1. Enforce maxRetries: track auto-fix attempts per query chain in toolHooks.ts
and stop feeding errors back after the configured limit is reached.
2. Wire abort signal to subprocess: subscribe to AbortController signal in
runCommand() and kill the process tree on abort. Uses detached process
groups on Unix to ensure child processes are also terminated.
3. Replace hardcoded bash with shell:true: use Node's cross-platform shell
resolution instead of spawn('bash', ['-c', ...]) so auto-fix commands
work on Windows and non-bash environments.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add auto-fix lint/test check after existing PostToolUse hooks in
runPostToolUseHooks. When autoFix is configured in settings, runs
lint/test commands after file_edit/file_write tools and yields
errors as hook_additional_context for the model to act on.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Implements shouldRunAutoFix and buildAutoFixContext functions used by
the PostToolUse hook to determine when to run auto-fix and format
errors as AI-readable context for injection.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Integrates AutoFixConfigSchema into SettingsSchema so autoFix settings
are validated at the settings layer. Adds two integration tests verifying
that valid configs are accepted and invalid configs (enabled with no
commands) are rejected.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Implements AutoFixConfigSchema (Zod v4) with validation for lint/test
commands, maxRetries (0-10, default 3), and timeout (1000-300000ms,
default 30000). Adds getAutoFixConfig helper that returns null for
disabled or invalid configs. All 9 unit tests pass.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The select cursor highlight was broken because isDeepStrictEqual in
use-select-navigation.ts and use-multi-select-state.ts would fail when
options contained identity-unstable properties (JSX label elements,
function onChange callbacks, computed disabled booleans). This caused
the reset logic to fire on every re-render, resetting focusedValue
back to the first option.
Replace isDeepStrictEqual with optionsNavigateEqual which only compares
properties that affect navigation behavior: value, disabled, and type.
ReactNode labels and function callbacks are intentionally excluded as
they are identity-unstable but don't change navigation semantics.
Fixes#472
Co-authored-by: OpenClaude Worker 3 <worker-3@openclaude.local>
Fixes#430. In normalizeSchemaForOpenAI(), the strict branch was adding every
property key to required[], including optional ones. This caused providers like
Groq, Azure OpenAI, and others to reject valid tool calls with a 400 /
tool_use_failed error because the model correctly omits optional arguments but
the provider sees them as missing required fields.
Root cause: the strict branch used `[...existingRequired, ...allKeys]` instead
of `existingRequired.filter(k => k in normalizedProps)`. The Gemini branch
already had the correct logic.
Fix: align the strict branch with the Gemini branch — only keep properties that
were already marked required in the original schema. The additionalProperties:
false constraint is preserved as strict-mode providers still require it.
Add regression test covering the Read tool schema (file_path required,
offset/limit/pages optional).
* fix: defer startup plugin checks and suppress recommendation dialogs during startup window (issue #363)
Root cause: performStartupChecks() fires immediately on REPL mount,
triggering plugin loading which populates trackedFiles, which triggers
useLspPluginRecommendation to surface an LSP recommendation dialog.
Since promptTypingSuppressionActive is false before any user input,
getFocusedInputDialog() returns the dialog, unmounting PromptInput
entirely and making the CLI appear frozen.
Fix: Two-pronged approach:
1. Defer performStartupChecks by 1500ms and gate on
promptTypingSuppressionActive so startup checks dont run while
the user is typing or has early input buffered
2. Suppress lower-priority startup dialogs (LSP recommendation,
plugin hint, desktop upsell) until startupChecksStartedRef is
true, preventing them from stealing focus during the vulnerable
startup window
This also explains why --bare mode and disabling plugins work:
--bare mode skips plugin loading entirely, and disabling the
autoresearch plugin eliminates the LSP match, so lspRecommendation
stays null and PromptInput renders normally.
* fix: move startup checks effect after promptTypingSuppressionActive declaration
Fixes temporal dead zone warning flagged by code-quality bot.
promptTypingSuppressionActive is declared on line ~1340 but the
useEffect was on line ~800, causing a reference-before-declaration.
Also adds missing semicolons for style consistency.
* fix: gate startup checks on prompt readiness, not just a timeout (issue #363)
The previous approach used a fixed 1500ms timeout, but as gnanam1990
pointed out, if a user pauses for >1.5s before typing the timer can
still fire and recommendation dialogs can steal focus. This is a
timing mitigation, not a reliable fix.
New approach: gate startup checks on actual prompt readiness:
1. After first message submission (submitCount > 0) — always safe
2. After grace period (3s) elapsed AND user is idle — safe because
no dialog will interrupt an idle user who hasn't started typing
3. While user is actively typing — deferrred until they stop
This ensures startup checks never steal focus from a prompt the user
is about to type into, regardless of how long they pause before typing.
Also removes the old STARTUP_CHECK_DELAY_MS constant in favor of
STARTUP_GRACE_PERIOD_MS with clearer semantics.
* fix: move startup checks after submitCount declaration to avoid temporal dead zone
Code quality bot flagged that submitCount was used before its declaration.
Moved the entire startup checks block to after the submitCount useState
declaration. Also added nullish coalescing (submitCount ?? 0) per bot
suggestion.
* fix: gate startup checks strictly on first submission, remove grace period (issue #363)
As gnanam1990 pointed out, the 3s grace period still allows the failure
mode: if a user pauses for a few seconds before typing, startup checks
fire and recommendation dialogs steal focus. A grace period is still a
timing mitigation, not a reliable fix.
New approach: startup checks only run after the user has submitted their
first message (submitCount > 0). No grace period, no timeout. This
guarantees the prompt gets first interaction — no dialog can steal focus
before the user has actually used the CLI.
If the user never submits a message, startup checks never run. That's
acceptable because with no user interaction there's no need for plugin
installations or marketplace seeding.
---------
Co-authored-by: OpenClaude Worker 3 <worker-3@openclaude.local>
* update gitHub copilot API with offical client id and update model configurations
* test: add unit tests for exchangeForCopilotToken and enhance GitHub model normalization
* remove PAT token feature
* test(api): harden provider tests against env leakage
* Added back trimmed github auth token
* added auto refresh logic for auto token along with test
* fix: remove forked provider validation in cli.tsx and clear stale provider env vars in /onboard-github
* refactor: streamline environment variable handling in mergeUserSettingsEnv
* fix: clear stale provider env vars to ensure correct GH routing
* Remove internal-only tooling from the external build (#352)
* Remove internal-only tooling without changing external runtime contracts
This trims the lowest-risk internal-only surfaces first: deleted internal
modules are replaced by build-time no-op stubs, the bundled stuck skill is
removed, and the insights S3 upload path now stays local-only. The privacy
verifier is expanded and the remaining bundled internal Slack/Artifactory
strings are neutralized without broad repo-wide renames.
Constraint: Keep the first PR deletion-heavy and avoid mass rewrites of USER_TYPE, tengu, or claude_code identifiers
Rejected: One-shot DMCA cleanup branch | too much semantic risk for a first PR
Confidence: medium
Scope-risk: moderate
Reversibility: clean
Directive: Treat full-repo typecheck as a baseline issue on this upstream snapshot; do not claim this commit introduced the existing non-Phase-A errors without isolating them first
Tested: bun run build
Tested: bun run smoke
Tested: bun run verify:privacy
Not-tested: Full repo typecheck (currently fails on widespread pre-existing upstream errors outside this change set)
* Keep minimal source shims so CI can import Phase A cleanup paths
The first PR removed internal-only source files entirely, but CI provider
and context tests import those modules directly from source rather than
through the build-time no-telemetry stubs. This restores tiny no-op source
shims so tests and local source imports resolve while preserving the same
external runtime behavior.
Constraint: GitHub Actions runs source-level tests in addition to bundled build/privacy checks
Rejected: Revert the entire deletion pass | unnecessary once the import contract is satisfied by small shims
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: For later cleanup phases, treat build-time stubs and source-test imports as separate compatibility surfaces
Tested: bun run build
Tested: bun run smoke
Tested: bun run verify:privacy
Tested: bun run test:provider
Tested: bun run test:provider-recommendation
Not-tested: Full repo typecheck (still noisy on this upstream snapshot)
---------
Co-authored-by: anandh8x <test@example.com>
* Reduce internal-only labeling noise in source comments (#355)
This pass rewrites comment-only ANT-ONLY markers to neutral internal-only
language across the source tree without changing runtime strings, flags,
commands, or protocol identifiers. The goal is to lower obvious internal
prose leakage while keeping the diff mechanically safe and easy to review.
Constraint: Phase B is limited to comments/prose only; runtime strings and user-facing labels remain deferred
Rejected: Broad search-and-replace across strings and command descriptions | too risky for a prose-only pass
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Remaining ANT-ONLY hits are mostly runtime/user-facing strings and should be handled separately from comment cleanup
Tested: bun run build
Tested: bun run smoke
Tested: bun run verify:privacy
Tested: bun run test:provider
Tested: bun run test:provider-recommendation
Not-tested: Full repo typecheck (upstream baseline remains noisy)
Co-authored-by: anandh8x <test@example.com>
* Neutralize internal Anthropic prose in explanatory comments (#357)
This is a small prose-only follow-up that rewrites clearly internal or
explanatory Anthropic comment language to neutral wording in a handful of
high-confidence files. It avoids runtime strings, flags, command labels,
protocol identifiers, and provider-facing references.
Constraint: Keep this pass narrowly scoped to comments/documentation only
Rejected: Broader Anthropic comment sweep across functional API/protocol references | too ambiguous for a safe prose-only PR
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Leave functional Anthropic references (API behavior, SDKs, URLs, provider labels, protocol docs) for separate reviewed passes
Tested: bun run build
Tested: bun run smoke
Tested: bun run verify:privacy
Tested: bun run test:provider
Tested: bun run test:provider-recommendation
Not-tested: Full repo typecheck (upstream baseline remains noisy)
Co-authored-by: anandh8x <test@example.com>
* Neutralize remaining internal-only diagnostic labels (#359)
This pass rewrites a small set of ant-only diagnostic and UI labels to
neutral internal wording while leaving command definitions, flags, and
runtime logic untouched. It focuses on internal debug output, dead UI
branches, and noninteractive headings rather than broader product text.
Constraint: Label cleanup only; do not change command semantics or ant-only logic gates
Rejected: Renaming ant-only command descriptions in main.tsx | broader UX surface better handled in a separate reviewed pass
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Remaining ANT-ONLY hits are mostly command descriptions and intentionally deferred user-facing strings
Tested: bun run build
Tested: bun run smoke
Tested: bun run verify:privacy
Tested: bun run test:provider
Tested: bun run test:provider-recommendation
Not-tested: Full repo typecheck (upstream baseline remains noisy)
Co-authored-by: anandh8x <test@example.com>
* Finish eliminating remaining ANT-ONLY source labels (#360)
This extends the label-only cleanup to the remaining internal-only command,
debug, and heading strings so the source tree no longer contains ANT-ONLY
markers. The pass still avoids logic changes and only renames labels shown
in internal or gated surfaces.
Constraint: Update the existing label-cleanup PR without widening scope into behavior changes
Rejected: Leave the last ANT-ONLY strings for a later pass | low-cost cleanup while the branch is already focused on labels
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: The next phase should move off label cleanup and onto a separately scoped logic or rebrand slice
Tested: bun run build
Tested: bun run smoke
Tested: bun run verify:privacy
Tested: bun run test:provider
Tested: bun run test:provider-recommendation
Not-tested: Full repo typecheck (upstream baseline remains noisy)
Co-authored-by: anandh8x <test@example.com>
* Stub internal-only recording and model capability helpers (#377)
This follow-up Phase C-lite slice replaces purely internal helper modules
with stable external no-op surfaces and collapses internal elevated error
logging to a no-op. The change removes additional USER_TYPE-gated helper
behavior without touching product-facing runtime flows.
Constraint: Keep this PR limited to isolated helper modules that are already external no-ops in practice
Rejected: Pulling in broader speculation or logging sink changes | less isolated and easier to debate during review
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Continue Phase C with similarly isolated helpers before moving into mixed behavior files
Tested: bun run build
Tested: bun run smoke
Tested: bun run verify:privacy
Tested: bun run test:provider
Tested: bun run test:provider-recommendation
Not-tested: Full repo typecheck (upstream baseline remains noisy)
Co-authored-by: anandh8x <test@example.com>
* Remove internal-only bundled skills and mock helpers (#376)
* Remove internal-only bundled skills and mock rate-limit behavior
This takes the next planned Phase C-lite slice by deleting bundled skills
that only ever registered for internal users and replacing the internal
mock rate-limit helper with a stable no-op external stub. The external
build keeps the same behavior while removing a concentrated block of
USER_TYPE-gated dead code.
Constraint: Limit this PR to isolated internal-only helpers and avoid bridge, oauth, or rebrand behavior
Rejected: Broad USER_TYPE cleanup across mixed runtime surfaces | too risky for the next medium-sized PR
Confidence: high
Scope-risk: moderate
Reversibility: clean
Directive: The next cleanup pass should continue with similarly isolated USER_TYPE helpers before touching main.tsx or protocol-heavy code
Tested: bun run build
Tested: bun run smoke
Tested: bun run verify:privacy
Tested: bun run test:provider
Tested: bun run test:provider-recommendation
Not-tested: Full repo typecheck (upstream baseline remains noisy)
* Align internal-only helper removal with remaining user guidance
This follow-up fixes the mock billing stub to be a true no-op and removes
stale user-facing references to /verify and /skillify from the same PR.
It also leaves a clearer paper trail for review: the deleted verify skill
was explicitly ant-gated before removal, and the remaining mock helper
callers still resolve to safe no-op returns in the external build.
Constraint: Keep the PR focused on consistency fixes and reviewer-requested evidence, not new cleanup scope
Rejected: Leave stale guidance for a later PR | would make this branch internally inconsistent after skill removal
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: When deleting gated features, always sweep user guidance and coordinator prompts in the same pass
Tested: bun run build
Tested: bun run smoke
Tested: bun run verify:privacy
Tested: bun run test:provider
Tested: bun run test:provider-recommendation
Not-tested: Full repo typecheck (upstream baseline remains noisy; changed-file scan still shows only pre-existing tipRegistry errors outside edited lines)
* Clarify generic workflow wording after skill removal
This removes the last generic verification-skill wording that could still
be read as pointing at a deleted bundled command. The guidance now talks
about project workflows rather than a specific bundled verify skill.
Constraint: Keep the follow-up limited to reviewer-facing wording cleanup on the same PR
Rejected: Leave generic wording as-is | still too easy to misread after the explicit /verify references were removed
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: When removing bundled commands, scrub both explicit and generic references in the same branch
Tested: bun run build
Tested: bun run smoke
Not-tested: Additional checks unchanged by wording-only follow-up
---------
Co-authored-by: anandh8x <test@example.com>
* test(api): add GEMINI_AUTH_MODE to environment setup in tests
* test: isolate GitHub/Gemini credential tests with fresh module imports and explicit non-bare env setup to prevent cross-test mock/cache leaks
* fix: update GitHub Copilot base URL and model defaults for improved compatibility
* fix: enhance error handling in OpenAI API response processing
* fix: improve error handling for GitHub Copilot API responses and streamline error body consumption
* fix: enhance response handling in OpenAI API shim for better error reporting and support for streaming responses
* feat: enhance GitHub device flow with fresh module import and token validation improvements
* fix: separate Copilot API routing from GitHub Models, clear stale env vars, honor providerOverride.apiKey
* fix: route GitHub GPT-5/Codex to Copilot API, show all Copilot models in picker, clear stale env vars
* fix GitHub Models API regression
* feat: update GitHub authentication to require OAuth tokens, normalize model handling for Copilot and GitHub Models
* fix: update GitHub token validation to support OAuth tokens and improve endpoint type handling
---------
Co-authored-by: Anandan <anandan.8x@gmail.com>
Co-authored-by: anandh8x <test@example.com>
* fix: strip Anthropic-specific params from 3P provider paths
Three silent failure modes affecting all third-party provider users:
1. Thinking blocks serialized as <thinking> text corrupt multi-turn
context — strip them instead of converting to raw text tags.
2. Unknown models fall through to 200k context window default, so
auto-compact never triggers — use conservative 8k for unknown
3P models with a warning log.
3. Session resume with thinking blocks causes 400 or context corruption
on 3P providers — strip thinking/redacted_thinking content blocks
from deserialized messages when resuming against a non-Anthropic
provider.
Addresses findings 2, 3, and 5 from #248.
* test: align resume stripping expectation with orphan-thinking filter
* test: isolate provider env in conversation recovery tests
* test: move provider-sensitive resume coverage behind module mocks
* test: trim extra blank lines in conversation recovery test
Keep the focused provider-resume test diff clean so the regression branch stays easy to review.
Co-Authored-By: Claude Opus 4.6 <noreply@openclaude.dev>
---------
Co-authored-by: Claude Opus 4.6 <noreply@openclaude.dev>
* fix: restore Grep and Glob reliability on OpenAI paths
Preserve Grep and Glob pattern fields during OpenAI/Codex schema sanitization, and fall back to system ripgrep when the packaged binary is missing. This keeps search tool schemas intact and improves Linux usability for npm/source installs.
Co-Authored-By: Claude Opus 4.6 <noreply@openclaude.dev>
* test: clean up ripgrep fallback test helpers
Remove the unused ripgrepCommand import and normalize mocked builtin ripgrep paths so the test behaves consistently across platforms.
Co-Authored-By: Claude Opus 4.6 <noreply@openclaude.dev>
* test: remove duplicate Codex URI schema case
Drop the duplicated WebFetch URI-format test in codexShim.test.ts so test names stay unique and failures remain easier to read.
Co-Authored-By: Claude Opus 4.6 <noreply@openclaude.dev>
* test: stabilize ripgrep fallback coverage
Avoid fs/module mocking in ripgrep fallback tests by extracting the config selection logic into a pure helper. This preserves the fallback coverage while removing the test interaction that caused the narrowed Bun hang repro.
Co-Authored-By: Claude Opus 4.6 <noreply@openclaude.dev>
* test: tighten ripgrep and schema coverage
Align the ripgrep fallback test with the actual auto-fallback branch, clean up strict typing in schema sanitizer tests, and tighten ripgrep error narrowing for type safety.
Co-Authored-By: Claude Opus 4.6 <noreply@openclaude.dev>
---------
Co-authored-by: Claude Opus 4.6 <noreply@openclaude.dev>
* fix: address code scanning alerts
Parse Gemini hostnames instead of matching raw URL substrings, redact gRPC error logs, and harden the Finder drag-drop test escape helper so the flagged paths are fixed without regressing working behavior.
* Potential fix for pull request finding 'CodeQL / Clear-text logging of sensitive information'
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* fix: restore safe grpc error summaries
A later autofix commit removed the exported gRPC error summarizer while the new regression test still imported it. Restore the safe name/code-only summary so CI stays green without reintroducing clear-text logging.
* fix: keep grpc logging generic
Remove the stale helper/test pair and keep the gRPC startup and stream logs free of error-derived data so the CodeQL clear-text logging alert stays closed while the rest of the security fixes remain intact.
---------
Co-authored-by: OpenClaude Worker 3 <worker-3@openclaude.local>
Co-authored-by: Vasanth T <148849890+Vasanthdev2004@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
When a proxy is configured, configureGlobalAgents() loads undici to set a
global dispatcher. However, undici v7.24.6 requires Node.js >= 20.18.1 and
references globalThis.File at module evaluation time for webidl type assertions.
Node 18 lacks the File global, causing ReferenceError inside the bundled
__commonJS require chain, which deadlocks due to unresolved circular
dependencies in the module initialization.
Fix by polyfilling globalThis.File early in cli.tsx entrypoint, before any
undici code loads. Try node:buffer.File (available in Node 18.13+), fallback
to minimal Blob-based stub.
Fixes: bun run start hangs indefinitely when HTTP_PROXY/HTTPS_PROXY is set
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: address code scanning alerts
Parse Gemini hostnames instead of matching raw URL substrings, redact gRPC error logs, and harden the Finder drag-drop test escape helper so the flagged paths are fixed without regressing working behavior.
* Potential fix for pull request finding 'CodeQL / Clear-text logging of sensitive information'
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* fix: restore safe grpc error summaries
A later autofix commit removed the exported gRPC error summarizer while the new regression test still imported it. Restore the safe name/code-only summary so CI stays green without reintroducing clear-text logging.
* fix: keep grpc logging generic
Remove the stale helper/test pair and keep the gRPC startup and stream logs free of error-derived data so the CodeQL clear-text logging alert stays closed while the rest of the security fixes remain intact.
---------
Co-authored-by: OpenClaude Worker 3 <worker-3@openclaude.local>
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
## Summary
- Added `isCompactableTool()` helper in `microCompact.ts` that matches
both the existing COMPACTABLE_TOOLS set and any tool prefixed `mcp__`
- MCP tool results were never compacted because the hardcoded allowlist
only contained 9 built-in tools — MCP tools fell through and persisted
in full for the entire session, wasting 10-500K tokens/session
## Impact
- user-facing impact: long sessions using MCP servers (GitHub, Slack,
Playwright, etc.) will compact stale MCP tool results, reducing token
usage and delaying autocompact triggers
- developer/maintainer impact: new MCP servers are automatically covered
via prefix match — no need to update the allowlist per-server
## Testing
- [x] `bun run build`
- [x] `bun run smoke`
- [x] focused tests: `bun test src/services/compact/microCompact.test.ts`
- module exports load correctly
- estimateMessageTokens counts MCP tool_use blocks
- microcompactMessages processes MCP tools without error
- microcompactMessages processes mixed built-in and MCP tools
## Notes
- provider/model path tested: n/a (compaction logic is model-agnostic)
- screenshots attached (if UI changed): n/a
- follow-up work or known limitations: subagent results and thinking
blocks are still not compacted (separate RFCs)
https://claude.ai/code/session_01D7kprMn4c66a5WrZscF7rv
Co-authored-by: Claude <noreply@anthropic.com>
* fix: normalize malformed Bash tool arguments from OpenAI-compatible providers
* fix: keep invalid Bash tool args from becoming commands
* fix: preserve malformed Bash JSON literals
* test: stabilize rebased PR 385 checks
* test: isolate provider profile env assertions
* fix: extend tool argument normalization to all tools and harden edge cases
- Extend STRING_ARGUMENT_TOOL_FIELDS to normalize Read, Write, Edit,
Glob, and Grep plain-string arguments (fixes "Invalid tool parameters"
errors reported by VennDev)
- Normalize streaming Bash args regardless of finish_reason, not only
when finish_reason is 'tool_calls'
- Broaden isLikelyStructuredObjectLiteral to catch malformed object-shaped
strings like {command:"pwd"} and {'command':'pwd'} (fixes CR2 from
Vasanthdev2004)
- Apply blank/object-literal guard to all tools, not just Bash
- Extract duplicated JSON repair suffix combinations into shared constant
- Add 32 isolated unit tests for toolArgumentNormalization
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: skip streaming normalization on finish_reason length
Truncated tool calls (finish_reason: 'length') now preserve the raw
buffer instead of normalizing into executable commands, preventing
incomplete commands from becoming runnable.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: comprehensive tool argument normalization hardening
- Remove all { raw: ... } returns that caused InputValidationError with
z.strictObject schemas — return {} instead for clean Zod errors
- Extend normalizeAtStop buffering to all mapped tools (Read, Write,
Edit, Glob, Grep) so streaming paths also get normalized
- Make repairPossiblyTruncatedObjectJson generic — repair any valid
JSON object, not just ones with a command field
- Export hasToolFieldMapping for streaming normalizeAtStop decision
- Skip normalization on finish_reason: length to preserve raw truncated
buffer
- Update all test expectations to match new behavior
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* Fix GLM-5 and other reasoning models appearing to hang via OpenAI shim
Reasoning models like GLM-5 and DeepSeek stream chain-of-thought in
`reasoning_content` while `content` stays empty (""). The OpenAI shim
only read `delta.content`, so it saw empty strings and never emitted
any Anthropic stream events — causing the UI to appear frozen.
- Add `reasoning_content` to streaming chunk and non-streaming response types
- Emit `reasoning_content` as thinking blocks (thinking_delta) in streaming mode
- Properly transition from thinking to text blocks when content phase begins
- Fall back to `reasoning_content` in non-streaming mode when content is null
Fixes#214
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Fix non-streaming reasoning_content fallback and add tests
- Use explicit empty-string check instead of || for content fallback
so content: "" doesn't leak reasoning_content as visible text
- Close thinking block before tool call blocks in streaming path
- Add non-streaming and streaming reasoning_content tests
Co-Authored-By: GLM-5.1 <noreply@openclaude.dev>
* Fix flaky Ink reconciler tests caused by react-compiler memoization
Remove hard throw in createTextInstance that crashed when hostContext.isInsideText
was stale due to react-compiler element caching. Add timeout guards to prevent
test hangs when render errors prevent exit() from firing.
Co-Authored-By: Claude GLM-5.1 <noreply@openclaude.dev>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: GLM-5.1 <noreply@openclaude.dev>
* docs(docs): add agent guidance and repository instructions
- Created `AGENTS.md` and `CLAUDE.md` to provide high-signal guidance for AI agents and developers working in the repository.
- Outlined critical developer commands for building, testing, and running diagnostics using `bun`.
- Documented the repository architecture, source entrypoints, and core service logic.
- Defined framework-specific quirks, including module stubbing for internal modules and macro versioning.
- Established style and workflow guidelines regarding telemetry, environment variables, and security scan requirements.
* feat(api): support gemini thought signatures in openai shim
- Added `isGeminiMode` utility to detect Gemini backends via `CLAUDE_CODE_USE_GEMINI` or `OPENAI_BASE_URL`.
- Updated `convertMessages` to extract `thought_signature` from thinking blocks and inject them into tool calls.
- Implemented a fallback mechanism that provides a `skip_thought_signature_validator` string to avoid 400 validation errors when a signature is missing.
- Enhanced `openaiStreamToAnthropic` and `OpenAIShimMessages` to correctly preserve and pass through Gemini-specific metadata in `extra_content`.
* refactor(api): improve gemini metadata handling and remove redundant docs
- Updated `src/services/api/openaiShim.ts` to merge existing `google`-specific metadata within `extra_content` instead of overwriting it.
- Simplified the `thought_signature` assignment logic to use a fallback value of `skip_thought_signature_validator` when no signature is provided.
- Deleted `AGENTS.md` and `CLAUDE.md` files to eliminate redundant agent guidance documentation.
* fix(api): propagate gemini thought signatures to all parallel tool calls
- Removed the index constraint when assigning the `signature` from a `thinkingBlock` to tool calls in `openaiShim.ts`.
- Ensured that the `thought_signature` is applied to every tool call in a parallel set, rather than just the first one.
- Aligned the shim with Gemini API requirements, which mandate that the same signature must be present on every replayed function call part within an assistant turn.
* gRPC Server
* gRPC fix
* UpdProto
* fix: address PR review feedback for gRPC server
- Update bun.lock for new dependencies (frozen-lockfile CI fix)
- Add multi-turn session persistence via initialMessages
- Replace hardcoded done payload with real token counts
- Default bind to localhost instead of 0.0.0.0
* fix(grpc): startup parity, cancel interrupt, and cli text fallback
- Replace enableConfigs() with await init() in start-grpc.ts for full
bootstrap parity with the main CLI (env vars, CA certs, mTLS, proxy,
OAuth, Windows shell)
- Call engine.interrupt() before call.end() in the cancel handler so
in-flight model/tool execution is actually stopped
- Show done.full_text in the CLI client when no text_chunk was received,
preventing silent drops when streaming is unavailable
* fix(grpc): wire session_id end-to-end and remove dead provider field
- Move session_id from ClientMessage into ChatRequest to fix proto-loader
oneofs encoding bug and make the field functional
- Implement in-memory session store so reconnecting with the same
session_id resumes conversation context across streams
- Remove ChatRequest.provider — per-request provider routing requires
global process.env mutation, unsafe for concurrent clients; provider
is configured via env vars at server startup
* fix(grpc): mirror CLI auth bootstrap in start-grpc and fix tool_name field
scripts/start-grpc.ts now runs the same provider/auth bootstrap as the
normal CLI entrypoint: enableConfigs, safe env vars, Gemini/GitHub token
hydration, saved-profile resolution with warn-and-fallback, and provider
validation before the server binds.
ToolCallResult.tool_name was being populated with the tool_use_id UUID.
Added a toolNameById map (filled in canUseTool) so tool_name now carries
the actual tool name (e.g. "Bash"). The UUID moves to a new tool_use_id
field (proto field 4) for client-side correlation.
* fix(grpc): add tool_use_id to ToolCallStart and interrupt engine on stream close
Two blocker-level issues flagged in code review:
- ToolCallStart was missing tool_use_id, making it impossible for clients
to correlate tool_start events with tool_result when the same tool runs
multiple times. Added tool_use_id = 3 to the proto message and populated
it from the toolUseID parameter in canUseTool.
- On stream close without an explicit CancelSignal the server only nulled
the engine reference, leaving the underlying model/tool work running
as an orphan. Added engine.interrupt() in the call.on('end') handler
to stop work immediately when the client disconnects.
* fix(grpc): resolve pending promises on disconnect and guard post-cancel writes
Four lifecycle and contract issues identified during proactive review:
- Pending permission Promises in canUseTool would hang forever if the
client disconnected mid-stream. On call 'end', all pending resolvers
are now called with 'no' so the engine can unblock and terminate.
- The done message and session save could fire after call.end() when
a CancelSignal arrived mid-generation. Added an `interrupted` flag
set on both cancel and stream close to gate all post-loop writes.
- The session map had no eviction policy, allowing unbounded memory
growth. Capped at MAX_SESSIONS=1000 with FIFO eviction of the
oldest entry.
- Field 3 was silently absent from ChatRequest. Added `reserved 3`
to document the gap and prevent accidental reuse in future.
* fix(grpc): reset previousMessages on each new request to prevent session history leak
previousMessages was declared at stream scope and only overwritten when
the incoming session_id already existed in the session store. A second
request on the same stream with a new session_id would silently inherit
the first request's conversation history in initialMessages instead of
starting fresh, violating the session contract.
Fix: reset previousMessages to [] at the start of each ChatRequest
before the session-store lookup.
* fix(grpc): reset interrupted flag between requests and guard against concurrent ChatRequest
Two stream-scoped state bugs found during proactive audit:
- The `interrupted` flag was never reset between requests on the same
stream. If the first request was cancelled, all subsequent requests
would silently skip the done message, causing the client to hang.
- A second ChatRequest arriving while the first was still processing
would overwrite the engine reference, corrupting the lifecycle of
both requests. Now returns ALREADY_EXISTS error instead. Engine is
nulled after the for-await loop completes so subsequent requests
can proceed normally.
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: convert dragged file paths to @mentions for attachment
When non-image files are dragged into the terminal, the file path was
inserted as plain text and never attached. Now detected absolute paths
are converted to @mentions so they get picked up by the attachment system.
* test: add tests for drag-and-drop file path detection
* fix: multi-image drag-and-drop only showing last image
insertTextAtCursor read input and cursorOffset from the React closure,
which is stale when called in a synchronous loop (e.g. onImagePaste for
multiple dragged images). Now uses refs so each insertion chains on the
previous one.
* fix: quote Windows absolute paths to avoid MCP mention collision
Paths containing ':' (e.g. Windows drive letters) are now emitted in
quoted @"..." form so they don't match the MCP resource mention regex.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* refactor: decouple dragDropPaths from imagePaste and harden image checks
- Check image extension against the cleaned path (post quote/escape
stripping) so quoted or backslash-escaped image drops are reliably
routed to the image paste handler.
- Inline the image extension regex and drop the imagePaste/fsOperations
imports so the module (and its tests) no longer pull in `bun:bundle`
and the heavier fs wrapper chain. Use plain `fs.existsSync` for the
on-disk check.
- Add tests covering quoted image paths, uppercase extensions,
backslash-escaped image paths, escaped real files with spaces, mixed
segments containing an image, quoted-nonexistent paths, and leading
or trailing whitespace.
* test: verify dragged paths with an `@` segment are preserved
Adds a fixture under a scoped-package-style subdir (`@types/index.d.ts`)
so we exercise the realistic `node_modules/@types/...` drag case and
lock in that `extractDraggedFilePaths` returns the raw path unchanged —
the `@` inside the path must not collide with the mention prefix the
caller prepends downstream.
* test: parametrize dragDropPaths cases with test.each
Groups the 21 scenarios into four table-driven describes
(empty-result, single-path, multi-path, backslash-escaped) so that
adding a new case is a one-line row instead of a new `test()` block.
Fixture directories are now created synchronously at describe-load
time so their paths are available to the test.each tables, which are
built before any hook runs.
* test: add contract tests for @-mention extractor boundary
Pins the contract between `extractAtMentionedFiles` and
`extractMcpResourceMentions` so the MCP regex can't silently swallow
quoted file-path mentions.
These tests fail on current HEAD — 3 of 11 cases expose the regression
pointed out in the review on #382: `extractMcpResourceMentions`'s
trailing `\b` backtracks past the closing `"` of a quoted mention and
produces a ghost match for `@"C:\Users\..."`, `@C:\Users\...`, and
`@"/tmp/weird:name.txt"`. The remaining 8 cases lock in the behaviour
that must not change (legitimate `server:resource` mentions and plain
file-path mentions).
Committed failing on purpose as the first half of a test-then-fix
pair; the regex fix follows in a subsequent commit.
* fix: prevent MCP extractor from ghost-matching quoted/Windows paths
The MCP resource regex used `\b` as a trailing anchor with `[^\s]+`
character classes. On any quoted file mention containing a colon
(`@"C:\Users\me\file.txt"`, `@"/tmp/weird:name.txt"`), the engine
backtracked past the closing `"` to satisfy `\b`, producing a ghost
match that collided with `extractAtMentionedFiles`. Unquoted Windows
drive-letter paths (`@C:\Users\me\file.txt`) also matched because a
drive letter is structurally identical to an MCP `server:resource`
token.
Two guards:
1. `(?!")` right after `@` drops quoted tokens entirely, and adding
`"` to the character classes blocks any mid-match backtracking.
2. A post-match filter discards `^[A-Za-z]:[\\/]` — a single-letter
server followed by a path separator is always a Windows drive
prefix, never a real MCP resource.
Legitimate MCP forms (`@server:resource/path`, plugin-scoped like
`@asana-plugin:project-status/123`, inline prose mentions) remain
matched and are pinned by the contract tests added in 04998d5.
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* docs: add LiteLLM proxy setup guide
Document the setup process for LiteLLM and its integration with OpenClaude, including prerequisites, configuration, and troubleshooting steps.
* Revise LiteLLM setup steps for Adocs: fix /provider walkthrough to match actual OpenAI-compatible flowPI key and model
Updated setup instructions for LiteLLM provider configuration.
* docs: fix sub-bullet formatting in /provider steps
* docs: clarify key scope in troubleshooting (LiteLLM proxy process env)
Clarified instruction for upstream provider error regarding API key.
Models served through Ollama/vLLM with strict Jinja templates (Devstral,
Mistral, etc.) require strict user↔assistant role alternation and reject
requests with consecutive messages of the same role.
convertMessages() could produce consecutive user or assistant messages in
three scenarios: batched user input, text-only + tool_use assistant turns,
and tool result remainders followed by another user message.
Added a coalescing pass at the end of convertMessages() that merges
consecutive same-role messages (string concat or array concat), preserving
tool_calls on assistant messages. Tool and system messages are excluded
from coalescing as they have their own alternation rules.
Includes regression tests for both user and assistant coalescing.
Fixes#202
* Add local OpenAI-compatible model discovery to /model
* Guard local OpenAI model discovery from Codex routing
* Preserve remote OpenAI Codex alias behavior
Models not in the lookup table fall through to a 200k default, causing
auto-compact to never trigger for models with smaller actual context
windows. Users hit hard context_window_exceeded errors instead.
Added to both context window and max output token tables:
- o1, o1-mini, o1-preview, o1-pro (OpenAI reasoning models)
- llama3.2:1b, qwen3:8b, codestral (common Ollama models)
Relates to #248
* security: force lodash-es 4.18.0 for transitive dependencies
PR #225 bumped the direct lodash-es dependency to 4.18.0, but
@anthropic-ai/sandbox-runtime still pulled lodash-es@4.17.23 via its
own ^4.17.23 range. The transitive copy was vulnerable to:
- HIGH: Code Injection via _.template (GHSA-r5fr-rjxr-66jc)
- MODERATE: Prototype Pollution via _.unset/_.omit (GHSA-f23m-r3pf-42rh)
Added overrides field in package.json to force all copies to 4.18.0.
bun audit now reports zero vulnerabilities.
* fix: use lodash-es 4.18.1 instead of deprecated 4.18.0
lodash-es 4.18.0 is explicitly deprecated by the maintainer with
the message "Bad release. Please use lodash-es@4.17.23 instead."
Updated both the direct dependency and the override to 4.18.1, which
is the latest non-deprecated release that patches the CVEs.
Reproduction:
- Enable `frontend-design@claude-code-plugins`
- Enable `frontend-design@claude-plugins-official`
- Start OpenClaude with both marketplace plugins active
- Both plugins load, but downstream command and skill scopes key off the short plugin name, so both collapse to `frontend-design` and can interfere with interactive startup
Fix:
- Collapse duplicate marketplace plugins by short name during merge
- Keep the enabled copy when enabled state differs; otherwise keep the later config entry
- Add regression coverage for both cases
## Summary
- Extract retry-after header from 429 API errors and include timing
guidance in the user-facing error message
- Previously, non-quota 429 errors showed a generic message with no
guidance on when to retry, only a link to status.anthropic.com
## Impact
- user-facing impact: 429 error messages now tell users when to retry
instead of just linking to a status page
- developer/maintainer impact: none
## Testing
- [x] `bun run build`
- [ ] `bun run smoke`
- [ ] focused tests: error formatting is pure string construction,
verified via build + manual inspection
## Notes
- provider/model path tested: applies to all providers returning 429
- screenshots attached (if UI changed): n/a
- follow-up work or known limitations: 529 errors could get similar
treatment in a follow-up
https://claude.ai/code/session_01D7kprMn4c66a5WrZscF7rv
Co-authored-by: Claude <noreply@anthropic.com>
* Remove internal-only bundled skills and mock rate-limit behavior
This takes the next planned Phase C-lite slice by deleting bundled skills
that only ever registered for internal users and replacing the internal
mock rate-limit helper with a stable no-op external stub. The external
build keeps the same behavior while removing a concentrated block of
USER_TYPE-gated dead code.
Constraint: Limit this PR to isolated internal-only helpers and avoid bridge, oauth, or rebrand behavior
Rejected: Broad USER_TYPE cleanup across mixed runtime surfaces | too risky for the next medium-sized PR
Confidence: high
Scope-risk: moderate
Reversibility: clean
Directive: The next cleanup pass should continue with similarly isolated USER_TYPE helpers before touching main.tsx or protocol-heavy code
Tested: bun run build
Tested: bun run smoke
Tested: bun run verify:privacy
Tested: bun run test:provider
Tested: bun run test:provider-recommendation
Not-tested: Full repo typecheck (upstream baseline remains noisy)
* Align internal-only helper removal with remaining user guidance
This follow-up fixes the mock billing stub to be a true no-op and removes
stale user-facing references to /verify and /skillify from the same PR.
It also leaves a clearer paper trail for review: the deleted verify skill
was explicitly ant-gated before removal, and the remaining mock helper
callers still resolve to safe no-op returns in the external build.
Constraint: Keep the PR focused on consistency fixes and reviewer-requested evidence, not new cleanup scope
Rejected: Leave stale guidance for a later PR | would make this branch internally inconsistent after skill removal
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: When deleting gated features, always sweep user guidance and coordinator prompts in the same pass
Tested: bun run build
Tested: bun run smoke
Tested: bun run verify:privacy
Tested: bun run test:provider
Tested: bun run test:provider-recommendation
Not-tested: Full repo typecheck (upstream baseline remains noisy; changed-file scan still shows only pre-existing tipRegistry errors outside edited lines)
* Clarify generic workflow wording after skill removal
This removes the last generic verification-skill wording that could still
be read as pointing at a deleted bundled command. The guidance now talks
about project workflows rather than a specific bundled verify skill.
Constraint: Keep the follow-up limited to reviewer-facing wording cleanup on the same PR
Rejected: Leave generic wording as-is | still too easy to misread after the explicit /verify references were removed
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: When removing bundled commands, scrub both explicit and generic references in the same branch
Tested: bun run build
Tested: bun run smoke
Not-tested: Additional checks unchanged by wording-only follow-up
---------
Co-authored-by: anandh8x <test@example.com>
This follow-up Phase C-lite slice replaces purely internal helper modules
with stable external no-op surfaces and collapses internal elevated error
logging to a no-op. The change removes additional USER_TYPE-gated helper
behavior without touching product-facing runtime flows.
Constraint: Keep this PR limited to isolated helper modules that are already external no-ops in practice
Rejected: Pulling in broader speculation or logging sink changes | less isolated and easier to debate during review
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Continue Phase C with similarly isolated helpers before moving into mixed behavior files
Tested: bun run build
Tested: bun run smoke
Tested: bun run verify:privacy
Tested: bun run test:provider
Tested: bun run test:provider-recommendation
Not-tested: Full repo typecheck (upstream baseline remains noisy)
Co-authored-by: anandh8x <test@example.com>
This extends the label-only cleanup to the remaining internal-only command,
debug, and heading strings so the source tree no longer contains ANT-ONLY
markers. The pass still avoids logic changes and only renames labels shown
in internal or gated surfaces.
Constraint: Update the existing label-cleanup PR without widening scope into behavior changes
Rejected: Leave the last ANT-ONLY strings for a later pass | low-cost cleanup while the branch is already focused on labels
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: The next phase should move off label cleanup and onto a separately scoped logic or rebrand slice
Tested: bun run build
Tested: bun run smoke
Tested: bun run verify:privacy
Tested: bun run test:provider
Tested: bun run test:provider-recommendation
Not-tested: Full repo typecheck (upstream baseline remains noisy)
Co-authored-by: anandh8x <test@example.com>
