respond briefly</think>Hey! How can I help you today?"}]}],"usage":{"input_tokens":2,"output_tokens":1}},"sequence_number":4}',
       '',
     ].join('\n')
 
@@ -564,6 +677,50 @@ describe('Codex request translation', () => {
       }
     }
 
-    expect(textDeltas).toEqual(['Hey! How can I help you today?'])
+    expect(textDeltas.join('')).toBe('Hey! How can I help you today?')
+  })
+
+  test('preserves prose without tags (no phrase-based false positive)', async () => {
+    // Regression test: older phrase-based sanitizer would incorrectly strip text
+    // starting with "I should" or "The user". The tag-based approach leaves it alone.
+    const responseText = [
+      'event: response.output_item.added',
+      'data: {"type":"response.output_item.added","item":{"id":"msg_1","type":"message","status":"in_progress","content":[],"role":"assistant"},"output_index":0,"sequence_number":0}',
+      '',
+      'event: response.content_part.added',
+      'data: {"type":"response.content_part.added","content_index":0,"item_id":"msg_1","output_index":0,"part":{"type":"output_text","text":""},"sequence_number":1}',
+      '',
+      'event: response.output_text.delta',
+      'data: {"type":"response.output_text.delta","content_index":0,"delta":"I should note that the user role requires a briefly concise friendly response format.","item_id":"msg_1","output_index":0,"sequence_number":2}',
+      '',
+      'event: response.output_item.done',
+      'data: {"type":"response.output_item.done","item":{"id":"msg_1","type":"message","status":"completed","content":[{"type":"output_text","text":"I should note that the user role requires a briefly concise friendly response format."}],"role":"assistant"},"output_index":0,"sequence_number":3}',
+      '',
+      'event: response.completed',
+      'data: {"type":"response.completed","response":{"id":"resp_1","status":"completed","model":"gpt-5.4","output":[{"type":"message","role":"assistant","content":[{"type":"output_text","text":"I should note that the user role requires a briefly concise friendly response format."}]}],"usage":{"input_tokens":2,"output_tokens":1}},"sequence_number":4}',
+      '',
+    ].join('\n')
+
+    const stream = new ReadableStream({
+      start(controller) {
+        controller.enqueue(new TextEncoder().encode(responseText))
+        controller.close()
+      },
+    })
+
+    const textDeltas: string[] = []
+    for await (const event of codexStreamToAnthropic(
+      new Response(stream),
+      'gpt-5.4',
+    )) {
+      const delta = (event as { delta?: { type?: string; text?: string } }).delta
+      if (delta?.type === 'text_delta' && typeof delta.text === 'string') {
+        textDeltas.push(delta.text)
+      }
+    }
+
+    expect(textDeltas.join('')).toBe(
+      'I should note that the user role requires a briefly concise friendly response format.',
+    )
   })
 })

src/services/api/codexShim.ts

@@ -1,14 +1,15 @@
 import { APIError } from '@anthropic-ai/sdk'
+import { compressToolHistory } from './compressToolHistory.js'
+import { fetchWithProxyRetry } from './fetchWithProxyRetry.js'
 import type {
   ResolvedCodexCredentials,
   ResolvedProviderRequest,
 } from './providerConfig.js'
 import { sanitizeSchemaForOpenAICompat } from './openaiSchemaSanitizer.js'
 import {
-  looksLikeLeakedReasoningPrefix,
-  shouldBufferPotentialReasoningPrefix,
-  stripLeakedReasoningPreamble,
-} from './reasoningLeakSanitizer.js'
+  createThinkTagFilter,
+  stripThinkTags,
+} from './thinkTagSanitizer.js'
 
 export interface AnthropicUsage {
   input_tokens: number
@@ -484,13 +485,15 @@ export async function performCodexRequest(options: {
   defaultHeaders: Record<string, string>
   signal?: AbortSignal
 }): Promise<Response> {
-  const input = convertAnthropicMessagesToResponsesInput(
+  const compressedMessages = compressToolHistory(
     options.params.messages as Array<{
       role?: string
       message?: { role?: string; content?: unknown }
       content?: unknown
     }>,
+    options.request.resolvedModel,
   )
+  const input = convertAnthropicMessagesToResponsesInput(compressedMessages)
   const body: Record<string, unknown> = {
     model: options.request.resolvedModel,
     input: input.length > 0
@@ -559,12 +562,15 @@ export async function performCodexRequest(options: {
   }
   headers.originator ??= 'openclaude'
 
-  const response = await fetch(`${options.request.baseUrl}/responses`, {
-    method: 'POST',
-    headers,
-    body: JSON.stringify(body),
-    signal: options.signal,
-  })
+  const response = await fetchWithProxyRetry(
+    `${options.request.baseUrl}/responses`,
+    {
+      method: 'POST',
+      headers,
+      body: JSON.stringify(body),
+      signal: options.signal,
+    },
+  )
 
   if (!response.ok) {
     const errorBody = await response.text().catch(() => 'unknown error')
@@ -580,15 +586,55 @@ export async function performCodexRequest(options: {
   return response
 }
 
-async function* readSseEvents(response: Response): AsyncGenerator<CodexSseEvent> {
+async function* readSseEvents(response: Response, signal?: AbortSignal): AsyncGenerator<CodexSseEvent> {
   const reader = response.body?.getReader()
   if (!reader) return
 
   const decoder = new TextDecoder()
   let buffer = ''
+  const STREAM_IDLE_TIMEOUT_MS = 120_000 // 2 minutes without data
+  let lastDataTime = Date.now()
+
+  /**
+   * Read from the stream with an idle timeout. Respects the caller's
+   * AbortSignal — clears the idle timer on abort so the AbortError
+   * surfaces cleanly instead of a spurious idle timeout.
+   */
+  async function readWithTimeout(): Promise<ReadableStreamReadResult<Uint8Array>> {
+    return new Promise((resolve, reject) => {
+      const timeoutId = setTimeout(() => {
+        const elapsed = Math.round((Date.now() - lastDataTime) / 1000)
+        reject(new Error(
+          `Codex SSE stream idle for ${elapsed}s (limit: ${STREAM_IDLE_TIMEOUT_MS / 1000}s). Connection likely dropped.`,
+        ))
+      }, STREAM_IDLE_TIMEOUT_MS)
+
+      let abortCleanup: (() => void) | undefined
+      if (signal) {
+        abortCleanup = () => {
+          clearTimeout(timeoutId)
+        }
+        signal.addEventListener('abort', abortCleanup, { once: true })
+      }
+
+      reader.read().then(
+        result => {
+          clearTimeout(timeoutId)
+          if (signal && abortCleanup) signal.removeEventListener('abort', abortCleanup)
+          if (result.value) lastDataTime = Date.now()
+          resolve(result)
+        },
+        err => {
+          clearTimeout(timeoutId)
+          if (signal && abortCleanup) signal.removeEventListener('abort', abortCleanup)
+          reject(err)
+        },
+      )
+    })
+  }
 
   while (true) {
-    const { done, value } = await reader.read()
+    const { done, value } = await readWithTimeout()
     if (done) break
 
     buffer += decoder.decode(value, { stream: true })
@@ -649,10 +695,11 @@ function determineStopReason(
 
 export async function collectCodexCompletedResponse(
   response: Response,
+  signal?: AbortSignal,
 ): Promise<Record<string, any>> {
   let completedResponse: Record<string, any> | undefined
 
-  for await (const event of readSseEvents(response)) {
+  for await (const event of readSseEvents(response, signal)) {
     if (event.event === 'response.failed') {
       const msg = event.data?.response?.error?.message ??
         event.data?.error?.message ?? 'Codex response failed'
@@ -681,6 +728,7 @@ export async function collectCodexCompletedResponse(
 export async function* codexStreamToAnthropic(
   response: Response,
   model: string,
+  signal?: AbortSignal,
 ): AsyncGenerator<AnthropicStreamEvent> {
   const messageId = makeMessageId()
   const toolBlocksByItemId = new Map<
@@ -688,25 +736,22 @@ export async function* codexStreamToAnthropic(
     { index: number; toolUseId: string }
   >()
   let activeTextBlockIndex: number | null = null
-  let activeTextBuffer = ''
-  let textBufferMode: 'none' | 'pending' | 'strip' = 'none'
+  const thinkFilter = createThinkTagFilter()
   let nextContentBlockIndex = 0
   let sawToolUse = false
   let finalResponse: Record<string, any> | undefined
 
   const closeActiveTextBlock = async function* () {
     if (activeTextBlockIndex === null) return
-    if (textBufferMode !== 'none') {
-      const sanitized = stripLeakedReasoningPreamble(activeTextBuffer)
-      if (sanitized) {
-        yield {
-          type: 'content_block_delta',
-          index: activeTextBlockIndex,
-          delta: {
-            type: 'text_delta',
-            text: sanitized,
-          },
-        }
+    const tail = thinkFilter.flush()
+    if (tail) {
+      yield {
+        type: 'content_block_delta',
+        index: activeTextBlockIndex,
+        delta: {
+          type: 'text_delta',
+          text: tail,
+        },
       }
     }
     yield {
@@ -714,8 +759,6 @@ export async function* codexStreamToAnthropic(
       index: activeTextBlockIndex,
     }
     activeTextBlockIndex = null
-    activeTextBuffer = ''
-    textBufferMode = 'none'
   }
 
   const startTextBlockIfNeeded = async function* () {
@@ -742,7 +785,7 @@ export async function* codexStreamToAnthropic(
     },
   }
 
-  for await (const event of readSseEvents(response)) {
+  for await (const event of readSseEvents(response, signal)) {
     const payload = event.data
 
     if (event.event === 'response.output_item.added') {
@@ -791,43 +834,17 @@ export async function* codexStreamToAnthropic(
 
     if (event.event === 'response.output_text.delta') {
       yield* startTextBlockIfNeeded()
-      activeTextBuffer += payload.delta ?? ''
       if (activeTextBlockIndex !== null) {
-        if (
-          textBufferMode === 'strip' ||
-          looksLikeLeakedReasoningPrefix(activeTextBuffer)
-        ) {
-          textBufferMode = 'strip'
-          continue
-        }
-
-        if (textBufferMode === 'pending') {
-          if (shouldBufferPotentialReasoningPrefix(activeTextBuffer)) {
-            continue
-          }
+        const visible = thinkFilter.feed(payload.delta ?? '')
+        if (visible) {
           yield {
             type: 'content_block_delta',
             index: activeTextBlockIndex,
             delta: {
               type: 'text_delta',
-              text: activeTextBuffer,
+              text: visible,
             },
           }
-          textBufferMode = 'none'
-          continue
-        }
-
-        if (shouldBufferPotentialReasoningPrefix(activeTextBuffer)) {
-          textBufferMode = 'pending'
-          continue
-        }
-        yield {
-          type: 'content_block_delta',
-          index: activeTextBlockIndex,
-          delta: {
-            type: 'text_delta',
-            text: payload.delta ?? '',
-          },
         }
       }
       continue
@@ -923,7 +940,7 @@ export function convertCodexResponseToAnthropicMessage(
         if (part?.type === 'output_text') {
           content.push({
             type: 'text',
-            text: stripLeakedReasoningPreamble(part.text ?? ''),
+            text: stripThinkTags(part.text ?? ''),
           })
         }
       }

src/services/api/codexUsage.ts

@@ -1,7 +1,13 @@
+import {
+  readCodexCredentialsAsync,
+  refreshCodexAccessTokenIfNeeded,
+} from '../../utils/codexCredentials.js'
+import { logForDebugging } from '../../utils/debug.js'
+import { isBareMode } from '../../utils/envUtils.js'
 import {
   DEFAULT_CODEX_BASE_URL,
   isCodexBaseUrl,
-  resolveCodexApiCredentials,
+  resolveRuntimeCodexCredentials,
   resolveProviderRequest,
 } from './providerConfig.js'
 
@@ -391,6 +397,18 @@ export function getCodexUsageUrl(baseUrl = DEFAULT_CODEX_BASE_URL): string {
 }
 
 export async function fetchCodexUsage(): Promise<CodexUsageData> {
+  const refreshResult = await refreshCodexAccessTokenIfNeeded().catch(
+    async error => {
+      logForDebugging(
+        `[codex] access token refresh failed before usage fetch: ${error instanceof Error ? error.message : String(error)}`,
+        { level: 'warn' },
+      )
+      return {
+        refreshed: false,
+        credentials: await readCodexCredentialsAsync(),
+      }
+    },
+  )
   const request = resolveProviderRequest({
     model: process.env.OPENAI_MODEL,
     baseUrl: process.env.OPENAI_BASE_URL,
@@ -401,16 +419,19 @@ export async function fetchCodexUsage(): Promise<CodexUsageData> {
     )
   }
 
-  const credentials = resolveCodexApiCredentials()
+  const credentials = resolveRuntimeCodexCredentials({
+    storedCredentials: refreshResult.credentials,
+  })
   if (!credentials.apiKey) {
+    const oauthHint = isBareMode() ? '' : ', choose Codex OAuth in /provider'
     const authHint = credentials.authPath
-      ? ` or place a Codex auth.json at ${credentials.authPath}`
-      : ''
+      ? `${oauthHint} or place a Codex auth.json at ${credentials.authPath}`
+      : oauthHint
     throw new Error(`Codex auth is required. Set CODEX_API_KEY${authHint}.`)
   }
   if (!credentials.accountId) {
     throw new Error(
-      'Codex auth is missing chatgpt_account_id. Re-login with the Codex CLI or set CHATGPT_ACCOUNT_ID/CODEX_ACCOUNT_ID.',
+      'Codex auth is missing chatgpt_account_id. Re-login with Codex OAuth, the Codex CLI, or set CHATGPT_ACCOUNT_ID/CODEX_ACCOUNT_ID.',
     )
   }
 

src/services/api/compressToolHistory.test.ts

@@ -0,0 +1,572 @@
+import { afterEach, beforeEach, expect, mock, test } from 'bun:test'
+import { compressToolHistory, getTiers } from './compressToolHistory.js'
+
+// Mock the two dependencies so tests are deterministic and don't read disk config.
+const mockState = {
+  enabled: true,
+  effectiveWindow: 100_000,
+}
+
+mock.module('../../utils/config.js', () => ({
+  getGlobalConfig: () => ({
+    toolHistoryCompressionEnabled: mockState.enabled,
+  }),
+}))
+
+mock.module('../compact/autoCompact.js', () => ({
+  getEffectiveContextWindowSize: () => mockState.effectiveWindow,
+}))
+
+beforeEach(() => {
+  mockState.enabled = true
+  mockState.effectiveWindow = 100_000
+})
+
+afterEach(() => {
+  mockState.enabled = true
+  mockState.effectiveWindow = 100_000
+})
+
+type Block = Record<string, unknown>
+type Msg = { role: string; content: Block[] | string }
+
+function bigText(n: number): string {
+  return 'x'.repeat(n)
+}
+
+function buildToolExchange(id: number, resultLength: number): Msg[] {
+  return [
+    {
+      role: 'assistant',
+      content: [
+        {
+          type: 'tool_use',
+          id: `toolu_${id}`,
+          name: 'Read',
+          input: { file_path: `/path/to/file${id}.ts` },
+        },
+      ],
+    },
+    {
+      role: 'user',
+      content: [
+        {
+          type: 'tool_result',
+          tool_use_id: `toolu_${id}`,
+          content: bigText(resultLength),
+        },
+      ],
+    },
+  ]
+}
+
+function buildConversation(numToolExchanges: number, resultLength = 5_000): Msg[] {
+  const out: Msg[] = [{ role: 'user', content: 'Initial request' }]
+  for (let i = 0; i < numToolExchanges; i++) {
+    out.push(...buildToolExchange(i, resultLength))
+  }
+  return out
+}
+
+function getResultMessages(messages: Msg[]): Msg[] {
+  return messages.filter(
+    m => Array.isArray(m.content) && m.content.some((b: any) => b.type === 'tool_result'),
+  )
+}
+
+function getResultBlock(msg: Msg): Block {
+  return (msg.content as Block[]).find((b: any) => b.type === 'tool_result') as Block
+}
+
+function getResultText(msg: Msg): string {
+  const block = getResultBlock(msg)
+  const c = block.content
+  if (typeof c === 'string') return c
+  if (Array.isArray(c)) {
+    return c
+      .filter((b: any) => b.type === 'text')
+      .map((b: any) => b.text)
+      .join('\n')
+  }
+  return ''
+}
+
+// ---------- getTiers ----------
+
+test('getTiers: < 16k window → recent=2, mid=3', () => {
+  expect(getTiers(8_000)).toEqual({ recent: 2, mid: 3 })
+})
+
+test('getTiers: 16k–32k → recent=3, mid=5', () => {
+  expect(getTiers(20_000)).toEqual({ recent: 3, mid: 5 })
+})
+
+test('getTiers: 32k–64k → recent=4, mid=8', () => {
+  expect(getTiers(48_000)).toEqual({ recent: 4, mid: 8 })
+})
+
+test('getTiers: 64k–128k (Copilot gpt-4o) → recent=5, mid=10', () => {
+  expect(getTiers(100_000)).toEqual({ recent: 5, mid: 10 })
+})
+
+test('getTiers: 128k–256k (Copilot Claude) → recent=8, mid=15', () => {
+  expect(getTiers(200_000)).toEqual({ recent: 8, mid: 15 })
+})
+
+test('getTiers: 256k–500k → recent=12, mid=25', () => {
+  expect(getTiers(400_000)).toEqual({ recent: 12, mid: 25 })
+})
+
+test('getTiers: ≥ 500k (gpt-4.1 1M) → recent=25, mid=50', () => {
+  expect(getTiers(1_000_000)).toEqual({ recent: 25, mid: 50 })
+})
+
+// ---------- master switch ----------
+
+test('pass-through when toolHistoryCompressionEnabled is false', () => {
+  mockState.enabled = false
+  const messages = buildConversation(20)
+  const result = compressToolHistory(messages, 'gpt-4o')
+  expect(result).toBe(messages) // same reference (no transformation)
+})
+
+test('pass-through when total tool_results <= recent tier', () => {
+  // 100k effective → recent=5; only 4 exchanges → no compression
+  const messages = buildConversation(4)
+  const result = compressToolHistory(messages, 'gpt-4o')
+  expect(result).toBe(messages)
+})
+
+// ---------- per-tier behavior ----------
+
+test('recent tier: tool_result content untouched', () => {
+  // 100k effective → recent=5, mid=10. With 6 exchanges, only the oldest is touched.
+  const messages = buildConversation(6, 5_000)
+  const result = compressToolHistory(messages, 'gpt-4o')
+  const resultMsgs = getResultMessages(result)
+
+  // Last 5 should be untouched (full 5000 chars)
+  for (let i = resultMsgs.length - 5; i < resultMsgs.length; i++) {
+    expect(getResultText(resultMsgs[i]).length).toBe(5_000)
+  }
+})
+
+test('mid tier: long content truncated to MID_MAX_CHARS with marker', () => {
+  // 100k → recent=5, mid=10. 10 exchanges: 5 recent + 5 mid (none old).
+  const messages = buildConversation(10, 5_000)
+  const result = compressToolHistory(messages, 'gpt-4o')
+  const resultMsgs = getResultMessages(result)
+
+  // First 5 are mid tier — should be truncated to ~2000 chars + marker
+  for (let i = 0; i < 5; i++) {
+    const text = getResultText(resultMsgs[i])
+    expect(text).toContain('[…truncated')
+    expect(text).toContain('chars from tool history]')
+    // Should be roughly 2000 chars + marker (under 2200)
+    expect(text.length).toBeLessThan(2_200)
+    expect(text.length).toBeGreaterThan(2_000)
+  }
+})
+
+test('mid tier: short content (< MID_MAX_CHARS) untouched', () => {
+  const messages = buildConversation(10, 500) // 500 < MID_MAX_CHARS
+  const result = compressToolHistory(messages, 'gpt-4o')
+  const resultMsgs = getResultMessages(result)
+
+  for (let i = 0; i < 5; i++) {
+    expect(getResultText(resultMsgs[i])).toBe(bigText(500))
+  }
+})
+
+test('old tier: content replaced with stub [name args={...} → N chars omitted]', () => {
+  // 100k → recent=5, mid=10, old=rest. 20 exchanges → 5 old + 10 mid + 5 recent.
+  const messages = buildConversation(20, 5_000)
+  const result = compressToolHistory(messages, 'gpt-4o')
+  const resultMsgs = getResultMessages(result)
+
+  // First 5 are old tier — should be stubs
+  for (let i = 0; i < 5; i++) {
+    const text = getResultText(resultMsgs[i])
+    expect(text).toMatch(/^\[Read args=\{.*\} → 5000 chars omitted\]$/)
+  }
+})
+
+test('old tier: stub args truncated to 200 chars', () => {
+  const longArg = bigText(500)
+  const messages: Msg[] = [
+    { role: 'user', content: 'start' },
+    {
+      role: 'assistant',
+      content: [
+        {
+          type: 'tool_use',
+          id: 'toolu_x',
+          name: 'Bash',
+          input: { command: longArg },
+        },
+      ],
+    },
+    {
+      role: 'user',
+      content: [
+        { type: 'tool_result', tool_use_id: 'toolu_x', content: 'output' },
+      ],
+    },
+    // Pad with enough recent exchanges to push the above into old tier
+    ...buildConversation(20, 100).slice(1),
+  ]
+  const result = compressToolHistory(messages, 'gpt-4o')
+  const resultMsgs = getResultMessages(result)
+  const text = getResultText(resultMsgs[0])
+
+  // Stub format: [Bash args=<json≤200chars> → N chars omitted]
+  // The args portion (between args= and →) must be ≤ 200 chars.
+  const argsMatch = text.match(/args=(.*?) →/)
+  expect(argsMatch).not.toBeNull()
+  expect(argsMatch![1].length).toBeLessThanOrEqual(200)
+})
+
+test('old tier: orphan tool_result (no matching tool_use) falls back to "tool"', () => {
+  const messages: Msg[] = [
+    { role: 'user', content: 'start' },
+    // Orphan: tool_result without matching tool_use in history
+    {
+      role: 'user',
+      content: [
+        { type: 'tool_result', tool_use_id: 'orphan_id', content: 'data' },
+      ],
+    },
+    ...buildConversation(20, 100).slice(1),
+  ]
+  const result = compressToolHistory(messages, 'gpt-4o')
+  const resultMsgs = getResultMessages(result)
+  const text = getResultText(resultMsgs[0])
+
+  expect(text).toMatch(/^\[tool args=\{\} → 4 chars omitted\]$/)
+})
+
+// ---------- structural preservation ----------
+
+test('tool_use blocks always preserved', () => {
+  const messages = buildConversation(20, 5_000)
+  const result = compressToolHistory(messages, 'gpt-4o')
+
+  const useCount = (msgs: Msg[]) =>
+    msgs.reduce((sum, m) => {
+      if (!Array.isArray(m.content)) return sum
+      return sum + m.content.filter((b: any) => b.type === 'tool_use').length
+    }, 0)
+
+  expect(useCount(result as Msg[])).toBe(useCount(messages))
+})
+
+test('text blocks always preserved', () => {
+  const messages: Msg[] = [
+    { role: 'user', content: 'first' },
+    {
+      role: 'assistant',
+      content: [
+        { type: 'text', text: 'reasoning before tool' },
+        { type: 'tool_use', id: 'toolu_1', name: 'Read', input: {} },
+      ],
+    },
+    {
+      role: 'user',
+      content: [{ type: 'tool_result', tool_use_id: 'toolu_1', content: bigText(5000) }],
+    },
+    ...buildConversation(20, 5_000).slice(1),
+  ]
+  const result = compressToolHistory(messages, 'gpt-4o')
+  const assistantMsg = (result as Msg[])[1]
+  const textBlock = (assistantMsg.content as Block[]).find((b: any) => b.type === 'text')
+
+  expect(textBlock).toEqual({ type: 'text', text: 'reasoning before tool' })
+})
+
+test('thinking blocks always preserved', () => {
+  const messages: Msg[] = [
+    { role: 'user', content: 'first' },
+    {
+      role: 'assistant',
+      content: [
+        { type: 'thinking', thinking: 'internal reasoning', signature: 'sig' },
+        { type: 'tool_use', id: 'toolu_1', name: 'Read', input: {} },
+      ],
+    },
+    {
+      role: 'user',
+      content: [{ type: 'tool_result', tool_use_id: 'toolu_1', content: bigText(5000) }],
+    },
+    ...buildConversation(20, 5_000).slice(1),
+  ]
+  const result = compressToolHistory(messages, 'gpt-4o')
+  const assistantMsg = (result as Msg[])[1]
+  const thinking = (assistantMsg.content as Block[]).find((b: any) => b.type === 'thinking')
+
+  expect(thinking).toEqual({
+    type: 'thinking',
+    thinking: 'internal reasoning',
+    signature: 'sig',
+  })
+})
+
+test('non-array content (string) handled gracefully', () => {
+  const messages: Msg[] = [
+    { role: 'user', content: 'plain string content' },
+    ...buildConversation(20, 100).slice(1),
+  ]
+  const result = compressToolHistory(messages, 'gpt-4o')
+  expect((result as Msg[])[0].content).toBe('plain string content')
+})
+
+test('empty content array handled gracefully', () => {
+  const messages: Msg[] = [
+    { role: 'user', content: [] },
+    ...buildConversation(20, 100).slice(1),
+  ]
+  expect(() => compressToolHistory(messages, 'gpt-4o')).not.toThrow()
+})
+
+// ---------- message shape compatibility ----------
+
+test('wrapped shape ({ message: { role, content } }) handled', () => {
+  type WrappedMsg = { message: { role: string; content: Block[] | string } }
+  const wrap = (m: Msg): WrappedMsg => ({ message: { role: m.role, content: m.content } })
+  const messages = buildConversation(20, 5_000).map(wrap)
+  const result = compressToolHistory(messages as any, 'gpt-4o')
+
+  // First wrapped tool-result message should have stub content (old tier)
+  const firstResultMsg = (result as WrappedMsg[]).find(
+    m =>
+      Array.isArray(m.message.content) &&
+      m.message.content.some((b: any) => b.type === 'tool_result'),
+  )
+  const block = (firstResultMsg!.message.content as Block[]).find(
+    (b: any) => b.type === 'tool_result',
+  ) as Block
+  const text = ((block.content as Block[])[0] as any).text
+  expect(text).toMatch(/^\[Read args=.*→ 5000 chars omitted\]$/)
+})
+
+test('flat shape ({ role, content }) handled', () => {
+  const messages = buildConversation(20, 5_000)
+  const result = compressToolHistory(messages, 'gpt-4o')
+  const resultMsgs = getResultMessages(result)
+
+  expect(getResultText(resultMsgs[0])).toMatch(/^\[Read args=.*→ 5000 chars omitted\]$/)
+})
+
+// ---------- tier boundary correctness ----------
+
+test('tier boundaries: 6 exchanges → 1 mid + 5 recent (recent=5)', () => {
+  const messages = buildConversation(6, 5_000)
+  const result = compressToolHistory(messages, 'gpt-4o')
+  const resultMsgs = getResultMessages(result)
+
+  // Oldest: mid (truncated)
+  expect(getResultText(resultMsgs[0])).toContain('[…truncated')
+  // Last 5: untouched
+  for (let i = 1; i < 6; i++) {
+    expect(getResultText(resultMsgs[i]).length).toBe(5_000)
+  }
+})
+
+test('tier boundaries: 16 exchanges → 1 old + 10 mid + 5 recent', () => {
+  const messages = buildConversation(16, 5_000)
+  const result = compressToolHistory(messages, 'gpt-4o')
+  const resultMsgs = getResultMessages(result)
+
+  // Oldest 1: stub (old tier)
+  expect(getResultText(resultMsgs[0])).toMatch(/^\[Read .*chars omitted\]$/)
+  // Next 10: mid (truncated)
+  for (let i = 1; i < 11; i++) {
+    expect(getResultText(resultMsgs[i])).toContain('[…truncated')
+  }
+  // Last 5: untouched
+  for (let i = 11; i < 16; i++) {
+    expect(getResultText(resultMsgs[i]).length).toBe(5_000)
+  }
+})
+
+test('large window (1M) with 30 exchanges: all untouched (recent=25 ≥ 30 - 5)', () => {
+  // ≥500k → recent=25, mid=50. 30 exchanges → 5 mid + 25 recent. None old.
+  mockState.effectiveWindow = 1_000_000
+  const messages = buildConversation(30, 5_000)
+  const result = compressToolHistory(messages, 'gpt-4.1')
+  const resultMsgs = getResultMessages(result)
+
+  // Last 25: untouched
+  for (let i = 5; i < 30; i++) {
+    expect(getResultText(resultMsgs[i]).length).toBe(5_000)
+  }
+})
+
+// ---------- attribute preservation ----------
+
+test('is_error flag preserved in mid tier', () => {
+  const messages: Msg[] = [
+    { role: 'user', content: 'start' },
+    {
+      role: 'assistant',
+      content: [{ type: 'tool_use', id: 'toolu_err', name: 'Bash', input: {} }],
+    },
+    {
+      role: 'user',
+      content: [
+        {
+          type: 'tool_result',
+          tool_use_id: 'toolu_err',
+          is_error: true,
+          content: bigText(5_000),
+        },
+      ],
+    },
+    // Pad with enough recent exchanges to push the above into MID tier
+    ...buildConversation(10, 100).slice(1),
+  ]
+  const result = compressToolHistory(messages, 'gpt-4o')
+  const resultMsgs = getResultMessages(result)
+  const block = getResultBlock(resultMsgs[0]) as { is_error?: boolean; content: unknown }
+
+  expect(block.is_error).toBe(true)
+  expect(getResultText(resultMsgs[0])).toContain('[…truncated')
+})
+
+test('is_error flag preserved in old tier (stub)', () => {
+  const messages: Msg[] = [
+    { role: 'user', content: 'start' },
+    {
+      role: 'assistant',
+      content: [{ type: 'tool_use', id: 'toolu_err', name: 'Bash', input: {} }],
+    },
+    {
+      role: 'user',
+      content: [
+        {
+          type: 'tool_result',
+          tool_use_id: 'toolu_err',
+          is_error: true,
+          content: bigText(5_000),
+        },
+      ],
+    },
+    ...buildConversation(20, 100).slice(1),
+  ]
+  const result = compressToolHistory(messages, 'gpt-4o')
+  const resultMsgs = getResultMessages(result)
+  const block = getResultBlock(resultMsgs[0]) as { is_error?: boolean; content: unknown }
+
+  expect(block.is_error).toBe(true)
+  expect(getResultText(resultMsgs[0])).toMatch(/^\[Bash .*chars omitted\]$/)
+})
+
+// ---------- COMPACTABLE_TOOLS filter ----------
+
+test('non-compactable tool (e.g. Task/Agent) is NEVER compressed', () => {
+  // Build conversation where the OLDEST exchange uses a non-compactable tool name
+  const messages: Msg[] = [
+    { role: 'user', content: 'start' },
+    {
+      role: 'assistant',
+      content: [
+        { type: 'tool_use', id: 'task_1', name: 'Task', input: { goal: 'plan' } },
+      ],
+    },
+    {
+      role: 'user',
+      content: [
+        { type: 'tool_result', tool_use_id: 'task_1', content: bigText(5_000) },
+      ],
+    },
+    // Pad with 20 compactable exchanges to push Task into old tier
+    ...buildConversation(20, 100).slice(1),
+  ]
+  const result = compressToolHistory(messages, 'gpt-4o')
+  const resultMsgs = getResultMessages(result)
+
+  // First tool_result is for Task (non-compactable) → must remain full
+  expect(getResultText(resultMsgs[0]).length).toBe(5_000)
+  expect(getResultText(resultMsgs[0])).not.toContain('chars omitted')
+  expect(getResultText(resultMsgs[0])).not.toContain('[…truncated')
+})
+
+test('mcp__ prefixed tools ARE compactable (matches microCompact behavior)', () => {
+  const messages: Msg[] = [
+    { role: 'user', content: 'start' },
+    {
+      role: 'assistant',
+      content: [
+        { type: 'tool_use', id: 'mcp_1', name: 'mcp__github__get_issue', input: {} },
+      ],
+    },
+    {
+      role: 'user',
+      content: [
+        { type: 'tool_result', tool_use_id: 'mcp_1', content: bigText(5_000) },
+      ],
+    },
+    ...buildConversation(20, 100).slice(1),
+  ]
+  const result = compressToolHistory(messages, 'gpt-4o')
+  const resultMsgs = getResultMessages(result)
+
+  // MCP tool result is compressed (gets stub since it's in old tier)
+  expect(getResultText(resultMsgs[0])).toMatch(/^\[mcp__github__get_issue .*chars omitted\]$/)
+})
+
+// ---------- skip already-cleared blocks ----------
+
+test('blocks already cleared by microCompact are NOT re-compressed', () => {
+  const messages: Msg[] = [
+    { role: 'user', content: 'start' },
+    {
+      role: 'assistant',
+      content: [{ type: 'tool_use', id: 'cleared_1', name: 'Read', input: {} }],
+    },
+    {
+      role: 'user',
+      content: [
+        {
+          type: 'tool_result',
+          tool_use_id: 'cleared_1',
+          content: '[Old tool result content cleared]', // microCompact's marker
+        },
+      ],
+    },
+    ...buildConversation(20, 100).slice(1),
+  ]
+  const result = compressToolHistory(messages, 'gpt-4o')
+  const resultMsgs = getResultMessages(result)
+
+  // Already-cleared marker survives untouched (no double processing)
+  expect(getResultText(resultMsgs[0])).toBe('[Old tool result content cleared]')
+})
+
+test('extra block attributes (e.g. cache_control) preserved across rewrites', () => {
+  const cacheControl = { type: 'ephemeral' }
+  const messages: Msg[] = [
+    { role: 'user', content: 'start' },
+    {
+      role: 'assistant',
+      content: [{ type: 'tool_use', id: 'toolu_cc', name: 'Read', input: {} }],
+    },
+    {
+      role: 'user',
+      content: [
+        {
+          type: 'tool_result',
+          tool_use_id: 'toolu_cc',
+          cache_control: cacheControl,
+          content: bigText(5_000),
+        },
+      ],
+    },
+    ...buildConversation(20, 100).slice(1),
+  ]
+  const result = compressToolHistory(messages, 'gpt-4o')
+  const resultMsgs = getResultMessages(result)
+  const block = getResultBlock(resultMsgs[0]) as { cache_control?: unknown }
+
+  // The custom attribute survived the stub rewrite via ...block spread
+  expect(block.cache_control).toEqual(cacheControl)
+})

src/services/api/compressToolHistory.ts

@@ -0,0 +1,255 @@
+/**
+ * Compresses old tool_result content for stateless OpenAI-compatible providers
+ * (Copilot, Mistral, Ollama). Preserves all conversation structure — tool_use,
+ * tool_result pairing, text, thinking, and is_error all survive intact. Only
+ * the BULK text of older tool_results is shrunk to delay context saturation.
+ *
+ * Tier sizes scale with the model's effective context window via
+ * getEffectiveContextWindowSize() — same calculation used by auto-compact, so
+ * the two systems stay aligned.
+ *
+ * Complements (does not replace) microCompact.ts:
+ * - microCompact: time/cache-based, runs from query.ts, binary clear/keep,
+ *   limited to Claude (cache editing) or idle gaps (time-based).
+ * - compressToolHistory: size-based, runs at the shim layer, tiered
+ *   compression, covers the gap for active sessions on non-Claude providers.
+ *
+ * Reuses isCompactableTool from microCompact to avoid touching tools the
+ * project already classifies as unsafe to compress (e.g. Task, Agent).
+ * Skips blocks already cleared by microCompact (TOOL_RESULT_CLEARED_MESSAGE).
+ *
+ * Anthropic native bypasses both shims, so it is unaffected by this module.
+ */
+import { getEffectiveContextWindowSize } from '../compact/autoCompact.js'
+import { isCompactableTool } from '../compact/microCompact.js'
+import { TOOL_RESULT_CLEARED_MESSAGE } from '../../utils/toolResultStorage.js'
+import { getGlobalConfig } from '../../utils/config.js'
+
+// Mid-tier truncation budget. 2k chars ≈ 500 tokens, enough to preserve the
+// shape of most tool outputs (file headers, command stderr, top grep hits)
+// without ballooning context. Bump too high and the tier loses its purpose.
+const MID_MAX_CHARS = 2_000
+
+// Stub args budget. JSON.stringify of a typical tool input fits in 200 chars
+// (file paths, short commands, small queries). Long inputs are rare and clamping
+// here keeps the stub size bounded even when callers pass oversized arguments.
+const STUB_ARGS_MAX_CHARS = 200
+
+type AnyMessage = {
+  role?: string
+  message?: { role?: string; content?: unknown }
+  content?: unknown
+}
+
+type ToolResultBlock = {
+  type: 'tool_result'
+  tool_use_id?: string
+  is_error?: boolean
+  content?: unknown
+}
+
+type ToolUseBlock = {
+  type: 'tool_use'
+  id?: string
+  name?: string
+  input?: unknown
+}
+
+type Tiers = { recent: number; mid: number }
+
+// Tier sizes scale with effective window. Targets roughly:
+// - recent tier stays under ~25% of available window (full fidelity kept)
+// - recent + mid tier stays under ~50% of available window (bounded bulk)
+// - everything older collapses to ~15-token stubs
+// Values assume ~5KB avg tool_result, which matches the Copilot default case
+// (parallel_tool_calls=true means multiple Read/Bash outputs per turn). For
+// ≥ 500k models the tiers are so generous that compression is effectively
+// inert for any realistic session — see compressToolHistory.test.ts.
+export function getTiers(effectiveWindow: number): Tiers {
+  if (effectiveWindow < 16_000) return { recent: 2, mid: 3 }
+  if (effectiveWindow < 32_000) return { recent: 3, mid: 5 }
+  if (effectiveWindow < 64_000) return { recent: 4, mid: 8 }
+  if (effectiveWindow < 128_000) return { recent: 5, mid: 10 }
+  if (effectiveWindow < 256_000) return { recent: 8, mid: 15 }
+  if (effectiveWindow < 500_000) return { recent: 12, mid: 25 }
+  return { recent: 25, mid: 50 }
+}
+
+function extractText(content: unknown): string {
+  if (typeof content === 'string') return content
+  if (Array.isArray(content)) {
+    return content
+      .filter(
+        (b: { type?: string; text?: string }) =>
+          b?.type === 'text' && typeof b.text === 'string',
+      )
+      .map((b: { text?: string }) => b.text ?? '')
+      .join('\n')
+  }
+  return ''
+}
+
+// Old-tier compression strategy. Replaces content entirely with a one-line
+// metadata marker ~10× more token-efficient than a 500-char truncation AND
+// unambiguous — partial truncations can look authoritative to the model. The
+// stub format encodes tool name + args so the model can re-invoke the same
+// tool if it needs the omitted output back.
+function buildStub(
+  block: ToolResultBlock,
+  toolUsesById: Map<string, ToolUseBlock>,
+): ToolResultBlock {
+  const original = extractText(block.content)
+  const toolUse = toolUsesById.get(block.tool_use_id ?? '')
+  const name = toolUse?.name ?? 'tool'
+  const args = toolUse?.input
+    ? JSON.stringify(toolUse.input).slice(0, STUB_ARGS_MAX_CHARS)
+    : '{}'
+  return {
+    ...block,
+    content: [
+      {
+        type: 'text',
+        text: `[${name} args=${args} → ${original.length} chars omitted]`,
+      },
+    ],
+  }
+}
+
+// Mid-tier compression. The trailing marker is load-bearing: without it, the
+// model can't distinguish "tool returned 2000 chars" from "tool returned 20k
+// chars that we cut to 2000". Distinguishing those matters for the model's
+// decision to re-invoke the tool.
+function truncateBlock(
+  block: ToolResultBlock,
+  maxChars: number,
+): ToolResultBlock {
+  const text = extractText(block.content)
+  if (text.length <= maxChars) return block
+  const omitted = text.length - maxChars
+  return {
+    ...block,
+    content: [
+      {
+        type: 'text',
+        text: `${text.slice(0, maxChars)}\n[…truncated ${omitted} chars from tool history]`,
+      },
+    ],
+  }
+}
+
+function getInner(msg: AnyMessage): { role?: string; content?: unknown } {
+  return (msg.message ?? msg) as { role?: string; content?: unknown }
+}
+
+function indexToolUses(messages: AnyMessage[]): Map<string, ToolUseBlock> {
+  const map = new Map<string, ToolUseBlock>()
+  for (const msg of messages) {
+    const content = getInner(msg).content
+    if (!Array.isArray(content)) continue
+    for (const b of content as Array<{ type?: string; id?: string }>) {
+      if (b?.type === 'tool_use' && b.id) {
+        map.set(b.id, b as ToolUseBlock)
+      }
+    }
+  }
+  return map
+}
+
+function indexToolResultMessages(messages: AnyMessage[]): number[] {
+  const indices: number[] = []
+  for (let i = 0; i < messages.length; i++) {
+    const inner = getInner(messages[i])
+    const role = inner.role ?? messages[i].role
+    const content = inner.content
+    if (
+      role === 'user' &&
+      Array.isArray(content) &&
+      content.some((b: { type?: string }) => b?.type === 'tool_result')
+    ) {
+      indices.push(i)
+    }
+  }
+  return indices
+}
+
+function rewriteMessage<T extends AnyMessage>(
+  msg: T,
+  newContent: unknown[],
+): T {
+  if (msg.message) {
+    return { ...msg, message: { ...msg.message, content: newContent } }
+  }
+  return { ...msg, content: newContent }
+}
+
+// microCompact.maybeTimeBasedMicrocompact may have already replaced old
+// tool_result content with TOOL_RESULT_CLEARED_MESSAGE before we see it.
+// Re-compressing produces a stub over a marker (e.g. `[Read args={} → 40
+// chars omitted]`), wasteful and less informative than the canonical marker.
+function isAlreadyCleared(block: ToolResultBlock): boolean {
+  const text = extractText(block.content)
+  return text === TOOL_RESULT_CLEARED_MESSAGE
+}
+
+function shouldCompressBlock(
+  block: ToolResultBlock,
+  toolUsesById: Map<string, ToolUseBlock>,
+): boolean {
+  if (isAlreadyCleared(block)) return false
+  const toolUse = toolUsesById.get(block.tool_use_id ?? '')
+  // Unknown tool name (orphan tool_result with no matching tool_use) falls
+  // through to compression with a generic "tool" stub. Safer default: the
+  // original tool_use vanished so there's no downstream use for the output.
+  if (!toolUse?.name) return true
+  // Respect microCompact's curated safe-to-compress set (Read/Bash/Grep/…/
+  // mcp__*) so user-facing flow tools (Task, Agent, custom) stay intact.
+  return isCompactableTool(toolUse.name)
+}
+
+export function compressToolHistory<T extends AnyMessage>(
+  messages: T[],
+  model: string,
+): T[] {
+  // Master kill-switch. Returns the original reference so callers skip a
+  // defensive copy when the feature is disabled.
+  if (!getGlobalConfig().toolHistoryCompressionEnabled) return messages
+
+  const tiers = getTiers(getEffectiveContextWindowSize(model))
+
+  const toolResultIndices = indexToolResultMessages(messages)
+  const total = toolResultIndices.length
+  // If every tool-result fits in the recent tier, no boundary crosses; return
+  // the same reference for the same copy-elision reason.
+  if (total <= tiers.recent) return messages
+
+  // O(1) lookup: messageIndex → tool-result position (0 = oldest). Replaces
+  // the naive Array.indexOf(i) that was O(n²) across the .map below.
+  const positionByIndex = new Map<number, number>()
+  for (let pos = 0; pos < toolResultIndices.length; pos++) {
+    positionByIndex.set(toolResultIndices[pos], pos)
+  }
+
+  const toolUsesById = indexToolUses(messages)
+
+  return messages.map((msg, i) => {
+    const pos = positionByIndex.get(i)
+    if (pos === undefined) return msg
+
+    const fromEnd = total - 1 - pos
+    if (fromEnd < tiers.recent) return msg
+
+    const inMidWindow = fromEnd < tiers.recent + tiers.mid
+    const content = getInner(msg).content as unknown[]
+    const newContent = content.map(block => {
+      const b = block as { type?: string }
+      if (b?.type !== 'tool_result') return block
+      const tr = block as ToolResultBlock
+      if (!shouldCompressBlock(tr, toolUsesById)) return block
+      return inMidWindow
+        ? truncateBlock(tr, MID_MAX_CHARS)
+        : buildStub(tr, toolUsesById)
+    })
+
+    return rewriteMessage(msg, newContent)
+  })
+}

src/services/api/errors.openaiCompatibility.test.ts

@@ -0,0 +1,44 @@
+import { APIError } from '@anthropic-ai/sdk'
+import { expect, test } from 'bun:test'
+
+import { getAssistantMessageFromError } from './errors.js'
+
+function getFirstText(message: ReturnType<typeof getAssistantMessageFromError>): string {
+  const first = message.message.content[0]
+  if (!first || typeof first !== 'object' || !('text' in first)) {
+    return ''
+  }
+  return typeof first.text === 'string' ? first.text : ''
+}
+
+test('maps endpoint_not_found category markers to actionable setup guidance', () => {
+  const error = APIError.generate(
+    404,
+    undefined,
+    'OpenAI API error 404: Not Found [openai_category=endpoint_not_found] Hint: Confirm OPENAI_BASE_URL includes /v1.',
+    new Headers(),
+  )
+
+  const message = getAssistantMessageFromError(error, 'qwen2.5-coder:7b')
+  const text = getFirstText(message)
+
+  expect(message.isApiErrorMessage).toBe(true)
+  expect(text).toContain('Provider endpoint was not found')
+  expect(text).toContain('OPENAI_BASE_URL')
+  expect(text).toContain('/v1')
+})
+
+test('maps tool_call_incompatible category markers to model/tool guidance', () => {
+  const error = APIError.generate(
+    400,
+    undefined,
+    'OpenAI API error 400: tool_calls are not supported [openai_category=tool_call_incompatible]',
+    new Headers(),
+  )
+
+  const message = getAssistantMessageFromError(error, 'qwen2.5-coder:7b')
+  const text = getFirstText(message)
+
+  expect(text).toContain('rejected tool-calling payloads')
+  expect(text).toContain('/model')
+})

src/services/api/errors.ts

@@ -50,9 +50,110 @@ import {
 } from '../claudeAiLimits.js'
 import { shouldProcessRateLimits } from '../rateLimitMocking.js' // Used for /mock-limits command
 import { extractConnectionErrorDetails, formatAPIError } from './errorUtils.js'
+import {
+  extractOpenAICategoryMarker,
+  type OpenAICompatibilityFailureCategory,
+} from './openaiErrorClassification.js'
 
 export const API_ERROR_MESSAGE_PREFIX = 'API Error'
 
+function stripOpenAICompatibilityMetadata(message: string): string {
+  return message
+    .replace(/\s*\[openai_category=[a-z_]+\]\s*/g, ' ')
+    .replace(/\s{2,}/g, ' ')
+    .trim()
+}
+
+function mapOpenAICompatibilityFailureToAssistantMessage(options: {
+  category: OpenAICompatibilityFailureCategory
+  model: string
+  rawMessage: string
+}): AssistantMessage {
+  const switchCmd = getIsNonInteractiveSession() ? '--model' : '/model'
+  const compactHint = getIsNonInteractiveSession()
+    ? 'Reduce prompt size or start a new session.'
+    : 'Run /compact or start a new session with /new.'
+
+  switch (options.category) {
+    case 'localhost_resolution_failed':
+    case 'connection_refused':
+      return createAssistantAPIErrorMessage({
+        content:
+          'Could not connect to the local OpenAI-compatible provider. Ensure the local server is running, then use OPENAI_BASE_URL=http://127.0.0.1:11434/v1 for Ollama.',
+        error: 'unknown',
+      })
+
+    case 'endpoint_not_found':
+      return createAssistantAPIErrorMessage({
+        content:
+          'Provider endpoint was not found. Confirm OPENAI_BASE_URL targets an OpenAI-compatible /v1 endpoint (for Ollama: http://127.0.0.1:11434/v1).',
+        error: 'invalid_request',
+      })
+
+    case 'model_not_found':
+      return createAssistantAPIErrorMessage({
+        content: `The selected model (${options.model}) is not available on this provider. Run ${switchCmd} to choose another model, or verify installed local models (for Ollama: ollama list).`,
+        error: 'invalid_request',
+      })
+
+    case 'auth_invalid':
+      return createAssistantAPIErrorMessage({
+        content: `${API_ERROR_MESSAGE_PREFIX}: Authentication failed for your OpenAI-compatible provider. Verify OPENAI_API_KEY and endpoint-specific auth requirements.`,
+        error: 'authentication_failed',
+      })
+
+    case 'rate_limited':
+      return createAssistantAPIErrorMessage({
+        content: `${API_ERROR_MESSAGE_PREFIX}: Provider rate limit reached. Retry in a few seconds.`,
+        error: 'rate_limit',
+      })
+
+    case 'request_timeout':
+      return createAssistantAPIErrorMessage({
+        content: `${API_ERROR_MESSAGE_PREFIX}: Provider request timed out. Local models may be loading or overloaded; retry shortly or increase API_TIMEOUT_MS.`,
+        error: 'unknown',
+      })
+
+    case 'context_overflow':
+      return createAssistantAPIErrorMessage({
+        content: `The conversation exceeded the provider context limit. ${compactHint}`,
+        error: 'invalid_request',
+      })
+
+    case 'tool_call_incompatible':
+      return createAssistantAPIErrorMessage({
+        content: `The selected provider/model rejected tool-calling payloads. Try ${switchCmd} to pick a tool-capable model or continue without tools.`,
+        error: 'invalid_request',
+      })
+
+    case 'malformed_provider_response':
+      return createAssistantAPIErrorMessage({
+        content: `${API_ERROR_MESSAGE_PREFIX}: Provider returned a malformed response. Confirm endpoint compatibility and check local proxy/network middleware.`,
+        error: 'unknown',
+        errorDetails: stripOpenAICompatibilityMetadata(options.rawMessage),
+      })
+
+    case 'provider_unavailable':
+      return createAssistantAPIErrorMessage({
+        content: `${API_ERROR_MESSAGE_PREFIX}: Provider is temporarily unavailable. Retry in a moment.`,
+        error: 'unknown',
+      })
+
+    case 'network_error':
+    case 'unknown':
+      return createAssistantAPIErrorMessage({
+        content: `${API_ERROR_MESSAGE_PREFIX}: ${stripOpenAICompatibilityMetadata(options.rawMessage)}`,
+        error: 'unknown',
+      })
+
+    default:
+      return createAssistantAPIErrorMessage({
+        content: `${API_ERROR_MESSAGE_PREFIX}: ${stripOpenAICompatibilityMetadata(options.rawMessage)}`,
+        error: 'unknown',
+      })
+  }
+}
+
 export function startsWithApiErrorPrefix(text: string): boolean {
   return (
     text.startsWith(API_ERROR_MESSAGE_PREFIX) ||
@@ -457,6 +558,19 @@ export function getAssistantMessageFromError(
     })
   }
 
+  // OpenAI-compatible transport and HTTP failures include structured category
+  // markers from openaiShim.ts for actionable end-user remediation.
+  if (error instanceof APIError) {
+    const openaiCategory = extractOpenAICategoryMarker(error.message)
+    if (openaiCategory) {
+      return mapOpenAICompatibilityFailureToAssistantMessage({
+        category: openaiCategory,
+        model,
+        rawMessage: error.message,
+      })
+    }
+  }
+
   // Check for emergency capacity off switch for Opus PAYG users
   if (
     error instanceof Error &&
@@ -924,6 +1038,30 @@ export function getAssistantMessageFromError(
     })
   }
 
+  // 500 errors caused by context overflow — the API returns 500 instead of 400
+  // when the request body (including conversation context) exceeds limits.
+  // This happens when auto-compact fails or the token estimation undercounts.
+  // Detect by checking for context-related keywords in 500 responses.
+  if (
+    error instanceof APIError &&
+    error.status >= 500 &&
+    (error.message.toLowerCase().includes('too many tokens') ||
+      error.message.toLowerCase().includes('request too large') ||
+      error.message.toLowerCase().includes('context length') ||
+      error.message.toLowerCase().includes('maximum context') ||
+      error.message.toLowerCase().includes('input length') ||
+      error.message.toLowerCase().includes('payload too large'))
+  ) {
+    const rewindInstruction = getIsNonInteractiveSession()
+      ? ''
+      : ' Press esc twice to go up a few messages, or run /compact to reduce context.'
+    return createAssistantAPIErrorMessage({
+      content: `The conversation has grown too large for the API to process.${rewindInstruction} Alternatively, start a new session with /new.`,
+      error: 'invalid_request',
+      errorDetails: `Context overflow (500): ${error.message}`,
+    })
+  }
+
   // Connection errors (non-timeout) — use formatAPIError for detailed messages
   if (error instanceof APIConnectionError) {
     return createAssistantAPIErrorMessage({

src/services/api/fetchWithProxyRetry.test.ts

@@ -0,0 +1,86 @@
+import { afterEach, beforeEach, expect, test } from 'bun:test'
+
+import { _resetKeepAliveForTesting } from '../../utils/proxy.js'
+import {
+  fetchWithProxyRetry,
+  isRetryableFetchError,
+} from './fetchWithProxyRetry.js'
+
+type FetchType = typeof globalThis.fetch
+
+const originalFetch = globalThis.fetch
+const originalEnv = {
+  HTTP_PROXY: process.env.HTTP_PROXY,
+  HTTPS_PROXY: process.env.HTTPS_PROXY,
+}
+
+function restoreEnv(key: 'HTTP_PROXY' | 'HTTPS_PROXY', value: string | undefined): void {
+  if (value === undefined) {
+    delete process.env[key]
+  } else {
+    process.env[key] = value
+  }
+}
+
+beforeEach(() => {
+  process.env.HTTP_PROXY = 'http://127.0.0.1:15236'
+  delete process.env.HTTPS_PROXY
+  _resetKeepAliveForTesting()
+})
+
+afterEach(() => {
+  globalThis.fetch = originalFetch
+  restoreEnv('HTTP_PROXY', originalEnv.HTTP_PROXY)
+  restoreEnv('HTTPS_PROXY', originalEnv.HTTPS_PROXY)
+  _resetKeepAliveForTesting()
+})
+
+test('isRetryableFetchError matches Bun socket-closed failures', () => {
+  expect(
+    isRetryableFetchError(
+      new Error(
+        'The socket connection was closed unexpectedly. For more information, pass `verbose: true` in the second argument to fetch()',
+      ),
+    ),
+  ).toBe(true)
+})
+
+test('fetchWithProxyRetry retries once with keepalive disabled after socket closure', async () => {
+  const calls: Array<RequestInit | undefined> = []
+
+  globalThis.fetch = (async (_input, init) => {
+    calls.push(init)
+    if (calls.length === 1) {
+      throw new Error(
+        'The socket connection was closed unexpectedly. For more information, pass `verbose: true` in the second argument to fetch()',
+      )
+    }
+    return new Response('ok')
+  }) as FetchType
+
+  const response = await fetchWithProxyRetry('https://example.com/search', {
+    method: 'POST',
+  })
+
+  expect(await response.text()).toBe('ok')
+  expect(calls).toHaveLength(2)
+  expect((calls[0] as RequestInit & { proxy?: string }).proxy).toBe(
+    'http://127.0.0.1:15236',
+  )
+  expect((calls[0] as RequestInit).keepalive).toBeUndefined()
+  expect((calls[1] as RequestInit).keepalive).toBe(false)
+})
+
+test('fetchWithProxyRetry does not retry non-network errors', async () => {
+  let attempts = 0
+
+  globalThis.fetch = (async () => {
+    attempts += 1
+    throw new Error('400 bad request')
+  }) as FetchType
+
+  await expect(fetchWithProxyRetry('https://example.com')).rejects.toThrow(
+    '400 bad request',
+  )
+  expect(attempts).toBe(1)
+})

src/services/api/fetchWithProxyRetry.ts

@@ -0,0 +1,44 @@
+import { disableKeepAlive, getProxyFetchOptions } from '../../utils/proxy.js'
+
+const RETRYABLE_FETCH_ERROR_PATTERN =
+  /socket connection was closed unexpectedly|ECONNRESET|EPIPE|socket hang up|Connection reset by peer|fetch failed/i
+
+export function isRetryableFetchError(error: unknown): boolean {
+  if (!(error instanceof Error)) {
+    return false
+  }
+  if (error.name === 'AbortError') {
+    return false
+  }
+  return RETRYABLE_FETCH_ERROR_PATTERN.test(error.message)
+}
+
+export async function fetchWithProxyRetry(
+  input: string | URL | Request,
+  init?: RequestInit,
+  options?: { forAnthropicAPI?: boolean; maxAttempts?: number },
+): Promise<Response> {
+  const maxAttempts = Math.max(1, options?.maxAttempts ?? 2)
+  let lastError: unknown
+
+  for (let attempt = 1; attempt <= maxAttempts; attempt++) {
+    try {
+      return await fetch(input, {
+        ...init,
+        ...getProxyFetchOptions({
+          forAnthropicAPI: options?.forAnthropicAPI,
+        }),
+      })
+    } catch (error) {
+      lastError = error
+      if (attempt >= maxAttempts || !isRetryableFetchError(error)) {
+        throw error
+      }
+      disableKeepAlive()
+    }
+  }
+
+  throw lastError instanceof Error
+    ? lastError
+    : new Error('Fetch failed without an error object')
+}

src/services/api/openaiErrorClassification.test.ts

@@ -0,0 +1,97 @@
+import { expect, test } from 'bun:test'
+
+import {
+  buildOpenAICompatibilityErrorMessage,
+  classifyOpenAIHttpFailure,
+  classifyOpenAINetworkFailure,
+  extractOpenAICategoryMarker,
+  formatOpenAICategoryMarker,
+} from './openaiErrorClassification.js'
+
+test('classifies localhost ECONNREFUSED as connection_refused', () => {
+  const error = Object.assign(new TypeError('fetch failed'), {
+    code: 'ECONNREFUSED',
+  })
+
+  const failure = classifyOpenAINetworkFailure(error, {
+    url: 'http://localhost:11434/v1/chat/completions',
+  })
+
+  expect(failure.category).toBe('connection_refused')
+  expect(failure.retryable).toBe(true)
+  expect(failure.code).toBe('ECONNREFUSED')
+  expect(failure.hint).toContain('local server is running')
+})
+
+test('classifies localhost ENOTFOUND as localhost_resolution_failed', () => {
+  const error = Object.assign(new TypeError('getaddrinfo ENOTFOUND localhost'), {
+    code: 'ENOTFOUND',
+  })
+
+  const failure = classifyOpenAINetworkFailure(error, {
+    url: 'http://localhost:11434/v1/chat/completions',
+  })
+
+  expect(failure.category).toBe('localhost_resolution_failed')
+  expect(failure.retryable).toBe(true)
+  expect(failure.code).toBe('ENOTFOUND')
+  expect(failure.hint).toContain('127.0.0.1')
+})
+
+test('classifies model-not-found 404 responses', () => {
+  const failure = classifyOpenAIHttpFailure({
+    status: 404,
+    body: 'The model qwen2.5-coder:7b was not found',
+  })
+
+  expect(failure.category).toBe('model_not_found')
+  expect(failure.retryable).toBe(false)
+})
+
+test('classifies generic 404 responses as endpoint_not_found', () => {
+  const failure = classifyOpenAIHttpFailure({
+    status: 404,
+    body: 'Not Found',
+  })
+
+  expect(failure.category).toBe('endpoint_not_found')
+  expect(failure.hint).toContain('/v1')
+})
+
+test('classifies context-overflow responses', () => {
+  const failure = classifyOpenAIHttpFailure({
+    status: 500,
+    body: 'request too large: maximum context length exceeded',
+  })
+
+  expect(failure.category).toBe('context_overflow')
+  expect(failure.retryable).toBe(false)
+})
+
+test('classifies tool compatibility failures', () => {
+  const failure = classifyOpenAIHttpFailure({
+    status: 400,
+    body: 'tool_calls are not supported by this model',
+  })
+
+  expect(failure.category).toBe('tool_call_incompatible')
+})
+
+test('embeds and extracts category markers in formatted messages', () => {
+  const marker = formatOpenAICategoryMarker('endpoint_not_found')
+  expect(marker).toBe('[openai_category=endpoint_not_found]')
+
+  const formatted = buildOpenAICompatibilityErrorMessage('OpenAI API error 404: Not Found', {
+    category: 'endpoint_not_found',
+    hint: 'Confirm OPENAI_BASE_URL includes /v1.',
+  })
+
+  expect(formatted).toContain('[openai_category=endpoint_not_found]')
+  expect(formatted).toContain('Hint: Confirm OPENAI_BASE_URL includes /v1.')
+  expect(extractOpenAICategoryMarker(formatted)).toBe('endpoint_not_found')
+})
+
+test('ignores unknown category markers during extraction', () => {
+  const malformed = 'OpenAI API error 500 [openai_category=totally_fake_category]'
+  expect(extractOpenAICategoryMarker(malformed)).toBeUndefined()
+})

src/services/api/openaiErrorClassification.ts

@@ -0,0 +1,352 @@
+export type OpenAICompatibilityFailureCategory =
+  | 'connection_refused'
+  | 'localhost_resolution_failed'
+  | 'request_timeout'
+  | 'network_error'
+  | 'auth_invalid'
+  | 'rate_limited'
+  | 'model_not_found'
+  | 'endpoint_not_found'
+  | 'context_overflow'
+  | 'tool_call_incompatible'
+  | 'malformed_provider_response'
+  | 'provider_unavailable'
+  | 'unknown'
+
+export type OpenAICompatibilityFailure = {
+  source: 'network' | 'http'
+  category: OpenAICompatibilityFailureCategory
+  retryable: boolean
+  message: string
+  hint?: string
+  code?: string
+  status?: number
+}
+
+const OPENAI_CATEGORY_MARKER_PREFIX = '[openai_category='
+
+const LOCALHOST_HOSTNAMES = new Set(['localhost', '127.0.0.1', '::1'])
+
+const OPENAI_COMPATIBILITY_FAILURE_CATEGORIES: ReadonlySet<OpenAICompatibilityFailureCategory> =
+  new Set<OpenAICompatibilityFailureCategory>([
+    'connection_refused',
+    'localhost_resolution_failed',
+    'request_timeout',
+    'network_error',
+    'auth_invalid',
+    'rate_limited',
+    'model_not_found',
+    'endpoint_not_found',
+    'context_overflow',
+    'tool_call_incompatible',
+    'malformed_provider_response',
+    'provider_unavailable',
+    'unknown',
+  ])
+
+function isOpenAICompatibilityFailureCategory(
+  value: string,
+): value is OpenAICompatibilityFailureCategory {
+  return OPENAI_COMPATIBILITY_FAILURE_CATEGORIES.has(
+    value as OpenAICompatibilityFailureCategory,
+  )
+}
+
+function getErrorCode(error: unknown): string | undefined {
+  let current: unknown = error
+  const maxDepth = 5
+
+  for (let depth = 0; depth < maxDepth; depth++) {
+    if (
+      current &&
+      typeof current === 'object' &&
+      'code' in current &&
+      typeof (current as { code?: unknown }).code === 'string'
+    ) {
+      return (current as { code: string }).code
+    }
+
+    if (
+      current &&
+      typeof current === 'object' &&
+      'cause' in current &&
+      (current as { cause?: unknown }).cause !== current
+    ) {
+      current = (current as { cause?: unknown }).cause
+      continue
+    }
+
+    break
+  }
+
+  return undefined
+}
+
+function getHostname(url: string): string | null {
+  try {
+    return new URL(url).hostname.toLowerCase()
+  } catch {
+    return null
+  }
+}
+
+function isLocalhostLikeHostname(hostname: string | null): boolean {
+  if (!hostname) return false
+  if (LOCALHOST_HOSTNAMES.has(hostname)) return true
+  return /^127\./.test(hostname)
+}
+
+function isContextOverflowMessage(body: string): boolean {
+  const lower = body.toLowerCase()
+  return (
+    lower.includes('too many tokens') ||
+    lower.includes('request too large') ||
+    lower.includes('context length') ||
+    lower.includes('maximum context') ||
+    lower.includes('input length') ||
+    lower.includes('payload too large') ||
+    lower.includes('prompt is too long')
+  )
+}
+
+function isToolCompatibilityMessage(body: string): boolean {
+  const lower = body.toLowerCase()
+  return (
+    lower.includes('tool_calls') ||
+    lower.includes('tool_call') ||
+    lower.includes('tool_use') ||
+    lower.includes('tool_result') ||
+    lower.includes('function calling') ||
+    lower.includes('function call')
+  )
+}
+
+function isMalformedProviderResponse(body: string): boolean {
+  const lower = body.toLowerCase()
+  return (
+    lower.includes('<!doctype html') ||
+    lower.includes('<html') ||
+    lower.includes('invalid json') ||
+    lower.includes('malformed') ||
+    lower.includes('unexpected token') ||
+    lower.includes('cannot parse') ||
+    lower.includes('not valid json')
+  )
+}
+
+function isModelNotFoundMessage(body: string): boolean {
+  const lower = body.toLowerCase()
+  return (
+    lower.includes('model') &&
+    (
+      lower.includes('not found') ||
+      lower.includes('does not exist') ||
+      lower.includes('unknown model') ||
+      lower.includes('unavailable model')
+    )
+  )
+}
+
+export function formatOpenAICategoryMarker(
+  category: OpenAICompatibilityFailureCategory,
+): string {
+  return `${OPENAI_CATEGORY_MARKER_PREFIX}${category}]`
+}
+
+export function extractOpenAICategoryMarker(
+  message: string,
+): OpenAICompatibilityFailureCategory | undefined {
+  const match = message.match(/\[openai_category=([a-z_]+)]/)
+  const category = match?.[1]
+
+  if (!category || !isOpenAICompatibilityFailureCategory(category)) {
+    return undefined
+  }
+
+  return category
+}
+
+export function buildOpenAICompatibilityErrorMessage(
+  baseMessage: string,
+  failure: Pick<OpenAICompatibilityFailure, 'category' | 'hint'>,
+): string {
+  const marker = formatOpenAICategoryMarker(failure.category)
+  const hint = failure.hint ? ` Hint: ${failure.hint}` : ''
+  return `${baseMessage} ${marker}${hint}`
+}
+
+export function classifyOpenAINetworkFailure(
+  error: unknown,
+  options: { url: string },
+): OpenAICompatibilityFailure {
+  const message = error instanceof Error ? error.message : String(error)
+  const lowerMessage = message.toLowerCase()
+  const code = getErrorCode(error)
+  const hostname = getHostname(options.url)
+  const isLocalHost = isLocalhostLikeHostname(hostname)
+
+  if (
+    code === 'ETIMEDOUT' ||
+    code === 'UND_ERR_CONNECT_TIMEOUT' ||
+    lowerMessage.includes('timeout') ||
+    lowerMessage.includes('timed out') ||
+    lowerMessage.includes('aborterror')
+  ) {
+    return {
+      source: 'network',
+      category: 'request_timeout',
+      retryable: true,
+      message,
+      code,
+      hint: 'The provider took too long to respond. Check local model load time or increase API timeout.',
+    }
+  }
+
+  if (
+    isLocalHost &&
+    (
+      code === 'ENOTFOUND' ||
+      code === 'EAI_AGAIN' ||
+      lowerMessage.includes('getaddrinfo') ||
+      (code === undefined && lowerMessage.includes('fetch failed'))
+    )
+  ) {
+    return {
+      source: 'network',
+      category: 'localhost_resolution_failed',
+      retryable: true,
+      message,
+      code,
+      hint: 'Localhost failed for this request. Retry with 127.0.0.1 and confirm Ollama is serving on the configured port.',
+    }
+  }
+
+  if (code === 'ECONNREFUSED') {
+    return {
+      source: 'network',
+      category: 'connection_refused',
+      retryable: true,
+      message,
+      code,
+      hint: isLocalHost
+        ? 'Connection to the local provider was refused. Ensure the local server is running and listening on the configured port.'
+        : 'Connection was refused by the provider endpoint. Ensure the server is running and the port is correct.',
+    }
+  }
+
+  return {
+    source: 'network',
+    category: 'network_error',
+    retryable: true,
+    message,
+    code,
+    hint: 'Network transport failed before a provider response was received.',
+  }
+}
+
+export function classifyOpenAIHttpFailure(options: {
+  status: number
+  body: string
+}): OpenAICompatibilityFailure {
+  const body = options.body ?? ''
+
+  if (options.status === 401 || options.status === 403) {
+    return {
+      source: 'http',
+      category: 'auth_invalid',
+      retryable: false,
+      status: options.status,
+      message: body,
+      hint: 'Authentication failed. Verify API key, token source, and endpoint-specific auth headers.',
+    }
+  }
+
+  if (options.status === 429) {
+    return {
+      source: 'http',
+      category: 'rate_limited',
+      retryable: true,
+      status: options.status,
+      message: body,
+      hint: 'Provider rate-limited the request. Retry after backoff.',
+    }
+  }
+
+  if (options.status === 404 && isModelNotFoundMessage(body)) {
+    return {
+      source: 'http',
+      category: 'model_not_found',
+      retryable: false,
+      status: options.status,
+      message: body,
+      hint: 'The selected model is not installed or not available on this endpoint.',
+    }
+  }
+
+  if (options.status === 404) {
+    return {
+      source: 'http',
+      category: 'endpoint_not_found',
+      retryable: false,
+      status: options.status,
+      message: body,
+      hint: 'Endpoint was not found. Confirm OPENAI_BASE_URL includes /v1 for OpenAI-compatible local providers.',
+    }
+  }
+
+  if (
+    options.status === 413 ||
+    ((options.status === 400 || options.status >= 500) &&
+      isContextOverflowMessage(body))
+  ) {
+    return {
+      source: 'http',
+      category: 'context_overflow',
+      retryable: false,
+      status: options.status,
+      message: body,
+      hint: 'Prompt context exceeded model/server limits. Reduce context or increase provider context length.',
+    }
+  }
+
+  if (options.status === 400 && isToolCompatibilityMessage(body)) {
+    return {
+      source: 'http',
+      category: 'tool_call_incompatible',
+      retryable: false,
+      status: options.status,
+      message: body,
+      hint: 'Provider/model rejected tool-calling payload. Retry without tools or use a tool-capable model.',
+    }
+  }
+
+  if (options.status >= 400 && isMalformedProviderResponse(body)) {
+    return {
+      source: 'http',
+      category: 'malformed_provider_response',
+      retryable: false,
+      status: options.status,
+      message: body,
+      hint: 'Provider returned malformed or non-JSON response where JSON was expected.',
+    }
+  }
+
+  if (options.status >= 500) {
+    return {
+      source: 'http',
+      category: 'provider_unavailable',
+      retryable: true,
+      status: options.status,
+      message: body,
+      hint: 'Provider reported a server-side failure. Retry after a short delay.',
+    }
+  }
+
+  return {
+    source: 'http',
+    category: 'unknown',
+    retryable: false,
+    status: options.status,
+    message: body,
+  }
+}

src/services/api/openaiShim.compression.test.ts

@@ -0,0 +1,317 @@
+import { afterEach, beforeEach, expect, mock, test } from 'bun:test'
+import { createOpenAIShimClient } from './openaiShim.js'
+
+type FetchType = typeof globalThis.fetch
+const originalFetch = globalThis.fetch
+
+const originalEnv = {
+  OPENAI_BASE_URL: process.env.OPENAI_BASE_URL,
+  OPENAI_API_KEY: process.env.OPENAI_API_KEY,
+  OPENAI_MODEL: process.env.OPENAI_MODEL,
+}
+
+// Mock config + autoCompact so the shim sees deterministic state.
+const mockState = {
+  enabled: true,
+  effectiveWindow: 100_000, // Copilot gpt-4o tier
+}
+
+mock.module('../../utils/config.js', () => ({
+  getGlobalConfig: () => ({
+    toolHistoryCompressionEnabled: mockState.enabled,
+    autoCompactEnabled: false,
+  }),
+}))
+
+mock.module('../compact/autoCompact.js', () => ({
+  getEffectiveContextWindowSize: () => mockState.effectiveWindow,
+}))
+
+type OpenAIShimClient = {
+  beta: {
+    messages: {
+      create: (
+        params: Record<string, unknown>,
+        options?: Record<string, unknown>,
+      ) => Promise<unknown>
+    }
+  }
+}
+
+function bigText(n: number): string {
+  return 'A'.repeat(n)
+}
+
+function buildToolExchange(id: number, resultLength: number) {
+  return [
+    {
+      role: 'assistant',
+      content: [
+        {
+          type: 'tool_use',
+          id: `toolu_${id}`,
+          name: 'Read',
+          input: { file_path: `/path/to/file${id}.ts` },
+        },
+      ],
+    },
+    {
+      role: 'user',
+      content: [
+        {
+          type: 'tool_result',
+          tool_use_id: `toolu_${id}`,
+          content: bigText(resultLength),
+        },
+      ],
+    },
+  ]
+}
+
+function buildLongConversation(numExchanges: number, resultLength = 5_000) {
+  const out: Array<{ role: string; content: unknown }> = [
+    { role: 'user', content: 'start the work' },
+  ]
+  for (let i = 0; i < numExchanges; i++) {
+    out.push(...buildToolExchange(i, resultLength))
+  }
+  return out
+}
+
+function makeFakeResponse(): Response {
+  return new Response(
+    JSON.stringify({
+      id: 'chatcmpl-1',
+      model: 'gpt-4o',
+      choices: [
+        {
+          message: { role: 'assistant', content: 'done' },
+          finish_reason: 'stop',
+        },
+      ],
+      usage: { prompt_tokens: 8, completion_tokens: 2, total_tokens: 10 },
+    }),
+    { headers: { 'Content-Type': 'application/json' } },
+  )
+}
+
+beforeEach(() => {
+  process.env.OPENAI_BASE_URL = 'http://example.test/v1'
+  process.env.OPENAI_API_KEY = 'test-key'
+  delete process.env.OPENAI_MODEL
+  mockState.enabled = true
+  mockState.effectiveWindow = 100_000
+})
+
+afterEach(() => {
+  if (originalEnv.OPENAI_BASE_URL === undefined) delete process.env.OPENAI_BASE_URL
+  else process.env.OPENAI_BASE_URL = originalEnv.OPENAI_BASE_URL
+  if (originalEnv.OPENAI_API_KEY === undefined) delete process.env.OPENAI_API_KEY
+  else process.env.OPENAI_API_KEY = originalEnv.OPENAI_API_KEY
+  if (originalEnv.OPENAI_MODEL === undefined) delete process.env.OPENAI_MODEL
+  else process.env.OPENAI_MODEL = originalEnv.OPENAI_MODEL
+  globalThis.fetch = originalFetch
+})
+
+async function captureRequestBody(
+  messages: Array<{ role: string; content: unknown }>,
+  model: string,
+): Promise<Record<string, unknown>> {
+  let captured: Record<string, unknown> | undefined
+
+  globalThis.fetch = (async (_input, init) => {
+    captured = JSON.parse(String(init?.body))
+    return makeFakeResponse()
+  }) as FetchType
+
+  const client = createOpenAIShimClient({}) as OpenAIShimClient
+  await client.beta.messages.create({
+    model,
+    system: 'system prompt',
+    messages,
+  })
+
+  if (!captured) throw new Error('request not captured')
+  return captured
+}
+
+function getToolMessages(body: Record<string, unknown>): Array<{ content: string }> {
+  const messages = body.messages as Array<{ role: string; content: string }>
+  return messages.filter(m => m.role === 'tool')
+}
+
+function getAssistantToolCalls(body: Record<string, unknown>): unknown[] {
+  const messages = body.messages as Array<{
+    role: string
+    tool_calls?: unknown[]
+  }>
+  return messages
+    .filter(m => m.role === 'assistant' && Array.isArray(m.tool_calls))
+    .flatMap(m => m.tool_calls ?? [])
+}
+
+// ============================================================================
+// BUG REPRO: without compression, full tool history is resent every turn
+// ============================================================================
+
+test('BUG REPRO: without compression, all 30 tool results are sent at full size', async () => {
+  mockState.enabled = false
+  const messages = buildLongConversation(30, 5_000)
+
+  const body = await captureRequestBody(messages, 'gpt-4o')
+  const toolMessages = getToolMessages(body)
+  const payloadSize = JSON.stringify(body).length
+
+  // All 30 tool results present, none truncated
+  expect(toolMessages.length).toBe(30)
+  for (const m of toolMessages) {
+    expect(m.content.length).toBeGreaterThanOrEqual(5_000)
+    expect(m.content).not.toContain('[…truncated')
+    expect(m.content).not.toContain('chars omitted')
+  }
+
+  // Total payload is large (~150KB raw) — this is the cost being paid every turn
+  expect(payloadSize).toBeGreaterThan(150_000)
+})
+
+// ============================================================================
+// FIX: with compression, recent kept full, mid truncated, old stubbed
+// ============================================================================
+
+test('FIX: with compression on Copilot gpt-4o (tier 5/10/rest), 30 turns shrinks dramatically', async () => {
+  mockState.enabled = true
+  mockState.effectiveWindow = 100_000 // 64–128k → recent=5, mid=10
+  const messages = buildLongConversation(30, 5_000)
+
+  const body = await captureRequestBody(messages, 'gpt-4o')
+  const toolMessages = getToolMessages(body)
+  const payloadSize = JSON.stringify(body).length
+
+  // Structure preserved: still 30 tool messages, no orphan tool_calls
+  expect(toolMessages.length).toBe(30)
+  expect(getAssistantToolCalls(body).length).toBe(30)
+
+  // Tier breakdown (oldest → newest):
+  //   indices 0..14  → old tier (stubs)
+  //   indices 15..24 → mid tier (truncated)
+  //   indices 25..29 → recent (full)
+  for (let i = 0; i <= 14; i++) {
+    expect(toolMessages[i].content).toMatch(/^\[Read args=.*chars omitted\]$/)
+  }
+  for (let i = 15; i <= 24; i++) {
+    expect(toolMessages[i].content).toContain('[…truncated')
+  }
+  for (let i = 25; i <= 29; i++) {
+    expect(toolMessages[i].content.length).toBe(5_000)
+    expect(toolMessages[i].content).not.toContain('[…truncated')
+    expect(toolMessages[i].content).not.toContain('chars omitted')
+  }
+
+  // Significant reduction: from ~150KB to <60KB (10 mid×2KB + structure overhead)
+  expect(payloadSize).toBeLessThan(60_000)
+})
+
+// ============================================================================
+// FIX: large-context model gets generous tiers — compression effectively inert
+// ============================================================================
+
+test('FIX: gpt-4.1 (1M context) with 25 exchanges keeps all full (recent tier=25)', async () => {
+  mockState.enabled = true
+  mockState.effectiveWindow = 1_000_000 // ≥500k → recent=25, mid=50
+  const messages = buildLongConversation(25, 5_000)
+
+  const body = await captureRequestBody(messages, 'gpt-4.1')
+  const toolMessages = getToolMessages(body)
+
+  expect(toolMessages.length).toBe(25)
+  for (const m of toolMessages) {
+    expect(m.content.length).toBe(5_000)
+    expect(m.content).not.toContain('[…truncated')
+    expect(m.content).not.toContain('chars omitted')
+  }
+})
+
+test('FIX: gpt-4.1 (1M context) with 30 exchanges → only first 5 mid-truncated', async () => {
+  mockState.enabled = true
+  mockState.effectiveWindow = 1_000_000 // recent=25, mid=50
+  const messages = buildLongConversation(30, 5_000)
+
+  const body = await captureRequestBody(messages, 'gpt-4.1')
+  const toolMessages = getToolMessages(body)
+
+  // 30 total: indices 0..4 mid, indices 5..29 recent
+  for (let i = 0; i < 5; i++) {
+    expect(toolMessages[i].content).toContain('[…truncated')
+  }
+  for (let i = 5; i < 30; i++) {
+    expect(toolMessages[i].content.length).toBe(5_000)
+  }
+})
+
+// ============================================================================
+// FIX: stub preserves tool name and args — model can re-invoke if needed
+// ============================================================================
+
+test('FIX: stub format includes original tool name and arguments', async () => {
+  mockState.enabled = true
+  mockState.effectiveWindow = 100_000
+  const messages = buildLongConversation(30, 5_000)
+
+  const body = await captureRequestBody(messages, 'gpt-4o')
+  const toolMessages = getToolMessages(body)
+  const oldestStub = toolMessages[0].content
+
+  // Format: [<tool_name> args=<json> → <N> chars omitted]
+  expect(oldestStub).toMatch(/^\[Read /)
+  expect(oldestStub).toMatch(/file_path/)
+  expect(oldestStub).toMatch(/→ 5000 chars omitted\]$/)
+})
+
+// ============================================================================
+// FIX: tool_use blocks (assistant tool_calls) are never modified
+// ============================================================================
+
+test('FIX: every tool_call retains its full id, name, and arguments', async () => {
+  mockState.enabled = true
+  mockState.effectiveWindow = 100_000
+  const messages = buildLongConversation(30, 5_000)
+
+  const body = await captureRequestBody(messages, 'gpt-4o')
+  const toolCalls = getAssistantToolCalls(body) as Array<{
+    id: string
+    function: { name: string; arguments: string }
+  }>
+
+  expect(toolCalls.length).toBe(30)
+  for (let i = 0; i < toolCalls.length; i++) {
+    expect(toolCalls[i].id).toBe(`toolu_${i}`)
+    expect(toolCalls[i].function.name).toBe('Read')
+    expect(JSON.parse(toolCalls[i].function.arguments)).toEqual({
+      file_path: `/path/to/file${i}.ts`,
+    })
+  }
+})
+
+// ============================================================================
+// FIX: small-context provider (Mistral 32k) gets aggressive compression
+// ============================================================================
+
+test('FIX: 32k window (Mistral tier) → recent=3 keeps last 3 only', async () => {
+  mockState.enabled = true
+  mockState.effectiveWindow = 24_000 // 16–32k → recent=3, mid=5
+  const messages = buildLongConversation(15, 3_000)
+
+  const body = await captureRequestBody(messages, 'mistral-large-latest')
+  const toolMessages = getToolMessages(body)
+
+  // 15 total: indices 0..6 old, 7..11 mid, 12..14 recent
+  for (let i = 0; i <= 6; i++) {
+    expect(toolMessages[i].content).toContain('chars omitted')
+  }
+  for (let i = 7; i <= 11; i++) {
+    expect(toolMessages[i].content).toContain('[…truncated')
+  }
+  for (let i = 12; i <= 14; i++) {
+    expect(toolMessages[i].content.length).toBe(3_000)
+  }
+})

src/services/api/openaiShim.diagnostics.test.ts

@@ -0,0 +1,286 @@
+import { afterEach, expect, mock, test } from 'bun:test'
+
+const originalFetch = globalThis.fetch
+const originalEnv = {
+  OPENAI_BASE_URL: process.env.OPENAI_BASE_URL,
+  OPENAI_API_KEY: process.env.OPENAI_API_KEY,
+  OPENAI_MODEL: process.env.OPENAI_MODEL,
+}
+
+function restoreEnv(key: string, value: string | undefined): void {
+  if (value === undefined) {
+    delete process.env[key]
+  } else {
+    process.env[key] = value
+  }
+}
+
+afterEach(() => {
+  globalThis.fetch = originalFetch
+  restoreEnv('OPENAI_BASE_URL', originalEnv.OPENAI_BASE_URL)
+  restoreEnv('OPENAI_API_KEY', originalEnv.OPENAI_API_KEY)
+  restoreEnv('OPENAI_MODEL', originalEnv.OPENAI_MODEL)
+  mock.restore()
+})
+
+test('logs classified transport diagnostics with category and code', async () => {
+  const debugSpy = mock(() => {})
+  mock.module('../../utils/debug.js', () => ({
+    logForDebugging: debugSpy,
+  }))
+
+  const nonce = `${Date.now()}-${Math.random()}`
+  const { createOpenAIShimClient } = await import(`./openaiShim.ts?ts=${nonce}`)
+
+  process.env.OPENAI_BASE_URL = 'http://localhost:11434/v1'
+  process.env.OPENAI_API_KEY = 'ollama'
+
+  const transportError = Object.assign(new TypeError('fetch failed'), {
+    code: 'ECONNREFUSED',
+  })
+
+  globalThis.fetch = mock(async () => {
+    throw transportError
+  }) as typeof globalThis.fetch
+
+  const client = createOpenAIShimClient({}) as {
+    beta: {
+      messages: {
+        create: (params: Record<string, unknown>) => Promise<unknown>
+      }
+    }
+  }
+
+  await expect(
+    client.beta.messages.create({
+      model: 'qwen2.5-coder:7b',
+      messages: [{ role: 'user', content: 'hello' }],
+      max_tokens: 64,
+      stream: false,
+    }),
+  ).rejects.toThrow('openai_category=connection_refused')
+
+  const transportLog = debugSpy.mock.calls.find(call =>
+    typeof call?.[0] === 'string' && call[0].includes('transport failure'),
+  )
+
+  expect(transportLog).toBeDefined()
+  expect(String(transportLog?.[0])).toContain('category=connection_refused')
+  expect(String(transportLog?.[0])).toContain('code=ECONNREFUSED')
+  expect(transportLog?.[1]).toEqual({ level: 'warn' })
+})
+
+test('redacts credentials in transport diagnostic URL logs', async () => {
+  const debugSpy = mock(() => {})
+  mock.module('../../utils/debug.js', () => ({
+    logForDebugging: debugSpy,
+  }))
+
+  const nonce = `${Date.now()}-${Math.random()}`
+  const { createOpenAIShimClient } = await import(`./openaiShim.ts?ts=${nonce}`)
+
+  process.env.OPENAI_BASE_URL = 'http://user:supersecret@localhost:11434/v1'
+  process.env.OPENAI_API_KEY = 'supersecret'
+
+  const transportError = Object.assign(new TypeError('fetch failed'), {
+    code: 'ECONNREFUSED',
+  })
+
+  globalThis.fetch = mock(async () => {
+    throw transportError
+  }) as typeof globalThis.fetch
+
+  const client = createOpenAIShimClient({}) as {
+    beta: {
+      messages: {
+        create: (params: Record<string, unknown>) => Promise<unknown>
+      }
+    }
+  }
+
+  await expect(
+    client.beta.messages.create({
+      model: 'qwen2.5-coder:7b',
+      messages: [{ role: 'user', content: 'hello' }],
+      max_tokens: 64,
+      stream: false,
+    }),
+  ).rejects.toThrow('openai_category=connection_refused')
+
+  const transportLog = debugSpy.mock.calls.find(call =>
+    typeof call?.[0] === 'string' && call[0].includes('transport failure'),
+  )
+
+  expect(transportLog).toBeDefined()
+  const logLine = String(transportLog?.[0])
+  expect(logLine).toContain('url=http://redacted:redacted@localhost:11434/v1/chat/completions')
+  expect(logLine).not.toContain('user:supersecret')
+  expect(logLine).not.toContain('supersecret@')
+})
+test('logs self-heal localhost fallback with redacted from/to URLs', async () => {
+  const debugSpy = mock(() => {})
+  mock.module('../../utils/debug.js', () => ({
+    logForDebugging: debugSpy,
+  }))
+
+  const nonce = `${Date.now()}-${Math.random()}`
+  const { createOpenAIShimClient } = await import(`./openaiShim.ts?ts=${nonce}`)
+
+  process.env.OPENAI_BASE_URL = 'http://user:supersecret@localhost:11434/v1'
+  process.env.OPENAI_API_KEY = 'supersecret'
+
+  globalThis.fetch = mock(async (input: string | Request) => {
+    const url = typeof input === 'string' ? input : input.url
+    if (url.includes('localhost')) {
+      throw Object.assign(new TypeError('fetch failed'), {
+        code: 'ENOTFOUND',
+      })
+    }
+
+    return new Response(
+      JSON.stringify({
+        id: 'chatcmpl-1',
+        model: 'qwen2.5-coder:7b',
+        choices: [
+          {
+            message: {
+              role: 'assistant',
+              content: 'ok',
+            },
+            finish_reason: 'stop',
+          },
+        ],
+        usage: {
+          prompt_tokens: 5,
+          completion_tokens: 2,
+          total_tokens: 7,
+        },
+      }),
+      {
+        status: 200,
+        headers: {
+          'Content-Type': 'application/json',
+        },
+      },
+    )
+  }) as typeof globalThis.fetch
+
+  const client = createOpenAIShimClient({}) as {
+    beta: {
+      messages: {
+        create: (params: Record<string, unknown>) => Promise<unknown>
+      }
+    }
+  }
+
+  await expect(
+    client.beta.messages.create({
+      model: 'qwen2.5-coder:7b',
+      messages: [{ role: 'user', content: 'hello' }],
+      max_tokens: 64,
+      stream: false,
+    }),
+  ).resolves.toBeDefined()
+
+  const fallbackLog = debugSpy.mock.calls.find(call =>
+    typeof call?.[0] === 'string' &&
+    call[0].includes('self-heal retry reason=localhost_resolution_failed'),
+  )
+
+  expect(fallbackLog).toBeDefined()
+  const logLine = String(fallbackLog?.[0])
+  expect(logLine).toContain('from=http://redacted:redacted@localhost:11434/v1/chat/completions')
+  expect(logLine).toContain('to=http://redacted:redacted@127.0.0.1:11434/v1/chat/completions')
+  expect(logLine).not.toContain('supersecret')
+})
+
+test('logs self-heal toolless retry for local tool-call incompatibility', async () => {
+  const debugSpy = mock(() => {})
+  mock.module('../../utils/debug.js', () => ({
+    logForDebugging: debugSpy,
+  }))
+
+  const nonce = `${Date.now()}-${Math.random()}`
+  const { createOpenAIShimClient } = await import(`./openaiShim.ts?ts=${nonce}`)
+
+  process.env.OPENAI_BASE_URL = 'http://localhost:11434/v1'
+  process.env.OPENAI_API_KEY = 'ollama'
+
+  let callCount = 0
+  globalThis.fetch = mock(async () => {
+    callCount += 1
+    if (callCount === 1) {
+      return new Response('tool_calls are not supported', {
+        status: 400,
+        headers: {
+          'Content-Type': 'text/plain',
+        },
+      })
+    }
+
+    return new Response(
+      JSON.stringify({
+        id: 'chatcmpl-1',
+        model: 'qwen2.5-coder:7b',
+        choices: [
+          {
+            message: {
+              role: 'assistant',
+              content: 'ok',
+            },
+            finish_reason: 'stop',
+          },
+        ],
+        usage: {
+          prompt_tokens: 7,
+          completion_tokens: 3,
+          total_tokens: 10,
+        },
+      }),
+      {
+        status: 200,
+        headers: {
+          'Content-Type': 'application/json',
+        },
+      },
+    )
+  }) as typeof globalThis.fetch
+
+  const client = createOpenAIShimClient({}) as {
+    beta: {
+      messages: {
+        create: (params: Record<string, unknown>) => Promise<unknown>
+      }
+    }
+  }
+
+  await expect(
+    client.beta.messages.create({
+      model: 'qwen2.5-coder:7b',
+      messages: [{ role: 'user', content: 'hello' }],
+      tools: [
+        {
+          name: 'Read',
+          description: 'Read file',
+          input_schema: {
+            type: 'object',
+            properties: {
+              filePath: { type: 'string' },
+            },
+            required: ['filePath'],
+          },
+        },
+      ],
+      max_tokens: 64,
+      stream: false,
+    }),
+  ).resolves.toBeDefined()
+
+  const fallbackLog = debugSpy.mock.calls.find(call =>
+    typeof call?.[0] === 'string' &&
+    call[0].includes('self-heal retry reason=tool_call_incompatible mode=toolless'),
+  )
+
+  expect(fallbackLog).toBeDefined()
+  expect(fallbackLog?.[1]).toEqual({ level: 'warn' })
+})

src/services/api/providerConfig.codexSecureStorage.test.ts

@@ -0,0 +1,225 @@
+import { afterEach, describe, expect, mock, test } from 'bun:test'
+import { mkdirSync, mkdtempSync, rmSync, writeFileSync } from 'node:fs'
+import { tmpdir } from 'node:os'
+import { join } from 'node:path'
+import * as realOs from 'node:os'
+
+function makeJwt(payload: Record<string, unknown>): string {
+  const header = Buffer.from(JSON.stringify({ alg: 'none', typ: 'JWT' }))
+    .toString('base64url')
+  const body = Buffer.from(JSON.stringify(payload)).toString('base64url')
+  return `${header}.${body}.signature`
+}
+
+describe('resolveCodexApiCredentials with secure storage', () => {
+  afterEach(() => {
+    mock.restore()
+  })
+
+  test('loads Codex credentials from OpenClaude secure storage', async () => {
+    mock.module('../../utils/codexCredentials.js', () => ({
+      isCodexRefreshFailureCoolingDown: () => false,
+      readCodexCredentials: () => ({
+        apiKey: 'codex-api-key-token',
+        accessToken: 'header.payload.signature',
+        accountId: 'acct_secure',
+      }),
+    }))
+
+    // @ts-expect-error cache-busting query string for Bun module mocks
+    const { resolveCodexApiCredentials } = await import(
+      './providerConfig.js?codex-secure-storage'
+    )
+
+    const credentials = resolveCodexApiCredentials({} as NodeJS.ProcessEnv)
+    expect(credentials.apiKey).toBe('codex-api-key-token')
+    expect(credentials.accountId).toBe('acct_secure')
+    expect(credentials.source).toBe('secure-storage')
+  })
+
+  test('prefers explicit env credentials over secure storage', async () => {
+    mock.module('../../utils/codexCredentials.js', () => ({
+      isCodexRefreshFailureCoolingDown: () => false,
+      readCodexCredentials: () => ({
+        accessToken: 'stored-token',
+        accountId: 'acct_stored',
+      }),
+    }))
+
+    // @ts-expect-error cache-busting query string for Bun module mocks
+    const { resolveCodexApiCredentials } = await import(
+      './providerConfig.js?codex-env-precedence'
+    )
+
+    const credentials = resolveCodexApiCredentials({
+      CODEX_API_KEY: 'env-token',
+      CHATGPT_ACCOUNT_ID: 'acct_env',
+    } as NodeJS.ProcessEnv)
+
+    expect(credentials.apiKey).toBe('env-token')
+    expect(credentials.accountId).toBe('acct_env')
+    expect(credentials.source).toBe('env')
+  })
+
+  test('parses nested chatgpt_account_id from a CODEX_API_KEY JWT', async () => {
+    mock.module('../../utils/codexCredentials.js', () => ({
+      isCodexRefreshFailureCoolingDown: () => false,
+      readCodexCredentials: () => undefined,
+    }))
+
+    // @ts-expect-error cache-busting query string for Bun module mocks
+    const { resolveCodexApiCredentials } = await import(
+      './providerConfig.js?codex-env-nested-account'
+    )
+
+    const credentials = resolveCodexApiCredentials({
+      CODEX_API_KEY: makeJwt({
+        'https://api.openai.com/auth': {
+          chatgpt_account_id: 'acct_nested_env',
+        },
+      }),
+    } as NodeJS.ProcessEnv)
+
+    expect(credentials.accountId).toBe('acct_nested_env')
+    expect(credentials.source).toBe('env')
+  })
+
+  test('parses nested chatgpt_account_id from auth.json tokens', async () => {
+    mock.module('../../utils/codexCredentials.js', () => ({
+      isCodexRefreshFailureCoolingDown: () => false,
+      readCodexCredentials: () => undefined,
+    }))
+
+    const tempDir = mkdtempSync(join(tmpdir(), 'openclaude-codex-auth-'))
+    const authPath = join(tempDir, 'auth.json')
+
+    writeFileSync(
+      authPath,
+      JSON.stringify({
+        openai_api_key: makeJwt({
+          'https://api.openai.com/auth': {
+            chatgpt_account_id: 'acct_nested_auth_json',
+          },
+        }),
+      }),
+      'utf8',
+    )
+
+    try {
+      // @ts-expect-error cache-busting query string for Bun module mocks
+      const { resolveCodexApiCredentials } = await import(
+        './providerConfig.js?codex-auth-json-nested-account'
+      )
+
+      const credentials = resolveCodexApiCredentials({
+        CODEX_AUTH_JSON_PATH: authPath,
+      } as NodeJS.ProcessEnv)
+
+      expect(credentials.accountId).toBe('acct_nested_auth_json')
+      expect(credentials.source).toBe('auth.json')
+    } finally {
+      rmSync(tempDir, { force: true, recursive: true })
+    }
+  })
+
+  test('does not read default auth.json when secure storage already has Codex credentials', async () => {
+    mock.module('../../utils/codexCredentials.js', () => ({
+      isCodexRefreshFailureCoolingDown: () => false,
+      readCodexCredentials: () => ({
+        apiKey: 'codex-api-key-token',
+        accessToken: 'header.payload.signature',
+        accountId: 'acct_secure',
+      }),
+    }))
+
+    // @ts-expect-error cache-busting query string for Bun module mocks
+    const { resolveCodexApiCredentials } = await import(
+      './providerConfig.js?codex-secure-storage-no-auth-io'
+    )
+
+    const credentials = resolveCodexApiCredentials({} as NodeJS.ProcessEnv)
+    expect(credentials.apiKey).toBe('codex-api-key-token')
+    expect(credentials.accountId).toBe('acct_secure')
+    expect(credentials.source).toBe('secure-storage')
+  })
+
+  test('falls back to the default auth.json when stored Codex refresh is cooling down', async () => {
+    const tempHomeDir = mkdtempSync(join(tmpdir(), 'openclaude-codex-home-'))
+    const authJson = JSON.stringify({
+      openai_api_key: makeJwt({
+        'https://api.openai.com/auth': {
+          chatgpt_account_id: 'acct_auth_json',
+        },
+      }),
+    })
+    mkdirSync(join(tempHomeDir, '.codex'), { recursive: true })
+    writeFileSync(join(tempHomeDir, '.codex', 'auth.json'), authJson, 'utf8')
+
+    mock.module('node:os', () => ({
+      ...realOs,
+      homedir: () => tempHomeDir,
+    }))
+
+    mock.module('../../utils/codexCredentials.js', () => ({
+      isCodexRefreshFailureCoolingDown: () => true,
+      readCodexCredentials: () => ({
+        accessToken: 'stored-token',
+        refreshToken: 'refresh-stored',
+        accountId: 'acct_stored',
+        lastRefreshFailureAt: Date.now(),
+      }),
+    }))
+
+    // @ts-expect-error cache-busting query string for Bun module mocks
+    const { resolveCodexApiCredentials } = await import(
+      './providerConfig.js?codex-refresh-cooldown-fallback'
+    )
+
+    try {
+      const credentials = resolveCodexApiCredentials({} as NodeJS.ProcessEnv)
+      expect(credentials.source).toBe('auth.json')
+      expect(credentials.accountId).toBe('acct_auth_json')
+      expect(credentials.apiKey).not.toBe('stored-token')
+    } finally {
+      rmSync(tempHomeDir, { force: true, recursive: true })
+    }
+  })
+
+  test('preserves the stored account id when auth.json fallback lacks one', async () => {
+    const tempHomeDir = mkdtempSync(join(tmpdir(), 'openclaude-codex-home-'))
+    const authJson = JSON.stringify({
+      openai_api_key: 'auth-json-access-token',
+    })
+    mkdirSync(join(tempHomeDir, '.codex'), { recursive: true })
+    writeFileSync(join(tempHomeDir, '.codex', 'auth.json'), authJson, 'utf8')
+
+    mock.module('node:os', () => ({
+      ...realOs,
+      homedir: () => tempHomeDir,
+    }))
+
+    mock.module('../../utils/codexCredentials.js', () => ({
+      isCodexRefreshFailureCoolingDown: () => true,
+      readCodexCredentials: () => ({
+        accessToken: 'stored-token',
+        refreshToken: 'refresh-stored',
+        accountId: 'acct_stored',
+        lastRefreshFailureAt: Date.now(),
+      }),
+    }))
+
+    // @ts-expect-error cache-busting query string for Bun module mocks
+    const { resolveCodexApiCredentials } = await import(
+      './providerConfig.js?codex-refresh-cooldown-account-id-fallback'
+    )
+
+    try {
+      const credentials = resolveCodexApiCredentials({} as NodeJS.ProcessEnv)
+      expect(credentials.source).toBe('auth.json')
+      expect(credentials.apiKey).toBe('auth-json-access-token')
+      expect(credentials.accountId).toBe('acct_stored')
+    } finally {
+      rmSync(tempHomeDir, { force: true, recursive: true })
+    }
+  })
+})

src/services/api/providerConfig.envDiagnostics.test.ts

@@ -0,0 +1,107 @@
+import { afterEach, expect, mock, test } from 'bun:test'
+
+const originalEnv = {
+  CLAUDE_CODE_USE_OPENAI: process.env.CLAUDE_CODE_USE_OPENAI,
+  CLAUDE_CODE_USE_MISTRAL: process.env.CLAUDE_CODE_USE_MISTRAL,
+  OPENAI_BASE_URL: process.env.OPENAI_BASE_URL,
+  OPENAI_MODEL: process.env.OPENAI_MODEL,
+  OPENAI_API_BASE: process.env.OPENAI_API_BASE,
+  MISTRAL_BASE_URL: process.env.MISTRAL_BASE_URL,
+  MISTRAL_MODEL: process.env.MISTRAL_MODEL,
+}
+
+function restoreEnv(key: string, value: string | undefined): void {
+  if (value === undefined) {
+    delete process.env[key]
+  } else {
+    process.env[key] = value
+  }
+}
+
+afterEach(() => {
+  restoreEnv('CLAUDE_CODE_USE_OPENAI', originalEnv.CLAUDE_CODE_USE_OPENAI)
+  restoreEnv('CLAUDE_CODE_USE_MISTRAL', originalEnv.CLAUDE_CODE_USE_MISTRAL)
+  restoreEnv('OPENAI_BASE_URL', originalEnv.OPENAI_BASE_URL)
+  restoreEnv('OPENAI_MODEL', originalEnv.OPENAI_MODEL)
+  restoreEnv('OPENAI_API_BASE', originalEnv.OPENAI_API_BASE)
+  restoreEnv('MISTRAL_BASE_URL', originalEnv.MISTRAL_BASE_URL)
+  restoreEnv('MISTRAL_MODEL', originalEnv.MISTRAL_MODEL)
+  mock.restore()
+})
+
+test('logs a warning when OPENAI_BASE_URL is literal undefined', async () => {
+  const debugSpy = mock(() => {})
+  mock.module('../../utils/debug.js', () => ({
+    logForDebugging: debugSpy,
+  }))
+
+  process.env.CLAUDE_CODE_USE_OPENAI = '1'
+  process.env.OPENAI_BASE_URL = 'undefined'
+  process.env.OPENAI_MODEL = 'gpt-4o'
+  delete process.env.OPENAI_API_BASE
+
+  const nonce = `${Date.now()}-${Math.random()}`
+  const { resolveProviderRequest } = await import(`./providerConfig.ts?ts=${nonce}`)
+
+  const resolved = resolveProviderRequest()
+
+  expect(resolved.baseUrl).toBe('https://api.openai.com/v1')
+
+  const warningCall = debugSpy.mock.calls.find(call =>
+    typeof call?.[0] === 'string' &&
+    call[0].includes('OPENAI_BASE_URL') &&
+    call[0].includes('"undefined"'),
+  )
+
+  expect(warningCall).toBeDefined()
+  expect(warningCall?.[1]).toEqual({ level: 'warn' })
+})
+
+test('does not warn for OPENAI_API_BASE when OPENAI_BASE_URL is active', async () => {
+  const debugSpy = mock(() => {})
+  mock.module('../../utils/debug.js', () => ({
+    logForDebugging: debugSpy,
+  }))
+
+  process.env.CLAUDE_CODE_USE_OPENAI = '1'
+  delete process.env.CLAUDE_CODE_USE_MISTRAL
+  process.env.OPENAI_BASE_URL = 'http://127.0.0.1:11434/v1'
+  process.env.OPENAI_MODEL = 'qwen2.5-coder:7b'
+  process.env.OPENAI_API_BASE = 'undefined'
+
+  const nonce = `${Date.now()}-${Math.random()}`
+  const { resolveProviderRequest } = await import(`./providerConfig.ts?ts=${nonce}`)
+
+  const resolved = resolveProviderRequest()
+
+  expect(resolved.baseUrl).toBe('http://127.0.0.1:11434/v1')
+
+  const aliasWarning = debugSpy.mock.calls.find(call =>
+    typeof call?.[0] === 'string' &&
+    call[0].includes('OPENAI_API_BASE') &&
+    call[0].includes('"undefined"'),
+  )
+
+  expect(aliasWarning).toBeUndefined()
+})
+
+test('uses OPENAI_API_BASE as fallback in mistral mode when MISTRAL_BASE_URL is unset', async () => {
+  const debugSpy = mock(() => {})
+  mock.module('../../utils/debug.js', () => ({
+    logForDebugging: debugSpy,
+  }))
+
+  delete process.env.CLAUDE_CODE_USE_OPENAI
+  process.env.CLAUDE_CODE_USE_MISTRAL = '1'
+  delete process.env.MISTRAL_BASE_URL
+  process.env.MISTRAL_MODEL = 'mistral-medium-latest'
+  process.env.OPENAI_API_BASE = 'http://127.0.0.1:11434/v1'
+
+  const nonce = `${Date.now()}-${Math.random()}`
+  const { resolveProviderRequest } = await import(`./providerConfig.ts?ts=${nonce}`)
+
+  const resolved = resolveProviderRequest()
+
+  expect(resolved.baseUrl).toBe('http://127.0.0.1:11434/v1')
+  expect(debugSpy.mock.calls).toHaveLength(0)
+})

src/services/api/providerConfig.local.test.ts

@@ -2,8 +2,10 @@ import { afterEach, expect, test } from 'bun:test'
 
 import {
   getAdditionalModelOptionsCacheScope,
+  getLocalProviderRetryBaseUrls,
   isLocalProviderUrl,
   resolveProviderRequest,
+  shouldAttemptLocalToollessRetry,
 } from './providerConfig.js'
 
 const originalEnv = {
@@ -83,3 +85,42 @@ test('skips local model cache scope for remote openai-compatible providers', ()
 
   expect(getAdditionalModelOptionsCacheScope()).toBeNull()
 })
+
+test('derives local retry base URLs with /v1 and loopback fallback candidates', () => {
+  expect(getLocalProviderRetryBaseUrls('http://localhost:11434')).toEqual([
+    'http://localhost:11434/v1',
+    'http://127.0.0.1:11434',
+    'http://127.0.0.1:11434/v1',
+  ])
+})
+
+test('does not derive local retry base URLs for remote providers', () => {
+  expect(getLocalProviderRetryBaseUrls('https://api.openai.com/v1')).toEqual([])
+})
+
+test('enables local toolless retry for likely Ollama endpoints with tools', () => {
+  expect(
+    shouldAttemptLocalToollessRetry({
+      baseUrl: 'http://localhost:11434/v1',
+      hasTools: true,
+    }),
+  ).toBe(true)
+})
+
+test('disables local toolless retry when no tools are present', () => {
+  expect(
+    shouldAttemptLocalToollessRetry({
+      baseUrl: 'http://localhost:11434/v1',
+      hasTools: false,
+    }),
+  ).toBe(false)
+})
+
+test('disables local toolless retry for non-Ollama local endpoints', () => {
+  expect(
+    shouldAttemptLocalToollessRetry({
+      baseUrl: 'http://localhost:1234/v1',
+      hasTools: true,
+    }),
+  ).toBe(false)
+})

src/services/api/providerConfig.runtimeCodexCredentials.test.ts

@@ -0,0 +1,107 @@
+import { afterEach, expect, mock, test } from 'bun:test'
+import { mkdtempSync, rmSync, writeFileSync } from 'node:fs'
+import { tmpdir } from 'node:os'
+import { join } from 'node:path'
+
+import { resolveRuntimeCodexCredentials } from './providerConfig.js'
+
+afterEach(() => {
+  mock.restore()
+})
+
+function makeJwt(payload: Record<string, unknown>): string {
+  const header = Buffer.from(JSON.stringify({ alg: 'none', typ: 'JWT' }))
+    .toString('base64url')
+  const body = Buffer.from(JSON.stringify(payload)).toString('base64url')
+  return `${header}.${body}.signature`
+}
+
+test('runtime credential resolution honors explicit auth.json over stored secure-storage tokens', () => {
+  const tempDir = mkdtempSync(join(tmpdir(), 'openclaude-codex-explicit-auth-'))
+  const authPath = join(tempDir, 'auth.json')
+
+  writeFileSync(
+    authPath,
+    JSON.stringify({
+      openai_api_key: makeJwt({
+        'https://api.openai.com/auth': {
+          chatgpt_account_id: 'acct_explicit_auth_json',
+        },
+      }),
+    }),
+    'utf8',
+  )
+
+  try {
+    const credentials = resolveRuntimeCodexCredentials({
+      env: {
+        CODEX_AUTH_JSON_PATH: authPath,
+      } as NodeJS.ProcessEnv,
+      storedCredentials: {
+        apiKey: 'stored-api-key',
+        accessToken: 'stored-access-token',
+        accountId: 'acct_stored',
+      },
+    })
+
+    expect(credentials.source).toBe('auth.json')
+    expect(credentials.accountId).toBe('acct_explicit_auth_json')
+    expect(credentials.apiKey).not.toBe('stored-api-key')
+  } finally {
+    rmSync(tempDir, { force: true, recursive: true })
+  }
+})
+
+test('runtime credential resolution preserves an explicit auth.json path even when it is missing', () => {
+  const tempDir = mkdtempSync(join(tmpdir(), 'openclaude-codex-missing-auth-'))
+  const authPath = join(tempDir, 'missing-auth.json')
+
+  try {
+    const credentials = resolveRuntimeCodexCredentials({
+      env: {
+        CODEX_AUTH_JSON_PATH: authPath,
+      } as NodeJS.ProcessEnv,
+      storedCredentials: {
+        apiKey: 'stored-api-key',
+        accessToken: 'stored-access-token',
+        accountId: 'acct_stored',
+      },
+    })
+
+    expect(credentials.source).toBe('none')
+    expect(credentials.authPath).toBe(authPath)
+    expect(credentials.apiKey).toBe('')
+  } finally {
+    rmSync(tempDir, { force: true, recursive: true })
+  }
+})
+
+test('runtime credential resolution avoids sync secure-storage reads when async credentials are provided', async () => {
+  let syncReadCalled = false
+
+  mock.module('../../utils/codexCredentials.js', () => ({
+    isCodexRefreshFailureCoolingDown: () => false,
+    readCodexCredentials: () => {
+      syncReadCalled = true
+      throw new Error('sync secure-storage read should not run in runtime resolution')
+    },
+  }))
+
+  // @ts-expect-error cache-busting query string for Bun module mocks
+  const { resolveRuntimeCodexCredentials } = await import(
+    './providerConfig.js?runtime-no-sync-secure-storage'
+  )
+
+  const credentials = resolveRuntimeCodexCredentials({
+    env: {} as NodeJS.ProcessEnv,
+    storedCredentials: {
+      accessToken: 'stored-access-token',
+      accountId: 'acct_stored',
+    },
+  })
+
+  expect(syncReadCalled).toBe(false)
+  expect(credentials.source).toBe('secure-storage')
+  expect(credentials.apiKey).toBe('stored-access-token')
+  expect(credentials.accountId).toBe('acct_stored')
+})

src/services/api/providerConfig.ts

@@ -3,13 +3,25 @@ import { isIP } from 'node:net'
 import { homedir } from 'node:os'
 import { join } from 'node:path'
 
+import {
+  isCodexRefreshFailureCoolingDown,
+  readCodexCredentials,
+  type CodexCredentialBlob,
+} from '../../utils/codexCredentials.js'
+import { logForDebugging } from '../../utils/debug.js'
 import { isEnvTruthy } from '../../utils/envUtils.js'
+import {
+  asTrimmedString,
+  parseChatgptAccountId,
+} from './codexOAuthShared.js'
+import { DEFAULT_GEMINI_BASE_URL } from 'src/utils/providerProfile.js'
 
 export const DEFAULT_OPENAI_BASE_URL = 'https://api.openai.com/v1'
 export const DEFAULT_CODEX_BASE_URL = 'https://chatgpt.com/backend-api/codex'
 export const DEFAULT_MISTRAL_BASE_URL = 'https://api.mistral.ai/v1'
 /** Default GitHub Copilot API model when user selects copilot / github:copilot */
 export const DEFAULT_GITHUB_MODELS_API_MODEL = 'gpt-4o'
+const warnedUndefinedEnvNames = new Set<string>()
 
 const CODEX_ALIAS_MODELS: Record<
   string,
@@ -60,6 +72,8 @@ const CODEX_ALIAS_MODELS: Record<
 type CodexAlias = keyof typeof CODEX_ALIAS_MODELS
 type ReasoningEffort = 'low' | 'medium' | 'high' | 'xhigh'
 
+const OPENAI_CODEX_SHORTCUT_ALIASES = new Set(['codexplan', 'codexspark'])
+
 export type ProviderTransport = 'chat_completions' | 'codex_responses'
 
 export type ResolvedProviderRequest = {
@@ -76,7 +90,7 @@ export type ResolvedCodexCredentials = {
   apiKey: string
   accountId?: string
   authPath?: string
-  source: 'env' | 'auth.json' | 'none'
+  source: 'env' | 'secure-storage' | 'auth.json' | 'none'
 }
 
 type ModelDescriptor = {
@@ -112,19 +126,39 @@ function isPrivateIpv6Address(hostname: string): boolean {
   return (prefix & 0xfe00) === 0xfc00 || (prefix & 0xffc0) === 0xfe80
 }
 
-function asTrimmedString(value: unknown): string | undefined {
-  if (typeof value !== 'string') return undefined
-  const trimmed = value.trim()
-  return trimmed ? trimmed : undefined
-}
-
 // Reads an env-var-style string intended as a URL or path, rejecting both
 // empty strings and the literal string "undefined" that Windows shells can
 // write when a variable is unset-then-referenced without quotes (issue #336).
 function asEnvUrl(value: string | undefined): string | undefined {
   if (!value) return undefined
   const trimmed = value.trim()
-  if (!trimmed || trimmed === 'undefined') return undefined
+  if (!trimmed) return undefined
+  if (trimmed === 'undefined') {
+    return undefined
+  }
+  return trimmed
+}
+
+function asNamedEnvUrl(
+  value: string | undefined,
+  envName: string,
+): string | undefined {
+  if (!value) return undefined
+
+  const trimmed = value.trim()
+  if (!trimmed) return undefined
+
+  if (trimmed === 'undefined') {
+    if (!warnedUndefinedEnvNames.has(envName)) {
+      warnedUndefinedEnvNames.add(envName)
+      logForDebugging(
+        `[provider-config] Environment variable ${envName} is the literal string "undefined"; ignoring it.`,
+        { level: 'warn' },
+      )
+    }
+    return undefined
+  }
+
   return trimmed
 }
 
@@ -149,23 +183,6 @@ function readNestedString(
   return undefined
 }
 
-function decodeJwtPayload(token: string): Record<string, unknown> | undefined {
-  const parts = token.split('.')
-  if (parts.length < 2) return undefined
-
-  try {
-    const normalized = parts[1].replace(/-/g, '+').replace(/_/g, '/')
-    const padded = normalized + '='.repeat((4 - (normalized.length % 4)) % 4)
-    const json = Buffer.from(padded, 'base64').toString('utf8')
-    const parsed = JSON.parse(json)
-    return parsed && typeof parsed === 'object'
-      ? (parsed as Record<string, unknown>)
-      : undefined
-  } catch {
-    return undefined
-  }
-}
-
 function parseReasoningEffort(value: string | undefined): ReasoningEffort | undefined {
   if (!value) return undefined
   const normalized = value.trim().toLowerCase()
@@ -220,6 +237,12 @@ export function isCodexAlias(model: string): boolean {
   return base in CODEX_ALIAS_MODELS
 }
 
+function isOpenAICodexShortcutAlias(model: string): boolean {
+  const normalized = model.trim().toLowerCase()
+  const base = normalized.split('?', 1)[0] ?? normalized
+  return OPENAI_CODEX_SHORTCUT_ALIASES.has(base)
+}
+
 export function shouldUseCodexTransport(
   model: string,
   baseUrl: string | undefined,
@@ -282,6 +305,101 @@ export function isLocalProviderUrl(baseUrl: string | undefined): boolean {
   }
 }
 
+function trimTrailingSlash(value: string): string {
+  return value.replace(/\/+$/, '')
+}
+
+function normalizePathWithV1(pathname: string): string {
+  const trimmed = trimTrailingSlash(pathname)
+  if (!trimmed || trimmed === '/') {
+    return '/v1'
+  }
+
+  if (trimmed.toLowerCase().endsWith('/v1')) {
+    return trimmed
+  }
+
+  return `${trimmed}/v1`
+}
+
+function isLikelyOllamaEndpoint(baseUrl: string): boolean {
+  try {
+    const parsed = new URL(baseUrl)
+    const hostname = parsed.hostname.toLowerCase()
+    const pathname = parsed.pathname.toLowerCase()
+
+    if (parsed.port === '11434') {
+      return true
+    }
+
+    return (
+      hostname.includes('ollama') ||
+      pathname.includes('ollama')
+    )
+  } catch {
+    return false
+  }
+}
+
+export function getLocalProviderRetryBaseUrls(baseUrl: string): string[] {
+  if (!isLocalProviderUrl(baseUrl)) {
+    return []
+  }
+
+  try {
+    const parsed = new URL(baseUrl)
+    const original = trimTrailingSlash(parsed.toString())
+    const seen = new Set<string>([original])
+    const candidates: string[] = []
+
+    const addCandidate = (hostname: string, pathname: string): void => {
+      const next = new URL(parsed.toString())
+      next.hostname = hostname
+      next.pathname = pathname
+      next.search = ''
+      next.hash = ''
+
+      const normalized = trimTrailingSlash(next.toString())
+      if (seen.has(normalized)) {
+        return
+      }
+
+      seen.add(normalized)
+      candidates.push(normalized)
+    }
+
+    const v1Pathname = normalizePathWithV1(parsed.pathname)
+    if (v1Pathname !== trimTrailingSlash(parsed.pathname)) {
+      addCandidate(parsed.hostname, v1Pathname)
+    }
+
+    const hostname = parsed.hostname.toLowerCase().replace(/^\[|\]$/g, '')
+    if (hostname === 'localhost' || hostname === '::1') {
+      addCandidate('127.0.0.1', parsed.pathname || '/')
+      addCandidate('127.0.0.1', v1Pathname)
+    }
+
+    return candidates
+  } catch {
+    return []
+  }
+}
+
+export function shouldAttemptLocalToollessRetry(options: {
+  baseUrl: string
+  hasTools: boolean
+}): boolean {
+  if (!options.hasTools) {
+    return false
+  }
+
+  if (!isLocalProviderUrl(options.baseUrl)) {
+    return false
+  }
+
+  return isLikelyOllamaEndpoint(options.baseUrl)
+}
+
 export function isCodexBaseUrl(baseUrl: string | undefined): boolean {
   if (!baseUrl) return false
   try {
@@ -359,20 +477,80 @@ export function resolveProviderRequest(options?: {
 }): ResolvedProviderRequest {
   const isGithubMode = isEnvTruthy(process.env.CLAUDE_CODE_USE_GITHUB)
   const isMistralMode = isEnvTruthy(process.env.CLAUDE_CODE_USE_MISTRAL)
+  const isGeminiMode = isEnvTruthy(process.env.CLAUDE_CODE_USE_GEMINI)
   const requestedModel =
     options?.model?.trim() ||
     (isMistralMode
       ? process.env.MISTRAL_MODEL?.trim()
       : process.env.OPENAI_MODEL?.trim()) ||
+    (isGeminiMode
+      ? process.env.GEMINI_MODEL?.trim()
+      : process.env.OPENAI_MODEL?.trim()) ||
     options?.fallbackModel?.trim() ||
     (isGithubMode ? 'github:copilot' : 'gpt-4o')
   const descriptor = parseModelDescriptor(requestedModel)
-  const rawBaseUrl =
-    asEnvUrl(options?.baseUrl) ??
-    asEnvUrl(
-      isMistralMode ? (process.env.MISTRAL_BASE_URL ?? DEFAULT_MISTRAL_BASE_URL) : process.env.OPENAI_BASE_URL,
-    ) ??
-    asEnvUrl(process.env.OPENAI_API_BASE)
+  const explicitBaseUrl = asEnvUrl(options?.baseUrl)
+
+  const normalizedMistralEnvBaseUrl = asNamedEnvUrl(
+    process.env.MISTRAL_BASE_URL,
+    'MISTRAL_BASE_URL',
+  )
+
+  const normalizedGeminiEnvBaseUrl = asNamedEnvUrl(
+    process.env.GEMINI_BASE_URL,
+    'GEMINI_BASE_URL',
+  )
+
+  const primaryEnvBaseUrl = isMistralMode
+    ? normalizedMistralEnvBaseUrl
+    : isGeminiMode
+    ? normalizedGeminiEnvBaseUrl
+    : asNamedEnvUrl(process.env.OPENAI_BASE_URL, 'OPENAI_BASE_URL')
+
+  // In Mistral mode, a literal "undefined" MISTRAL_BASE_URL is treated as
+  // misconfiguration and falls back to OPENAI_API_BASE, then
+  // DEFAULT_MISTRAL_BASE_URL for a safe default endpoint.
+  const fallbackEnvBaseUrl = isMistralMode
+    ? (primaryEnvBaseUrl === undefined
+      ? asNamedEnvUrl(process.env.OPENAI_API_BASE, 'OPENAI_API_BASE') ?? DEFAULT_MISTRAL_BASE_URL
+      : undefined)
+    : isGeminiMode
+    ? (primaryEnvBaseUrl === undefined
+      ? asNamedEnvUrl(process.env.OPENAI_API_BASE, 'OPENAI_API_BASE') ?? DEFAULT_GEMINI_BASE_URL
+      : undefined)
+    : (primaryEnvBaseUrl === undefined
+      ? asNamedEnvUrl(process.env.OPENAI_API_BASE, 'OPENAI_API_BASE')
+      : undefined)
+
+  const envBaseUrlRaw =
+    explicitBaseUrl ??
+    primaryEnvBaseUrl ??
+    fallbackEnvBaseUrl
+
+  const isCodexModelForGithub = isGithubMode && isCodexAlias(requestedModel)
+  const envBaseUrl =
+    isCodexModelForGithub && envBaseUrlRaw && getGithubEndpointType(envBaseUrlRaw) === 'custom'
+      ? undefined
+      : envBaseUrlRaw
+
+  const rawBaseUrl = explicitBaseUrl ?? envBaseUrl
+
+  const shellModel = process.env.OPENAI_MODEL?.trim() ?? ''
+  const envIsCodexShortcut = isOpenAICodexShortcutAlias(shellModel)
+  const envResolvedCodexModel = envIsCodexShortcut
+    ? parseModelDescriptor(shellModel).baseModel
+    : null
+  const requestedMatchesEnvCodexShortcut =
+    Boolean(options?.model) &&
+    Boolean(envResolvedCodexModel) &&
+    descriptor.baseModel === envResolvedCodexModel
+  const isCodexAliasModel =
+    isOpenAICodexShortcutAlias(requestedModel) || requestedMatchesEnvCodexShortcut
+  const hasUserSetBaseUrl = rawBaseUrl && rawBaseUrl !== DEFAULT_OPENAI_BASE_URL
+  const finalBaseUrl =
+    !isGithubMode && isCodexAliasModel && !hasUserSetBaseUrl
+      ? DEFAULT_CODEX_BASE_URL
+      : rawBaseUrl
 
   const githubEndpointType = isGithubMode
     ? getGithubEndpointType(rawBaseUrl)
@@ -386,7 +564,7 @@ export function resolveProviderRequest(options?: {
     : requestedModel
 
   const transport: ProviderTransport =
-    shouldUseCodexTransport(requestedModel, rawBaseUrl) ||
+    shouldUseCodexTransport(requestedModel, finalBaseUrl) ||
       (isGithubCopilot && shouldUseGithubResponsesApi(githubResolvedModel))
       ? 'codex_responses'
       : 'chat_completions'
@@ -410,7 +588,7 @@ export function resolveProviderRequest(options?: {
     requestedModel,
     resolvedModel,
     baseUrl:
-      (rawBaseUrl ??
+      (finalBaseUrl ??
         (isGithubCopilot && transport === 'codex_responses'
           ? GITHUB_COPILOT_BASE_URL
           : (isGithubMode
@@ -458,18 +636,6 @@ export function resolveCodexAuthPath(
   return join(homedir(), '.codex', 'auth.json')
 }
 
-export function parseChatgptAccountId(
-  token: string | undefined,
-): string | undefined {
-  if (!token) return undefined
-  const payload = decodeJwtPayload(token)
-  const fromClaim = asTrimmedString(
-    payload?.['https://api.openai.com/auth.chatgpt_account_id'],
-  )
-  if (fromClaim) return fromClaim
-  return asTrimmedString(payload?.chatgpt_account_id)
-}
-
 function loadCodexAuthJson(
   authPath: string,
 ): Record<string, unknown> | undefined {
@@ -485,8 +651,97 @@ function loadCodexAuthJson(
   }
 }
 
-export function resolveCodexApiCredentials(
-  env: NodeJS.ProcessEnv = process.env,
+function resolveCodexAuthJsonCredentials(options: {
+  authJson: Record<string, unknown> | undefined
+  authPath: string
+  envAccountId?: string
+  missingSource?: ResolvedCodexCredentials['source']
+}): ResolvedCodexCredentials {
+  const { authJson, authPath, envAccountId } = options
+
+  if (!authJson) {
+    return {
+      apiKey: '',
+      authPath,
+      source: options.missingSource ?? 'none',
+    }
+  }
+
+  const apiKey = readNestedString(authJson, [
+    ['openai_api_key'],
+    ['openaiApiKey'],
+    ['access_token'],
+    ['accessToken'],
+    ['tokens', 'access_token'],
+    ['tokens', 'accessToken'],
+    ['auth', 'access_token'],
+    ['auth', 'accessToken'],
+    ['token', 'access_token'],
+    ['token', 'accessToken'],
+  ])
+  // OIDC identity tokens can carry the ChatGPT account id, but they are not
+  // valid bearer credentials for Codex API requests.
+  const idToken = readNestedString(authJson, [
+    ['id_token'],
+    ['idToken'],
+    ['tokens', 'id_token'],
+    ['tokens', 'idToken'],
+  ])
+  const accountId =
+    envAccountId ??
+    readNestedString(authJson, [
+      ['account_id'],
+      ['accountId'],
+      ['tokens', 'account_id'],
+      ['tokens', 'accountId'],
+      ['auth', 'account_id'],
+      ['auth', 'accountId'],
+    ]) ??
+    parseChatgptAccountId(apiKey) ??
+    parseChatgptAccountId(idToken)
+
+  if (!apiKey) {
+    return {
+      apiKey: '',
+      accountId,
+      authPath,
+      source: options.missingSource ?? 'none',
+    }
+  }
+
+  return {
+    apiKey,
+    accountId,
+    authPath,
+    source: 'auth.json',
+  }
+}
+
+export function resolveStoredCodexCredentials(options: {
+  storedCredentials: Pick<
+    CodexCredentialBlob,
+    'apiKey' | 'accessToken' | 'idToken' | 'accountId'
+  >
+  envAccountId?: string
+}): ResolvedCodexCredentials {
+  const { storedCredentials, envAccountId } = options
+
+  return {
+    apiKey: storedCredentials.apiKey ?? storedCredentials.accessToken,
+    accountId:
+      envAccountId ??
+      storedCredentials.accountId ??
+      parseChatgptAccountId(storedCredentials.idToken) ??
+      parseChatgptAccountId(storedCredentials.accessToken),
+    source: 'secure-storage',
+  }
+}
+
+function resolveEnvOrAuthJsonCodexCredentials(
+  env: NodeJS.ProcessEnv,
+  options?: {
+    explicitAuthPathOnly?: boolean
+  },
 ): ResolvedCodexCredentials {
   const envApiKey = asTrimmedString(env.CODEX_API_KEY)
   const envAccountId =
@@ -501,55 +756,127 @@ export function resolveCodexApiCredentials(
     }
   }
 
+  const explicitAuthPathConfigured = Boolean(
+    asTrimmedString(env.CODEX_AUTH_JSON_PATH) ?? asTrimmedString(env.CODEX_HOME),
+  )
+
+  if (!explicitAuthPathConfigured && options?.explicitAuthPathOnly) {
+    return {
+      apiKey: '',
+      accountId: envAccountId,
+      source: 'none',
+    }
+  }
+
   const authPath = resolveCodexAuthPath(env)
   const authJson = loadCodexAuthJson(authPath)
-  if (!authJson) {
-    return {
-      apiKey: '',
-      authPath,
-      source: 'none',
-    }
-  }
-
-  const apiKey = readNestedString(authJson, [
-    ['access_token'],
-    ['accessToken'],
-    ['tokens', 'access_token'],
-    ['tokens', 'accessToken'],
-    ['auth', 'access_token'],
-    ['auth', 'accessToken'],
-    ['token', 'access_token'],
-    ['token', 'accessToken'],
-    ['tokens', 'id_token'],
-    ['tokens', 'idToken'],
-  ])
-  const accountId =
-    envAccountId ??
-    readNestedString(authJson, [
-      ['account_id'],
-      ['accountId'],
-      ['tokens', 'account_id'],
-      ['tokens', 'accountId'],
-      ['auth', 'account_id'],
-      ['auth', 'accountId'],
-    ]) ??
-    parseChatgptAccountId(apiKey)
-
-  if (!apiKey) {
-    return {
-      apiKey: '',
-      accountId,
-      authPath,
-      source: 'none',
-    }
-  }
-
-  return {
-    apiKey,
-    accountId,
+  return resolveCodexAuthJsonCredentials({
+    authJson,
     authPath,
-    source: 'auth.json',
+    envAccountId,
+  })
+}
+
+export function resolveRuntimeCodexCredentials(options?: {
+  env?: NodeJS.ProcessEnv
+  storedCredentials?: Pick<
+    CodexCredentialBlob,
+    'apiKey' | 'accessToken' | 'idToken' | 'accountId'
+  >
+}): ResolvedCodexCredentials {
+  const env = options?.env ?? process.env
+  const explicitCredentials = resolveEnvOrAuthJsonCodexCredentials(env, {
+    explicitAuthPathOnly: true,
+  })
+  const explicitAuthPathConfigured = Boolean(
+    asTrimmedString(env.CODEX_AUTH_JSON_PATH) ?? asTrimmedString(env.CODEX_HOME),
+  )
+  const hasStoredCredentialsOption = Boolean(
+    options &&
+      Object.prototype.hasOwnProperty.call(options, 'storedCredentials'),
+  )
+
+  if (
+    explicitAuthPathConfigured ||
+    explicitCredentials.source === 'env' ||
+    explicitCredentials.source === 'auth.json'
+  ) {
+    return explicitCredentials
   }
+
+  if (options?.storedCredentials?.accessToken) {
+    return resolveStoredCodexCredentials({
+      storedCredentials: options.storedCredentials,
+      envAccountId:
+        asTrimmedString(env.CODEX_ACCOUNT_ID) ??
+        asTrimmedString(env.CHATGPT_ACCOUNT_ID),
+    })
+  }
+
+  if (hasStoredCredentialsOption) {
+    return resolveEnvOrAuthJsonCodexCredentials(env)
+  }
+
+  return resolveCodexApiCredentials(env)
+}
+
+export function resolveCodexApiCredentials(
+  env: NodeJS.ProcessEnv = process.env,
+): ResolvedCodexCredentials {
+  const envAccountId =
+    asTrimmedString(env.CODEX_ACCOUNT_ID) ??
+    asTrimmedString(env.CHATGPT_ACCOUNT_ID)
+  const envOrExplicitAuthJsonCredentials = resolveEnvOrAuthJsonCodexCredentials(
+    env,
+    {
+      explicitAuthPathOnly: true,
+    },
+  )
+
+  if (
+    envOrExplicitAuthJsonCredentials.source === 'env' ||
+    envOrExplicitAuthJsonCredentials.source === 'auth.json' ||
+    envOrExplicitAuthJsonCredentials.authPath
+  ) {
+    return envOrExplicitAuthJsonCredentials
+  }
+
+  const storedCredentials = readCodexCredentials()
+  if (storedCredentials?.accessToken) {
+    const resolvedStoredCredentials = resolveStoredCodexCredentials({
+      storedCredentials,
+      envAccountId,
+    })
+
+    const shouldCheckDefaultAuthJson =
+      !resolvedStoredCredentials.accountId ||
+      isCodexRefreshFailureCoolingDown(storedCredentials)
+
+    if (!shouldCheckDefaultAuthJson) {
+      return resolvedStoredCredentials
+    }
+
+    const authPath = resolveCodexAuthPath(env)
+    const authJson = loadCodexAuthJson(authPath)
+    const resolvedAuthJsonCredentials = resolveCodexAuthJsonCredentials({
+      authJson,
+      authPath,
+      envAccountId,
+    })
+
+    if (resolvedAuthJsonCredentials.apiKey) {
+      return {
+        ...resolvedAuthJsonCredentials,
+        accountId:
+          resolvedAuthJsonCredentials.accountId ??
+          resolvedStoredCredentials.accountId,
+      }
+    }
+
+    return resolvedStoredCredentials
+  }
+
+  return resolveEnvOrAuthJsonCodexCredentials(env)
 }
 
 export function getReasoningEffortForModel(model: string): ReasoningEffort | undefined {
@@ -559,3 +886,18 @@ export function getReasoningEffortForModel(model: string): ReasoningEffort | und
   const aliasConfig = CODEX_ALIAS_MODELS[alias]
   return aliasConfig?.reasoningEffort
 }
+
+export function supportsCodexReasoningEffort(model: string): boolean {
+  const normalized = model.trim().toLowerCase()
+  const base = normalized.split('?', 1)[0] ?? normalized
+
+  if (base === 'gpt-5.3-codex-spark' || base === 'codexspark') {
+    return false
+  }
+
+  if (getReasoningEffortForModel(base) !== undefined) {
+    return true
+  }
+
+  return /^gpt-5(?:[.-]|$)/.test(base)
+}

src/services/api/reasoningLeakSanitizer.test.ts

@@ -1,46 +0,0 @@
-import { describe, expect, test } from 'bun:test'
-
-import {
-  looksLikeLeakedReasoningPrefix,
-  shouldBufferPotentialReasoningPrefix,
-  stripLeakedReasoningPreamble,
-} from './reasoningLeakSanitizer.ts'
-
-describe('reasoning leak sanitizer', () => {
-  test('strips explicit internal reasoning preambles', () => {
-    const text =
-      'The user just said "hey" - a simple greeting. I should respond briefly and friendly.\n\nHey! How can I help you today?'
-
-    expect(looksLikeLeakedReasoningPrefix(text)).toBe(true)
-    expect(stripLeakedReasoningPreamble(text)).toBe(
-      'Hey! How can I help you today?',
-    )
-  })
-
-  test('does not strip normal user-facing advice that mentions "the user should"', () => {
-    const text =
-      'The user should reset their password immediately.\n\nHere are the steps...'
-
-    expect(looksLikeLeakedReasoningPrefix(text)).toBe(false)
-    expect(shouldBufferPotentialReasoningPrefix(text)).toBe(false)
-    expect(stripLeakedReasoningPreamble(text)).toBe(text)
-  })
-
-  test('does not strip legitimate first-person advice about responding to an incident', () => {
-    const text =
-      'I need to respond to this security incident immediately. The system is compromised.\n\nHere are the remediation steps...'
-
-    expect(looksLikeLeakedReasoningPrefix(text)).toBe(false)
-    expect(shouldBufferPotentialReasoningPrefix(text)).toBe(false)
-    expect(stripLeakedReasoningPreamble(text)).toBe(text)
-  })
-
-  test('does not strip legitimate first-person advice about answering a support ticket', () => {
-    const text =
-      'I need to answer the support ticket before end of day. The customer is waiting.\n\nHere is the response I drafted...'
-
-    expect(looksLikeLeakedReasoningPrefix(text)).toBe(false)
-    expect(shouldBufferPotentialReasoningPrefix(text)).toBe(false)
-    expect(stripLeakedReasoningPreamble(text)).toBe(text)
-  })
-})

src/services/api/reasoningLeakSanitizer.ts

@@ -1,54 +0,0 @@
-const EXPLICIT_REASONING_START_RE =
-  /^\s*(i should\b|i need to\b|let me think\b|the task\b|the request\b)/i
-
-const EXPLICIT_REASONING_META_RE =
-  /\b(user|request|question|prompt|message|task|greeting|small talk|briefly|friendly|concise)\b/i
-
-const USER_META_START_RE =
-  /^\s*the user\s+(just\s+)?(said|asked|is asking|wants|wanted|mentioned|seems|appears)\b/i
-
-const USER_REASONING_RE =
-  /^\s*the user\s+(just\s+)?(said|asked|is asking|wants|wanted|mentioned|seems|appears)\b[\s\S]*\b(i should|i need to|let me think|respond|reply|answer|greeting|small talk|briefly|friendly|concise)\b/i
-
-export function shouldBufferPotentialReasoningPrefix(text: string): boolean {
-  const normalized = text.trim()
-  if (!normalized) return false
-
-  if (looksLikeLeakedReasoningPrefix(normalized)) {
-    return true
-  }
-
-  const hasParagraphBoundary = /\n\s*\n/.test(normalized)
-  if (hasParagraphBoundary) {
-    return false
-  }
-
-  return (
-    EXPLICIT_REASONING_START_RE.test(normalized) ||
-    USER_META_START_RE.test(normalized)
-  )
-}
-
-export function looksLikeLeakedReasoningPrefix(text: string): boolean {
-  const normalized = text.trim()
-  if (!normalized) return false
-  return (
-    (EXPLICIT_REASONING_START_RE.test(normalized) &&
-      EXPLICIT_REASONING_META_RE.test(normalized)) ||
-    USER_REASONING_RE.test(normalized)
-  )
-}
-
-export function stripLeakedReasoningPreamble(text: string): string {
-  const normalized = text.replace(/\r\n/g, '\n')
-  const parts = normalized.split(/\n\s*\n/)
-  if (parts.length < 2) return text
-
-  const first = parts[0]?.trim() ?? ''
-  if (!looksLikeLeakedReasoningPrefix(first)) {
-    return text
-  }
-
-  const remainder = parts.slice(1).join('\n\n').trim()
-  return remainder || text
-}

src/services/api/smartModelRouting.test.ts

@@ -0,0 +1,191 @@
+import { describe, expect, test } from 'bun:test'
+
+import {
+  routeModel,
+  type SmartRoutingConfig,
+} from './smartModelRouting.ts'
+
+const ENABLED: SmartRoutingConfig = {
+  enabled: true,
+  simpleModel: 'claude-haiku-4-5',
+  strongModel: 'claude-opus-4-7',
+}
+
+describe('routeModel — disabled / misconfigured', () => {
+  test('disabled config routes to strong', () => {
+    const decision = routeModel(
+      { userText: 'hi' },
+      { ...ENABLED, enabled: false },
+    )
+    expect(decision.model).toBe('claude-opus-4-7')
+    expect(decision.complexity).toBe('strong')
+    expect(decision.reason).toContain('disabled')
+  })
+
+  test('missing simpleModel falls back to strong', () => {
+    const decision = routeModel(
+      { userText: 'hi' },
+      { ...ENABLED, simpleModel: '' },
+    )
+    expect(decision.model).toBe('claude-opus-4-7')
+    expect(decision.complexity).toBe('strong')
+  })
+
+  test('simpleModel === strongModel routes to strong (no-op)', () => {
+    const decision = routeModel(
+      { userText: 'hi' },
+      { ...ENABLED, simpleModel: 'claude-opus-4-7' },
+    )
+    expect(decision.model).toBe('claude-opus-4-7')
+    expect(decision.complexity).toBe('strong')
+  })
+})
+
+describe('routeModel — simple path', () => {
+  test('short greeting routes to simple', () => {
+    const decision = routeModel({ userText: 'thanks!', turnNumber: 5 }, ENABLED)
+    expect(decision.model).toBe('claude-haiku-4-5')
+    expect(decision.complexity).toBe('simple')
+  })
+
+  test('empty input routes to simple', () => {
+    const decision = routeModel({ userText: '   ' }, ENABLED)
+    expect(decision.model).toBe('claude-haiku-4-5')
+    expect(decision.complexity).toBe('simple')
+  })
+
+  test('mid-length chatter routes to simple', () => {
+    const decision = routeModel(
+      { userText: 'yep looks good, go ahead', turnNumber: 10 },
+      ENABLED,
+    )
+    expect(decision.complexity).toBe('simple')
+  })
+})
+
+describe('routeModel — strong path', () => {
+  test('first turn always routes to strong, even when short', () => {
+    const decision = routeModel(
+      { userText: 'fix the bug', turnNumber: 1 },
+      ENABLED,
+    )
+    expect(decision.model).toBe('claude-opus-4-7')
+    expect(decision.complexity).toBe('strong')
+    expect(decision.reason).toContain('first turn')
+  })
+
+  test('code fence routes to strong', () => {
+    const decision = routeModel(
+      {
+        userText: 'change this:\n```\nfoo()\n```',
+        turnNumber: 5,
+      },
+      ENABLED,
+    )
+    expect(decision.complexity).toBe('strong')
+    expect(decision.reason).toContain('code')
+  })
+
+  test('inline code span routes to strong', () => {
+    const decision = routeModel(
+      { userText: 'rename `foo` to `bar`', turnNumber: 5 },
+      ENABLED,
+    )
+    expect(decision.complexity).toBe('strong')
+  })
+
+  test('reasoning keyword "plan" routes to strong even when short', () => {
+    const decision = routeModel(
+      { userText: 'plan the refactor', turnNumber: 5 },
+      ENABLED,
+    )
+    expect(decision.complexity).toBe('strong')
+    expect(decision.reason).toContain('keyword')
+  })
+
+  test('reasoning keyword "debug" routes to strong', () => {
+    const decision = routeModel(
+      { userText: 'debug the test', turnNumber: 5 },
+      ENABLED,
+    )
+    expect(decision.complexity).toBe('strong')
+  })
+
+  test('"root cause" multi-word keyword routes to strong', () => {
+    const decision = routeModel(
+      { userText: 'find the root cause', turnNumber: 5 },
+      ENABLED,
+    )
+    expect(decision.complexity).toBe('strong')
+  })
+
+  test('multi-paragraph input routes to strong', () => {
+    const decision = routeModel(
+      {
+        userText: 'first thought.\n\nsecond thought.',
+        turnNumber: 5,
+      },
+      ENABLED,
+    )
+    expect(decision.complexity).toBe('strong')
+    expect(decision.reason).toContain('multi-paragraph')
+  })
+
+  test('over-long input routes to strong', () => {
+    const long = 'ok '.repeat(100) // ~300 chars, 100 words
+    const decision = routeModel(
+      { userText: long, turnNumber: 5 },
+      ENABLED,
+    )
+    expect(decision.complexity).toBe('strong')
+  })
+
+  test('exactly at the boundary stays simple', () => {
+    const text = 'a'.repeat(160)
+    const decision = routeModel(
+      { userText: text, turnNumber: 5 },
+      { ...ENABLED, simpleMaxChars: 160, simpleMaxWords: 28 },
+    )
+    expect(decision.complexity).toBe('simple')
+  })
+
+  test('one char over the boundary routes to strong', () => {
+    const text = 'a'.repeat(161)
+    const decision = routeModel(
+      { userText: text, turnNumber: 5 },
+      { ...ENABLED, simpleMaxChars: 160, simpleMaxWords: 28 },
+    )
+    expect(decision.complexity).toBe('strong')
+    expect(decision.reason).toContain('160 chars')
+  })
+})
+
+describe('routeModel — config overrides', () => {
+  test('custom simpleMaxChars is honored', () => {
+    const decision = routeModel(
+      { userText: 'abcdefghijklmnop', turnNumber: 5 },
+      { ...ENABLED, simpleMaxChars: 10 },
+    )
+    expect(decision.complexity).toBe('strong')
+    expect(decision.reason).toContain('10 chars')
+  })
+
+  test('custom simpleMaxWords is honored', () => {
+    const decision = routeModel(
+      { userText: 'one two three four five', turnNumber: 5 },
+      { ...ENABLED, simpleMaxWords: 3 },
+    )
+    expect(decision.complexity).toBe('strong')
+    expect(decision.reason).toContain('3 words')
+  })
+})
+
+describe('routeModel — reason strings', () => {
+  test('simple decisions include char + word counts', () => {
+    const decision = routeModel(
+      { userText: 'sounds good', turnNumber: 5 },
+      ENABLED,
+    )
+    expect(decision.reason).toMatch(/\d+ chars, \d+ words/)
+  })
+})

src/services/api/smartModelRouting.ts

@@ -0,0 +1,215 @@
+/**
+ * Smart model routing — cheap-for-simple, strong-for-hard.
+ *
+ * For everyday short chatter ("ok", "thanks", "what does this do?") the
+ * incremental quality of Opus/GPT-5 over Haiku/Mini is negligible while the
+ * cost and latency are an order of magnitude worse. Smart routing opts a
+ * user into routing such "obviously simple" turns to a cheaper model while
+ * keeping the strong model for the anything-non-trivial path.
+ *
+ * This module is a pure primitive: it takes a turn description (the user's
+ * text + light context) and returns which model to use, based on config.
+ * It never reads env vars or state directly — caller supplies everything.
+ *
+ * Off by default. Users opt in via settings.smartRouting.enabled. Intent:
+ * make this a copy-paste-small config block rather than a hidden heuristic,
+ * so the tradeoff is visible and the user controls it.
+ */
+
+export type SmartRoutingConfig = {
+  enabled: boolean
+  /** Model to use for turns classified as "simple". */
+  simpleModel: string
+  /** Model to use for turns classified as "strong" (or when unsure). */
+  strongModel: string
+  /** Max characters in user input to qualify as "simple". Default 160. */
+  simpleMaxChars?: number
+  /** Max whitespace-separated words to qualify as "simple". Default 28. */
+  simpleMaxWords?: number
+}
+
+export type RoutingDecision = {
+  model: string
+  complexity: 'simple' | 'strong'
+  /** Human-readable reason — useful for the UI indicator and debug logs. */
+  reason: string
+}
+
+export type RoutingInput = {
+  /** The user's message text for this turn. */
+  userText: string
+  /**
+   * Optional: how many tool-use blocks the assistant has emitted in the
+   * recent conversation. High values correlate with "continue this work"
+   * follow-ups that can still be cheap, UNLESS the user also typed code
+   * or strong-keyword text.
+   */
+  recentToolUses?: number
+  /**
+   * Optional: turn number within the current session (1-indexed). The first
+   * turn is often task-setup and benefits from the strong model even if
+   * short — a bare "build X" opens the whole task.
+   */
+  turnNumber?: number
+}
+
+const DEFAULT_SIMPLE_MAX_CHARS = 160
+const DEFAULT_SIMPLE_MAX_WORDS = 28
+
+// Keywords that strongly suggest reasoning/planning/design work.
+// Matching is word-boundary / case-insensitive. Must include enough anchors
+// that short prompts like "plan the refactor" route to strong even under
+// the char/word cutoff.
+const STRONG_KEYWORDS = [
+  'plan',
+  'design',
+  'architect',
+  'architecture',
+  'refactor',
+  'debug',
+  'investigate',
+  'analyze',
+  'analyse',
+  'implement',
+  'optimize',
+  'optimise',
+  'review',
+  'audit',
+  'diagnose',
+  'root cause',
+  'root-cause',
+  'why does',
+  'why is',
+  'how should',
+  'why did',
+  'propose',
+  'trace',
+  'reproduce',
+]
+
+const STRONG_KEYWORD_RE = new RegExp(
+  `\\b(?:${STRONG_KEYWORDS.map(k => k.replace(/[-]/g, '[-\\s]')).join('|')})\\b`,
+  'i',
+)
+
+const CODE_FENCE_RE = /```[\s\S]*?```|`[^`\n]+`/
+
+function countWords(text: string): number {
+  const trimmed = text.trim()
+  if (!trimmed) return 0
+  return trimmed.split(/\s+/).length
+}
+
+function hasMultiParagraph(text: string): boolean {
+  return /\n\s*\n/.test(text)
+}
+
+function hasCode(text: string): boolean {
+  return CODE_FENCE_RE.test(text)
+}
+
+function hasStrongKeyword(text: string): boolean {
+  return STRONG_KEYWORD_RE.test(text)
+}
+
+/**
+ * Decide whether to route to the simple or strong model based on heuristics.
+ * Returns the chosen model + a reason. When routing is disabled or both
+ * models match, the strong model is used (safe default).
+ */
+export function routeModel(
+  input: RoutingInput,
+  config: SmartRoutingConfig,
+): RoutingDecision {
+  if (!config.enabled) {
+    return {
+      model: config.strongModel,
+      complexity: 'strong',
+      reason: 'smart-routing disabled',
+    }
+  }
+  if (!config.simpleModel || !config.strongModel) {
+    return {
+      model: config.strongModel,
+      complexity: 'strong',
+      reason: 'simpleModel or strongModel missing from config',
+    }
+  }
+  if (config.simpleModel === config.strongModel) {
+    return {
+      model: config.strongModel,
+      complexity: 'strong',
+      reason: 'simpleModel equals strongModel',
+    }
+  }
+
+  const text = input.userText ?? ''
+  const trimmed = text.trim()
+
+  if (!trimmed) {
+    // Empty input (e.g. resuming a tool-use chain) — cheap by default.
+    return {
+      model: config.simpleModel,
+      complexity: 'simple',
+      reason: 'empty user text',
+    }
+  }
+
+  // First turn of a session is task-setup — always use strong.
+  if (input.turnNumber === 1) {
+    return {
+      model: config.strongModel,
+      complexity: 'strong',
+      reason: 'first turn of session',
+    }
+  }
+
+  const maxChars = config.simpleMaxChars ?? DEFAULT_SIMPLE_MAX_CHARS
+  const maxWords = config.simpleMaxWords ?? DEFAULT_SIMPLE_MAX_WORDS
+
+  if (hasCode(trimmed)) {
+    return {
+      model: config.strongModel,
+      complexity: 'strong',
+      reason: 'contains code block or inline code',
+    }
+  }
+
+  if (hasStrongKeyword(trimmed)) {
+    return {
+      model: config.strongModel,
+      complexity: 'strong',
+      reason: 'contains reasoning/planning keyword',
+    }
+  }
+
+  if (hasMultiParagraph(trimmed)) {
+    return {
+      model: config.strongModel,
+      complexity: 'strong',
+      reason: 'multi-paragraph input',
+    }
+  }
+
+  if (trimmed.length > maxChars) {
+    return {
+      model: config.strongModel,
+      complexity: 'strong',
+      reason: `input > ${maxChars} chars`,
+    }
+  }
+
+  if (countWords(trimmed) > maxWords) {
+    return {
+      model: config.strongModel,
+      complexity: 'strong',
+      reason: `input > ${maxWords} words`,
+    }
+  }
+
+  return {
+    model: config.simpleModel,
+    complexity: 'simple',
+    reason: `short (${trimmed.length} chars, ${countWords(trimmed)} words)`,
+  }
+}

src/services/api/thinkTagSanitizer.test.ts

@@ -0,0 +1,183 @@
+import { describe, expect, test } from 'bun:test'
+
+import {
+  createThinkTagFilter,
+  stripThinkTags,
+} from './thinkTagSanitizer.ts'
+
+describe('stripThinkTags — whole-text cleanup', () => {
+  test('strips closed think pair', () => {
+    expect(stripThinkTags('<think>reasoning</think>Hello')).toBe('Hello')
+  })
+
+  test('strips closed thinking pair', () => {
+    expect(stripThinkTags('<thinking>x</thinking>Out')).toBe('Out')
+  })
+
+  test('strips closed reasoning pair', () => {
+    expect(stripThinkTags('<reasoning>x</reasoning>Out')).toBe('Out')
+  })
+
+  test('strips REASONING_SCRATCHPAD pair', () => {
+    expect(stripThinkTags('<REASONING_SCRATCHPAD>plan</REASONING_SCRATCHPAD>Answer'))
+      .toBe('Answer')
+  })
+
+  test('is case-insensitive', () => {
+    expect(stripThinkTags('<THINKING>x</THINKING>out')).toBe('out')
+    expect(stripThinkTags('<Think>x</Think>out')).toBe('out')
+  })
+
+  test('handles attributes on open tag', () => {
+    expect(stripThinkTags('<think id="plan-1">reason</think>ok')).toBe('ok')
+  })
+
+  test('strips unterminated open tag at block boundary', () => {
+    expect(stripThinkTags('<think>reasoning that never closes')).toBe('')
+  })
+
+  test('strips unterminated open tag after newline', () => {
+    // Block-boundary match consumes the leading newline, same as hermes.
+    expect(stripThinkTags('Answer: 42\n<think>second-guess myself'))
+      .toBe('Answer: 42')
+  })
+
+  test('strips orphan close tag', () => {
+    expect(stripThinkTags('trailing </think>done')).toBe('trailing done')
+  })
+
+  test('strips multiple blocks', () => {
+    expect(stripThinkTags('<think>a</think>B<think>c</think>D')).toBe('BD')
+  })
+
+  test('handles reasoning mid-response after content', () => {
+    expect(stripThinkTags('Answer: 42\n<think>double-check</think>\nDone'))
+      .toBe('Answer: 42\n\nDone')
+  })
+
+  test('handles nested-looking tags (lazy match + orphan cleanup)', () => {
+    expect(stripThinkTags('<think><think>x</think></think>y')).toBe('y')
+  })
+
+  test('preserves legitimate non-think tags', () => {
+    expect(stripThinkTags('use <div> and <span>')).toBe('use <div> and <span>')
+  })
+
+  test('preserves text without any tags', () => {
+    expect(stripThinkTags('Hello, world. I should respond briefly.')).toBe(
+      'Hello, world. I should respond briefly.',
+    )
+  })
+
+  test('handles empty input', () => {
+    expect(stripThinkTags('')).toBe('')
+  })
+})
+
+describe('createThinkTagFilter — streaming state machine', () => {
+  test('passes through plain text', () => {
+    const f = createThinkTagFilter()
+    expect(f.feed('Hello, ')).toBe('Hello, ')
+    expect(f.feed('world!')).toBe('world!')
+    expect(f.flush()).toBe('')
+  })
+
+  test('strips a complete think block in one chunk', () => {
+    const f = createThinkTagFilter()
+    expect(f.feed('pre<think>reason</think>post')).toBe('prepost')
+    expect(f.flush()).toBe('')
+  })
+
+  test('handles open tag split across deltas', () => {
+    const f = createThinkTagFilter()
+    expect(f.feed('before<th')).toBe('before')
+    expect(f.feed('ink>reason</think>after')).toBe('after')
+    expect(f.flush()).toBe('')
+  })
+
+  test('handles close tag split across deltas', () => {
+    const f = createThinkTagFilter()
+    expect(f.feed('<think>reason</th')).toBe('')
+    expect(f.feed('ink>keep')).toBe('keep')
+    expect(f.flush()).toBe('')
+  })
+
+  test('handles tag split on bare < boundary', () => {
+    const f = createThinkTagFilter()
+    expect(f.feed('leading <')).toBe('leading ')
+    expect(f.feed('think>inner</think>tail')).toBe('tail')
+    expect(f.flush()).toBe('')
+  })
+
+  test('preserves partial non-tag < at boundary when next char rules it out', () => {
+    const f = createThinkTagFilter()
+    // "<d" — 'd' cannot start any of our tag names, so emit immediately
+    expect(f.feed('pre<d')).toBe('pre<d')
+    expect(f.feed('iv>rest')).toBe('iv>rest')
+    expect(f.flush()).toBe('')
+  })
+
+  test('case-insensitive streaming', () => {
+    const f = createThinkTagFilter()
+    expect(f.feed('<THINKING>x</THINKING>out')).toBe('out')
+    expect(f.flush()).toBe('')
+  })
+
+  test('unterminated open tag — flush drops remainder', () => {
+    const f = createThinkTagFilter()
+    expect(f.feed('<think>reasoning with no close ')).toBe('')
+    expect(f.feed('and more reasoning')).toBe('')
+    expect(f.flush()).toBe('')
+    expect(f.isInsideBlock()).toBe(false)
+  })
+
+  test('multiple blocks in single feed', () => {
+    const f = createThinkTagFilter()
+    expect(f.feed('<think>a</think>B<think>c</think>D')).toBe('BD')
+    expect(f.flush()).toBe('')
+  })
+
+  test('flush after clean stream emits nothing extra', () => {
+    const f = createThinkTagFilter()
+    expect(f.feed('complete message')).toBe('complete message')
+    expect(f.flush()).toBe('')
+  })
+
+  test('flush of bare < at end emits it (not a tag prefix)', () => {
+    const f = createThinkTagFilter()
+    // bare '<' held back; flush emits it since it has no tag-name chars
+    expect(f.feed('x <')).toBe('x ')
+    expect(f.flush()).toBe('<')
+  })
+
+  test('flush of partial tag-name prefix at end drops it', () => {
+    const f = createThinkTagFilter()
+    expect(f.feed('x <thi')).toBe('x ')
+    expect(f.flush()).toBe('')
+  })
+
+  test('handles attributes on streaming open tag', () => {
+    const f = createThinkTagFilter()
+    expect(f.feed('<think type="plan">reason</think>ok')).toBe('ok')
+    expect(f.flush()).toBe('')
+  })
+
+  test('mid-delta transition: content, reasoning, content', () => {
+    const f = createThinkTagFilter()
+    expect(f.feed('Answer: 42\n<think>')).toBe('Answer: 42\n')
+    expect(f.feed('double-check')).toBe('')
+    expect(f.feed('</think>\nDone')).toBe('\nDone')
+    expect(f.flush()).toBe('')
+  })
+
+  test('orphan close tag mid-stream is stripped on flush via safety-net behavior', () => {
+    // Filter alone treats orphan close as "we're not inside", so it emits as-is.
+    // Safety net (stripThinkTags on final text) removes orphans.
+    const f = createThinkTagFilter()
+    const chunk1 = f.feed('trailing ')
+    const chunk2 = f.feed('</think>done')
+    const final = chunk1 + chunk2 + f.flush()
+    // Orphan close appears in stream output; safety net cleans it
+    expect(stripThinkTags(final)).toBe('trailing done')
+  })
+})

src/services/api/thinkTagSanitizer.ts

@@ -0,0 +1,162 @@
+/**
+ * Think-tag sanitizer for reasoning content leaks.
+ *
+ * Some OpenAI-compatible reasoning models (MiniMax M2.7, GLM-4.5/5, DeepSeek, Kimi K2,
+ * self-hosted vLLM builds) emit chain-of-thought inline inside the `content` field using
+ * XML-like tags instead of the separate `reasoning_content` channel. Example:
+ *
+ *   <think>the user wants foo, let me check bar</think>Here is the answer: ...
+ *
+ * This module strips those blocks structurally (tag-based), independent of English
+ * phrasings. Three layers:
+ *
+ *   1. `createThinkTagFilter()` — streaming state machine. Feeds deltas, emits only
+ *      the visible (non-reasoning) portion, and buffers partial tags across chunk
+ *      boundaries so `</th` + `ink>` still parses correctly.
+ *
+ *   2. `stripThinkTags()` — whole-text cleanup. Removes closed pairs, unterminated
+ *      opens at block boundaries, and orphan open/close tags. Used for non-streaming
+ *      responses and as a safety net after stream close.
+ *
+ *   3. Flush discards buffered partial tags at stream end (false-negative bias —
+ *      prefer losing a partial reasoning fragment over leaking it).
+ */
+
+const TAG_NAMES = [
+  'think',
+  'thinking',
+  'reasoning',
+  'thought',
+  'reasoning_scratchpad',
+] as const
+
+const TAG_ALT = TAG_NAMES.join('|')
+
+const OPEN_TAG_RE = new RegExp(`<\\s*(?:${TAG_ALT})\\b[^>]*>`, 'i')
+const CLOSE_TAG_RE = new RegExp(`<\\s*/\\s*(?:${TAG_ALT})\\s*>`, 'i')
+
+const CLOSED_PAIR_RE_G = new RegExp(
+  `<\\s*(${TAG_ALT})\\b[^>]*>[\\s\\S]*?<\\s*/\\s*\\1\\s*>`,
+  'gi',
+)
+const UNTERMINATED_OPEN_RE = new RegExp(
+  `(?:^|\\n)[ \\t]*<\\s*(?:${TAG_ALT})\\b[^>]*>[\\s\\S]*$`,
+  'i',
+)
+const ORPHAN_TAG_RE_G = new RegExp(
+  `<\\s*/?\\s*(?:${TAG_ALT})\\b[^>]*>\\s*`,
+  'gi',
+)
+
+const MAX_PARTIAL_TAG = 64
+
+/**
+ * Remove reasoning/thinking blocks from a complete text body.
+ *
+ * Handles:
+ *   - Closed pairs: <think>...</think> (lazy match, anywhere in text)
+ *   - Unterminated open tags at a block boundary: strips from the tag to end of string
+ *   - Orphan open or close tags (no matching partner)
+ *
+ * False-negative bias: prefers leaving a few tag characters in rare edge cases over
+ * stripping legitimate content.
+ */
+export function stripThinkTags(text: string): string {
+  if (!text) return text
+  let out = text
+  out = out.replace(CLOSED_PAIR_RE_G, '')
+  out = out.replace(UNTERMINATED_OPEN_RE, '')
+  out = out.replace(ORPHAN_TAG_RE_G, '')
+  return out
+}
+
+export interface ThinkTagFilter {
+  feed(chunk: string): string
+  flush(): string
+  isInsideBlock(): boolean
+}
+
+/**
+ * Streaming state machine. Feed deltas, emits visible (non-reasoning) text.
+ * Handles tags split across chunk boundaries by holding back a short tail buffer
+ * whenever the current buffer ends with what looks like a partial tag.
+ */
+export function createThinkTagFilter(): ThinkTagFilter {
+  let inside = false
+  let buffer = ''
+
+  function findPartialTagStart(s: string): number {
+    const lastLt = s.lastIndexOf('<')
+    if (lastLt === -1) return -1
+    if (s.indexOf('>', lastLt) !== -1) return -1
+    const tail = s.slice(lastLt)
+    if (tail.length > MAX_PARTIAL_TAG) return -1
+
+    const m = /^<\s*\/?\s*([a-zA-Z_]\w*)?\s*$/.exec(tail)
+    if (!m) return -1
+    const partialName = (m[1] ?? '').toLowerCase()
+    if (!partialName) return lastLt
+    if (TAG_NAMES.some(name => name.startsWith(partialName))) return lastLt
+    return -1
+  }
+
+  function feed(chunk: string): string {
+    if (!chunk) return ''
+    buffer += chunk
+    let out = ''
+
+    while (buffer.length > 0) {
+      if (!inside) {
+        const open = OPEN_TAG_RE.exec(buffer)
+        if (open) {
+          out += buffer.slice(0, open.index)
+          buffer = buffer.slice(open.index + open[0].length)
+          inside = true
+          continue
+        }
+
+        const partialStart = findPartialTagStart(buffer)
+        if (partialStart === -1) {
+          out += buffer
+          buffer = ''
+        } else {
+          out += buffer.slice(0, partialStart)
+          buffer = buffer.slice(partialStart)
+        }
+        return out
+      }
+
+      const close = CLOSE_TAG_RE.exec(buffer)
+      if (close) {
+        buffer = buffer.slice(close.index + close[0].length)
+        inside = false
+        continue
+      }
+
+      const partialStart = findPartialTagStart(buffer)
+      if (partialStart === -1) {
+        buffer = ''
+      } else {
+        buffer = buffer.slice(partialStart)
+      }
+      return out
+    }
+
+    return out
+  }
+
+  function flush(): string {
+    const held = buffer
+    const wasInside = inside
+    buffer = ''
+    inside = false
+
+    if (wasInside) return ''
+    if (!held) return ''
+
+    if (/^<\s*\/?\s*[a-zA-Z_]/.test(held)) return ''
+    return held
+  }
+
+  return { feed, flush, isInsideBlock: () => inside }
+}

src/services/autoFix/autoFixRunner.test.ts

@@ -70,7 +70,7 @@ describe('runAutoFixCheck', () => {
 
   test('handles timeout gracefully', async () => {
     const result = await runAutoFixCheck({
-      lint: 'sleep 10',
+      lint: 'node -e "setTimeout(() => {}, 10000)"',
       timeout: 100,
 
       cwd: '/tmp',