* fix: error output truncation (10KB→40KB) and MCP tool bugs
- toolErrors.ts: increase error truncation limit from 10KB to 40KB
Shell output can be up to 30KB, so 10KB was silently cutting off
error logs from systemctl, apt, python, etc.
- MCPTool: cache compiled AJV validators (was recompiling every call)
- MCPTool: fix validateInput error message showing [object Object]
- MCPTool: null-guard mapToolResultToToolResultBlockParam
- MCPTool: explicit null check in isResultTruncated
- ReadMcpResourceTool: null-guard mapToolResultToToolResultBlockParam
Tests (84 passing):
- src/utils/toolErrors.test.ts (13 tests)
- src/tools/BashTool/commandSemantics.test.ts (24 tests)
- src/tools/BashTool/utils.test.ts (32 tests)
- src/tools/MCPTool/MCPTool.test.ts (15 tests)
* fix: address review blockers from PR #885
Blocker 1: Fix abort path in callMCPTool
- Previously returned { content: undefined } on AbortError, which masked
the cancellation and caused mapToolResultToToolResultBlockParam to send
empty content to the API as if it were a successful result.
- Now converts abort errors to our AbortError class and re-throws, so the
tool execution framework handles it properly (skips logging, creates
is_error: true result with [Request interrupted by user for tool use]).
Blocker 2: Fix memory leak in AJV validator cache
- Changed compiledValidatorCache from Map to WeakMap so schemas from
disconnected/refreshed MCP tools can be garbage collected instead of
accumulating strong references indefinitely.
Also: null guards now return descriptive indicators instead of empty
strings, making it clear when content is unexpectedly missing.
---------
Co-authored-by: FluxLuFFy <FluxLuFFy@users.noreply.github.com>
Co-authored-by: Fix Bot <fix@openclaw.ai>
* chore: rebrand user-facing copy to OpenClaude
Replace lingering Claude Code branding in CLI, tips, and runtime UI with OpenClaude/openclaude, including the startup tip Gitlawb mention.
Co-Authored-By: Claude GPT-5.4 <noreply@openclaude.dev>
* chore: address branding-sweep review feedback
- PermissionRequest.tsx: rebrand the two remaining "Claude needs your
approval/permission" notifications to OpenClaude (review-artifact and
generic tool permission paths).
- main.tsx, teleport.tsx, session.tsx, WebFetchTool/utils.ts,
skills/bundled/{debug,updateConfig}.ts: replace leftover `claude --…`
CLI hints and "Claude Code" labels missed by the original sweep.
- main.tsx: drop the inline gitlawb.com marketing copy from the
stale-prompt tip; keep it a pure rebrand.
- auth.ts: finish the half-rename so both `claude setup-token` and
`claude auth login` references in the same error block now read
`openclaude …`.
- mcp/client.ts: keep `name: 'claude-code'` for MCP server allowlist
compatibility (now explicit via comment) and replace the
"Anthropic's agentic coding tool" description with an OpenClaude one.
- MCPSettings.tsx: point the empty-server-list hint at
https://github.com/Gitlawb/openclaude instead of code.claude.com.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* chore: replace help link with OpenClaude repo URL
Replace https://code.claude.com/docs/en/overview with
https://github.com/Gitlawb/openclaude in the help screen.
Co-Authored-By: OpenClaude <openclaude@gitlawb.com>
---------
Co-authored-by: Claude GPT-5.4 <noreply@openclaude.dev>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: OpenClaude <openclaude@gitlawb.com>
* feat: add xAI as official provider
- Add xAI preset to ProviderManager (alphabetical order)
- Add xAI provider detection via XAI_API_KEY
- Add xAI startup screen heuristic (x.ai base URL or grok model)
- Add xAI status display properties
- Add grok-4 and grok-3 context windows
- Add xAI model fallbacks across all tiers
- Fix JSDoc priority order in providerAutoDetect
Co-Authored-By: Claude Opus 4.6 <noreply@openclaude.dev>
* fix(xai): persist relaunch classification for xAI profiles
Addresses reviewer feedback on feat/xai-official-provider:
- isProcessEnvAlignedWithProfile now validates XAI_API_KEY for x.ai
base URLs, mirroring the Bankr pattern. Without this, relaunch
skips re-applying the profile, XAI_API_KEY stays unset, and
getAPIProvider() falls back to 'openai'.
- buildOpenAICompatibleStartupEnv now sets XAI_API_KEY when syncing
active xAI profile to the legacy fallback file.
- Adds 'xai' to VALID_PROVIDERS and --provider xai CLI flag support.
- Adds xAI detection to providerDiscovery label heuristics.
- Adds 'xai' to legacy ProviderProfile type/isProviderProfile guard.
- Adds targeted tests for relaunch alignment, flag application, and
discovery labeling.
Co-Authored-By: OpenClaude <openclaude@gitlawb.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@openclaude.dev>
Co-authored-by: OpenClaude <openclaude@gitlawb.com>
The startup screen was only reading model from env vars and settings,
ignoring the --model CLI flag since it's parsed by Commander.js after
the banner prints. Now eagerly parses --model from argv before rendering
so the displayed model matches what the session will actually use.
* fix(agent): provider-aware fallback for haiku/sonnet aliases
Explore agent fails on custom providers (Z.AI GLM, Alibaba Anthropic-compatible,
local OpenAI endpoints) because 'haiku' alias resolves to a non-existent model.
Changes:
- Add isClaudeNativeProvider check (Bedrock, Vertex, Foundry, official Anthropic)
- For non-Claude-native providers, haiku/sonnet aliases inherit parent model
- Add 8 tests for provider-aware fallback behavior
Fixes Explore agent "model not found" errors on custom Anthropic-compatible APIs.
* test(agent): use Bun mock.module() for provider tests
Replace env manipulation with proper Bun mock.module() to reliably
mock getAPIProvider() and isFirstPartyAnthropicBaseUrl() functions.
This ensures tests work correctly on CI where module caching caused
false negatives.
---------
Co-authored-by: Ali Alakbarli <ali.alakbarli@users.noreply.github.com>
- import getGlobalConfig — six call sites referenced it without an import;
five short-circuited via feature() gates, but src/query.ts:1896 always
ran and crashed every queryLoop iteration with "getGlobalConfig is not
defined" (e.g. Explore subagent: "Agent failed: getGlobalConfig is not
defined").
- stop coercing SystemPrompt (string[]) into a template-string before
appendSystemContext — that made [...systemPrompt] spread the string
character-by-character, replacing the structured prompt with thousands
of one-char system blocks. Append arcSummary as its own array element
instead.
- gate the finalizeArcTurn call behind feature('CONVERSATION_ARC') so it
matches the rest of the memory-PR call sites and gets dead-code-
eliminated for users without the flag.
Co-authored-by: OpenClaude <openclaude@gitlawb.com>
* feat(zai): add Z.AI GLM Coding Plan provider preset
Add dedicated Z.AI provider support for the GLM Coding Plan, enabling
use of GLM-5.1, GLM-5-Turbo, GLM-4.7, and GLM-4.5-Air models through
the OpenAI-compatible shim with proper thinking mode (reasoning_content),
max_tokens handling, and context window sizing.
* fix(zai): unify GLM max output token limits across casing variants
glm-5/glm-4.7 had conservative 16K max output while GLM-5/GLM-4.7
had 131K. Use consistent Z.AI coding plan limits for all GLM variants.
* fix(zai): restore DashScope GLM limits, enable GLM thinking support
- Restore lowercase glm-5/glm-4.7 to 16_384 max output (DashScope limits)
while keeping Z.AI coding plan high limits on uppercase GLM-* keys only
- Add GLM model support to modelSupportsThinking() so reasoning_content
is enabled when using GLM-5.x/GLM-4.7 models on Z.AI
* fix(zai): tighten GLM regexes, fix misleading context window comment
- Use precise regex in thinking.ts: exact GLM model matches only,
no false positives on glm-50/glm-4, includes glm-4.5-air
- Use uppercase-only match in StartupScreen rawModel fallback so
DashScope lowercase glm-* models aren't mislabeled as Z.AI
- Clarify context window comment: lowercase glm-5.1/glm-5-turbo/
glm-4.5-air are Z.AI-specific aliases, not DashScope
* fix(zai): scope GLM detection to Z.AI
* improve readability of max_completion_tokens check
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
* feat: multi-turn context and conversation arc memory
PR 2E - Section 2.9, 2.10:
- Add multiTurnContext.ts with turn tracking and state preservation
- Add conversationArc.ts with goal/decision/milestone tracking
- Wire into query.ts after tool execution
- Feature-flags: MULTI_TURN_CONTEXT, CONVERSATION_ARC
- Add comprehensive tests (22 passing)
* feat(cli): add /knowledge command to manage native memory
- Add /knowledge enable <yes|no> to toggle Knowledge Graph learning\n- Add /knowledge clear to reset memory\n- Add persistent knowledgeGraphEnabled setting to global config\n- Integrated user setting into the query execution loop
* feat(cli): add /knowledge command (stable local-jsx version)
- Resolve conflicts between .ts and .tsx files\n- Align with LocalJSXCommandCall signature\n- Fix onDone and args errors
* test(cli): fix knowledge command tests by properly isolating global config
* fix(cli): make knowledge command defensive against undefined args and leaky tests
* fix(cli): correct data source for entity count and fix test isolation
* fix(cli): reinforce knowledge test by explicitly defining property on test config
* fix(cli): explicitly define property in test config to avoid undefined in CI
* fix(cli): make knowledge tests resistant to global config mocks in CI
* chore(memory): surgical improvements from architectural audit
- Fix: Implement entity deduplication in Knowledge Graph\n- Fix: Ensure fact extraction from user messages in query loop\n- Fix: Refine regexes for better quality learning (less noise)
---------
Co-authored-by: LifeJiggy <Bloomtonjovish@gmail.com>
* feat: multi-turn context and conversation arc memory
PR 2E - Section 2.9, 2.10:
- Add multiTurnContext.ts with turn tracking and state preservation
- Add conversationArc.ts with goal/decision/milestone tracking
- Wire into query.ts after tool execution
- Feature-flags: MULTI_TURN_CONTEXT, CONVERSATION_ARC
- Add comprehensive tests (22 passing)
* feat(memory): resolve review blockers and integrate native Knowledge Graph into Conversation Arcs
- Fix: Extract text from production block arrays in phase detector\n- Fix: Ensure proper turn segmentation in query loop\n- Fix: Respect options in multi-turn context tracker\n- Feat: Add native Knowledge Graph (Entities/Relations) to ConversationArc architecture\n- Test: Comprehensive test suite for all fixes and new graph features
* test(perf): add automated performance benchmarks for Knowledge Graph extraction and summary
---------
Co-authored-by: LifeJiggy <Bloomtonjovish@gmail.com>
* feat(provider): add Bankr LLM Gateway support
Add Bankr as an OpenAI-compatible provider preset with dedicated env vars:
- BNKR_API_KEY, BANKR_BASE_URL, BANKR_MODEL
- Uses X-API-Key header instead of Authorization Bearer
- Base URL: https://llm.bankr.bot/v1
- Default model: claude-opus-4.6
Changes:
- Add 'bankr' to VALID_PROVIDERS and provider flag handling
- Add buildBankrProfileEnv() with env key registration
- Add Bankr detection in startup screen and provider discovery
- Map Bankr env vars to OpenAI-compatible vars in shim
- Add Bankr preset to ProviderManager (alphabetical order)
- Update PRESET_ORDER test to include Bankr
Co-Authored-By: OpenClaude <openclaude@gitlawb.com>
* fixup(provider): address Bankr PR review feedback
1. Map BNKR_API_KEY → OPENAI_API_KEY in providerFlag.ts so
--provider bankr works with BNKR_API_KEY in non-interactive startup.
2. Remove unconditional BANKR_MODEL read from model.ts; it maps to
OPENAI_MODEL via providerFlag.ts and openaiShim.ts, preventing
cross-provider leakage.
3. Use X-API-Key for Bankr model discovery in openaiModelDiscovery.ts
and providerDiscovery.ts, matching chat request auth.
Co-Authored-By: OpenClaude <openclaude@gitlawb.com>
---------
Co-authored-by: OpenClaude <openclaude@gitlawb.com>
- Bump Codex provider defaults from gpt-5.4 to gpt-5.5 across all ModelConfigs
- Update codexplan alias to resolve to gpt-5.5
- Add gpt-5.5 and gpt-5.5-mini to model picker with reasoning effort mappings
- Add context window and max output token specs for gpt-5.5 family
- Add gpt-5.5 entries to COPILOT_MODELS registry
- Keep official OpenAI API preset at gpt-5.4 (API availability pending)
- Update codexShim tests to expect gpt-5.5 from codexplan alias
Co-authored-by: OpenClaude <openclaude@gitlawb.com>
Closes#856.
MCP servers that expose resources (e.g. RepoPrompt) failed to load
their tools in the open build with:
Error fetching tools/commands/resources:
fetchMcpSkillsForClient is not a function
Root cause: scripts/build.ts set MCP_SKILLS: true, which made
feature('MCP_SKILLS') evaluate to true at build time. The guards
around the dynamic skill discovery path therefore stayed live. The
underlying source file src/skills/mcpSkills.ts is not mirrored into
the open tree, so the bundler fell back to its generic missing-module
stub — which only exports `default` for require()-style imports, not
the named `fetchMcpSkillsForClient` binding. At runtime the require
returned an object without that property, and calling it threw.
`openclaude mcp doctor` reported RepoPrompt as healthy because doctor
does not exercise the skills-fetch path.
Fix: flip MCP_SKILLS to false and move it into the "Disabled: missing
source" group. With the flag off, every `if (feature('MCP_SKILLS'))`
guard becomes a no-op at build time, the require() branch is dead
code, and MCP servers with resources load normally via the existing
`Promise.resolve([])` fallbacks already present at each call site.
Also adds scripts/feature-flags-source-guard.test.ts to fail fast if
MCP_SKILLS (or any future flag in the same category) is re-enabled
without the corresponding source file being mirrored first.
Verification:
- Test fails on main, passes with this fix
- `bun run build` produces a bundle with no
`missing-module-stub:../../skills/mcpSkills.js` reference
- Full `bun test` — 1222 pass / 12 fail (same pre-existing 12 as
main; new test adds the +1 pass)
* fix(shell): recover when CWD path was replaced by a non-directory
Closes#844.
When the session's cached working directory is renamed on disk and
a file is subsequently created at the old path (e.g. `mv orig renamed
&& touch orig`), every Bash tool invocation failed with
`ENOTDIR: not a directory, posix_spawn '/usr/bin/zsh'` (exit 126),
and `!`-prefixed commands silently failed. No recovery was possible
without restarting the session.
Root cause: the pre-spawn guard in `src/utils/Shell.ts:exec()` used
`realpath(cwd)` to detect a missing CWD. `realpath()` succeeds on
any existing path — file or directory — so a path that was replaced
with a regular file slipped past the check. spawn() was then called
with `cwd` pointing at a non-directory and failed with ENOTDIR.
Fix: replace `realpath()` with `stat().isDirectory()` for both the
primary CWD check and the `getOriginalCwd()` fallback check. When
the cached CWD is no longer a directory, fall back to the original
CWD (as before) and update state so subsequent tools recover
transparently.
Verification:
- Repro: `mkdir -p /tmp/x/orig && mv /tmp/x/orig /tmp/x/renamed
&& touch /tmp/x/orig`, then exec with stale cwd=/tmp/x/orig
- Before: exit 126, stderr "ENOTDIR: not a directory, posix_spawn"
- After: exit 0, cwd transparently recovered to originalCwd
- `bun test` — no new regressions (pre-existing model/provider
test failures are unrelated and present on main)
* fix(shell): drop now-unused realpath import
The `openclaude update` / `openclaude upgrade` command printed
`Current version: 99.0.0` and, in the development-build branch, exited
with only `Warning: Cannot update development build` (closes#852).
Root cause: `MACRO.VERSION` is hardcoded to `'99.0.0'` in
`scripts/build.ts` as an internal compatibility sentinel so OpenClaude
passes upstream minimum-version guards. The real package version is
exposed separately as `MACRO.DISPLAY_VERSION`. `update.ts` was using
`MACRO.VERSION` for both the version shown to the user and for every
`latestVersion` comparison, which meant:
- Users always saw `99.0.0` as their "current version".
- `99.0.0 >= <any real npm version>`, so the "up to date" and
"update available" checks could never fire correctly.
Fix (scoped to `src/cli/update.ts`):
- Use `MACRO.DISPLAY_VERSION` for all user-facing version strings and
version comparisons.
- Replace the dead-end `Warning: Cannot update development build`
(which exited 1 with no guidance) with actionable instructions for
both source builds (`git pull && bun install && bun run build`) and
npm installs (`npm install -g @gitlawb/openclaude@latest`).
- Extend the existing third-party-provider branch to also show the
current version and the npm reinstall command, so users who
installed via npm aren't told only to rebuild from source.
The banner provider branch tested model-name substrings (`/deepseek/`, `/kimi/`,
`/mistral/`, `/llama/`) before aggregator base-URL substrings (`/openrouter/`,
`/together/`, `/groq/`, `/azure/`). When running OpenRouter/Together/Groq with
vendor-prefixed model IDs (e.g. `deepseek/deepseek-chat`, `moonshotai/kimi-k2`,
`deepseek-r1-distill-llama-70b`), the banner mislabelled the provider.
Reorder: explicit env flags (NVIDIA_NIM, MINIMAX_API_KEY) and codex transport
win first; base-URL host checks run before rawModel fallback; rawModel only
fires when the base URL is generic/custom. Add unit tests covering the
aggregator × vendor-prefixed-model matrix plus direct-vendor regressions.
Closes#855
* fix: make OpenAI fallback context window configurable and support external lookup table
Unknown OpenAI-compatible models fell back to a hardcoded 128k constant,
causing auto-compact to fire prematurely on models with larger windows
(issue #635 follow-up). Two escape hatches are added without touching the
built-in table:
- CLAUDE_CODE_OPENAI_FALLBACK_CONTEXT_WINDOW (number): overrides the 128k
default for all unknown models.
- CLAUDE_CODE_OPENAI_CONTEXT_WINDOWS (JSON object): per-model overrides that
take precedence over the built-in OPENAI_CONTEXT_WINDOWS table; supports
the same provider-qualified and prefix-matching lookup as the built-in path.
- CLAUDE_CODE_OPENAI_MAX_OUTPUT_TOKENS (JSON object): same pattern for output
token limits.
This lets operators deploy new or private models without patching
openaiContextWindows.ts on every model release.
* docs: add new OpenAI context window env vars to .env.example
Document CLAUDE_CODE_OPENAI_FALLBACK_CONTEXT_WINDOW,
CLAUDE_CODE_OPENAI_CONTEXT_WINDOWS, and
CLAUDE_CODE_OPENAI_MAX_OUTPUT_TOKENS with usage examples.
Addresses reviewer feedback on PR #861.
---------
Co-authored-by: opencode <dev@example.com>
Gates three injection sites behind OPENCLAUDE_DISABLE_TOOL_REMINDERS:
- FileReadTool cyber-risk mitigation reminder (appended to every Read
result when the model is not in MITIGATION_EXEMPT_MODELS)
- todo_reminder attachment for TodoWrite usage
- task_reminder attachment for TaskCreate/TaskUpdate usage
All three reminders are model-only side-channel instructions the user
cannot see today. Users who want full transparency over what the model
receives can now opt out without patching dist/cli.mjs on every upgrade.
Default behavior is unchanged when the flag is unset.
Closes#809
mock.module('./teammate.js', ...) only declared getAgentName/getTeamName/
getTeammateColor. Bun applies module mocks process-globally and
mock.restore() does not undo them, so whenever another test file ran
after hookChains.integration.test.ts and reached the real teammate
module it received undefined for isTeammate/isPlanModeRequired/
getAgentId/getParentSessionId.
This surfaced in CI as intermittent failures in
src/commands/provider/provider.test.tsx (TextEntryDialog / wizard
remount / ProviderWizard hides Codex OAuth), because getDefaultAppState
in AppStateStore.ts calls teammateUtils.isTeammate().
Match the mock surface to the real teammate.ts exports so downstream
consumers keep working even after the integration test pollutes the
module cache. Keeps the same behavioral overrides this test needed.
Closes#839
- Add exponential backoff retry to DuckDuckGo adapter (3 attempts with
jitter) to handle transient rate-limiting and connection errors.
- Add native fetch() fallback in WebFetch when axios hangs with custom
DNS lookup in bundled contexts.
- Prevent broken native-path fallback for web search on OpenAI shim
providers (minimax, moonshot, nvidia-nim, etc.) that do not support
Anthropic's web_search_20250305 tool.
- Cherry-pick existing fixes:
- a48bd56: cover codex/minimax/nvidia-nim in getSmallFastModel()
- 31f0b68: 45s budget + raw-markdown fallback for secondary model
- 446c1e8: sparse Codex /responses payload parsing
- ae3f0b2: echo reasoning_content on assistant tool-call messages
- Fix domainCheck.test.ts mock modules to include isFirstPartyAnthropicBaseUrl
and isGithubNativeAnthropicMode exports.
Co-authored-by: OpenClaude <openclaude@gitlawb.com>
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>
Kimi / Moonshot's chat completions endpoint requires that every assistant
message carrying tool_calls also carry reasoning_content when the
"thinking" feature is active. When an agent sends prior-turn assistant
history back (standard multi-turn / subagent / Explore patterns), the
shim previously stripped the thinking block:
case 'thinking':
case 'redacted_thinking':
// Strip thinking blocks for OpenAI-compatible providers.
break
That's correct for providers that would mis-interpret serialized
<thinking> tags, but Moonshot validates the schema strictly and rejects
with:
API Error: 400 {"error":{"message":"thinking is enabled but
reasoning_content is missing in assistant tool call message at
index N","type":"invalid_request_error"}}
Reproducer: launch with Kimi profile, run any tool-using command
(Explore, Bash, etc.) — every request after the first 400s.
Fix: in convertMessages(), when the per-request flag
preserveReasoningContent is set (only for Moonshot baseUrls today),
attach the original thinking block's text as reasoning_content on the
outgoing OpenAI-shaped assistant message. Other providers continue to
strip (unknown-field rejection risk).
OpenAIMessage type grows a reasoning_content?: string field.
convertMessages() accepts an options object and threads the flag
through; the only call site (_doOpenAIRequest) gates via
isMoonshotBaseUrl(request.baseUrl).
Tests (openaiShim.test.ts):
- Moonshot: echoes reasoning_content on assistant tool-call messages
(regression for the reported 400)
- non-Moonshot providers do NOT receive reasoning_content (guards
against leaking the field to strict-parse endpoints)
Full suite: 1195/1195 pass under --max-concurrency=1. PR scan clean.
Co-authored-by: OpenClaude <openclaude@gitlawb.com>
* Integrate request logging and streaming optimizer
- Add logApiCallStart/End for API request tracking with correlation IDs
- Add streaming state tracking with processStreamChunk
- Flush buffer and log stream stats at stream end
- Resolve merge conflict with main branch
* feat: add streaming optimizer and structured request logging
* fix: address PR review feedback
- Remove buffering from streamingOptimizer - now purely observational
- Use logForDebugging instead of console.log for structured logging
- Remove dead code (streamResponse, bufferedStreamResponse, etc.)
- Use existing logging infrastructure instead of raw console.log
- Keep only used functions: createStreamState, processStreamChunk, getStreamStats
* test: add unit tests for requestLogging and streamingOptimizer
- streamingOptimizer.test.ts: 6 tests for createStreamState, processStreamChunk, getStreamStats
- requestLogging.test.ts: 6 tests for createCorrelationId, logApiCallStart, logApiCallEnd
* fix: correct durationMs test to be >= 0 instead of exactly 0
* fix: address PR #703 blockers and non-blockers
1. BLOCKER FIX: Skip clone() for streaming responses
- Only call response.clone() + .json() for non-streaming requests
- For streaming, usage comes via stream chunks anyway
2. NON-BLOCKER: Document dead code in flushStreamBuffer
- Added comment explaining it's a no-op kept for API compat
3. NON-BLOCKER: vi.mock in tests - left as-is (test framework issue)
* fix: address all remaining non-blockers for PR #703
1. Remove dead code: flushStreamBuffer call and unused import
2. Fix test for Bun: remove vi.mock, use simple no-throw tests
The test "never returns negative even for unknown 3P models (issue #635)"
asserted that getEffectiveContextWindowSize() returns >= 33_000 for an
unknown 3P model under the OpenAI shim. That specific number assumes
reservedTokensForSummary = 20_000 (MAX_OUTPUT_TOKENS_FOR_SUMMARY), which
holds only when the tengu_otk_slot_v1 GrowthBook flag is disabled.
When the flag is ON — which is the case in CI but not always locally —
getMaxOutputTokensForModel() caps the model's default output at
CAPPED_DEFAULT_MAX_TOKENS (8_000). Then reservedTokensForSummary = 8_000,
floor = 8_000 + 13_000 = 21_000, and the test fails with 21_000 < 33_000.
The test reliably passes locally and reliably fails in CI, manifesting as
the intermittent PR-check failure.
Fix: relax the lower bound to 21_000 (cap-enabled worst case), which is
still well above zero — preserving the anti-regression intent of
issue #635 (no infinite auto-compact from a negative effective window)
without binding the test to GrowthBook flag state.
Co-authored-by: OpenClaude <openclaude@gitlawb.com>
getUserSpecifiedModelSetting() decides which env var to consult based on
the active provider. The check included openai and github but omitted
codex, nvidia-nim, and minimax — even though all three use the OpenAI
shim transport and get their model routing via CLAUDE_CODE_USE_OPENAI=1
+ OPENAI_MODEL (set by applyProviderProfileToProcessEnv).
Concrete failure: user switches from Moonshot profile (which persisted
settings.model='kimi-k2.6') to the Codex profile. The new profile
correctly writes OPENAI_MODEL=codexplan + base URL to
chatgpt.com/backend-api/codex. Startup banner reflects Codex / gpt-5.4
correctly. But at request time getUserSpecifiedModelSetting() returns
early for provider='codex' (not in the env-consult list), falls through
to the stale settings.model='kimi-k2.6', and the Codex API rejects:
API Error 400: "The 'kimi-k2.6' model is not supported when using
Codex with a ChatGPT account."
Fix: extract an isOpenAIShimProvider flag covering openai|codex|github|
nvidia-nim|minimax — all providers that set OPENAI_MODEL as their model
env var. The Gemini and Mistral branches stay as-is (they use
GEMINI_MODEL / MISTRAL_MODEL).
Five regression tests pin the fix for each OpenAI-shim provider plus
guard tests for openai and github that already worked.
Co-authored-by: OpenClaude <openclaude@gitlawb.com>
Adds Atomic Chat as a first-class preset inside the in-session /provider
slash command, mirroring the Ollama auto-detect flow. Picking it probes
127.0.0.1:1337/v1/models, lists loaded models for direct selection, and
falls back to "Enter manually" / "Back" when the server is unreachable
or no models are loaded. README updated to reflect the new setup path.
Made-with: Cursor
* fix(provider): saved profile ignored when stale CLAUDE_CODE_USE_* in shell
Users reported "my saved /provider profile isn't picked up at startup —
the banner shows gpt-4o / api.openai.com even though I saved Moonshot".
Root cause: applyActiveProviderProfileFromConfig() bailed out whenever
hasProviderSelectionFlags(processEnv) was true — i.e. whenever ANY
CLAUDE_CODE_USE_* flag was present. But a bare `CLAUDE_CODE_USE_OPENAI=1`
with no paired OPENAI_BASE_URL / OPENAI_MODEL is almost always a stale
shell export left over from a prior manual setup, not genuine startup
intent. Respecting it skipped the saved profile and let StartupScreen.ts
fall through to the hardcoded `gpt-4o` / `https://api.openai.com/v1`
defaults — the exact symptom users see.
Fix: narrow the guard from "any flag set" to "flag set AND at least one
concrete config value (BASE_URL, MODEL, or API_KEY)". A bare stale flag
no longer blocks the saved profile. A real shell selection (flag + URL
or flag + model) still wins, preserving the "explicit startup intent
overrides saved profile" contract.
New helper: hasCompleteProviderSelection(env). Per-provider check for a
paired concrete value. Bedrock/Vertex/Foundry keep the flag-alone
semantic since they rely on ambient AWS/GCP credentials rather than env
config.
Three new tests cover the bug and the two counter-cases:
- bare USE flag → profile applies (fixes the bug)
- USE flag + BASE_URL → profile blocked (preserves explicit intent)
- USE flag + MODEL → profile blocked (preserves explicit intent)
Co-Authored-By: OpenClaude <openclaude@gitlawb.com>
* fix(provider): don't overlay stale legacy profile on plural-managed env
Second half of the "saved profile not picked up in banner" bug. The prior
commit fixed the guard that prevented applyActiveProviderProfileFromConfig()
from firing when a stale CLAUDE_CODE_USE_* flag was in the shell. But even
when the plural system applies correctly, buildStartupEnvFromProfile() was
then loading the legacy .openclaude-profile.json AND overwriting the
plural-managed env with whatever that file contained.
addProviderProfile() (the call path the /provider preset picker uses) does
NOT sync the legacy file, so a user who went:
manual setup: CLAUDE_CODE_USE_OPENAI=1 + OPENAI_MODEL=gpt-4o
→ writes .openclaude-profile.json as { openai, gpt-4o, ... }
/provider: add Moonshot preset, mark active
→ writes plural config; legacy file UNCHANGED
would see startup reliably apply Moonshot env first, then get it clobbered
by the stale legacy file. Banner shows gpt-4o / api.openai.com while
runtime ends up with the correct env via a different code path — exactly
the user-reported symptom.
Fix: in buildStartupEnvFromProfile, when the plural system has already
set env (CLAUDE_CODE_PROVIDER_PROFILE_ENV_APPLIED === '1'), skip the
legacy-file overlay entirely and return processEnv unchanged. Legacy is
now strictly a first-run / fallback path for users who haven't adopted
the plural system.
Also removes the stripped-then-rebuilt env construction that was part of
the old overlay path — no longer needed.
Test updates:
- Replaced "lets saved startup profile override profile-managed env"
(encoded the old broken behavior) with a regression test that pins
the new semantic: plural env survives when legacy is stale.
- Added "falls back to legacy when plural hasn't applied" to pin the
first-run path still works.
Co-Authored-By: OpenClaude <openclaude@gitlawb.com>
---------
Co-authored-by: OpenClaude <openclaude@gitlawb.com>
First-run users with a credential already exported (ANTHROPIC_API_KEY,
OPENAI_API_KEY, etc.) currently still have to navigate the provider picker
or set CLAUDE_CODE_USE_* flags manually. Selecting the right provider from
ambient state should be automatic.
New module src/utils/providerAutoDetect.ts:
- detectProviderFromEnv() — synchronous env scan in a deterministic priority
order (anthropic → codex → github → openai → gemini → mistral → minimax).
Also detects Codex via ~/.codex/auth.json presence.
- detectLocalService() — parallel probes for Ollama (:11434) and LM Studio
(:1234), with honoring of OLLAMA_BASE_URL / LM_STUDIO_BASE_URL overrides.
Short 1.2s default timeout so first-run latency stays low when no local
service is running.
- detectBestProvider() — orchestrator. Env scan short-circuits the probe;
only hits the network when env has nothing.
All detection paths are side-effect-free: returns a DetectedProvider
descriptor describing what was found and why. Callers decide whether to
apply it (gated on hasExplicitProviderSelection() / profile file existence)
and how to hydrate the launch env.
Codex auth-file check is injectable (hasCodexAuth option) so tests are
hermetic from the dev machine's ~/.codex/auth.json state.
Co-authored-by: OpenClaude <openclaude@gitlawb.com>
* feat: add thinking token tracking and historical analytics
- extractThinkingTokens(): separate thinking from output tokens
- TokenUsageTracker class for historical analytics
- Track: cache hit rate, most used model, requests per hour/day
- Analytics: average tokens per request, totals
- Add tests (7 passing)
PR 4B: Features 1.10 + 1.11
* refactor: extract thinking and analytics to separate files
- Create thinkingTokenExtractor.ts with ThinkingTokenAnalyzer
- Create tokenAnalytics.ts with TokenUsageTracker
- Add production-grade methods and tests
- Update test imports
Fixes#774. When tool_result content contains multiple text blocks,
they were serialized as arrays instead of strings, causing DeepSeek
to reject the request with 400 error.
Changes:
- convertToolResultContent: collapse all-text arrays to joined string
- convertContentBlocks: defensive collapse for user/assistant messages
- Arrays with images are preserved (not collapsed)
Tests: 3 new tests added, 53 pass, 0 fail
Co-authored-by: nick.mesen <nickmesen@users.noreply.github.com>
Most everyday turns ("ok", "thanks", "yep go ahead", "what does that do?")
get no measurable quality improvement from Opus-tier models over Haiku-tier,
but cost ~10x more and stream slower. Smart routing opts a user into
automatically routing obviously-simple turns to a cheaper model while
keeping the strong model for anything non-trivial.
New module src/services/api/smartModelRouting.ts:
- routeModel(input, config) → { model, complexity, reason }
- Pure primitive: no env reads, no state, caller supplies everything.
- Config is opt-in (enabled: false by default).
Routes to strong (conservative) when ANY of:
- First turn of session (task-setup is worth the quality)
- Code fence or inline code span present
- Reasoning/planning keyword (plan, design, refactor, debug, architect,
investigate, root cause, etc. — 20+ anchors)
- Multi-paragraph input
- Over char/word cutoff (defaults: 160 chars, 28 words; matches hermes)
Routes to simple only for clearly-trivial chatter.
Decision includes a reason string for a future UI indicator that shows
which tier handled the turn.
Integration into query path is intentionally deferred to a follow-up PR so
the heuristics can be reviewed and tuned in isolation first.
Co-authored-by: OpenClaude <openclaude@gitlawb.com>
* feat(provider): first-class Moonshot (Kimi) direct-API support
Moonshot's direct API (api.moonshot.ai/v1) is OpenAI-compatible and works
today via the generic OpenAI shim, including the reasoning_content channel
that Kimi returns alongside the user-visible content. But the UX was rough:
unknown context window triggered the conservative 128k fallback + a warning,
and the provider displayed as "Local OpenAI-compatible".
Makes Moonshot a recognized provider:
- src/utils/model/openaiContextWindows.ts: add the Kimi K2 family and
moonshot-v1-* variants to both the context-window and max-output tables.
Values from Moonshot's model card — K2.6 and K2-thinking are 256K,
K2/K2-instruct are 128K, moonshot-v1 sizes are embedded in the model id.
- src/utils/providerDiscovery.ts: recognize the api.moonshot.ai hostname
and label it "Moonshot (Kimi)" in the startup banner and provider UI.
Users can now launch with:
CLAUDE_CODE_USE_OPENAI=1 \
OPENAI_BASE_URL=https://api.moonshot.ai/v1 \
OPENAI_API_KEY=sk-... \
OPENAI_MODEL=kimi-k2.6 \
openclaude
and get accurate compaction + correct labeling + correct max_tokens out
of the box.
Co-Authored-By: OpenClaude <openclaude@gitlawb.com>
* fix(openai-shim): Moonshot API compatibility — max_tokens + strip store
Moonshot's direct API (api.moonshot.ai and api.moonshot.cn) uses the
classic OpenAI `max_tokens` parameter, not the newer `max_completion_tokens`
that the shim defaults to. It also hasn't published support for `store`
and may reject it on strict-parse — same class of error as Gemini's
"Unknown name 'store': Cannot find field" 400.
- Adds isMoonshotBaseUrl() that recognizes both .ai and .cn hosts.
- Converts max_completion_tokens → max_tokens for Moonshot requests
(alongside GitHub / Mistral / local providers).
- Strips body.store for Moonshot requests (alongside Mistral / Gemini).
Two shim tests cover both the .ai and .cn hostnames.
Co-Authored-By: OpenClaude <openclaude@gitlawb.com>
* fix: null-safe access on getCachedMCConfig() in external builds
External builds stub src/services/compact/cachedMicrocompact.ts so
getCachedMCConfig() returns null, but two call sites still dereferenced
config.supportedModels directly. The ?. operator was in the wrong place
(config.supportedModels? instead of config?.supportedModels), so the null
config threw "Cannot read properties of null (reading 'supportedModels')"
on every request.
Reproduces with any external-build provider (notably Kimi/Moonshot just
enabled in the sibling commits, but equally DeepSeek, Mistral, Groq,
Ollama, etc.):
❯ hey
⏺ Cannot read properties of null (reading 'supportedModels')
- prompts.ts: early-return from getFunctionResultClearingSection() when
config is null, before touching .supportedModels.
- claude.ts: guard the debug-log jsonStringify with ?. so the log line
never throws.
Co-Authored-By: OpenClaude <openclaude@gitlawb.com>
* fix(startup): show "Moonshot (Kimi)" on the startup banner
The startup-screen provider detector had regex branches for OpenRouter,
DeepSeek, Groq, Together, Azure, etc., but nothing for Moonshot. Remote
Moonshot sessions fell through to the generic "OpenAI" label —
getLocalOpenAICompatibleProviderLabel() only runs for local URLs, and
api.moonshot.ai / api.moonshot.cn are not local.
Adds a Moonshot branch matching /moonshot/ in the base URL OR /kimi/ in
the model id. Now launches with:
OPENAI_BASE_URL=https://api.moonshot.ai/v1 OPENAI_MODEL=kimi-k2.6
display the Provider row as "Moonshot (Kimi)" instead of "OpenAI".
Co-Authored-By: OpenClaude <openclaude@gitlawb.com>
* refactor(provider): sort preset picker alphabetically; Custom at end
The /provider preset picker was in ad-hoc order (Anthropic, Ollama,
OpenAI, then a jumble of third-party / local / codex / Alibaba / custom /
nvidia / minimax). Hard to scan when you know the provider name you want.
Sorts the list alphabetically by label A→Z. Pins "Custom" to the end —
it's the catch-all / escape hatch so it's scanned last, not shuffled into
the alphabetical run where a user looking for a named provider might
grab it by mistake. First-run-only "Skip for now" stays at the very
bottom, after Custom.
Test churn:
- ProviderManager.test.tsx: four tests hardcoded press counts (1 or 3 'j'
presses) that broke when targets moved. Replaces them with a
navigateToPreset(stdin, label) helper driven from a declared
PRESET_ORDER array, so future list edits only update the array.
- ConsoleOAuthFlow.test.tsx: the 13-row test frame only renders the first
~13 providers. "Ollama", "OpenAI", "LM Studio" sentinels moved below
the fold; swap them for alphabetically-early providers still visible
in-frame ("Azure OpenAI", "DeepSeek", "Google Gemini"). Test intent
(picker opened with providers listed) is preserved.
Co-Authored-By: OpenClaude <openclaude@gitlawb.com>
---------
Co-authored-by: OpenClaude <openclaude@gitlawb.com>
* feat: add model caching and benchmarking utilities
- Add modelCache.ts for disk caching of model lists
- Add benchmark.ts for testing model speed/quality
* fix: address review feedback - async fs, multi-provider support, error handling
* feat: add /benchmark slash command and unit tests
* feat: add /benchmark slash command and unit tests
* feat: enable 16 additional feature flags in open build
Activate features whose source is fully available in the mirror and
that have no Anthropic-internal infrastructure dependencies:
UI/UX: MESSAGE_ACTIONS, HISTORY_PICKER, QUICK_SEARCH, HOOK_PROMPTS
Reasoning: ULTRATHINK, TOKEN_BUDGET, SHOT_STATS
Agents: FORK_SUBAGENT, VERIFICATION_AGENT, MCP_SKILLS
Memory: EXTRACT_MEMORIES, AWAY_SUMMARY
Optimization: CACHED_MICROCOMPACT, PROMPT_CACHE_BREAK_DETECTION
Safety: TRANSCRIPT_CLASSIFIER
Debug: DUMP_SYSTEM_PROMPT
Also reorganize featureFlags into documented sections (disabled/upstream/new)
with inline comments explaining each flag's purpose.
* feat: add centralized GrowthBook defaults map for open build
Add _openBuildDefaults in the GrowthBook stub (no-telemetry-plugin.ts)
with all 66 runtime feature keys, organized by category with inline
comments describing each flag's purpose.
Override tengu_sedge_lantern (AWAY_SUMMARY) and tengu_hive_evidence
(VERIFICATION_AGENT) to true so these features work out of the box
without requiring manual ~/.claude/feature-flags.json setup.
Priority: feature-flags.json > _openBuildDefaults > upstream default
* feat: replace refusal language with positive security guidance
Remove refusal instructions from CYBER_RISK_INSTRUCTION since they are
redundant for Anthropic models (applied server-side) and useless for
uncensored models in multi-provider setups. Keep positive guidance for
security testing contexts and add red teaming support.
* Revert "feat: replace refusal language with positive security guidance"
This reverts commit 0463676a8f.
* fix: add EXTRACT_MEMORIES runtime gate overrides to open-build defaults
EXTRACT_MEMORIES was enabled at build-time but its runtime GrowthBook
gates (tengu_passport_quail, tengu_coral_fern) still defaulted to false,
preventing the feature from activating. Add both keys to
_openBuildDefaults so memory extraction works out of the box.
Also adds test coverage for _openBuildDefaults precedence behavior.
* docs: update GrowthBook runtime keys catalog to 88 keys
Expand the reference catalog in no-telemetry-plugin.ts from ~62 to 88
unique keys, covering all tengu_* call sites found in src/. Adds 27
previously undocumented keys including VSCode gates, dynamic configs
(auto-mode, cron, bridge), security gates, and KAIROS cron keys.
Adds "not exhaustive" disclaimer as suggested by Copilot reviewer.
Reorganizes categories with section dividers for readability.
