mirror of
https://github.com/Gitlawb/openclaude.git
synced 2026-09-28 01:55:44 -04:00
e1e277a3af7217822d41e5b9dc919033d0839db8
579
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Firebug24k
|
e1e277a3af |
fix: replace unsupported Unicode glyphs with widely available alternatives (#1088)
* fix: replace unsupported Unicode glyphs with widely available alternatives Replace TUI characters from obscure Unicode blocks (Miscellaneous Technical, Dentistry Symbols) that render as tofu boxes on most Linux terminal fonts, including all Nerd Font variants. Replacements: - ⏵⏵ (U+23F5) → ▶▶ (U+25B6) — permission mode indicator - ⎿ (U+23BF) → └ (U+2514) — tool output connector bracket U+23F5 and U+23BF are not present in any common monospace or Nerd Font. U+25B6 and U+2514 (Box Drawing) are universally supported. Fixes rendering on Linux terminals (kitty, xterm, Ptyxis), Windows terminal emulators (MobaXterm, PuTTY), and mosh sessions. Related upstream issues: - anthropics/claude-code#24102 - anthropics/claude-code#39127 - anthropics/claude-code#53080 * fix: replace remaining escaped \u23BF glyphs with \u2514 The initial patch replaced literal ⎿ characters but missed 5 escaped \u23BF forms in AgentProgressLine, SystemTextMessage, and UserLocalCommandOutputMessage. These render to the same unsupported U+23BF codepoint at runtime, producing tofu boxes on terminals without CJK serif fonts. Addresses reviewer feedback from jatmn and techbrewboss. |
||
 Németh Áron
|
e66d6e285a |
Prevent duplicate startup plugin hooks (#1073)
* Deduplicate duplicate plugin hooks on startup * Kill running hook processes on interrupt * Fix asyncRewake interrupt handling and hook dedupe tests * Reuse stable stringify for hook dedupe keys |
||
 3kin0x
|
5873bc6714 |
feat(knowledge): introduce local Orama persistence (feature-flagged) (#1015)
* feat(knowledge): introduce local Orama persistence (clean phase 1) - Added @orama/orama and persistence plugin. - Implemented optional local-only Orama backend in knowledgeGraph.ts. - Gated Orama logic behind OPENCLAUDE_KNOWLEDGE_ORAMA=1. - Converted knowledge and conversation arc functions to async. - Fixed circular dependency between knowledgeGraph and sessionStorage by moving getProjectsDir to envUtils. - Updated all call sites and tests to handle async Knowledge API. - Verified build and tests pass on latest main. * fix: address PR review comments for knowledge feature (async finalizeArcTurn and Orama cleanup) * test: add comprehensive stress and edge case testing for Orama Knowledge Graph * fix: prevent test pollution by restoring Orama env flag in stress test * refactor: harden Knowledge architecture with concurrency locks, optimized I/O, and consolidated state |
||
  JATMNandJATMN
|
23f6a956bd |
Fix theme picker OpenClaude branding (#1082)
Update the startup theme picker demo patch so the added console.log line says OpenClaude instead of Claude. Validation: bun run build; bun run smoke. Co-authored-by: JATMN <12479882+jatmn@users.noreply.github.com> |
||
 TechBrewBoss
|
ed7b6972f9 |
Feat: Add startup logo palette picker (#1072)
* Add startup logo palette picker * Address logo picker review feedback |
||
 jackil182
|
41b2496101 |
docs: update setup guides to clarify the only available auth method for Gemini (#1064)
* Update README.md Access token and local ADC workflow authentication is NOT available for Gemini. * Update advanced-setup.md API key authentication is the only available method for Gemini |
||
|
TechBrewBoss
|
16726399d8 | fix plan mode branding and plan path (#1062) | ||
 0xfandom
|
4830d6f778 |
fix(openai-shim): strip store for local providers (vLLM, custom) (#1048)
Local OpenAI-compatible servers (vLLM, llama.cpp, custom self-hosted gateways) often validate request bodies against a strict JSON schema and reject unknown fields with `400 Bad Request`. The shim already sends `store: false` (an OpenAI-only field for cloud conversation persistence) and strips it for known cloud hosts that share the same intolerance (Gemini, Cerebras). Local servers have no notion of remote conversation storage and fall in the same bucket. Add `isLocal` to `shouldStripResponsesStore` so any baseUrl resolved by `isLocalProviderUrl` (localhost / 127.0.0.1 / ::1 / 0.0.0.0) gets the field removed. Lenient locals (Ollama) already ignored it; this unblocks strict ones (vLLM Qwen) without behavior change for the former. Closes #672 (the `store: false` symptom; the separate `max_tokens` default vs. vLLM `max_model_len` collision is a different concern). |
||
 ArkhAngelLifeJiggy
|
4b1e516fc7 |
feat: incremental and cached token counting (#795)
* feat: incremental and cached token counting - Add IncrementalTokenCounter for performance (avoids recounting entire context) - Add getCacheTokens() to extract cache read/creation tokens - Add getNewTokensOnly() to get new tokens excluding cache - Add getTokenBreakdown() with cache efficiency percentage - Add comprehensive tests (10 passing) PR 1A: Token Counting Core (Features 1.6, 1.13) * refactor: extract IncrementalTokenCounter and tokenCache to separate files - Move IncrementalTokenCounter to incrementalTokenCounter.ts with stats tracking - Move cache utilities to tokenCache.ts with cost estimation and analytics - Remove duplicate implementations from tokens.ts - Update tokens.test.ts to import from new files - Add comprehensive tests for both new modules * fix: content-aware cache invalidation + high-precision costs Blocker fixes: - IncrementalTokenCounter: hash last message content for cache key - tokenCache: use 4-decimal precision for cost estimates (was 3, collapsed to $0) - exceedsBudget: use raw high-precision cost for budget comparisons Content hash prevents stale cache on same-length edits. * fix: PR 795 - fix cache invalidation and hash collisions Blockers: - getMessageHash now hashes ALL messages with full content (not just last message) - Prevents hash collisions when edits occur outside recent window - Incremental branch now verifies prefix hash matches before using cached count - If earlier messages mutated, full recalculation instead of stale increment * fix: PR 795 - fix prefix mutation + append invalidation Blocking: - Store both lastFullHash and lastPrefixHash separately - Compare actual prefix hash values, not just length (which always passes) - If prefix mutated, do full recalculation instead of stale increment Non-blocking: - Add regression tests for prefix mutation + append case * fix: PR 795 - fix isApproachingLimit to use tokenBudget not cache size Blocking: - Rename maxCacheSize to tokenBudget in IncrementalCounterConfig - isApproachingLimit now correctly compares against token budget (context window size) - Not cache entry size which was meaningless - Update CounterFactory to use appropriate tokenBudget values * fix: PR 795 - wire IncrementalTokenCounter into tokenCountWithEstimation - Integrate incremental counter into production token counting path - tokenCountWithEstimation now uses IncrementalTokenCounter.getCount() for rough estimation - Preserves exact usage baseline from last API response - getIncrementalTokenCounter() exported for external use - Uses lazy init to avoid circular dependency issues * fix: PR 795 - trim unused token cache surface - Remove tokenCache.ts (300+ line unused utility with no production caller) - Remove tokenCache.test.ts - Remove unused getCacheInfoFromUsage() from tokens.ts - Remove related tests in tokens.test.ts - PR now focused on IncrementalTokenCounter wired into tokenCountWithEstimation |
||
 Fernando Xavier
|
e438c89fbc |
fix: resolve two bugs making interactive mode unusable with plugin ecosystems (#825) (#830)
* fix(ink): import logForDebugging in App.tsx to prevent ReferenceError App.tsx used `logForDebugging()` in four call sites (XTVERSION async handlers, handleReadable/handleDataChunk stdin error-recovery branches) without importing it. When esbuild bundled this, the unresolved symbol collided with another identifier in scope; the bundler renamed most references to `logForDebugging2` but left the four in App.tsx pointing at the original name, which became undefined in the bundle. At runtime any modern terminal replying to the XTVERSION probe triggers an `unhandledRejection: logForDebugging is not defined`. Adding the missing import resolves the symbol before bundling, so the bundler emits a single consistent name for every call site. Refs #825 * fix(hooks): always close stdin after initial hook payload The conditional `if (!requestPrompt) child.stdin.end()` kept stdin open in interactive mode (where requestPrompt is always truthy while the REPL is mounted). Every plugin hook written against the Anthropic hook input contract reads stdin until EOF, so hooks blocked on the per-hook timeout (default 60s) on every user message — no HTTP request to the provider was made until every UserPromptSubmit hook had timed out. With ~10 plugins hooked to UserPromptSubmit (pipeline-orchestrator, superpowers, skill-advisor, episodic-memory, reflexion, etc.), a single prompt accumulated minutes of wait before any model call. Always closing stdin after the initial JSON payload restores the documented EOF-based contract. Verified locally: typical `oi` turnaround drops from ~60s to ~1s. Trade-off: the existing duplex-stdin path (hooks emitting prompt requests on stdout and receiving responses written back to stdin at hooks.ts:1237) is incompatible with an EOF contract by design and stops working with this change. Restoring that feature requires a separate IPC channel (named pipe, node IPC, or a second stream) rather than reusing the initial stdin; that refactor is out of scope for this fix. Given the blast radius of the current behaviour (every user with a plugin ecosystem sees unusable interactive mode), trading the rarely-used duplex path for the documented single-shot contract is the right short-term move. Closes #825 |
||
|
0xfandom
|
7cfc8d5dad |
feat(cli): honor --model alone without requiring --provider (#854)
Closes #808. Today `openclaude --model <name>` is parsed by Commander inside main.tsx but the startup banner and any provider-env-reading code run first, so the override is invisible until request time and saved-profile users see their stale model in the banner. Add applyModelFlagFromArgs that runs after saved-profile env application and before the banner. It routes the value to the env var matching the already-active provider (OPENAI_MODEL / GEMINI_MODEL / MISTRAL_MODEL / ANTHROPIC_MODEL) so the banner, resolution, and request payload all agree. Skipped when --provider is also present; that path is still handled by applyProviderFlagFromArgs. No writes to .openclaude-profile.json — override is process-scoped. |
||
 Dan Nakhla
|
402cd3dbe8 |
feat(websearch): add first-class Brave adapter; fix Google + Brave presets; restore Exa snippets (#1044)
This PR addresses three real bugs in WebSearch's provider layer plus adds Brave
as a first-class adapter so users with a BRAVE_API_KEY get auto-detection +
auto-chain inclusion (matching the ergonomics of TAVILY_API_KEY, EXA_API_KEY,
etc.).
## 1. New: Brave first-class adapter
`providers/brave.ts` — auto-detects `BRAVE_API_KEY`, slots into the auto chain
between Jina and Bing. Sends the bare token in `X-Subscription-Token` per
Brave's API contract. Mirrors the structure of `tavily.ts` / `bing.ts`.
Brave runs an independent web index (~30B pages), making it a useful
non-Google, non-Bing fallback. Bing's hosted API was sunsetted in Aug 2025
for new users, so Brave is a more practical default fallback in 2026.
## 2. Bug fix: Brave preset sent malformed auth header
The `WEB_PROVIDER=brave` preset in `custom.ts` declared
`authHeader: 'X-Subscription-Token'` but no `authScheme`, so the default
`'Bearer'` scheme prefix kicked in, producing:
X-Subscription-Token: Bearer <token> ← wrong, returns 401
Brave's API expects:
X-Subscription-Token: <token> ← bare token, no scheme
Fix: declare `authScheme: ''` on the preset; update
`buildAuthHeadersForPreset` to emit a bare token (no leading space) when the
scheme is empty.
## 3. Bug fix: Google preset never worked
`WEB_PROVIDER=google` was wired with `Authorization: Bearer <key>`, but the
Google Custom Search JSON API does not support Bearer auth. It requires:
- `?key=<API_KEY>` as a query param
- `?cx=<ENGINE_ID>` as a query param (Programmable Search Engine ID)
The preset previously had no slot for the engine ID at all, so any user
trying `WEB_PROVIDER=google` hit a 400/401 immediately.
Fix: extend `ProviderPreset` with two minimal fields — `authQueryParam` (key
goes in URL, not header) and `envQueryParams` (additional URL params sourced
from env vars). Rewire the `google` preset to use them; reading
`GOOGLE_CSE_ID` for `cx`.
A clear error fires fast if either `WEB_KEY` or `GOOGLE_CSE_ID` is missing,
instead of silently producing a 400 from upstream.
> Note: Google has announced the Custom Search JSON API will be discontinued
> on 2027-01-01 and is closed to new customers. The fix unbreaks existing
> users for the remaining ~8 months; the README includes a sunset notice and
> recommends Brave/Tavily/Exa for new setups.
## 4. Bug fix: Exa results had empty descriptions
`providers/exa.ts` never passed `contents` in the request body. Per the Exa
docs (https://docs.exa.ai/reference/search-api-guide-for-coding-agents):
> Use `highlights` for agent workflows. Highlights return 10x fewer
> tokens with the most relevant excerpts.
Without `contents: { highlights: true }`, the Exa response includes only
`{title, url, id, ...}` — no `text`, no `highlights`, no `summary`. The
adapter was then mapping `r.snippet ?? r.text` (neither field exists in the
default response shape), so every Exa hit came back with
`description: undefined`. Tavily/Brave/DDG all return snippets — Exa was
silently degraded.
Fix: request `contents: { highlights: true }` in the body, and map
`results[].highlights[]` (an array of strings) into the description by
joining up to 3 excerpts with ` … `. Falls back to `text` when present, then
`undefined` if neither field is populated.
## Tests
105 / 105 pass in `src/tools/WebSearchTool/providers/`:
- `providers/brave.test.ts` (new) — 7 tests: auth header, mapping,
domain filters, error paths
- `providers/exa.test.ts` (new) — 9 tests: contents request shape,
highlights mapping, fallback
chain, error paths
- `providers/custom.test.ts` (extended) — 6 new tests covering
`authScheme: ''` (Brave preset),
`authQueryParam` suppression
(Google preset), GOOGLE_CSE_ID +
WEB_KEY fail-fast errors, full
request shape via mocked fetch
205 / 205 pass across `src/tools/`. tsc clean for changed files.
## Docs
- `README_SEARCH_PROVIDERS.md` — promotes `BRAVE_API_KEY` to first-class,
documents `GOOGLE_CSE_ID` + sunset notice, fixes the provider table,
updates the auto-chain priority list and mode list
- `.env.example` — adds `BRAVE_API_KEY` line, documents `GOOGLE_CSE_ID`
requirement + sunset notice, updates auto-chain priority comment
## Migration / behavior changes
- `WEB_PROVIDER=google` users must now set `GOOGLE_CSE_ID` (was previously
unable to function at all, so this is a strict improvement).
- `WEB_PROVIDER=brave` users with `WEB_AUTH_SCHEME=""` workarounds can
drop the workaround — the preset now emits a bare token by default.
- Brave joins the auto-chain priority order
(firecrawl → tavily → exa → you → jina → **brave** → bing → mojeek →
linkup → ddg).
|
||
|
0xfandom
|
0adf97dc14 |
fix(openai-shim): strip store when baseUrl points at Cerebras (#1040)
Cerebras Cloud's chat-completions endpoint rejects requests with a `store` field — `400 store: property 'store' is unsupported`. The shim already strips `store` for Gemini hosts via `hasGeminiApiHost`; add the symmetric host check for Cerebras so users hitting `api.cerebras.ai` (directly or via the Custom provider preset) don't hit the same wall. Closes #1023. |
||
|
0xfandom
|
feb5791320 |
fix(effort): persist xhigh and send reasoning_effort on chat_completions (#857)
* fix(effort): persist xhigh and send reasoning_effort on chat_completions Fixes #853. Persistence: - EffortPicker.handleSelect normalizes the OpenAI-shaped `xhigh` to the standard `max` before writing AppState/settings. Previously `xhigh` fell through `toPersistableEffort` as undefined and the setting reverted on reload. - `/effort xhigh` takes the same normalization path. - `toPersistableEffort` maps `xhigh` -> `max` as a defensive backstop. - EffortPicker initialFocus reflects the user's stored selection (`max` shown as `xhigh`) instead of always snapping to the alias default. Payload: - openaiShim chat_completions body now emits `reasoning_effort` from `request.reasoning.effort`. Previously only codex_responses transport forwarded it, so Custom API users on chat_completions got no effort. - `getAnthropicClient` accepts `effortValue` and forwards it as `reasoningEffort` to `createOpenAIShimClient` (both providerOverride and direct-OpenAI paths) after converting `max` -> `xhigh` at the OpenAI boundary via `standardEffortToOpenAI`. - `claude.ts` threads the resolved effort through main streaming and both non-streaming fallback call sites. Tests: - openaiShim.test.ts: reasoning_effort emitted when override is passed, omitted otherwise, falls back to codex alias default. - effort.codex.test.ts: xhigh -> max normalization and standard<->OpenAI conversion. * fix(effort): skip max→high clamp for OpenAI/Codex models resolveAppliedEffort() unconditionally downgraded any non-Opus 'max' to 'high'. OpenAI/Codex models use 'max' as the standard internal form of 'xhigh' (the client shim converts on the wire), so the clamp was silently turning xhigh selections into high. The picker stored xhigh→max correctly and the shim emitted reasoning_effort, but the resolver in between rewrote max→high before the shim ever saw it. End result: UI showed xhigh, request sent high. Skip the clamp when modelUsesOpenAIEffort(model). Anthropic non-Opus clamp behavior unchanged. Adds two e2e tests in effort.codex.test.ts walking the full chain (persist → resolve → wire) so the regression can't recur silently. * test(effort): keep mocked module surfaces compatible with downstream tests bun:test's `mock.module()` is process-global and is not undone by `mock.restore()` (see comment in user.test.ts). When this file mocked `./auth.js`, `./thinking.js`, `../services/api/providerConfig.js`, etc. with reduced surfaces, later test files that imported the missing exports (refreshAndGetAwsCredentials, getRainbowColor, ...) crashed at module load with `SyntaxError: Export named 'X' not found`. Spread the real module exports into each mock factory so subsequent imports keep the full surface, while the targeted overrides for this file's tests still take effect. |
||
 Dolph Prefect
|
6af709e65e |
fix(agent): ensure main agent waits for subagent completion (#1032)
Updated the tool result instructions for async launched agents to explicitly command the model to end its turn. This prevents the main agent from prematurely continuing and duplicating work already delegated to a subagent, reducing redundant costs and improving orchestration reliability. |
||
 github-actions[bot]
|
280a7c14be |
chore(main): release 0.9.2 (#1038)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>v0.9.2 |
||
 Paweł
|
c873725d90 |
fix(cli): replace createRequire with static import for teammate.js (#1026) (#1033)
In commit
|
||
|
github-actions[bot]
|
00263c5a0e |
chore(main): release 0.9.1 (#1022)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>v0.9.1 |
||
  Vasanth Tandroot
|
094f04c803 |
fix(theme): remove stale memo wrappers from theme context hooks (#534)
* fix(theme): remove stale React Compiler memo wrappers from theme hooks Rebase on current main (includes #589 reconciler fix). The React Compiler memo caches (_c) in useTheme() and usePreviewTheme() use referential equality checks on destructured context values. These caches can return stale references when the ThemeProvider's useMemo recreates the context value object but the individual property references (setThemeSetting, setPreviewTheme, etc.) compare equal — the memo short-circuits and returns a cached tuple/object that still holds the old closure captures. This is a distinct bug from #589 (which fixed the ink reconciler's commitUpdate path for host prop updates). #589 ensures that when React _does_ re-render a component with new props, those props actually reach the DOM node. But the memo wrappers here prevent React from _even seeing_ the new context value in the first place — the hook returns the stale cached result. Removing the memo wrappers ensures useTheme() and usePreviewTheme() always read the current context value, eliminating the stale-reference path entirely. * test(theme): add regression tests for useTheme()/usePreviewTheme() stale-value bug These tests verify that context hooks always return fresh values after ThemeProvider re-renders, even when React Compiler memo caches are in play. - useTheme() must reflect currentTheme changes immediately after setThemeSetting is called (not return a stale cached tuple). - usePreviewTheme() must return functional actions after context re-renders (not stale closures from before the theme change). On current main (with _c memo wrappers), these tests expose the bug: the memo cache compares setThemeSetting by reference (stable across renders via useMemo) and short-circuits, returning the old cached result with stale currentTheme. * fix(test): correct import paths for ThemeProvider.test.tsx Fix relative paths for ink.js, KeybindingSetup, AppStateProvider, useStdin mock, systemTheme mock, and config mock to account for the test file being in src/components/design-system/ rather than src/components/. * fix(test): rewrite ThemeProvider tests using Ink renderer Use Ink's createRoot instead of react-dom/client, matching the pattern from ThemePicker.test.tsx. The tests now render through Ink's terminal renderer and check frame output for theme values, which is the same environment ThemeProvider actually runs in. * fix(test): correct all relative import paths for design-system/ depth - ink.js, KeybindingSetup, AppStateProvider: ../ → ../../ - StructuredDiff: same pattern as ThemePicker test adjusted for depth --------- Co-authored-by: root <root@vm7508.lumadock.com> |
||
 Kevin Codex
|
d19f4d335d | fix flaky test (#1021) | ||
|
github-actions[bot]
|
9994b50b0a |
chore(main): release 0.9.0 (#978)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>v0.9.0 |
||
 Kevin CodexandOpenClaude
|
7b02695b15 |
Feat/codex default provider (#1014)
* chore: add .openclaude/ to gitignore The .openclaude/ directory contains auto-generated project-local files (wiki pages, convention cache, local settings) that should not be committed to the repository. Co-Authored-By: OpenClaude <openclaude@gitlawb.com> * feat: make Codex + GPT 5.5 the default provider and model Changes the default provider to Codex and default model to GPT 5.5: - package.json: dev script now uses provider-launch.ts codex - providerRecommendation.ts: getGoalDefaultOpenAIModel returns gpt-5.5 for coding and balanced goals (was gpt-4o) - providerConfig.ts: fallback model changed from gpt-4o to codexplan (resolves to gpt-5.5) - ProviderManager.tsx: Codex OAuth option now shows green "★ Recommended" badge in the provider picker Co-Authored-By: OpenClaude <openclaude@gitlawb.com> * fix: replace Box with nested Text in Codex label Ink's <Text> component cannot contain <Box>. The label is rendered inside a <Text> parent, so use nested <Text> elements instead. Co-Authored-By: OpenClaude <openclaude@gitlawb.com> * fix: default to Codex when no provider profile is saved When no persisted provider profile exists (fresh install / first run), buildStartupEnvFromProfile now injects Codex + GPT 5.5 env vars instead of returning process.env unchanged. Falls back gracefully — if Codex credentials are available (OAuth or existing), uses those; otherwise injects base URL and model defaults so the provider picker shows GPT 5.5 as the default. This closes the gap where node dist/cli.mjs (production start) would default to firstParty (Anthropic) when no profile or env vars were set. Co-Authored-By: OpenClaude <openclaude@gitlawb.com> * chore: resolve stash conflict markers from accidental stash pop Cleans up merge conflict artifacts left by a git stash pop from an unrelated branch (chore/add-atomic-chat-partner). Kept upstream (current branch) version in all cases. Co-Authored-By: OpenClaude <openclaude@gitlawb.com> * fix: restore memoize import and cleanup stash artifacts Restores the memoize import dropped during conflict resolution in modelSupportOverrides.ts. Removes duplicate originalEnv declaration and redundant delete statements in providerValidation.test.ts. Co-Authored-By: OpenClaude <openclaude@gitlawb.com> * revert change in package.json * fix broken test * fix color --------- Co-authored-by: OpenClaude <openclaude@gitlawb.com> |
||
|
Kevin Codex
|
1f66d322ad | fix flaky tests in full test run (#1020) | ||
|
0xfandom
|
40ae1e7200 |
fix(shims): strip x-anthropic-billing-header block before forwarding system prompt (#1019)
`getAttributionHeader()` (src/constants/system.ts) builds an `x-anthropic-billing-header: cc_version=...; cc_entrypoint=...; ...` line that gets prepended to the system-prompt block array in src/services/api/claude.ts:1390-1401. The Anthropic API path needs it (server _parse_cc_header consumes it), but the OpenAI / Codex shims joined every text block straight into the outbound `system` / `instructions` payload, so non-Anthropic providers received an Anthropic-only billing string in their prompt — token waste, plus a per-build fingerprint that churns local-model KV cache and any upstream prompt cache (the slowdown unsloth flagged for Claude Code). Fix the two `convertSystemPrompt` helpers (openaiShim.ts:241, codexShim.ts:124) to drop blocks whose text starts with `x-anthropic-billing-header`. Anthropic-bound traffic is unaffected — the block is built into Anthropic-shaped requests directly and never flows through these helpers. Tests: - openaiShim.test.ts: e2e capturedBody assertions on chat-completions + responses-API paths confirm the line is absent and the rest of the system prompt survives. - codexShim.test.ts: convertSystemPrompt is now exported (pure helper) and unit-tested for array + only-attribution + plain-string cases. Closes #607. |
||
|
0xfandom
|
1020663990 |
chore(engines): require Node >=22 to match runtime deps (#1018)
@mendable/firecrawl-js@4.18.1 (lazy-loaded by WebSearch + WebFetch) requires Node >=22, and CI runs Node 22 + 24, but package.json still advertised >=20.0.0. Result: npm install on Node 20 surfaced an EBADENGINE warning that users routinely ignored, then exploded with a cryptic syntax error the first time a web tool actually pulled firecrawl in. Bump engines.node to >=22.0.0 so npm refuses Node 20 up front, and refresh the stale comment in withResolvers.ts that still pointed at the long-gone >=18.0.0 baseline. Closes #1009 (engine half — the EACCES half is standard global-install perms, not openclaude's to fix). |
||
|
0xfandom
|
1c746750f6 |
fix(web-search): surface diagnostic when adapter returns 0 hits and no native fallback (#1006)
For openai-shim providers (minimax, moonshot, nvidia-nim, github copilot, etc.) hasNativeSearchFallback() is false, so when the DuckDuckGo adapter returns 0 hits in auto mode the call() path silently falls through to the native Anthropic web_search_20250305 tool. Those providers don't support that tool, producing a silent "Did 0 searches" with no signal that the default DDG backend is rate-limited or that no API-key backend is configured. Convert the silent fallthrough into an actionable result that names the active provider, the failing backend, and the env vars to set (FIRECRAWL_API_KEY / TAVILY_API_KEY / EXA_API_KEY / JINA_API_KEY / BING_API_KEY / MOJEEK_API_KEY / LINKUP_API_KEY / YOU_API_KEY) plus the native-provider escape hatch (Anthropic / Vertex / Foundry). Same root-cause family as the catch branch directly below — that already throws an actionable error for the throw-on-failure case; this matches it for the success-with-0-hits case. Auto mode + 0 hits + native fallback available is unchanged: still falls through so Anthropic/Vertex/Foundry/Codex can serve the result. Explicit adapter mode is unchanged. Adds bun:test coverage for the new helpers via the WebSearchTool __test export. Refs #614, #994 |
||
  Ali AlakbarliandAli Alakbarli
|
60c76b6599 |
feat: SDK Runtime — Query Engine, Sessions, and Build Pipeline (#984)
* feat(sdk): add SDK foundation — type declarations, errors, and utilities Adds standalone SDK building blocks with no SDK source dependencies: - sdk.d.ts: ambient type declarations for SDK bundle - coreSchemas.ts + coreTypes.generated.ts: Zod schemas and generated types - errors.ts: SDK-specific error classes - validation.ts: input validation utilities - messageFilters.ts: extracted message filter logic - handlePromptSubmit.ts: imports from messageFilters - 16 generated-types tests * fix(sdk): narrow assertFunction type from broad Function to callable signature Code review finding: assertFunction used `asserts value is Function` which accepts any function-like value without narrowing. Changed to `(...args: any[]) => any` for better type safety. * fix(sdk): update sdk.d.ts header — manually maintained, not generated Reviewer noted the header said "Generated from index.ts" but no generator produces this file. Updated to "Manually maintained — keep in sync with index.ts". Drift detection added in validate-externals.ts (PR 3). * fix(sdk): align sdk.d.ts types with canonical coreTypes.generated.ts Tighten SDK public type contract to resolve reviewer blockers: - PermissionResult: unknown[] → precise 6-shape discriminated union (addRules/replaceRules/removeRules/setMode/addDirectories/removeDirectories) - SDKSessionInfo: snake_case → camelCase (sessionId, lastModified, etc.) - ForkSessionResult: session_id → sessionId - SDKPermissionRequestMessage: uuid + session_id now required - SDKPermissionTimeoutMessage: added uuid + session_id - SessionMessage: parent_uuid → parentUuid - SDKMessage/SDKUserMessage/SDKResultMessage: replaced loose inline definitions with re-exports from coreTypes.generated.ts * feat(sdk): wire existing code modules + SDK shared utilities Modifies core modules for SDK integration: - QueryEngine, tools, state, commands: SDK type hooks - SDK shared utilities (shared.ts, permissions.ts) - 21 SDK tests (shared-utils, permissions) Stack: main ← pr1-foundation ← pr2-sdk-core * feat(sdk): add snake_case ↔ camelCase key mapping utilities casing.ts provides recursive key transformation for the SDK boundary layer. Internal runtime uses snake_case; public API exposes camelCase. Will be used by shared.ts, sessions.ts, query.ts at export boundaries. * test(sdk): add tests for snake_case ↔ camelCase mapping utilities Covers snakeToCamel, camelToSnake, mapKeysToCamel, mapKeysToSnake including nested objects, arrays, null/undefined, and round-trips. * feat(sdk): add SDK runtime — query engine, sessions, build pipeline Completes the SDK implementation: - SDK build target (dist/sdk.mjs) with TUI dependency stubbing - External dependency lists (scripts/externals.ts) - SDK type generation from Zod schemas (scripts/generate-sdk-types.ts) - External validation (scripts/validate-externals.ts) - SDK source: index, query, v2, sessions modules - agentSdkTypes: re-exports SDK functions (query, createSession, etc.) - 136 SDK tests + 7 build scanner tests Stack: main ← pr1-foundation ← pr2-sdk-core ← pr3-sdk-runtime * fix(sdk): align internal SDK types with camelCase public contract shared.ts: SDKSessionInfo, ForkSessionResult, SessionMessage fields now use camelCase matching sdk.d.ts. SDKPermissionRequestMessage and SDKPermissionTimeoutMessage gain required uuid + session_id fields. permissions.ts: onPermissionRequest/onTimeout callbacks now include uuid and session_id in emitted messages. * fix(sdk): update runtime modules to use camelCase field names sessions.ts: toSDKSessionInfo outputs camelCase keys, entryToSessionMessage uses parentUuid, forkSession returns sessionId. query.ts: reads sessionId from listSessions/forkSession results instead of snake_case session_id. * fix(test): update session tests to use camelCase field names session_id → sessionId in forkSession result assertions and getSessionMessages calls. * fix(sdk): prevent permission timeout race condition with once-only resolve wrapper Add createOnceOnlyResolve utility to prevent double-resolution of promises when timeout and host response happen simultaneously. This ensures deterministic behavior in the permission handling flow. * fix(sdk): improve race condition test robustness * fix(sdk): handle consecutive underscores in snakeToCamel conversion Changes: - Use _+([a-z]) regex to match multiple consecutive underscores before letters - Add lookahead (?=. ) to preserve underscore-letter pairs at string end - Handle dunder names (__proto__, __typename) by stripping wrapper and capitalizing - Add tests for consecutive underscores and trailing underscore preservation * fix(sdk): include original error message in permission callback denial When a canUseTool callback throws an error, the catch block now includes the original error message in the denial message, making debugging easier for SDK consumers. * feat(sdk): add optional timeout to env mutex for deadlock prevention Add timeout parameter to acquireEnvMutex() to prevent infinite waits in deadlock scenarios. The timeout is optional and defaults to no timeout (wait forever) for backward compatibility. Returns a MutexAcquireResult object with acquired status and optional timeout reason for failed acquisitions. * fix(sdk): remove timed-out callback from mutex queue to prevent deadlock * test(sdk): add missing error path and timeout scenario tests Add tests for timeout scenarios when host doesn't respond to permission requests, fallback behavior when no onPermissionRequest callback, and MCP connection edge cases for undefined/empty config. * fix(sdk): address code review issues - race conditions, validation, error handling - Add createPermissionTarget() factory that applies onceOnlyResolve at registration time, fixing race condition where timeout and host response could both try to resolve the same promise - Add try-catch to releaseEnvMutex() to prevent permanent lock if callback throws - Extract DEFAULT_PERMISSION_TIMEOUT_MS constant (30 seconds) - Add MCP config validation rejecting null, non-objects, and arrays - Preserve error stack traces in MCP connection failures - Add runtime validation to mapMessageToSDK for null/non-object/invalid type - Update tests to use createPermissionTarget and add validation tests * fix(sdk): syntax fixes and MCP connection error handling - Remove extra closing parenthesis in permissions.ts - Remove extra closing braces in shared.ts type definitions - Wrap MCP connection in try/catch to continue without MCP tools on failure * fix(sdk): syntax fixes, MCP error handling, and logic clarity - Remove extra closing parenthesis in permissions.ts - Remove extra closing braces in shared.ts type definitions - Wrap MCP connection in try/catch to continue without MCP tools on failure - Clarify thinkingConfig logic: use ?? true instead of !== false - Add explanatory comment about thinkingEnabled default behavior - Apply createOnceOnlyResolve wrapper in QueryImpl.registerPendingPermission * fix(sdk): comprehensive error handling and resource cleanup - Add try-catch around injectAgents() to gracefully handle plugin agent tool validation failures (prevents test crashes from unknown 'LS' tool) - Add console.warn logging to agent loading/injection catch blocks for debugging visibility (matches v2.ts pattern) - Add pendingPermissionPrompts.clear() to close() and interrupt() methods in both query.ts and v2.ts to prevent memory accumulation - Add close() method to SDKSession interface and SDKSessionImpl - Wrap MCP connection in query.ts with try-catch (matches v2.ts behavior) - Add timeoutQueue cleanup in finally blocks (query.ts + v2.ts) - Remove error.stack from MCP error messages to prevent internal path leak All 208 SDK tests pass. TypeScript errors are pre-existing. * fix(sdk): address code review non-blocking issues - Add SDKAgentLoadFailureMessage type for agent load failure events - Emit agent definition/injection failures to SDK message stream - Add tool name to permission timeout denial message - Replace 'as any' casts with proper typed state access - Fix supportedCommands to use correct mcp.commands/plugins.commands paths - Update test for correct AppState structure * fix(sdk): address code review blocking and non-blocking issues Blocking Issues Fixed: - MCP cleanup missing on session/query close - now disconnects MCP clients to prevent resource leaks in long-running processes with multiple sessions - Engine reference not cleared on close - now sets _engine = null to prevent memory leaks - Added MCP cleanup tests (9 new tests covering cleanup scenarios) Non-Blocking Issues Fixed: - Removed redundant catch block that just rethrew errors (query.ts) - Fixed inconsistent timeout denial message format (permissions.ts) - Fixed hardcoded tool name 'Bash' in test (permissions.test.ts) - Exported PermissionResolveDecision type for SDK consumers (index.ts) All 217 SDK tests pass. * fix(sdk): address code review type consistency issues - Add close() method to SDKSession interface (documented but missing from type) - Fix SDKSessionInfo, ForkSessionResult, SessionMessage field naming: snake_case → camelCase to match sdk.d.ts public contract and implementation - Add uuid and session_id to SDKPermissionTimeoutMessage for correlation - Fix JSDoc comment in forkSession to use sessionId (not session_id) These changes align internal types (shared.ts) with the public SDK contract (sdk.d.ts) and actual implementation output. The merge from origin/main introduced snake_case types that mismatched camelCase implementation and tests. * fix: restore openclaude.json comment in REPL.tsx Merge |
||
 TechBrewBossandCopilot Autofix powered by AI
|
6636bce74b |
Add opt-in Karpathy guidelines skill (#909)
* Add opt-in Karpathy guidelines skill * Potential fix for pull request finding 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> |
||
|
TechBrewBoss
|
de0e395467 |
Fix commit attribution configuration (#920)
* fix: configure commit attribution * fix: avoid duplicate commit-message usage * fix: clarify commit attribution command * fix: clarify set usage and default email * fix: address commit attribution review feedback * fix: use openclaude email for all attribution * fix: tighten attribution model formatting |
||
|
TechBrewBoss
|
f5ec185609 | Store provider profiles in user config (#969) | ||
  
|
a133e7631a |
feat: support self-hosted Firecrawl via FIRECRAWL_API_URL (#949)
* feat: support self-hosted Firecrawl via FIRECRAWL_API_URL Adds FIRECRAWL_API_URL env var to enable self-hosted Firecrawl instances. Both WebFetchTool and firecrawl search provider now check for either FIRECRAWL_API_KEY (cloud) or FIRECRAWL_API_URL (self-hosted). The FirecrawlClient accepts apiUrl for custom endpoints. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: remove incorrect non-null assertion on FIRECRAWL_API_KEY Passing undefined to FirecrawlClient.apiKey is correct when using FIRECRAWL_API_URL without an API key. Also adds regression tests for isConfigured() covering all four env combinations. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: trigger CI --------- Co-authored-by: Kunthawat Greethong <kunthawat@gmailcom> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> |
||
|
ArkhAngelLifeJiggy
|
ca676affc4 |
feat: context partitioning and relevance-based pruning (#849)
* feat: context partitioning and relevance-based pruning PR 2B - Section 2.3, 2.4: - Add contextPartitioning.ts with priority zones - Add relevancePruning.ts with keyword overlap scoring - Add comprehensive tests (13 passing) * fix: resolve PR 849 blocking issues - Fix older system messages now appended in partitionContext() - Fix getAvailableSpace() accepts contextWindow param - Fix hasToolCalls/hasErrors() handle structured content blocks - Wire helpers into autoCompact.ts * fix: resolve PR 849 remaining blockers - Preserve system messages in pruning (not dropped) - Group messages by id to preserve transcript pairs - Add test for message ID group preservation * fix: rewrite pruneByRelevance to use API-round grouping - preserves tool_use/tool_result pairs - Add groupMessagesByApiRound() matching repo invariant from grouping.ts - Groups both recent and older messages at assistant message.id boundaries - Ensures tool_use + tool_result pairs stay together, not split across prune boundary - Add test for API-round grouping with real tool_use + tool_result transcript shape |
||
|
TechBrewBoss
|
a8f71f3ac0 |
Fix user agent loading from OpenClaude config dirs (#972)
* Load OpenClaude agents from config dir * Address agent path review feedback |
||
|
JATMN
|
6d0953a79c | fix(groq): strip unsupported store field (#983) | ||
|
TechBrewBoss
|
884746dbe9 |
Provider: Add Hicap gateway provider (#979)
* Add Hicap provider and gateway auth presets * Fix Hicap compatibility preset coverage * Authenticate ripgrep download in PR checks * Use Opus 4.7 as Hicap default * Address Hicap review feedback * Address provider review blockers * Clarify gateway header UI docs * Remove Hicap endpoint from README |
||
|
JATMN
|
3d791bf07f |
Disable feedback/mobile commands and refresh OpenClaude branding (#980)
- disable /feedback and /mobile from command availability while keeping implementation code in place - remove or rewrite lingering user guidance that pointed to /feedback or /mobile - switch HelpV2 to a public build version helper and fix the help dialog wrapper regression - update OpenClaude-facing links and prompt copy for issue reporting and branding consistency |
||
 chioarub
|
11f265c094 | test(api): cover first-party fetch wrapper runtime path (#990) | ||
  Muralikrishna DudakaandMurali D
|
7bb4c2e10d |
Merge configured and discovered provider profile models (#991)
Co-authored-by: Murali D <mdudaka@cisco.com> |
||
|
3kin0xandKevin Codex
|
990a5a2afb |
fix(tests): resolve flakiness due to module leak and env state leakage (#988)
- StartupScreen.test.ts: Scope settings module mock to prevent process-global pollution. - providerConfig.github.test.ts: Explicitly scrub environment variables before each test. - providerProfiles.test.ts: Add beforeEach to clear RESTORED_KEYS and ensure fresh registry state. - providerValidation.test.ts: Ensure integrations registry is loaded and scrub environment to prevent leakage from host shell. This consolidates fixes from PR 944 and addresses additional failures found after rebasing onto main (v0.8.0). Co-authored-by: Kevin Codex <kevin@gitlawb.com> |
||
|
JATMN
|
d948769dd5 |
feat: rework release notes around GitHub releases (#981)
* feat: rework release notes around GitHub releases - switch /release-notes from upstream changelog parsing to OpenClaude GitHub release data - add a public build version helper and use it for release URL/seen-version tracking - render release notes in-app with section headers like Features and Bug Fixes - cache serialized GitHub release notes locally for startup and command fallback paths - preserve snake_case identifiers while sanitizing markdown content - keep LogoV2 whats-new output within its display budget - add focused tests for parsing, formatting, version tags, and display slicing * Normalize release-please changelog versions Use normalizePublicVersion when parsing cached changelog headings so release-please markdown headings like ## [0.8.0](...) (2026-05-02) map to the expected version key. Also normalize direct version lookups consistently and add a regression test covering getReleaseNotesForVersion and getRecentReleaseNotes against the new CHANGELOG.md format. |
||
 chioarubandCursor
|
35f86a9580 |
fix(startup): make CLAUDE logo D distinct (#986)
* fix(startup): make CLAUDE logo D distinct Adjust the startup ASCII logo so the D in CLAUDE no longer reads as an O, and add a focused regression test for the rendered shape. Co-authored-by: Cursor <cursoragent@cursor.com> * test(startup): clear CI flag for logo rendering assertion Ensure the startup logo regression test exercises the interactive render path under GitHub Actions, where CI is set by default. Co-authored-by: Cursor <cursoragent@cursor.com> --------- Co-authored-by: Cursor <cursoragent@cursor.com> |
||
 KRATOS
|
dc3c065c4a |
fix(mcp): allow third-party providers to approve project-scope .mcp.json servers (#696) (#937)
When a user runs openclaude with a third-party provider, project-scope MCP servers added via `openclaude mcp add -s project ...` were silently dropped from `/mcp` and `openclaude mcp list`. Re-adding the same server printed "MCP server already exists in .mcp.json" but the server never actually loaded. Reporter @gbmerrall pinpointed the cause to the `if (usesAnthropicSetup)` gate around `handleMcpjsonServerApprovals` in src/interactiveHelpers.tsx. The MCP approval dialog and the CLAUDE.md external-includes warning are about workspace trust, not about Anthropic auth. Gating them on `usesAnthropicSetup` meant 3P-provider users never saw the dialog that writes `enableAllProjectMcpServers: true` and `enabledMcpjsonServers: [...]` to settings.local.json — without those settings, the MCP server isn't loaded for use. Drop the `usesAnthropicSetup` gate around the approval flow. The inner logic is unchanged and `handleMcpjsonServerApprovals` already early-returns when no servers are pending, so users without project `.mcp.json` see no new behavior. - src/interactiveHelpers.tsx: drop the gate, add a comment explaining why (and cite #696 so future readers can find context). - src/__tests__/bugfixes.test.ts: +2 regression tests asserting the gate is gone and the issue is referenced. Verified locally on Linux: build passes (v0.7.0), 1634 tests pass, the 4 remaining failures (StartupScreen.test.ts, thinking.test.ts) reproduce on main and are unrelated. The bundled dist/cli.mjs shows `handleMcpjsonServerApprovals(root2)` running directly after `setSessionTrustAccepted(true)` with no auth gate. |
||
|
github-actions[bot]
|
da375271b4 |
chore(main): release 0.8.0 (#927)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>v0.8.0 |
||
|
Kevin CodexandOpenClaude
|
95a817fdb0 |
fix(provider): apply Codex OAuth session switch correctly (#974)
* fix(provider): apply Codex OAuth session switch correctly Ensure Codex OAuth activation in an existing session does not briefly apply an empty OpenAI API key, preventing missing Authorization headers until restart. Co-Authored-By: OpenClaude <openclaude@gitlawb.com> * fix(provider): preserve explicit env for Codex API profiles Limit the Codex session-switch override to OAuth profiles so explicit OpenAI environment settings keep taking precedence for regular Codex profiles. Co-Authored-By: OpenClaude <openclaude@gitlawb.com> * fix(provider): isolate Codex OAuth env from ambient credentials Keep Codex OAuth profile activation from inheriting ambient Codex API credentials so CI and user shells cannot poison the in-session OAuth regression path. Co-Authored-By: OpenClaude <openclaude@gitlawb.com> --------- Co-authored-by: OpenClaude <openclaude@gitlawb.com> |
||
|
KRATOS
|
cc0dab60a3 |
fix(openai-shim): don't label transport failures as HTTP 503 (#971) (#975)
Network/transport failures from custom OpenAI providers (e.g. ENETDOWN,
EAI_AGAIN, generic fetch failed) were thrown via APIError.generate(503,
...). The OpenAI SDK formats the error message as "${status} ${message}",
so users saw output like:
503 OpenAI API transport error: fetch failed (code=ENETDOWN)
This is misleading: a 503 implies the upstream server returned Service
Unavailable, but no HTTP response was received at all -- the failure
happened at the transport layer.
Use APIError.generate(0, ...) instead. The SDK's own factory returns
APIConnectionError for status 0, which is the semantically correct class
for "no response received" and produces a message without the spurious
"503" prefix. APIConnectionError extends APIError, so existing
`instanceof APIError` branches in errors.ts and elsewhere keep working.
Add a regression test that asserts the constructed error is an
APIConnectionError, has no status, and the message does not start with
"503".
|
||
 0xfandomand0xfandom
|
7711ddae48 |
fix(worktree): surface git stderr in rev-parse failure message (#690) (#954)
When /statusline (or any AgentTool path that creates a worktree) hits
`git rev-parse HEAD` failure during base-branch resolution, the
previous error swallowed git's stderr and reported only:
Failed to resolve base branch "HEAD": git rev-parse failed
That message gives users no way to distinguish empty repos
('unknown revision or path'), detached HEADs pointing at missing
objects, or a missing git binary on PATH — all surfaced identically.
Extract the message construction into buildRevParseFailureMessage()
and include git's stderr in the thrown Error. When the failing ref is
literally 'HEAD' (the fallback path when fetching origin/<branch>
fails), append a short hint about the most common cause (no commits)
and PATH check.
Adds focused tests in worktree.test.ts covering the empty-repo case,
the empty-stderr fallback (exit code), the branch-ref path (no HEAD
hint), and stderr whitespace trimming.
Fixes #690
Co-authored-by: 0xfandom <nikhoriariteish@gmail.com>
|
||
|
KRATOS
|
5c4fdca217 |
fix(plugins): sanitize env before spawning git so /plugin marketplace add works (#751) (#934)
Git 2.30+ refuses to start when any environment value contains a NUL,
CR, or LF character ("Unsafe environment: control characters are not
allowed in values"). User shells frequently leak such values — a
copy-pasted API key with a trailing newline, a terminal-set variable
with embedded escape sequences — which made every /plugin marketplace
add and /plugin install fail with that error before git even ran.
Add a small shared helper that builds the env passed to git child
processes and drops keys whose name or value contains a control
character. The legacy GIT_NO_PROMPT_ENV overrides (terminal prompt
disabled, askpass cleared) move into the same helper. Apply it to
every git invocation in marketplaceManager.ts (5 sites: gitPull,
gitClone, sparse-checkout, post-sparse checkout, reconcileSparseCheckout)
and pluginLoader.ts (8 sites: clone, fetch, checkout in both gitClone
and installFromGitSubdir).
A debug-level warning is logged once per process listing the dropped
key NAMES (not values) so the user can clean them up in their shell.
- src/utils/plugins/gitEnv.ts (new): sanitizeEnvForGit + buildGitChildEnv
- src/utils/plugins/gitEnv.test.ts (new): 10 unit tests covering CR/LF/NUL
in values, control char in key name, undefined values, defaults,
extras override
- src/utils/plugins/marketplaceManager.ts: replace 5 inline env spreads
with buildGitChildEnv()
- src/utils/plugins/pluginLoader.ts: pass env: buildGitChildEnv() to 8
git exec sites that previously inherited process.env unfiltered
Verified locally on Linux: before fix, git --version with a leaked
control-char env value fails with "Unsafe environment"; after fix it
runs cleanly. Live marketplaceManager.gitClone against a real GitHub
repo with the same leaked env succeeds and the repo is materialized
on disk.
|
||
|
chioarub
|
677d29ffd4 |
feat(lsp): add first-class code intelligence setup (#950)
* feat(lsp): add plugin candidate discovery * feat(lsp): add first-class setup command * fix(lsp): add bounded filesystem extension fallback * fix(lsp): repair official marketplace recommendations |
||
|
KRATOS
|
4fab8b913f |
fix(errors): show actual host in 404 message instead of Ollama hint (#926) (#931)
When an OpenAI-compatible provider returns a 404, the user-facing error message hardcoded "for Ollama: http://127.0.0.1:11434/v1" as a hint regardless of the configured base URL. Users on remote providers (NVIDIA NIM, OpenRouter, etc.) read this as the app ignoring their custom OPENAI_BASE_URL and routing to localhost. Plumb the request URL through the classifier and marker so the user-facing message can name the actual host. Localhost endpoints keep the existing Ollama-flavored guidance for backward compatibility. - classifyOpenAIHttpFailure now accepts an optional url and produces a host-aware hint for non-localhost 404s - the [openai_category=...] marker carries an optional host segment - mapOpenAICompatibilityFailureToAssistantMessage branches on host to show "Endpoint at <host> returned 404. Verify OPENAI_BASE_URL is correct and the selected model (<model>) is supported by this provider." for remote URLs - backward compatibility preserved when no URL is available |
||
|
emsanakhchivanandAli Alakbarli
|
a46b31c3ec |
feat: SDK Core — Permission System, Async Context, and Engine Extensions (#951)
* feat(sdk): add SDK foundation — type declarations, errors, and utilities
Adds standalone SDK building blocks with no SDK source dependencies:
- sdk.d.ts: ambient type declarations for SDK bundle
- coreSchemas.ts + coreTypes.generated.ts: Zod schemas and generated types
- errors.ts: SDK-specific error classes
- validation.ts: input validation utilities
- messageFilters.ts: extracted message filter logic
- handlePromptSubmit.ts: imports from messageFilters
- 16 generated-types tests
* fix(sdk): narrow assertFunction type from broad Function to callable signature
Code review finding: assertFunction used `asserts value is Function` which
accepts any function-like value without narrowing. Changed to
`(...args: any[]) => any` for better type safety.
* fix(sdk): update sdk.d.ts header — manually maintained, not generated
Reviewer noted the header said "Generated from index.ts" but no generator
produces this file. Updated to "Manually maintained — keep in sync with
index.ts". Drift detection added in validate-externals.ts (PR 3).
* fix(sdk): align sdk.d.ts types with canonical coreTypes.generated.ts
Tighten SDK public type contract to resolve reviewer blockers:
- PermissionResult: unknown[] → precise 6-shape discriminated union
(addRules/replaceRules/removeRules/setMode/addDirectories/removeDirectories)
- SDKSessionInfo: snake_case → camelCase (sessionId, lastModified, etc.)
- ForkSessionResult: session_id → sessionId
- SDKPermissionRequestMessage: uuid + session_id now required
- SDKPermissionTimeoutMessage: added uuid + session_id
- SessionMessage: parent_uuid → parentUuid
- SDKMessage/SDKUserMessage/SDKResultMessage: replaced loose inline
definitions with re-exports from coreTypes.generated.ts
* feat(sdk): wire existing code modules + SDK shared utilities
Modifies core modules for SDK integration:
- QueryEngine, tools, state, commands: SDK type hooks
- SDK shared utilities (shared.ts, permissions.ts)
- 21 SDK tests (shared-utils, permissions)
Stack: main ← pr1-foundation ← pr2-sdk-core
* feat(sdk): add snake_case ↔ camelCase key mapping utilities
casing.ts provides recursive key transformation for the SDK boundary
layer. Internal runtime uses snake_case; public API exposes camelCase.
Will be used by shared.ts, sessions.ts, query.ts at export boundaries.
* test(sdk): add tests for snake_case ↔ camelCase mapping utilities
Covers snakeToCamel, camelToSnake, mapKeysToCamel, mapKeysToSnake
including nested objects, arrays, null/undefined, and round-trips.
* fix(sdk): prevent permission timeout race condition with once-only resolve wrapper
Add createOnceOnlyResolve utility to prevent double-resolution of promises
when timeout and host response happen simultaneously. This ensures
deterministic behavior in the permission handling flow.
* fix(sdk): improve race condition test robustness
* fix(sdk): handle consecutive underscores in snakeToCamel conversion
Changes:
- Use _+([a-z]) regex to match multiple consecutive underscores before letters
- Add lookahead (?=. ) to preserve underscore-letter pairs at string end
- Handle dunder names (__proto__, __typename) by stripping wrapper and capitalizing
- Add tests for consecutive underscores and trailing underscore preservation
* fix(sdk): include original error message in permission callback denial
When a canUseTool callback throws an error, the catch block now
includes the original error message in the denial message, making
debugging easier for SDK consumers.
* feat(sdk): add optional timeout to env mutex for deadlock prevention
Add timeout parameter to acquireEnvMutex() to prevent infinite waits
in deadlock scenarios. The timeout is optional and defaults to no timeout
(wait forever) for backward compatibility.
Returns a MutexAcquireResult object with acquired status and optional
timeout reason for failed acquisitions.
* fix(sdk): remove timed-out callback from mutex queue to prevent deadlock
* test(sdk): add missing error path and timeout scenario tests
Add tests for timeout scenarios when host doesn't respond to permission
requests, fallback behavior when no onPermissionRequest callback, and
MCP connection edge cases for undefined/empty config.
* fix(sdk): address code review issues - race conditions, validation, error handling
- Add createPermissionTarget() factory that applies onceOnlyResolve at
registration time, fixing race condition where timeout and host response
could both try to resolve the same promise
- Add try-catch to releaseEnvMutex() to prevent permanent lock if callback throws
- Extract DEFAULT_PERMISSION_TIMEOUT_MS constant (30 seconds)
- Add MCP config validation rejecting null, non-objects, and arrays
- Preserve error stack traces in MCP connection failures
- Add runtime validation to mapMessageToSDK for null/non-object/invalid type
- Update tests to use createPermissionTarget and add validation tests
* test(sdk): add sequential timeout-then-host-response race condition tests
Adds two tests addressing reviewer request for proof that host response
after SDK timeout is safely handled with no double-resolve or leaked listener:
1. Integration test: stale host resolve called after timeout deny —
verifies no error, no mutation, map cleanup
2. Unit test: raw resolve called exactly once when timeout wins —
directly proves createOnceOnlyResolve prevents second execution
* fix: restore openclaude.json comment in REPL.tsx
Reviewer caught that the comment was incorrectly changed to
~/.claude.json during merge — project has already migrated to
~/.openclaude.json.
* fix(sdk): register pending permission before emitting onPermissionRequest
The previous code emitted onPermissionRequest before calling
registerPendingPermission, so a host responding synchronously from
the callback would find an empty map and its response was lost.
Swap the order so registration happens first.
Adds a regression test for the synchronous host response path.
* fix(sdk): make state setters context-aware for SDK isolation
When running inside runWithSdkContext(), setter functions (regenerateSessionId,
switchSession, setCwdState, setOriginalCwd) now write to the AsyncLocalStorage
context instead of global STATE. This prevents cross-session state leakage in
multi-session SDK scenarios.
Reads were already context-aware; this completes the isolation by making writes
consistent. Outside of SDK context, behavior is unchanged — all writes go to
global STATE as before.
* test(sdk): add context-aware state isolation tests
Tests verify that setters within runWithSdkContext() write to the SDK
context (not global STATE) and that parallel async contexts do not leak
state between sessions. Covers setCwdState, setOriginalCwd,
regenerateSessionId, switchSession, and an end-to-end parallel session
scenario.
* fix(sdk): selective tool schema cache invalidation for multi-engine isolation
Replace global clearToolSchemaCache() in QueryEngine.updateTools() with
selective invalidation that only removes cache entries for tools no longer
in the tool set. This preserves cached schemas for tools that remain,
avoiding unnecessary recomputation for concurrent QueryEngine instances
in multi-session SDK scenarios.
New function invalidateRemovedToolSchemas() handles both simple tool name
keys and schema-variant keys (format: "toolName:{...schemaJSON...}").
* docs(sdk): address PR2 non-blocking documentation and logging issues
- Document request_id vs tool_use_id relationship in shared.ts
(request_id for response correlation, tool_use_id for tracking)
- Add injectable SDKLogger interface to permissions.ts, replacing
direct console.warn calls with logger.warn (hosts can control noise)
- Document Node.js-only AsyncLocalStorage requirement in state.ts
(requires Node.js 12.17.0+ or 14.0.0+)
- Clarify env-mutex is host utility (SDK doesn't mutate process.env)
* fix(sdk): handle throwing onPermissionRequest and fix permission request shape
- Wrap onPermissionRequest in try-catch to clean up pending resolver on throw
- Add uuid and session_id to permission_request message to match SDK schema
- Add regression tests for throwing callback and message shape validation
* fix(sdk): use explicit no-session placeholder for standalone permission prompts
- Add NO_SESSION_PLACEHOLDER constant ('no-session') for permission requests
- Update SDKPermissionRequestMessage doc to explain session_id semantics
- Replace empty string fallback with explicit placeholder
- Add test verifying placeholder behavior when sessionId omitted
* docs(sdk): add example code to permission denial warning
Include canUseTool example in warning message to improve developer
experience and make SDK usage more discoverable for new users.
* fix(sdk): scope parentSessionId to SDK context for parallel isolation
regenerateSessionId({ setCurrentAsParent: true }) was writing to the
process-global STATE.parentSessionId even inside runWithSdkContext(),
allowing one SDK context to overwrite another's parent-session metadata.
Add parentSessionId to the SdkContext type and update both
regenerateSessionId and getParentSessionId to read/write from the
active context when one exists, using an explicit if-else pattern
rather than ?? to avoid undefined fallback leaking across contexts.
The non-SDK CLI path (no active context) continues to use STATE
directly, preserving existing behavior.
---------
Co-authored-by: Ali Alakbarli <ali.alakbarli@users.noreply.github.com>
|