mirror of
https://github.com/Gitlawb/openclaude.git
synced 2026-08-24 02:34:15 -05:00
main
974
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
  BogdanandGitHub
|
ca7c3efb6e | fix(bg): identify sessions with persisted process markers (#2163) | ||
 CalandGitHub
|
e8026263ca |
fix(tui): proper Unicode/IME input handling for composed sequences (#2018) (#2154)
* fix(tui): proper Unicode/IME input handling for composed sequences (#2018) * test(tui): address CodeRabbit review - hook-level IME coverage, full Unicode marks, astral code points, timeout regression tests |
||
|
CalandGitHub
|
54f963d006 | fix(openai-shim): drop synthetic tool-results marker and guard echoes (#2039) (#2153) | ||
|
BogdanandGitHub
|
69aca780ea |
fix(effort): preserve known model exclusions when force-enabled (#2148)
* fix(effort): preserve known model exclusions when force-enabled * fix(effort): address review feedback * test(effort): cover provider-scoped capability overrides * fix(effort): preserve route-specific reasoning controls * fix(effort): honor scoped routing environment |
||
|
BogdanandGitHub
|
34536c6220 |
fix(settings): preserve concurrent updates (#2137)
* fix(settings): preserve concurrent updates Serialize the complete settings read-merge-write transaction under a physical-target lock with a bounded synchronous contention wait. Read the merge base fresh after ownership, preserve logical symlinks during publication, and route direct settings-sync replacements through the same lock. * fix(settings): address transaction review feedback * fix(settings): reject invalid merge bases * fix(settings): preserve lock ownership and apply outcomes * fix(settings): address transaction follow-up * fix(settings): avoid unsafe cleanup control flow * fix(settings): publish complete lock claims * test(settings): document pending lock claim * fix(settings): track lock owner process identity |
||
 
|
bb6d66faa3 |
feat(providers): live model lists for OpenRouter and OpenGateway (#2084)
* feat(providers): fetch live model lists for OpenRouter and OpenGateway Enable hybrid discovery so OpenGateway and OpenRouter load public GET /v1/models catalogs (with coding filters on OpenRouter), matching cairn-code and the Zero live-list fix. Refs #2083 * Address live model discovery review feedback. Remove hardcoded model allowlisting, deduplicate live MiMo routes, avoid duplicate startup probes, share mapping helpers, and strengthen provider documentation and tests.\n\nRefs #2083 * test(providers): Isolate OpenGateway picker discovery state. Prevent persisted live discovery cache entries from making the static catalog assertion nondeterministic. Refs #2083 * fix(test): restore OPENGATEWAY_API_KEY after discovery test The no-auth OpenGateway discovery test deletes OPENGATEWAY_API_KEY but originalEnv never snapshotted it and afterEach never restored it, so a worker starting with the credential set would run every later test in that worker without it. Snapshot and restore it like the other provider env vars. Refs #2084 * fix(integrations): preserve route shim maxTokensField for live-only discovered models * fix(test): drop unrelated permissions.test.ts optional-chaining tweak Not part of the OpenGateway/OpenRouter live discovery change; jatmn's review on #2084 flagged it as unrelated drift that should be dropped or split into its own PR. Refs #2084 * docs(integrations): Add JSDoc comments to model mapping helpers Add detailed JSDoc documentation for gateway model normalization, tooling and reasoning support detection, and core model mapping type guards and helpers across OpenGateway, OpenRouter, and modelMapping. Refs #2083 * fix(integrations): address review feedback on live discovery and proxy credentials Preserve caller credentials and custom headers for private route overrides, remove deep-research exclusion for text models, isolate test config directories, and align model picker assertions with upstream curated models. Refs #2083 Refs #2084 * test(integrations): test explicit openaiShim precedence and removeBodyFields merge Add unit test assertions verifying that explicit descriptor and catalog openaiShim configurations take precedence over inferred model settings and that removeBodyFields arrays merge correctly across layers. Refs #2083 Refs #2084 * Filter expired catalog entries at discovery boundary and revert permissions test hunk. Wrap static and merged route catalog model lists in filterAvailableCatalogEntries across all discoverModelsForRoute and refreshStartupDiscoveryForRoute return paths, preventing expired time-boxed catalog entries and live duplicates from resurfacing in model picker refresh, summary, or bootstrap additional options. Also restore permissions.test.ts to upstream/main without optional-chaining. Refs #2084 * Fix ModelCatalogEntry type import in model test suite. Import ModelCatalogEntry from descriptors.js rather than index.js to satisfy typecheck. Refs #2084 --------- Co-authored-by: euxaristia <euxaristia@users.noreply.github.com> |
||
 JATMNandGitHub
|
1e56d4e7b2 |
feat(providers): add focused LLMTR hybrid gateway (#2150)
* feat: add LLMTR hybrid gateway * feat: support LLMTR_API_KEY * fix: allow LLMTR provider env files * fix: protect LLMTR credential routing * fix: protect LLMTR profile credentials * fix: complete LLMTR env lifecycle * fix: select LLMTR model before client setup * fix: address LLMTR review findings * fix: route LLMTR auxiliary models correctly * fix: complete LLMTR credential boundaries * fix: clear persisted LLMTR startup keys * fix: normalize LLMTR generic credentials * fix: scope LLMTR credential support * fix: align LLMTR credential boundaries * fix: close LLMTR credential boundaries * fix: clear stale LLMTR auth state * fix: clear persisted LLMTR credentials * fix: complete LLMTR setup contracts * fix: close LLMTR lifecycle gaps * fix(providers): close LLMTR credential boundaries * fix(providers): preserve saved LLMTR profile keys |
||
 
|
31ac8a6eca |
perf: stop busting the prompt cache and slim per-turn context (#2142)
* perf: stop busting the prompt cache and slim per-turn context Benchmarked against a comparable harness on grok-4.6 (identical one-shot coding task), OpenClaude used 84k total tokens per task with near-zero cache reuse. Root causes and fixes: - Auto-memory now defaults off in non-interactive (-p) sessions (src/memdir/paths.ts). The conversation-arc append gated behind it rewrote the system prompt every request (Date.now()-relative durations, running token counters, per-turn RAG retrieval), which invalidates implicit prefix caches from byte one on chat-completions providers. An explicit settings opt-in (autoMemoryEnabled / memory.autoWrite) still enables it; also drops the ~3.2k-token memory protocol section from one-shot runs. - The OpenAI shim no longer runs compressToolHistory for providers with implicit prefix caching (OpenAI, xAI, DeepSeek, Kimi/Moonshot, Codex) (requestPreparation.ts, both call sites). Its end-relative window retro-edits already-sent tool results each turn, mutating the middle of the request prefix — the native Anthropic transport already guards against exactly this (claude.ts shouldCompressNativeToolHistory). - Remove the wall-clock-relative "Ns ago" line from the multi-turn tracking block (conversationArc.ts) — it changed on every request. - Ship the ~1.7k-token git commit/PR protocol in the Bash tool description only when the session is inside a git repository (gitSettings.ts). The probe is cached per cwd, not per process, since worktree tools and daemon/SDK processes change directories mid-life. - Add a code-robustness bullet to the Doing-tasks system prompt section: derive timing-sensitive logic from elapsed time, and wire up every element introduced (prompts.ts). Measured on the same benchmark (8 runs): 84k -> ~46.6k total tokens per task (-45%), 89s -> ~60s wall clock, per-call cache reads up from a constant 128 tokens to 12k-29k, baseline context 16.8k -> 11.7k tokens. Tests: 573 targeted tests pass, including new coverage for the non-interactive memory default and the per-cwd git probe; tsc --noEmit clean. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix: address review findings on the prompt-cache changes - Correct the prefix-caching route ids ('moonshot'/'kimi-code', not 'kimi'/'codex' — the latter never matched a real routeId) and replace the unanchored host regex with parsed-hostname comparison so path-routed gateways are not misclassified. - gitSettings: an explicit includeGitInstructions settings value now always wins over the repo probe (recourse for bare-repo/GIT_DIR layouts), and the probe reuses the existing LRU-memoized findGitRoot on getCwd() instead of a second process.cwd()-keyed implementation — fixing stale results after Bash `cd`, `git init`, and in daemon/SDK processes serving multiple directories. - Memory gate: env-provisioned memory (CLAUDE_COWORK_MEMORY_PATH_OVERRIDE, CLAUDE_CODE_REMOTE with a mounted memory dir) counts as explicit opt-in, so Cowork/remote sessions keep extraction and indexing. - Multi-turn tracking block: render only completed turns and drop the running token totals — the in-progress turn's tool-call list and the aggregate counters changed between model requests, still rewriting the system prompt mid-turn. - Update the Kimi K3 compression test to assert the new policy (history kept uncompressed on implicit-prefix-caching hosts) and extend gitSettings tests to cover settings overrides and session-cwd tracking. 569 tests pass, tsc --noEmit clean, benchmark re-run confirms metrics hold (45.1k total tokens, 62.8s, 3 calls). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix: green CI and address CodeRabbit review on the prompt-cache changes CI: the conversation-arc suites assumed the multi-turn tracking block renders with only an in-progress turn, and that auto-memory is on in the (non-interactive) test process. Both now seed a completed prior turn, mark the session interactive where they exercise interactive behavior, and assert the new cache-stability invariants directly: the in-progress turn is never rendered, and no Duration/token-total lines appear. CodeRabbit findings: - Codex transport now skips tool-history compression too: Codex talks to OpenAI Responses backends with implicit prefix caching, and the end-relative compression window rewrites already-sent tool results, busting the cache (mirrors the openaiShim/requestPreparation skip). Its compression test now pins the uncompressed behavior. - New regression tests for both compression decision paths: an implicit-prefix-caching host skips compression on chat-completions and Responses requests, while a non-caching custom endpoint still compresses. - New byte-stability test: the same turn rendered twice with an advanced clock and a grown in-progress tool-call list produces an identical system prompt. - gitSettings: cover the CLAUDE_CODE_DISABLE_GIT_INSTRUCTIONS=0 defined-falsy override outside a repository. - Focused system-prompt test asserting the new timing/wiring guidance without snapshotting the full prompt. bun run check (smoke, deadcode, full suite) passes; tsc --noEmit clean. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * test: isolate CLAUDE_CODE_SIMPLE in the doing-tasks prompt test getSystemPrompt short-circuits to a minimal prompt when CLAUDE_CODE_SIMPLE is truthy; save, unset, and restore it around the test so the full prompt path is always exercised regardless of process-level state. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com> |
||
  
|
c461a0363d |
feat: merge knowledge graph + conversation arc into memdir (#1811)
* feat: merge knowledge graph + conversation arc into memdir
Replace the standalone KG/ARC system (SQLite + JSON + Orama storage)
with direct integration into the existing auto-memory directory.
What changed:
- New memdir/vectorIndex.ts — Orama full-text index over all memory/ .md
files, replacing the separate knowledge.orama binary
- New memdir/autoExtractFacts.ts — auto-detects env vars, paths,
versions, URLs, IPs, backtick concepts from conversation and writes
them as structured .md files into memory/.facts/ with frontmatter
- conversationArc.ts now persists arc state (goals, decisions,
milestones, phase) to memory/.arc.json sidecar instead of the KG
- knowledgeGraph.ts gutted from 728→165 lines — now a thin
compatibility layer that reads .facts/ files from memdir and
delegates vector search to vectorIndex.ts
- build.ts: enabled CONVERSATION_ARC and MULTI_TURN_CONTEXT feature
flags (previously undefined → dead-code eliminated in production)
Removed:
- src/utils/storage/ (SQLiteProvider, JSONProvider, 3 test files) —
unused after KG migration
- src/utils/knowledgeGraph.test.ts, .stress.test.ts
- src/utils/conversationArc.test.ts, .perf.test.ts
- ~1700 lines of redundant storage code
Benefits:
- Single memory system (memdir) instead of two parallel systems
- Auto-extracted facts are plain .md files — visible to the model,
discoverable by the existing Sonnet prefetch
- Vector search indexes real memory content, not a separate DB
- Arc state survives across sessions via .arc.json
- ~700 lines removed from the production bundle
* fix: type errors, add test suites, fix resetArc() disk-write bug
- Fix vectorIndex.ts: parseFrontmatter returns nested {frontmatter, content},
Orama DB typed as 'any' matching existing code pattern
- Fix resetArc(): was overwriting .arc.json on disk — now clears only in-memory state
- Add vectorIndex.test.ts (6 tests): build/search/persist/rebuild
- Add autoExtractFacts.test.ts (10 tests): env vars, paths, versions,
URLs, backtick concepts, PascalCase, React/Redux, file signatures, frontmatter
- Add conversationArc.test.ts (14 tests): arc init, persistence, goals,
decisions, milestones, phase detection, arc summary, finalize, stats
- Update verify-kg-merge.sh: add test suite check (33 tests)
* fix: remove generic type param from restore() call
* fix: address CodeRabbit findings — YAML injection, secrets leak, cache invalidation, frontmatter parsing, test weakness
* fix: redact URL credentials/query/hash in endpoint extraction; add persistence + reindex regression test
* test: add regression for URL credential/query/hash redaction in fact extraction
* feat: wire getOrchestratedMemory into query.ts prompt; remove dead promises array in autoExtractFacts
* feat: enhance memory management by adding clearArcArtifacts function and integrating it into the clear command; implement file count tracking in vector index
* feat: enhance fact extraction by adding tests for absolute paths, backtick concepts, technical terms, project file signatures, and IP addresses; implement clearArcArtifacts function in tests
* Review-fix: scoped IP tagging, scrubbedContent, arcMemoryDir null, vector-index cleanup
* Review-fix: isAutoMemoryEnabled gate, scrubbed paths, clearIndex in cleanup
* Review-fix: URL-stripped path scan, digit-key/quoted-value env redaction, rm isAutoMemory gate
* Review-fix: quoted multi-token env values fully redacted, regression test
* Review-fix: freshness check on each search, integration test, typecheck in verifier
* Review-fix: missing-index-file reinit, full-pipeline integration test
* Review-fix: gate arc/RAG on isAutoMemoryEnabled, add integration+stale-index tests
Addresses three P1/P2 findings from code review:
1. P1: Honor auto-memory opt-out before writing arc facts
- Add isAutoMemoryEnabled() checks in query.ts before calling
updateArcPhase() and getOrchestratedMemory()
- Add same check inside conversationArc.ts extractFactsAutomatically()
- Prevents .facts file writes when auto-memory disabled via --bare,
CLAUDE_CODE_DISABLE_AUTO_MEMORY=1, or memory.autoWrite: false
2. P2: Add query-level integration test coverage
- New test in conversationArc.test.ts verifies query.ts path
- Confirms arc functions called behind feature gates and results
appended to system prompt (lines 555-575)
3. P2: Add stale-index regression tests
- 6 new tests in vectorIndex.test.ts cover:
* Searching after adding files
* Searching after editing files
* Searching after removing files
* Searching when .vector-index missing
* Searching when .vector-index-meta.json missing
* Mixed stale conditions
All tests pass (31 total, 99 assertions), typecheck clean.
* Review-fix: use >= for mtime staleness check to catch same-ms edits
The verification agent discovered a timing-dependent bug in the stale
index detection. When a file edit and index save occur within the same
millisecond, latestMtime equals indexMtime, causing the check
`latestMtime > indexMtime` to return false. The stale index is not
refreshed and searches miss the updated content.
Changed line 220 from `>` to `>=` in the mtime comparison. The file
count check catches add/remove operations, but edits that don't change
the file count rely on mtime comparison.
All 12 vector index tests now pass consistently, including the
"searching after editing a file picks up changes" test that previously
failed intermittently.
* Review-fix: move auto-memory gate to persistence layer
Addresses inline review comment: query.ts was incorrectly skipping
updateArcPhase() entirely when isAutoMemoryEnabled() returned false,
leaving the in-memory arc state stale.
Fixed by:
- Removed isAutoMemoryEnabled() gate from query.ts line 449
- Added gate inside conversationArc.ts updateArcPhase() at persistence
layer (line 223), so phase advances but only persistence is disabled
- Arc state tracking now works regardless of auto-memory setting
- Only disk writes (.arc.json, .facts files, index rebuilds) are gated
The 2ms delay in vectorIndex.test.ts is kept as a pragmatic fix for the
timing race. Content-hash detection would be ideal but adds complexity;
the mtime check works reliably in production.
All 31 tests pass, typecheck clean.
* Refactor memory handling: consolidate metadata retrieval and improve auto-memory checks
* Fix: update expectation to use toEqual for prompt comparison in conversationArc tests
* fix: detect same-size content changes via content hash; handle text-block user messages in arc query
* fix: skip symlinked dirs in vector index walk; enable arc/multi-turn flags; add production-path tests
* fix: follow symlinked dirs in vector index walk per review
* fix: skip symlinked dirs in vector index walk; add symlink-boundary regression tests
* fix: skip indexing symlinked directories and ensure only files are processed
* fix: show cmd output on failure in verifier; add multi-turn coverage; clear mempath cache; cover arc reset in knowledge clear test
* fix: clear memoized auto-mem path after teardown in knowledge + conversationArc tests
* fix: isolate vector index per memdir, filter secrets from backtick facts, clean trailing ws
* fix: extend credential filter for AWS/GitLab tokens; reject all symlinks in vector index
* fix: use repo's redactSecretSubstringsForDisplay; add npm/glpat/AKIA/ASIA/xox to shared patterns; cover NPM+JWT in tests
* fix: P1 backtick credential safety + untrusted-data boundary; P2 legacy migration + non-fatal writes; P3 type safety + build regression
* fix: B1-B5, M6, M8 — no message mutation, migration data loss, empty-file, non-fatal writes, probe, rebuildIndex resilience, dead import
* fix: address 8 reviewer findings (R1-R8)
P1:
- Keep retrieved facts in DATA ONLY block with strict system instruction
- Catch lowercase config secrets (api_key=...) in env scrubber
- Migrate SQLite working store (knowledge.db) before deleting provider
- /knowledge clear atomically archives legacy sources
P2:
- Run legacy migration on getOrchestratedMemory retrieval path
- Preserve entity attributes in migration frontmatter
- Only rebuild vector index when facts actually changed
- Fix feature-flag verifier --define syntax (declare const)
* fix: close 9 memory findings — approval gate, non-fatal writes, secret scrub, per-project migration, attribute/relation preservation, WAL cleanup, cheaper index
- Gate auto fact extraction on isMemoryWriteApprovalRequired() + isAutoMemoryEnabled() so default projects cannot silently persist conversation content
- Make ensureFactsDir/writeFactMemory degrade non-fatally (no turn-breaking throw on read-only dirs)
- Scrub token-like URL/path/hyphenated segments from durable facts via looksLikeSecret (reuses providerSecrets.looksLikeSecretValue)
- Restore passive project-rule extraction as rule facts
- Honor isAutoMemoryEnabled() before legacy migration; scope the migration guard per project (Set) instead of a single global
- Preserve legacy entity attributes and relations through migration (indented attributes + relation fact file, reconstructed in getGlobalGraph)
- Clear SQLite WAL/SHM sidecars on /knowledge clear
- Replace per-turn content hashing in vectorIndex getMdStats with size+mtime metadata; drop redundant initMemdirIndex call in getOrchestratedMemory
- Add knowledgeGraph tests covering P1#2/P1#4/P2#5/P2#8 and extend autoExtractFacts tests
* test: avoid global cwd pollution in knowledgeGraph tests
Replace process.chdir with a per-test setFsImplementation mock cwd that is
reset via setOriginalFsImplementation in afterEach, so the test no longer
leaks a changed process.cwd() into other test files. Assert the auto-memory
gate via the project-specific legacy file rather than the shared resolved
memdir dir (which bun runs concurrently across it blocks).
* fix: address 15 reviewer findings (R1-R15)
P1:
- Gate saveArcToDisk/finalizeArcTurn/saveIndex/migration on memory-write approval
- Retire legacy sources after successful migration (rmSync, backup preserved)
- Slugify entity.type and summary.id in migration filenames (path traversal)
- Fall back to JSON when SQLite has zero entities
- Scrub rule-fact extraction on scrubbedContent + looksLikeSecret/redact check
P2:
- Track skipped vs completed migration; re-enable clears skip marker
- Walk back to latest human text for tool-round vector queries
- Auto-extract goals/decisions from user messages in updateArcPhase
- /knowledge clear message says durable wipe, not session-only
- Bind arc state to projectKey (re-resolve on cwd change)
- clearIndex(memoryDir?) scopes to one memdir
- yamlQuote all migration frontmatter fields
- Real SHA-256 contentHash alongside fileFingerprint for same-size edits
- Stop claiming production-pipeline coverage in tests/verifier
* test: isolate governance mock by removing afterEach clear
Remove setGovernancePolicySettingsForSourceForTesting(null) from afterEach
in autoExtractFacts, conversationArc, and knowledgeGraph test files. The
module-level mock is set in each file's beforeEach and since there is no
afterEach cleardown, parallel test execution can no longer corrupt the
mock state across files.
This fixes 26 CI test failures caused by one file's afterEach clearing
the mock that another concurrently-running file had set in its beforeEach.
* fix: isolate governance mock per async context via executionAsyncId tracking
Replace the module-level variable in governancePolicy.ts with an
executionAsyncId-keyed Map and an async_hooks.createHook that propagates
the override from parent to child async resources. This ensures each
concurrent test's beforeEach/afterEach cannot corrupt the override set
by another test file, even when test bodies directly mutate the mock.
Also restore setGovernancePolicySettingsForSourceForTesting(null) calls
in afterEach hooks (removed in 39c68376), which are now safe because
each afterEach only clears its own async context.
Fixes 26 CI test failures across knowledgeGraph (2), conversationArc (7),
and autoExtractFacts (17/22, governance-gate tests).
* Refactor knowledge graph legacy migration, secure secrets and IP octets, optimize build-time feature flags, cap conversation arc collections, and resolve all verification check gaps
* Fix governancePolicy enablement in full test runs by checking for test runner globals
* fix: ensure auto memory is enabled in conversationArc, knowledgeGraph, autoExtractFacts tests
Delete CLAUDE_CODE_DISABLE_AUTO_MEMORY and CLAUDE_CODE_SIMPLE env vars
in beforeEach hooks so tests are not blocked when CI sets these vars.
Also revert governancePolicy.ts to the simple module-level variable
(removing the async ID tracking approach that broke with Bun v1.3.13).
Fixes 33 CI test failures where isAutoMemoryEnabled() returned false
causing all disk-persistence guards to fire.
* fix: address P1/P2 review findings — redaction, bounds, legacy backup
[P1] Redact goal/decision descriptions with redactLikelySecrets before
persisting to .arc.json, session summaries, and prompt summaries so
credentials captured by auto-extraction regexes are not durably stored.
[P1] Bound multi-turn tool input serialization to 2000 chars and apply
redactLikelySecrets, preventing oversized/credential-bearing tool inputs
from overflowing the next provider request or exposing secrets.
[P2] Archive the non-selected legacy store (JSON or SQLite) and its WAL
sidecars before retiring both sources, ensuring a recoverable snapshot
exists if generated fact files are incomplete or a migration bug surfaces.
* fix: address P1 findings — safe legacy retirement, multi-turn aggregate budget
[P1] Do not retire a legacy store unless every existing source was
successfully archived. Track archived sources in a Set and skip deletion
of any source whose backup failed (knowledgeGraph.ts).
[P1] Archive the selected SQLite WAL/SHM sidecars alongside its migration
backup, since committed state may reside only in the WAL file and the
advertised recovery backup would otherwise be incomplete (knowledgeGraph.ts).
[P1] Bound the aggregate multi-turn tool replay to 10KB total and stop
appending further turns once the budget is exceeded, preventing many
Agent/MCP calls per turn from adding unbounded text to system prompts
(conversationArc.ts).
* fix: address P1/P2 review findings — rule extraction gate, SQLite read status, atomic WAL/SHAM, KG status gate, byte budgets
* fix: tighten looksLikeOpaqueToken to avoid flagging compound model names
* fix: address P1/P2 review findings — rebase, test isolation, SQLite retry, attribute redaction, entity aliases, body content, project-scoped multiturn, skip unchanged writes, knowledge list gate
* fix: address P1/P2/P3 review findings — secret scrub on migrate, lean decision gate, git-root legacy lookup, backup retention, index rebuild chaining, single vector search, drop unreferenced fixture
* fix: scrub secret entity names on migrate, exclude summary facts from entities, reset multi-turn on /knowledge clear
* fix: address P1 review findings for legacy graph redaction, recovery-safe clear, stable change guards
- Redact embedded secrets in migrated legacy knowledge-graph entities,
summaries, and rules via shared sanitizeLegacyText() policy
- Preserve legacy artifacts (json/db/wal/shm) as migration-backup before
/knowledge clear; resetGlobalGraph returns { archived, failures }
- Skip rewrite + index rebuild on unchanged turns by stripping the volatile
detectedAt timestamp (facts and arc session summaries)
- Always recompute the authoritative content hash in getMdStats so edits of
equal size with preserved mtime are detected and served correctly
* Potential fix for pull request finding
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
* fix: redact protocol-relative URL userinfo in legacy migration
new URL() throws for scheme-less URLs, so the catch branch now redacts
obvious //user:pass@host userinfo instead of persisting credentials.
* fix(memory): harden memdir migration and retrieval
---------
Co-authored-by: Gravirei <gravirei@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Kevin Codex <kevin@gitlawb.com>
|
||
 
|
645d596ea4 |
fix(code-reviewer): require inline diff input and preserve read-only search in embedded-search builds (#2102)
* feat: add code reviewer agent * feat(agent): add code-reviewer built-in agent implementation and tests Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(code-reviewer): address review comments - Fix broken step numbering in system prompt (glob/grep as sub-bullets) - Remove unnecessary wrapper in getSystemPrompt - Drop unused beforeEach/afterEach lifecycle in tests - Remove redundant registration test (beforeAll already throws) - Fix CLAUDE_CONFIG_DIR leak in beforeAll (restore in finally) - Replace @ts-ignore with explicit ToolUseContext cast - Use placeholder in README agentRouting example Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * ci: trigger rerun — pre-existing test failures on main * fix(code-reviewer): enforce read-only contract by disallowing Bash Add Bash to disallowedTools so the reviewer cannot run shell commands regardless of parent session's acceptEdits/bypassPermissions mode. resolveAgentTools() treated undefined tools as wildcard — Bash was available and could auto-approve mkdir/rm/mv in acceptEdits mode. Remove Bash guidance from system prompt; diff must now be supplied by the caller inline. Update test to assert Bash is in disallowedTools. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(code-reviewer): deny all shell tools (Bash and PowerShell) Use SHELL_TOOL_NAMES constant instead of just BASH_TOOL_NAME to ensure all shell-capable tools are denied from the code-reviewer agent. This prevents Windows sessions with PowerShell enabled from bypassing the read-only contract. - Import SHELL_TOOL_NAMES from shellToolUtils - Use spread operator to include both Bash and PowerShell in disallowedTools - Update test to verify PowerShell is denied Fixes the finding: [P2] Deny all shell tools for the reviewer agent * fix(code-reviewer): explicit read-only allow-list; drop unrelated artifacts Switch code-reviewer to an explicit `tools` allow-list (Read, Glob, Grep) instead of relying on wildcard access minus a deny-list. resolveAgentTools() resolves only the named tools, so write-capable mcp__* server tools (and any other mutation-capable tool) can never be handed to the read-only reviewer. Keep the mutation deny-list as defense-in-depth. Remove generated/scratch artifacts unrelated to the reviewer agent: AGENTS.md, ARCHITECTURE.md, the .openlore/ .gitignore rule, temp_reference/, and the .tmp/sdk-consumer-* scratch files. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix: restore temp_reference/ gitignore entry from main Entry was present on main from #1350 and was unintentionally removed during PR cleanup. Restoring it so temp_reference/ scratch directories remain untracked after merge. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(code-reviewer): require inline diff input and preserve read-only search in embedded-search builds Summary: - Update the `code-reviewer` built-in agent to require the caller to provide the diff or changed hunks inline in the prompt. - Preserve read-only search behavior in embedded-search builds by omitting `Glob`/`Grep` from the explicit tool allow-list when embedded search tools are enabled. - Keep a strict read-only policy by disallowing shell and mutation tools. Usage: - The `code-reviewer` agent is now explicitly guided to only review changes when the diff is provided inline. - In embedded-search builds, the agent only receives `Read` and cannot access `Glob`/`Grep`. - This prevents the agent from attempting shell-based diff discovery and enforces caller-provided diff input. Test plan: - `bun test src/tools/AgentTool/built-in/codeReviewerAgent.test.ts` — 12 pass, 0 fail - `bun run build` — success - `bun run smoke` — success - `bun run security:pr-scan` — success - `git diff --check` — success Credit: prior work from #1381/#1420. * fix(code-reviewer): clear cached agent definitions and markdown loader cache after test cleanup * fix(code-reviewer): address all P2/P3 review findings from jatmn - Always list [Read, Glob, Grep] in the tool allow-list; in embedded-search builds resolveAgentTools() silently drops unavailable Glob/Grep at runtime. The system prompt explicitly documents the narrowed search contract for embedded builds instead of silently degrading. - Update the code-reviewer invocation example in prompt.ts to include the diff inline, satisfying the reviewer's contract and preventing an avoidable extra turn. - Rewrite the test suite with the same isolation protocol as loadAgentsDir.test.ts: shared mutation lock, OPENCLAUDE_CONFIG_DIR, setClaudeConfigHomeDirForTesting, setAllowedSettingSources, and full env/cache restore in finally blocks. - Exercise both embedded-search branches: non-embedded tests verify Glob/Grep guidance, embedded tests verify the limited-search documentation and Read-only path. - Fix settings file path in README.md and docs/agent-routing.md from ~/.openclaude.json to ~/.openclaude/settings.json (the path the runtime actually loads). - Add blank line after fenced code block (MD031), add code-reviewer to the routable built-in agent list in both README and agent-routing docs. * fix(code-reviewer): restore prior setting sources in test cleanup, add credential security warning - Capture getAllowedSettingSources() before overwriting and restore it in the finally block instead of resetting to the default list, preventing state leakage to concurrent suites. - Add plaintext-credential security warning before the agentModels JSON example in README. - Update 'All settings-driven' to 'Configured via settings, agent frontmatter, and environment variables' for accuracy. * fix(code-reviewer): address remaining PR feedback (P1/P3) * docs: document feature gate for Explore and Plan agents * docs: document inline-diff requirement for code-reviewer agent * fix(code-reviewer): address P1/P2 review findings — teammate boundary, resume safety, lock-aware tests [P1] Reject built-in agent types from teammate spawn path to preserve read-only boundary. The teammate branch bypasses resolveAgentTools(), so built-ins like code-reviewer would receive Bash/Edit/Write tools. Guard added in AgentTool.tsx before spawnTeammate is called. [P1] Fail closed when resuming an unavailable agent type instead of silently falling back to GENERAL_PURPOSE_AGENT. A resumed code-reviewer must never gain edit-capable tools through a compatibility fallback. [P2] Snapshot environment and config state only after acquiring the shared mutation lock in codeReviewerAgent.test.ts. Moved from module- scope const to post-lock capture in beforeAll, with cleanup and lock release in afterAll's finally block. Regression tests added for all three findings. * fix(code-reviewer): guard lock release against failed acquisition Only call releaseSharedMutationLock() in afterAll when the lock was successfully acquired. Prevents releasing another suite's lock if acquireSharedMutationLock() throws on timeout. * fix(code-reviewer): remove trailing whitespace * fix(code-reviewer): reliably block built-in teammate spawns Reject built-in agent types from the teammate spawn path by looking them up in allAgents rather than activeAgents. This ensures the restriction remains intact even when built-in agents are disabled (e.g. via CLAUDE_AGENT_SDK_DISABLE_BUILTIN_AGENTS) and omitted from activeAgents. Regression test added. * fix(code-reviewer): preserve original agent identity when resuming a read-only reviewer Background-agent metadata persisted only agentType, so resuming selected whichever active definition currently had that name. A built-in code-reviewer could be started, followed by a project/SDK definition named code-reviewer taking precedence; resuming the original agent would then use the replacement's ordinary wildcard tool set and grant that reviewer transcript Bash/Edit/Write tools. Persist the agent definition source and verify it matches the resolved definition on resume, rejecting the resumption if the original was spoofed. * fix(code-reviewer): address remaining CodeRabbit feedback on test cleanup and metadata source * fix(code-reviewer): address P1/P2 issues for teammate spawns and resume safety * docs: make OpenLore prerequisite explicitly optional in AGENTS.md * docs: fix pinned OpenLore version in AGENTS.md * Fix review issues * Revert AGENTS.md changes * Restore AGENTS.md to match upstream/main * fix(agent): address maintainer feedback on teammate spawns and resume persistence * test(agent): add regression coverage for legacy source-less agent resume * fix(agent): propagation pass — batch fork regression, TeamCreate policy, trailing whitespace, verification gate docs * fix(batch): allow specific custom agent types while requiring subagent_type --------- Co-authored-by: Laurent FRANCOISE <lfrancoise@gmail.com> Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com> |
||
|
787f2a9390 |
refactor(cli): commander-authoritative argv handling for SSH / cc:// and remote bypass (recovery of #1939) (#2098)
* fix(cli): mirror programmatic args onto process.argv (hardened) Address CodeRabbit's Critical finding: cliMain() parses process.argv directly, so a programmatic main(args) call must reflect args there or it silently runs the host's argv. Restores the args->argv sync but hardened against the three bugs the multi-agent review confirmed in the earlier scoped/serialized version: - no restore (was F3: a finally-restore flipped argv out from under the SIGINT handler and bypass-safety notice while the session was live) - length-guarded exec/script slots (was F4: <2 host argv entries, e.g. node -e, dropped the flag past commander's argv.slice(2)) - no serialization chain (was F2: overlapping calls hung indefinitely) For the normal binary launch (args defaulted from process.argv.slice(2)) the assignment is a value-identical no-op. Tests: programmatic args reach cliMain, argv is not restored, and the exec/script slots are padded under a short host argv. Verified: 48 entrypoint+safety tests, tsc, build, and e2e re-probes of all former --yolo bug scenarios on the built binary. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(cli): ssh strip-all dangerous-skip tokens; docs+tests for native alias Address the latest Copilot + CodeRabbit findings on the native-alias PR: - ssh argv pre-scan removed only the first dangerous-skip token, so `ssh --yolo --dangerously-skip-permissions host` (or a repeat) left a survivor that re-enabled bypass after the ssh rewrite. Strip every matching token. (connect already used the filter helper.) [Copilot] - web/src/data/cliFlags.ts: list the flag as '--yolo, --dangerously-skip-permissions' to match the commander registration, not just the description. [Copilot] - Replace the source-string-count registration test with (a) a behavioral test that the built CLI lists the alias in --help — proving the main-command registration is live, not dead code or the wrong command — and (b) a structured .option() assertion plus a check that the ssh pre-scan handles the alias (ssh --help renders root help, so the ssh --yolo path is the pre-scan, not the commander option). [CodeRabbit] - PR description rewritten to describe the native alias instead of the removed argv rewrite. [Copilot] Verified: 23 cli + 10 safety tests, tsc, build, e2e (--yolo --help lists the alias; ssh --help; mcp add --yolo names the typed flag). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * test(cli): runtime coverage for dangerous-skip strip; share one helper CodeRabbit (approved, follow-up): the strip-all fix was only source- checked, so the strip loop could regress unnoticed. Extract the argv scanners into src/utils/dangerousSkipFlags.ts (isDangerousSkipFlag / hasDangerousSkipFlag / stripDangerousSkipFlags) and unit-test them at runtime: both spellings detected, every token stripped (canonical + --yolo + repeats), input not mutated. Both the direct-connect and ssh rewrites in main.tsx now use the shared stripDangerousSkipFlags — the ssh path's bespoke single-splice while loop (the original survivor bug) is gone, replaced by an in-place splice(0, len, ...strip). One tested code path instead of two. Verified: helper + 23 cli + 10 safety tests, tsc, build, e2e. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * style(cli): semicolon + strip both spellings in safety-test reset Copilot review nits: - statusNoticeDefinitions.tsx: add the trailing semicolon to the parenthesized return to match the file's semicolon style. - safety.test.tsx: the beforeEach argv reset filtered only --dangerously-skip-permissions; strip --yolo too so the 'without the flag' cases can't go order-dependent if the runner is invoked with --yolo in argv. - PR description re-synced to the native-alias approach (the earlier edit had reverted to the old 'normalize via argv rewrite' wording). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(cli): notice names --yolo; move import out of boot-critical block Both bots on 50772d28: - The bypass-safety notice fires for --yolo but its text named only '--dangerously-skip-permissions is active'. Reword to '... (alias --yolo) is active' so the message matches what the user typed. Add a rendered-notice regression assertion for the --yolo case. [CodeRabbit + Copilot] - Move the dangerousSkipFlags import out of the boot-critical header block (it ran before profileCheckpoint('main_tsx_entry'), adding pre-checkpoint work in the order-preserving bundle) down to the regular internal-import group. [Copilot] Verified: 39 cli+safety+helper tests, tsc, build, e2e. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(cli): honor -- end-of-options in the raw-argv dangerous-skip scanners Copilot (3x on 5cd0e304): the pre-commander scanners matched --yolo / --dangerously-skip-permissions anywhere in argv, so a positional after the -- marker (openclaude -p -- --yolo, cc://… -- --yolo, ssh host -- --yolo) was misread as the bypass flag — enabling bypass / stripping the token / false-firing the safety notice, even though commander treats it as positional. Pre-existing for the canonical flag, but the short alias makes it far likelier. Make the shared helpers --aware in one place: hasDangerousSkipFlag and stripDangerousSkipFlags only consider option-position tokens (before the first --) and preserve everything from -- onward. Route the safety notice's hasDangerouslySkipPermissionsArg through the same helper. Regression tests: helper ignores/preserves post-- tokens; the notice does not fire for -p -- --yolo. Verified: 41 helper+safety+cli tests, tsc, build, e2e. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * refactor(cli): don't leak args via process.argv; stop simulating commander in the scanner Address jatmn's two P1 findings, both by removing a band-aid rather than adding another: - P1a: main() no longer mirrors its args onto the process-global process.argv. Verified there is no production or SDK caller that passes custom args (the sole entry is the no-arg auto-run), so the mirror only risked leaking a programmatic invocation's args (including a bypass flag) into an overlapping call or the host process. Back to the baseline signature; cliMain parses the real process.argv. - P1b: revert the end-of-options ("--") handling in the dangerous-skip scanner. As jatmn notes, correctly classifying "--yolo" (it can be a required option value like "--system-prompt --yolo", or follow a "--" consumed as a variadic value) requires commander's option-arity state machine, the exact simulation this feature was reworked to delete. The scanner now mirrors the canonical --dangerously-skip-permissions presence check exactly: both spellings behave identically, and the approximation is documented as a pre-existing limitation of pre-commander scanning. Net: every difference between --yolo and the canonical flag is now either native-commander-correct (the registration) or an identical approximation (the raw scanners). No new argv mutation, no parser simulation. Verified: 38 cli+helper+safety tests, tsc, build, e2e. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs(cli): clarify main() argv comment — skills/--update do rewrite argv Copilot: the "does not mirror args onto process.argv" comment was misleading — the skills and --update fast-paths reassign process.argv to re-route to their subcommand. Note the exception; the no-mirror rule is about not injecting the caller's args into the general cliMain flow. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(setup): name the --yolo alias in the root/sudo bypass error Copilot: the root/sudo safety error printed only --dangerously-skip-permissions; a user who typed --yolo saw a flag they didn't use. Mention both spellings, matching the ssh help and cliFlags. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * test(cli): import Command from @commander-js/extra-typings, matching prod Copilot: the alias behavioral test built its probe Command from 'commander', but production registers options via @commander-js/extra-typings. Use the same package so the test exercises the exact parser prod uses. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(ssh): don't treat an option value as the permission-bypass alias jatmn P1: `ssh host --permission-mode --yolo` stripped --yolo as a bypass flag (enabling bypass) and left --permission-mode valueless, whereas commander parses --yolo as the (invalid) mode value and rejects it — a silent privilege escalation. Same class affected --model / --resume / --fallback-model. Reorder the ssh pre-parser so value-taking flags consume their value — including a dangerous-skip token in the value slot — BEFORE the dangerous-skip strip runs. Extract the whole flag pre-parse into a pure, unit-tested helper (parseSshFlags) so the security-sensitive arity handling has regression coverage: escalation guards for --permission-mode/--model + a value of --yolo, plus genuine standalone --yolo still enabling bypass. Verified: 6 ssh + dangerousSkipFlags + cli tests, tsc, build, e2e. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * test(cli): update ssh-path source assertion for parseSshFlags extraction Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * chore(cli): revert unrelated --bare doc; drop stray blank line CodeRabbit/Copilot on the rebased branch: - Revert the --bare help rewrite (background prefetches / CLAUDE_CODE_SIMPLE / expanded flag list) in main.tsx and web/src/data/cliFlags.ts — it is unrelated to the --yolo alias and broadens scope. cliFlags.ts now changes only the --yolo alias line. - Remove the stray double blank line before cliMain. Skipped CodeRabbit's "alias order breaks property naming" (Major): verified against @commander-js/extra-typings that '--yolo, --dangerously-skip- permissions' maps BOTH spellings to opts().dangerouslySkipPermissions (commander keys off the last long flag); opts().yolo is undefined. Bypass is not broken. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(ssh): honor the -- end-of-options marker in the ssh pre-parser CodeRabbit Critical + jatmn P1 ("respect option arity/end-of-options semantics"): `ssh host -- --yolo` (or `-- --local`, `-- --permission-mode x`) parsed the post-`--` tokens as flags, so a positional --yolo escalated to bypass. parseSshFlags now parses only the prefix before `--` and keeps everything from `--` on positional. This is unambiguous here because the ssh subcommand registers no variadic options that could consume `--` as a value. The connect (cc://) path is deliberately left plain and documented: it rewrites to the main command, which HAS variadic options (--add-dir …) that commander lets consume `--` as a value, so a naive `--` split there would be the incomplete simulation flagged in P1b. That false-positive is pre-existing for the canonical flag. Skipped (both pre-existing, ported verbatim / out of scope): extractFlag mixed `--flag=x --flag y` precedence, and the setup.ts root/sudo message not naming --allow-dangerously-skip-permissions. Verified: 8 ssh + cli tests, tsc, build. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * refactor: make --yolo/bypass Commander-authoritative on cc:// connect + notice * fixup! address CodeRabbit/Copilot review findings on #2098 - Restore parseMaxTurnsCommanderArgument for --max-turns validation. - Generalize root/sudo error message for all bypass modes/flags. - Clarify cli.tsx comment about main() not leaking args into process.argv. - Detect -p/--print in all commander-accepted forms (including --print= and -p<value>). - Correct dangerousSkipFlags.ts doc: SSH strips, cc:// preserves for Commander. - Extend live help test to ssh and open subcommands. * fixup! extract hasPrintFlag helper + regression tests - Move print-flag detection to src/utils/printFlag.ts so it is unit-testable. - Add regression tests for -p, --print, --print=prompt, -pprompt, and -- separator. - Import the helper in main.tsx and drop the local copy. * fixup! use hasPrintFlag in every startup print-mode check - Replace exact-string includes in the SSH headless rejection and the main print-mode gate with the shared hasPrintFlag predicate. - Add source assertions confirming cc:// rewrite, SSH rejection, and main print-mode gate all use the same helper. * fixup! align dangerously-skip notice comment with commander-authoritative mode - Remove stale 'reads from process.argv' text; the notice now keys off the resolved permissionMode. * fixup! add SIGINT handler to hasPrintFlag source assertions - Include the SIGINT print-mode gate in the source-level consistency check. * fixup! restore maxTurns forwarding dropped during rebase - Re-add options.maxTurns to sessionConfig and the interactive REPL props for direct-connect, SSH, remote viewer, and remote creation paths (matches main). * fixup! address Copilot suppressed comments on #2098 - parseSshFlags now consumes required-arg values unconditionally, matching commander and preventing flag-like values from leaking into later guards. - Drop the now-unused isDangerousSkipFlag import from sshPreParse.ts. - Make the dangerously-skip notice text mode-agnostic so settings-driven bypassPermissions is not mislabeled as a CLI flag. * fixup: left-to-right SSH parse and fullAccess sandbox warning - Rewrite parseSshFlags as a single left-to-right arity-aware scan. Value-taking flags now consume every occurrence (including equals forms) and always consume the next token as their value, even if it resembles a flag (e.g. --permission-mode --local or --model --yolo value). - Cover fullAccess with the dangerously-skip-permissions sandbox warning and add focused regression tests for bypassPermissions/fullAccess rendering. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * fixup: preserve missing SSH option values and embedded equals - Keep value-taking SSH flags in remaining when they have no available value (last token before -- or trailing), letting commander report the missing required argument. - Use slice after the prefix for equals-form values so embedded '=' characters are preserved (e.g. --model=provider=model). - Add regression tests for last-token, before--, and embedded-equals cases. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * fixup: arity-aware print detection and optional --resume for SSH - hasPrintFlag now skips tokens consumed as values by preceding value-taking options (required, optional, and variadic), so --system-prompt --print=custom is no longer misclassified as print mode. - parseSshFlags treats --resume as an optional-value option: a bare --resume is forwarded, a non-option value is consumed, and following flags (e.g. --yolo) remain available for their own parsing. - Added focused regression tests for both fixes. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * fixup: handle inline values and -- in hasPrintFlag - Do not advance past a following flag when a required/optional/variadic option already provided its value inline via =. - Stop the scan when a value-taking option is immediately followed by --. - Added regression tests for --model=foo --print and --model -- --print. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * fixup! address jatmn review: arity-aware print/SSH parsing + fullAccess notice Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * fixup! correct bypassPermissions notice wording Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * Address remaining CodeRabbit findings on #2098 - Sync hasPrintFlag with all root-command required/variadic/optional options, including hidden/feature-gated flags (--agent-id, --sdk-url, --channels, etc.). - Treat the SDK 'full-access' spelling as fullAccess in the dangerous-skip-permissions status notice so the stronger warning is shown. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * fix(cli): make hasPrintFlag the single pre-Commander print classifier - Replace all startup .includes('-p')/.includes('--print') checks with the arity-aware hasPrintFlag() predicate so value-consumed tokens are not misclassified as print mode. - Centralize SSH headless detection in sshArgvImpliesHeadless(), covering both tail argv after host/cwd and flags forwarded via extraCliArgs (e.g. --resume=--print). - Soften the fullAccess status-notice wording to match runtime behavior: most consent checks are bypassed, but hard deny rules and user-interaction prompts still apply. - Add/extend tests for interactivity, SSH flag pre-parsing, status notices, and a regression check that prevents naive print-token checks from re-entering. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * fix(ssh): preserve --resume= values and run headless guard before host extraction - Keep the inline value attached when forwarding --resume=... extraCliArgs so optional-value semantics are preserved (e.g. --resume=--print resumes a conversation named "--print", it does not enable print mode). - Move the SSH headless guard before host/cwd extraction in main.tsx so print flags that appear before the host are rejected. - Update tests: --resume=--print is no longer headless, required-value options like --model -p remain non-headless, and add coverage for print flags before the host. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * fix(cli): remove repeatable single-value options from VARIADIC_OPTIONS --plugin-dir and --provider-env-file are registered as repeatable single-value options, not variadic. Keeping them in VARIADIC_OPTIONS made the arity model wrong and could consume extra tokens if check order changed. They are already covered by REQUIRED_VALUE_OPTIONS. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com> |
||
 anushka ✩andGitHub
|
294bd9a1df |
Add optional Sentry error reporting (env-driven, opt-in) (#2139)
* Add optional Sentry error reporting (env-driven, opt-in) * Fix Sentry init to use dynamic import instead of require (ESM compatibility) * Document SENTRY_DSN setup in advanced-setup docs * Disable Sentry default integrations; document runtime install requirement * Wire reportErrorToSentry into top-level error handlers; add sentry.test.ts |
||
|
JATMNandGitHub
|
084bc53463 |
feat(gateway): add Concentrate AI provider with dynamic model discovery (#2140)
* feat(gateway): add Concentrate AI provider with dynamic model discovery * fix(concentrate): prompt for Concentrate API key in /provider instead of pre-filling OPENAI_API_KEY * docs(concentrate): remove standalone setup guide to match other gateways * fix(concentrate): dedicated-credential-only routing, env-only identity, and credential isolation - Make Concentrate dedicatedCredentialsOnly so ambient OPENAI_API_KEY is never forwarded. Only CONCENTRATE_API_KEY authenticates the route. - Resolve Concentrate env-only route identity from CONCENTRATE_API_KEY, CONCENTRATE_BASE_URL, CONCENTRATE_MODEL, or a Concentrate-shaped OPENAI_BASE_URL. - Mirror the dedicated credential into OPENAI_API_KEY only after the route identity is established and only for the canonical /v1 inference endpoint. - Add Concentrate support to --provider concentrate, saved profiles, startup env rebuild, and .env allowlist. - Add regression tests for env-only, flag, saved-profile, and client routing. - Fix adjacent ApiSmart keyless profile leaking string 'undefined' into OPENAI_API_KEY and extend the first providerProfiles test timeout for the now-slower fresh module import. * fix(concentrate): protect credentials on noncanonical urls * fix(concentrate): drop legacy keys on retargeted profiles * fix(concentrate): remove legacy generic keys on proxies * fix(concentrate): reject noncanonical credential routes * fix(concentrate): validate env-only credentials * fix(concentrate): align env-only route validation * fix(concentrate): clear headers before client setup * test(validation): isolate Concentrate model env * fix(concentrate): honor provider precedence and model defaults * test(concentrate): cover model resolution precedence * fix(concentrate): preserve legacy model fallback * fix(concentrate): normalize early model selection * fix(concentrate): validate and select rejected models safely * fix(concentrate): reset stale route state * fix(concentrate): preserve proxy profile capabilities |
||
|
BogdanandGitHub
|
108a413493 |
fix(bg): preserve detached session terminal outcomes (#2133)
* fix(bg): preserve detached session terminal outcomes * fix(bg): harden terminal outcome routing |
||
|
BogdanandGitHub
|
e9e6beb15b |
fix(mcp): paginate discovery list operations (#2132)
* fix(mcp): paginate discovery list operations * fix(mcp): bound paginated discovery retries |
||
|
BogdanandGitHub
|
09eba26d30 |
feat(cost): support exact custom model pricing (#2131)
* feat(cost): support exact custom model pricing * fix(cost): address custom pricing review feedback |
||
|
BogdanandGitHub
|
c30578819e |
diagnostics(query): trace interruption causality (#2111)
* diagnostics(issue-1830): trace interruption causality * test(issue-1830): lock interruption ownership matrix * fix(codex): preserve stream deadline contract * fix(diagnostics): harden interruption trace lifecycle Refs #1830 * fix(diagnostics): harden interruption trace settlement Refs #1830 * fix(diagnostics): preserve interruption causality * fix(diagnostics): address interruption trace review * fix(diagnostics): preserve tracing observer contracts * fix(diagnostics): preserve interruption trace contracts * test(permissions): cover interactive hook interrupts |
||
|
BogdanandGitHub
|
ea655163d3 |
feat(zai): expand Coding Plan catalog support (#2127)
* feat(zai): expand Coding Plan catalog support Signed-off-by: chioarub <chioarub@gmail.com> * fix(zai): use supported low reasoning mode Signed-off-by: chioarub <chioarub@gmail.com> --------- Signed-off-by: chioarub <chioarub@gmail.com> |
||
 0xfandomandGitHub
|
6c7a12b2a2 |
fix(websearch): reject non-positive WEB_CUSTOM env overrides (#2124)
The custom web-search provider read WEB_CUSTOM_TIMEOUT_SEC and WEB_CUSTOM_MAX_BODY_KB with Number(x) || DEFAULT. That idiom only rescues 0 and NaN — a negative or Infinity value is truthy and passes straight through. A negative WEB_CUSTOM_MAX_BODY_KB makes the "body exceeds N bytes" check reject every POST search, and a negative WEB_CUSTOM_TIMEOUT_SEC drives an immediate abort on every request. Route both through readPositiveEnvNumber, which falls back to the default for missing, empty, non-finite, or non-positive input. |
||
|
0xfandomandGitHub
|
f553d0896d |
fix(api): resolve swarm-field tool names by own-property (#2123)
filterSwarmFieldsFromSchema() looked the tool name up with a bare SWARM_FIELDS_BY_TOOL[toolName] on a plain-object map. A tool whose name collides with an Object.prototype member (constructor, hasOwnProperty, isPrototypeOf, propertyIsEnumerable) resolves the inherited function, which is truthy with .length === 1 — so the empty/undefined guard is bypassed and the subsequent for...of throws "is not iterable", failing schema construction for the entire request. Guard the lookup with Object.hasOwn so a prototype-named tool is treated as unmapped, matching the own-key guard already used for provider- supplied tool names in services/api/toolArgumentNormalization.ts. |
||
 
|
fb9102c422 |
feat(aimlapi): passwordless onboarding and resumable card top-up (3/3) (#2032)
* feat(aimlapi): add checkout state persistence and sign-in key cache
* fix(aimlapi): cover lock recovery and complete the reset receipt
* test(aimlapi): cover CAS result, reset receipt and sign-in key permissions
* fix(aimlapi): make stale-lock recovery ownership-safe across processes
* test(aimlapi): pass a file URL specifier to the lock workers
* fix(aimlapi): use proper-lockfile and harden checkout-state persistence
* fix(aimlapi): preserve issued keys and survive stale-lock steal races
* fix(aimlapi): surface swallowed lock-retry conditions
* feat(aimlapi): resume interrupted checkouts in the top-up entry points
* fix(aimlapi): keep resumable checkouts through transient and paid states
* fix(aimlapi): surface a lost settled-receipt write to the caller
* fix(aimlapi): harden checkout resume across CLI resume, idempotency and transient errors
* fix(aimlapi): resume settling checkouts and preserve records on ambiguous reads
- Treat 'exchanging' as a paid/resumable status so a run interrupted between
payment and receipt resumes the exchange instead of opening a second,
chargeable checkout (matches pollUntilPaid).
- Preserve the recorded checkout on a malformed-but-successful status read
(AimlapiApiError status 200), alongside the existing transient-error path.
- Print the full recovery key in the receipt-write-failed warning; a masked
key is useless as a last copy.
- Re-register the real client/providerProfile modules in afterAll so the
test stubs cannot leak into later files (mock.restore does not undo
mock.module).
- Bound each lock worker's exit before draining its pipes, and loosen the
held-lock timeout assertion to any errno (Windows is not always ELOCKED).
* fix(aimlapi): stop mock leak, fail closed on spent sessions, clear GUI receipt
- topup.test.ts: capture the real client/providerProfile modules through a
cache-busting query so afterAll restores the genuine module instead of the
corrupted (stub-mutated) reference. Without this the './client.js' stub bled
past afterAll and failed 25 client.test.ts cases whenever it ran first.
- resolveCheckoutSession: fail closed when a resumed session is already
'exchanged' but no settled receipt survived locally, matching pollUntilPaid,
instead of opening a second chargeable checkout for a one-shot key that is
already gone.
- provisionAimlapiKey: return a clearReceipt closure; ProviderManager now calls
it only after persistDraft actually saves, so a second GUI top-up opens a
fresh checkout instead of short-circuiting to a stale key or throwing.
- claimAimlapiTopupState: refuse to replace a stored record that still has an
open resume token for a different intent, so a changed amount cannot strand a
still-payable checkout and open a second one.
- Mask the issued key in the CLI receipt-write-failed warning; a paid-for
credential should not land in scrollback.
- index.ts: note the live CLI/GUI callers and the clear-receipt obligation.
- Regression coverage for exchanged fail-closed, the claim guard, and the GUI
receipt clear.
* fix(aimlapi): inject the topup transport instead of mocking client.js globally
The prior mock.module('./client.js') stub in topup.test.ts leaked past its
afterAll into client.test.ts (25 failures when this file ran first in CI,
bun 1.3.13). Replace it with a local injection seam:
- topup.ts exposes setAimlapiTopupTestDoubles, and both entry points create
their client / write their profile through it (defaults unchanged, so
production behaviour is identical).
- topup.test.ts injects a stub transport through that seam and no longer calls
mock.module at all, so nothing can bleed OUT to client.test.ts.
- It still loads topup.js through a cache-busting ?ts= query so it stays immune
to ProviderManager.test.tsx's mock.module('../integrations/aimlapi/index.js'),
which mock.restore() does not undo and which would otherwise replace the
shared provisionAimlapiKey binding (verified: without the query the barrel
stub reaches this file and every topup test fails).
* fix(aimlapi): converge racing checkouts and preserve state on ambiguous reads
- Close a post-claim race: two runs of the same intent converge on one payment
id, then each can open a session before either records one, and the second
save overwrote the first's resume token (two payable checkouts). Add
recordAimlapiCheckoutSession, a compare-and-swap that only records while the
token is empty; resolveCheckoutSession adopts the winner's session and
abandons the one it just opened, so pay() converges idempotently on a single
charge.
- Resume path now preserves the record on any ambiguous getSession error
(transient, malformed-200, auth/4xx) and retires it only on a definitive
404/410 gone-session, instead of clearing on every non-transient error.
- pollUntilPaid retries a malformed-but-successful (status 200) body instead of
aborting, matching the resume path.
- Regression coverage for the peer-records-first race, ambiguous-error
preserve, 404 replace, and poll-retry-on-200.
* fix(aimlapi): re-validate an adopted peer session before paying it
When two racing runs converge and this one adopts the peer's recorded session,
route that session through the same status classification as the initial
resume: return it only while resumable, fail closed on 'exchanged', and surface
a re-run error on any other terminal status instead of calling pay() on a dead
session. Add regression coverage for an adopted session that is exchanged or
cancelled in the race window.
* test(aimlapi): make abandoned-lock recovery test deterministic
The stale-lock recovery test asserted that all racing claims return the same
payment id. Under a stale-lock steal two recoverers can briefly hold the lock
and mint distinct ids, so that assertion was flaky in CI. A diverged claim is
harmless — it is refused at its next compare-and-swap — so the invariant that
actually matters is that exactly ONE checkout gets established. Drive the
workers through the full claim->record flow and assert a single winner, which
the single-slot store plus the record CAS guarantee deterministically.
* fix(aimlapi): acquire checkout-state off the interactive thread and recover fresh orphans
The interactive top-up flow acquired the checkout-state lock synchronously,
parking the Ink event loop (UI, timers, SIGINT) on Atomics.wait for up to the
5s timeout, and that timeout was shorter than the 30s stale window so a lock
orphaned by an interrupted holder could not be recovered on an immediate resume.
- Add withStateLockAsync + async variants of the state mutators, sharing the
same inner operations. It acquires with the timer-free lockSync (a sub-ms
mkdir) but yields via await between retries, so the UI stays live, and its
longer deadline (15s) covers the stale window so a fresh orphan is reclaimed
once stale rather than timing out. Shrink the stale window to 8s (sub-ms
sections never approach it) so recovery is quick.
- Route topup.ts (CLI + GUI) through the async variants; provisioned.clearReceipt
is now async, and ProviderManager awaits it best-effort so a cleanup failure
cannot surface an error that invites a retry (a duplicate provider profile).
- Regression coverage for async orphan recovery (mutation-checked: a deadline
below the stale window fails to recover). Generous per-file test timeout since
the now-async provisioning yields to a loaded runner's event loop.
* test(aimlapi): cover the async state mutators and speed up the orphan-recovery test
- Add thin contract tests for saveAimlapiTopupStateAsync (CAS accepted/rejected),
recordAimlapiCheckoutSessionAsync (compare-and-swap on the empty resume token),
and clearAimlapiTopupStateAsync (ownership-scoped clear); the CLI/GUI flow now
routes through these and only claimAsync was exercised.
- Back-date the orphaned lock to just inside the stale window so the async
recovery test reclaims it in ~2s instead of burning the full 8s window.
* fix(aimlapi): fail closed on corrupt state, deliver keys on receipt failure, add a reset action
- Fail closed when the checkout-state file is present but unreadable/schema-
invalid instead of reading it as absent: a claim would otherwise overwrite an
open/paid checkout or an exchanged key and open a second chargeable one.
- Never strand a one-shot exchanged key: a receipt-write that throws (lock
timeout / fs / corrupt state), not just a lost CAS, is caught so the CLI still
writes the profile and the GUI still returns the key; the post-delivery clear
is best-effort too.
- Add an explicit discard/reset escape hatch — discardAimlapiCheckoutState, an
"openclaude aimlapi reset" command, and a GUI "Start over" on the top-up error
screen — so a terminal checkout (whose resume token blocks a different intent)
or a corrupt state file can be cleared without editing internal files.
- Surface a failed GUI receipt retirement: retry a few times, then show a
non-blocking warning instead of swallowing it silently.
- Only chmod a config directory this flow actually created (via mkdirSync's
return); never tighten a pre-existing OPENCLAUDE_CONFIG_DIR root. The state
file's own 0600 mode protects the credential.
- Tests for each, incl. corrupt/schema-invalid fail-closed, receipt-write-throw
key delivery (CLI + GUI), discard semantics, retried/surfaced GUI cleanup, and
a POSIX check that an existing config dir keeps its mode.
* fix(aimlapi): surface the CLI recovery-receipt clear failure and cover the reset handler
- The CLI finishCliTopup clear failure only went to logForDebugging (debug-only),
invisible to the user, unlike the loud receipt-write warning and the GUI
warning. Print a [warn] line pointing at "openclaude aimlapi reset" so a
stranded receipt that blocks a different top-up is not hidden.
- Add tests for the aimlapiReset CLI handler (discards a stored checkout /
reports when there is nothing to discard).
- Assert the CLI clear-failure warning is surfaced in the receipt-write-failure
test (mutation-checked).
- Document "openclaude aimlapi reset" and the GUI Start over recovery in
docs/aimlapi-setup.md.
* fix(aimlapi): protect a settled receipt from reset and bind method into the checkout identity
- Discard (CLI reset / GUI Start over) no longer deletes a settled receipt — the
only copy of a paid-for, one-shot key — unless forced. discard now returns
'discarded' | 'kept-settled' | 'none'; the CLI adds --force and the GUI refuses
and points back at the recovering retry.
- Add the payment method to AimlapiTopupIntent so a card->crypto (or reverse)
restart is a different intent and cannot adopt the prior checkout's reused
idempotency id on the wrong rail; covered by a changed-method resume test.
- Narrow the sign-in-key cache: it is a persistence primitive for the follow-up
guided passwordless flow with no in-tree consumer, so drop it from the public
barrel and document the scope (kept in topupState.ts for that follow-up).
- Regression + mutation coverage for the settled-receipt protection and the
method-scoped intent.
* fix(aimlapi): back off receipt-clear retries, expand the discard API, and test Start over
- Add a 150ms backoff between the GUI clearReceipt() retries so the loop can
actually ride out a lock-contention window instead of exhausting three
back-to-back attempts.
- Re-export AimlapiDiscardResult and add resetAimlapiCheckoutSessionAsync so
barrel consumers can name the discard outcome and use a non-blocking reset,
matching the other mutators.
- Cover the GUI Start over recovery: it is 'r' (settings:retry) on the top-up
error screen — the Settings context has no confirm:yes and Enter closes the
panel; tests drive both the discard and the kept-settled refusal path.
- Rename the test's stale-age constant (LOCK_AGE_WELL_PAST_STALE_MS) so it no
longer reads as the source's 8s window.
* fix(aimlapi): serialize the one-shot key exchange and recover receipts before login
Address three checkout-state review findings:
- [P1] Serialize the non-idempotent key exchange behind an exchange lease so
racing same-intent processes mint and record the credential exactly once. The
elected lease holder exchanges and records the settled receipt; a peer that
loses the election waits for that receipt and resumes from it instead of
exchanging in parallel; a lease abandoned by a crashed holder goes stale (past
the client request timeout) and is reclaimed on a later attempt. The lease is
released on a failed exchange so a retry is not blocked for the stale window.
- [P1] Recover a settled local receipt BEFORE authenticating in both the CLI and
guided entry points. A run interrupted after the one-shot exchange but before
the profile write leaves the paid-for key only in that receipt; requiring a
fresh login to reach it stranded the key whenever the password had changed or
the auth service was down. The receipt read is side-effect free and needs no
token, so it now runs first and only authenticates when a checkout must be
created/resumed/exchanged.
- [P2] Fix the guided-recovery key in the setup guide: Start over is bound to r,
not Enter (Enter closes the settings panel).
Covered by state-layer lease tests (acquire/held/stale-steal/settled/gone/
release), a two-process race asserting the exchange runs exactly once with the
loser resuming the receipt, and no-auth-on-settled tests for both entry points.
* test(aimlapi): harden the exchange-lease coverage
Address review follow-ups on the exchange-lease tests (all test-only):
- Gate the two-process race on the loser's own "waiting" status signal instead
of a fixed sleep, and assert it fired, so the test deterministically exercises
the held -> wait -> resume path rather than possibly reading settled directly.
- Type seedPersistedState's overrides as Partial<AimlapiPersistedTopup> so a
misspelled/wrong-typed seed key is a typecheck failure instead of a record
that silently reroutes the test down another branch.
- Cover re-acquiring your own lease (leaseOwner === owner) so the guard that
keeps a caller from mistaking its own fresh lease for a live peer's — and
self-blocking until the stale window — cannot regress unnoticed.
* fix(aimlapi): fence a superseded profile write, protect unreadable state, resume the receipt model
Address three checkout-state review findings:
- [P1] Fence an in-flight checkout before it writes its key to the provider
profile. If a reset (or a fresh top-up) replaces the stored slot while an
abandoned flow is awaiting client.exchange(), that flow's settled-receipt CAS
now misses; previously it still went on to write its stale key and could
clobber the profile the new top-up created. recordSettledReceipt now reports
recorded | superseded | errored, and the exchange path aborts (rejecting, and
pointing the user at rotating the orphaned key) on `superseded` while still
delivering on a transient `errored` so a paid-for key is never stranded.
- [P1] Do not discard an unreadable/corrupt state file without --force. Such a
file could be a damaged receipt holding the sole copy of a one-shot key, so
discardAimlapiCheckoutState now returns `kept-unreadable` and keeps it unless
forced — matching the safety promise (and existing settled-receipt protection)
that reset never loses an issued key. The CLI and guided "Start over" surface
the new outcome and point at `reset --force`; docs updated.
- [P2] Use the settled receipt's model when a peer completed the exchange. The
settled lease branch dropped lease.state.model, so a loser resuming another
run's receipt configured its own --model instead of the one actually
provisioned; it now propagates the receipt's model through both callers.
Covered by: a superseded-mid-exchange fence test, corrupt-discard-needs-force
tests (state layer + CLI + guided GUI), and a two-process race asserting the
loser adopts the winner's provisioned model. All three are mutation-proven.
* test(aimlapi): drop the flaky third guided Start-over drive test
The guided "Start over on a kept-unreadable discard" test added a third
consecutive full Ink mount+drive to ProviderManager.test.tsx. On the CI-pinned
bun (1.3.13) that destabilises the Ink stdin harness (`stdin.ref is not a
function`), so the 'r' keypress never reaches the handler and the awaited
discard call never fires — a timeout unrelated to the code under test (it passes
on local bun 1.3.14). The two-drive configuration is green on CI.
The kept-unreadable behaviour stays covered where it is deterministic: the state
layer (kept-unreadable unforced, discarded on --force) and the CLI handler (the
`reset --force` guidance). The guided keybinding→discard→refusal plumbing is
covered by the identical-structure kept-settled drive test; the kept-unreadable
GUI branch is a trivial mirror of it. A comment records why the third drive is
intentionally omitted.
* wip(aimlapi): converge integration + CLI to the passwordless card-only flow (#1988)
Mid-port checkpoint. Rewrites the AI/ML API integration backend and CLI to the
canonical passwordless, card-only design (target PR #1988), in the current
code style. NOTE: the branch does not yet compile — the GUI (ProviderManager
passwordless rewire) and the aimlapi test suite still reference the removed
API and are the remaining work.
Done (typecheck-clean in these files):
- config.ts: add payBaseUrl + verificationBaseUrl endpoints, buildPartnerReturnUrl.
- topupState.ts: reduce to the #1988 shape — intent keyed on payBaseUrl/
verificationBaseUrl (no `method`); sync lockfile-based state; drop the
exchange-lease, discard/reset-command surface, async variants and
fail-closed-on-corrupt (corrupt reads as absent).
- client.ts: drop the password path (signup/login) and PaymentMethod/crypto;
pay() is card-only.
- topup.ts: rewrite to the passwordless phase-machine flow (checkAccount ->
code sign-in / new-account -> provision or by-key top-up; resolveTopupSession;
pollUntilPaid / pollUntilExchangeSettled / pollUntilByKeyToppedUp). Keeps the
DI test seam (no cross-file mock.module). Profile env writes AIMLAPI_API_KEY
mirror + CLAUDE_CODE_PROVIDER_ROUTE_ID.
- onboarding.ts, messages.ts (canonical copy), validation.ts, index.ts (lean
barrel), providerManagerAimlapi.ts (GUI indirection layer): new.
- CLI: aimlapiCommand.ts (registerAimlapiCommand, --email/--code/--amount, no
--method/reset), main.tsx wiring, handlers/aimlapi.ts (redacted errors).
Mandatory attribution headers wired on EVERY aimlapi request: X-AIMLAPI-Source
(agent/openclaude) + X-AIMLAPI-Partner-ID — in client.ts request() (auth/
checkout) and the config attribution path (inference/catalog).
* wip(aimlapi): port the passwordless provider-manager GUI (#1988)
Rebase ProviderManager.tsx on the #1988 passwordless aimlapi flow (email ->
6-digit code -> low-balance -> top-up / paste-existing-key -> done), replacing
the old password/method/Start-over flow and importing the aimlapi surface from
providerManagerAimlapi.js. Re-apply the current newer-main, non-aimlapi
`apiFormat: 'auto'` feature that the rebase would otherwise revert (form
metadata, toDraft default, display label, startCreateFromPreset default, the
API-format picker's Automatic option, and persistDraft's selectedApiFormat
'auto' -> undefined branch, kept alongside #1988's deferNavigation/onSaved).
Re-export resolveRouteCredentialValue from integrations/index for the GUI.
All source now typechecks; the aimlapi test suite is the remaining work.
* test(aimlapi): port integration + CLI tests to the passwordless flow
- topupState/topup/onboarding/aimlapiCommand tests: port #1988's coverage,
adapting the transport to `globalThis.fetch` stubbing and the profile/prompt
doubles to the module's `setAimlapiTopupTestDoubles` DI seam (no process-global
mock.module, which leaks across files in this repo).
- client/config tests: keep the current repo's stricter versions (complete
session contracts), pruning the removed password/crypto cases.
- Add mandatory-attribution-header coverage on all four request classes: the
client sends X-AIMLAPI-Source + X-AIMLAPI-Partner-ID on auth/checkout, and the
config attribution path sends both on inference/catalog and strips them for a
non-canonical proxy endpoint.
- Remove the reset-based CLI handler test (reset no longer exists).
Full aimlapi integration + CLI suite green (67 tests). ProviderManager GUI test
is the remaining piece.
* test(aimlapi): port the passwordless provider-manager GUI tests (#1988)
Rebase ProviderManager.test.tsx on #1988's version for the passwordless aimlapi
GUI tests (email -> code -> low-balance -> top-up / paste-existing-key), which
mock ./providerManagerAimlapi.js. Re-apply HEAD's newer-main apiFormat 'auto'
test cases (API-mode picker, token field, OpenAI/GPT-5/MiniMax presets) since
the source keeps that feature, and restore the current preset list ('LongCat')
in the test's PRESET_ORDER so navigateToPreset indexes match the real presets.
ProviderManager suite green (42 tests).
* docs(aimlapi): rewrite the setup guide for the passwordless card-only flow (#1988)
Describe the passwordless /provider flow (saved-key continue, new-user email +
6-digit code, paste-existing-key, low-balance top-up) and the card-only CLI
`aimlapi topup --email/--code/--amount` (no --method, no reset). Document the
full endpoint override set and the two mandatory attribution headers
(X-AIMLAPI-Source + X-AIMLAPI-Partner-ID) sent on every request, stripped for a
non-canonical proxy endpoint.
* refactor(aimlapi): let tests inject prompt doubles into the top-up flow
* fix(aimlapi): lock the partner id and complete mandatory-header coverage
Lock the partner id to OpenClaude's own attribution id: drop the --partner-id
CLI flag and the AIMLAPI_PARTNER_ID env override so rebate/revenue-share
attribution can never be redirected. resolvePartnerId() now always returns the
built-in id; the mandatory X-AIMLAPI-Partner-ID header itself is unchanged.
Assert the mandatory X-AIMLAPI-Source header on the catalog/discovery and
inference paths (discoveryService, bootstrap, runtimeMetadata) — the header was
already sent, only the test expectations lagged. Refresh stale password-era copy
in the interactive prompt and a top-up comment left over from the removed flow.
* fix(aimlapi): address CodeRabbit review — settlement, key-safety, redaction
- Wait for a resumed sign-in top-up to settle before returning: the account
non-exchange path now mirrors the by-key flow, so a credited balance is never
reported while the billing operation is still in flight.
- Preserve a freshly minted sign-in key when the balance read is aborted, so an
abort cannot orphan a paid credential and mint a second key on the next run.
- Clear the first-run env-key adoption markers when validation fails, so a retry
re-validates instead of short-circuiting into persisting the unvalidated key.
- Never crash the top-up success screen on an amount parse edge — fall back to
the raw entered amount after the payment has already cleared.
- Show all four API-format options (visibleOptionCount 3 -> 4).
- Document that guided provisioning requires the canonical inference endpoint.
- Add regression tests: resumed-sign-in settlement, aborted-balance key
retention, failed-env-key re-validation, and CLI error redaction.
* test(aimlapi): wait for the masked code frame instead of a fixed delay
The AIMLAPI code-screen assertion captured output after a fixed 25ms sleep,
which is too short on a slower CI runner (Node 24) and intermittently missed the
freshly rendered mask characters. Wait for the masked frame instead so the
assertion is deterministic.
* test(aimlapi): harden the provider-manager GUI flows against CI timing
The GUI top-up flow intermittently failed on a loaded CI runner: the final
keystroke on the success screen was sent in the same tick as the render, before
Ink attached the input handler, so it was dropped and the flow stranded on the
done screen. Add the same input settle the other steps already use.
Also raise the shared waitForCondition default timeout (2s -> 5s). The predicate
is polled every 10ms and returns as soon as it is met, so this only adds patience
for a slow runner and never slows a passing wait — keeping the Ink-driven flows
deterministic under CI load.
* fix(aimlapi): gate attribution headers by trusted AI/ML API host
The client sent the mandatory source/partner headers on every request, but the
auth/app/pay/inference base URLs are all env-overridable — so a request pointed
at a user proxy (notably the balance probe against an overridden inference URL)
leaked OpenClaude's partner/source identity. Send them only when the resolved
request host is aimlapi.com (production or staging, over HTTPS), mirroring the
inference/catalog stripping contract in resolveAimlapiAttributionHeaders. Adds
an isTrustedAimlapiRequestUrl predicate plus canonical-sends / proxy-withholds
regression tests.
* test(aimlapi): wait for the done screen to settle before the final keystroke
Replace the fixed 25ms delay before the success-screen keystroke with an
observable frame-stability wait, so a slow CI runner cannot drop the keystroke
before Ink has committed the render and attached its input handler.
* fix(aimlapi): durable receipts and atomic election for concurrent top-ups
- Restore the atomic checkout-session election dropped during the passwordless
convergence: recordAimlapiCheckoutSession is a first-writer-wins CAS, so two
concurrent runs of the same intent settle on ONE payable checkout — a loser
adopts the winner's token and abandons the session it just opened instead of
leaving two chargeable checkouts. Wired through resolveTopupSession (the create
branch elects then adopts; the resume branch notifies once) and both the CLI
and GUI onSession callbacks.
- Persist the settled receipt (apiKey / apiKeyId / model / settled) in the GUI
BEFORE the profile write, so an interrupted or failed write resumes with the
paid, one-shot exchanged key instead of stranding it (mirrors the CLI).
- Clear the sign-in key cache with the just-minted key id on a sufficient-balance
sign-in: persistDraft runs onSaved synchronously, so the aimlapiIssuedKeyId
state setter has not applied yet — pass the id explicitly.
Adds regression tests for the election (first-writer-wins + loser adoption), the
settled-receipt ordering, and the sufficient-balance cache clear.
* fix(aimlapi): abort on a lost election and keep the receipt write best-effort
- Treat a null recordAimlapiCheckoutSession result as "the slot was cleared by a
sibling that already completed this top-up" and abort, instead of silently
proceeding to pay a second, unrecorded checkout (both the CLI persistSession
and the GUI reportSession). Closes the residual double-charge race.
- Make the GUI settled-receipt write best-effort: the payment already cleared, so
a receipt-write failure (lock contention, full/read-only disk) must not divert
the flow into the top-up error path — the profile write is what matters.
- Align the recordAimlapiCheckoutSession test double with the real semantics:
match on intent + payment id only and return null on a non-matching slot.
Adds a regression test that a sibling clearing the checkout mid-flow aborts
before any /pay call. The sufficient-balance sign-in test now waits for the code
screen to settle before typing (the transition dropped the first keystroke).
* test(aimlapi): settle after each awaited frame so keystrokes aren't dropped
The provider-manager GUI tests type on the line after waitForFrameOutput matches
a new screen, but Ink registers input handlers in an effect that runs after the
render commits. On a loaded CI runner the first post-transition keystroke could
be dropped, stranding the flow and timing out (seen intermittently on Node 22).
Add a short settle after every frame match — returning the same matched frame,
so no assertion changes — which lets the input handler attach before the caller
types. Fixes the class instead of patching individual call sites.
* fix(aimlapi): recover a settled GUI receipt and harden checkout/key edge cases
- Recover a settled checkout receipt in the provider-manager GUI before
provisioning: if a prior run paid + exchanged the key and saved the receipt but
was interrupted before the profile write, finish that write with the retained
key instead of re-entering provisioning against the now-exchanged session
(which fails in resolveTopupSession and strands the paid credential). Mirrors
the CLI.
- Reject a non-HTTPS checkout payUrl at the client response boundary (the
validator required only "openable"), so a session is never retained with an
address the flow refuses later and then polls with no usable link.
- Do not discard a freshly minted sign-in key when its cache write fails: copy
the key into memory before persisting and make the sign-in-cache / top-up-state
writes best-effort, in both the GUI and the CLI, so a lock/permission/disk
failure can't force a second key on retry.
- Narrow the setup guide: the canonical-inference requirement applies to
new-account onboarding + key provisioning; the existing-key top-up runs against
the configured endpoint.
Adds regression tests for the settled-receipt recovery (no re-provision) and the
non-HTTPS payUrl rejection.
* fix(aimlapi): HTTPS checkout callbacks, per-email key cache, safer edges
- Require a credential-free HTTPS base for the checkout return URLs (they embed
the resumable session token) and for the browser return/landing URL, so a
cleartext AIMLAPI_PAY_URL/AIMLAPI_RETURN_URL override can't leak the token or
break the documented HTTPS return-target contract.
- Store sign-in recovery keys as an email-keyed collection instead of a single
global record, so a concurrent/interrupted sign-in for one account no longer
evicts another's key (which forced a duplicate mint). Old single-record files
migrate on read; clear stays per-email ownership-aware.
- Treat post-success receipt cleanup as best-effort in both the CLI (finishProfile)
and the GUI (resetAimlapiCheckoutIntent): the profile is already saved, so a
lock/permission/IO failure clearing the receipt must not report failure.
- Reject scientific-notation amounts: parseAimlapiAmountUsd now requires a plain
decimal with at most two fractional digits, closing the "20.001e0" sub-cent
bypass that silently rounded to a wrong charge.
- Add the pay/verification/return env vars to the config-test snapshot so a set
override can't pollute default-endpoint assertions.
Adds regression tests for each.
* fix(aimlapi): async checkout-state clear for the Ink flow + reject malformed bases
- Clear the checkout receipt through an async lock in the provider-manager GUI:
restore withStateLockAsync + clearAimlapiTopupStateAsync and fire it
best-effort (unawaited) from the save callback, so a contended lock no longer
blocks Ink input/timers/SIGINT after the profile is already saved. The CLI keeps
the sync clear (one-shot command).
- Reject a query string or fragment in the checkout/return base URLs: a base like
https://pay.aimlapi.com/#x would swallow the appended /checkout?...sessionToken
into the fragment, so the token never reaches the callback as a query param.
- Surface a non-fatal CLI note when receipt cleanup fails (the profile is already
saved and the stale receipt reconciles on the next run).
Adds regression tests: async clear ownership, query/fragment rejection, and the
legacy single-record sign-in-cache migration.
* fix(aimlapi): reject bare ?/# delimiters in checkout and return base URLs
url.search / url.hash are empty for a bare delimiter (e.g. https://pay.aimlapi.com/?
or .../#), so those slipped past the query/fragment guard and still corrupted the
appended /checkout?...sessionToken=... . Reject any raw ?/# in the candidate in
both safeHttpsBaseUrl and requireHttpsBaseUrl, and cover the bare-delimiter cases.
* fix(aimlapi): harden checkout recovery — exchange lease, retry modes, payable guard
Addresses a fresh review round on the checkout state machine:
- Restore the cross-process exchange lease (dropped in the passwordless
convergence): the one-shot key exchange is serialized so two processes resuming
the same paid sign-up session cannot both exchange and strand the credential —
the lease winner exchanges, peers wait for its settled receipt.
- Persist the exchange mode in the receipt so a retry that has since become
sign-in still exchanges the paid session instead of minting an unrelated key
and clearing the paid checkout (CLI + GUI).
- Recover the checkout URL on a pending_payment resume by re-issuing the
idempotent pay/top-up (the stable paymentSessionId prevents a double charge)
instead of polling a session the user can never open.
- Route settled-receipt recovery through persistExistingAimlapi for an existing
saved profile / AIMLAPI_API_KEY top-up, so it updates the selected profile
(preserveEnv) rather than minting a new one and copying the env key.
- Confirm before abandoning an already-open checkout: editing amount/auto-top-up
after a checkout URL was opened now requires an explicit re-submit (the old
browser tab stays chargeable and no endpoint can cancel it).
- Treat a credentials/query/fragment inference base as non-canonical so a
`.../v1#x` override cannot be written as OPENAI_BASE_URL and break the shim.
Tests: exchange-lease election + failed-exchange release, retry-exchanges-the-
paid-session, idempotent URL recovery on resume, canonical-gate rejection, and
the re-edit confirmation.
* fix(aimlapi): repair exchange-lease liveness and the re-edit abandon guard
- exchange lease: a peer that finds a live foreign lease now re-attempts on each
poll instead of only watching for a settled receipt, so it resumes the moment
the holder settles OR frees the lease (failed/crashed) rather than hanging the
full 20-minute poll window; folds the wait into the lease loop.
- exchange lease: treat a future-dated exchangeLeaseAt (backwards clock jump or
an edited state file) as stale and reclaim it, instead of reading a negative
age as perpetually fresh and deadlocking every peer.
- re-edit guard: reset the abandon acknowledgement when a new checkout opens so a
further edit to a different amount/auto-top-up is confirmed again instead of
silently abandoning the freshly-opened chargeable tab; clear the opened-checkout
tracking once payment settles so a later re-edit never warns about a paid tab.
- tests: lease release is owner-scoped and preserves a settled receipt; a
future-dated lease is reclaimed; the GUI re-edit warning re-arms after a second
edit.
* test(aimlapi): sync re-edit test on rendered amount; guard vacuous lease seed
- re-edit GUI test: submit only once the edited amount is reflected in the
rendered frame instead of after a fixed 25ms delay, so Enter is never processed
against the stale amount on a slow runner.
- future-dated lease test: assert the seed compare-and-swap actually persisted the
lease before acquiring, so the reclaim path can never pass vacuously.
- exchange lease: record a swallowed release failure via file-backed debug logging
(safe on the Ink GUI path) so a lock/permission problem behind a slow takeover is
diagnosable.
* test(aimlapi): match the complete edited amount in the re-edit frame wait
Prefix matching let "$250" match a stray "$2500" (and "$2500" match "$25000"),
so a wrong-amount input regression could pass unnoticed. Pin the complete value
with a negative lookahead on a trailing digit.
* fix(aimlapi): make the one-shot key exchange crash-durable and per-operation
Three checkout-recovery correctness fixes:
- Persist the exchanged key under the CAS BEFORE returning it. The lease winner
used to hand the /exchange key to the caller, which wrote the receipt only
afterward; a crash in between left the checkout exchanged but its only key
unpersisted, so a retry re-ran (and was rejected by) the spent one-shot
exchange. exchangeKeyWithLease now records the settled receipt via
recordAimlapiSettledKeyAsync (merges over the record, clears the lease) as soon
as the exchange succeeds.
- Use a per-operation exchange-lease owner instead of a module-global id. Two
overlapping top-ups in the same process shared one owner, which the acquire
treats as self and immediately reclaims, so both could POST the non-idempotent
/exchange concurrently. A fresh owner per operation makes the second observe
the first's lease as foreign and back off; a retry within one operation keeps
its owner and still reclaims the lease it released.
- Never serialize an empty apiKey/apiKeyId. The existing-key top-up path reports
apiKeyId: '', which the reader rejects, making the whole settled receipt (and
the paid key it records) unrecoverable. The save path now coerces an empty
key/id to absent so the receipt stays readable.
* fix(aimlapi): refuse to overwrite an unfinished checkout when the intent changes
claimAimlapiTopupState backs a single slot, so rerunning with a different amount,
auto-top-up, or endpoint used to unconditionally replace the stored record. When
the prior checkout had opened a session (a resume token — possibly already paid
but not yet exchanged) or held a settled key not yet written to a profile, that
dropped the only handle to a paid session/key and stranded it permanently.
claim now refuses a changed intent while such a record exists, with an actionable
message to finish or cancel the earlier top-up first (re-running the same intent
still resumes it). A never-advanced claim — empty resume token, unsettled, no key
— is still replaced. The CLI surfaces the message directly; the interactive flow
already clears the prior record on edit, so normal re-edits are unaffected.
* fix(aimlapi): never settle a keyless receipt; keep the paid key reaching the profile
Addresses a further review batch:
- recordAimlapiSettledKeyAsync now refuses to mark a receipt settled (and clear
the lease) when no key resolves from the call or the stored record. A keyless
settled receipt would make a peer resume from a spent one-shot exchange with no
credential; the record and its lease now survive so a retry can still exchange.
- The CLI's pre-profile settled-receipt save is now best-effort (try/catch + a dim
note), matching the earlier saves. A lock/permission/IO failure there no longer
throws before finishProfile, so the paid, exchanged key still reaches the
provider profile.
- startCreateFromPreset drops aimlapiPersistedIntentRef on a fresh flow entry
(in-memory only) so a later resetAimlapiCheckoutIntent can never clear a previous
flow's on-disk receipt against a stale payment id.
- Prompt copy: "Do you have an aimlapi.com key?" / "I already have an aimlapi.com
key" (missing article).
Tests: keyless settle is rejected and leaves the lease intact; the CLI forwards
explicit --amount/--model; the settled-receipt recovery renders the top-up (not
"ready") done copy.
* test(aimlapi): assert the exchange lease stays held on a keyless settle attempt
Tighten the keyless-settlement guard test: a "not settled" assertion also passes
if the lease were wrongly cleared (a peer would then see 'acquired'). Assert the
peer acquisition returns 'held' so the test pins that a keyless settle preserves
the lease for a retry.
* fix(aimlapi): poll the checkout token, not the auth bearer, while waiting on a resumed exchange
pollUntilExchangeSettled was called with the passwordless-auth bearer
instead of the partner checkout-session token, so it polled the wrong
resource. A terminal error there clears the recovery receipt, stranding
a paid one-shot sign-up exchange.
* fix(aimlapi): keep the checkout receipt resumable through an unconfirmed amount/auto-top-up edit
Editing the amount or auto-top-up cleared the persisted checkout intent
and durable receipt immediately, before the abandon-ack confirmation
that gates actually starting a new payment session. A user who edits
and backs out (or completes the still-open browser checkout) before
confirming lost the only mapping to that chargeable checkout, so a
later run would open a new one instead of resuming the paid session.
The reset now happens only once the user has explicitly confirmed
abandonment: claimAimlapiTopupState takes an `abandonExisting` option
that atomically overwrites the retained record under the same lock
acquisition, instead of racing a separate async clear against a
synchronous claim.
* test(aimlapi): sync on the rendered email before submitting in the new receipt-resume test
A fixed sleep doesn't guarantee the TextInput has processed the typed
email before Enter is sent; a loaded runner can drop the submit. Wait
for the typed value to actually render, matching the amount-edit sync
already used later in this same test.
* docs(aimlapi): describe checkout retention as durable, not session-scoped
The prior wording ("retained while the provider flow remains open")
undersold what topupState.ts actually does: the payment identity and
any issued key are persisted to disk, so a restart resumes the same
checkout too, and a prior paid+exchanged run finishes the profile
write on the next run instead of re-provisioning.
* fix(aimlapi): unify error-status extraction, drop dead top-up state, tighten wrappers
- Extract aimlapiApiErrorStatus as the one place that reads an HTTP
status off a caught error, structurally (not `instanceof
AimlapiApiError`) since some callers surface a duck-typed error with
a bolted-on `status` instead of the real class; use it at both call
sites that previously duplicated (and disagreed on) this check.
- Remove aimlapiPaymentSessionId/isAimlapiTopupRunning: both were
write-only state (declared with a blank destructure slot, never
read), so every setter call scheduled a render for no observable
effect.
- Switch providerManagerAimlapi.ts's wrappers to `...args` forwarding
so an implementation gaining a parameter can't silently get it
dropped by a wrapper that still names the old ones positionally.
- Stop exporting pollUntilPaid from the aimlapi barrel; nothing
imports it through there (topup.test.ts imports it directly from
topup.js), so keep it out of the public surface.
- Normalize the email key while rebuilding the sign-in key store's
collection branch on read, matching the legacy single-record
migration branch right above it - a hand-edited or older-build file
with a mixed-case key would otherwise be invisible to
loadAimlapiSignInKey and mint a duplicate key.
* test(aimlapi): cover resetAimlapiCheckoutSession, by-key top-up args, and error edges
- resetAimlapiCheckoutSession: refreshes the payment session while
preserving a minted key, and is a no-op when there's no key to
preserve.
- ProviderManager: a low-balance saved key that gets topped up charges
the EXISTING key via topUpAimlapiByApiKey (apiKey, non-empty
paymentSessionId, empty resumeSessionToken) instead of opening a new
passwordless-account checkout - previously only exercised through
the default test mock, with no assertion on the call.
- The three negative assertions in the top-up progress-frame check
tested strings that don't exist anywhere in this GUI (CLI-only or
pure invention), so they could never fail; add a check against the
real failure copy so a regression that silently fails at that point
is actually caught.
- CLI: pin the --no-open default (false) when the flag is absent, and
cover the non-Error (thrown string) branch of the handler's
credential-redaction path - both previously only exercised through
the Error/AimlapiApiError branches.
* fix(aimlapi): close checkout-state concurrency and exchange-lease races
- saveAimlapiTopupState now merges resumeSessionToken like the other
retained fields instead of spreading the caller's value verbatim. A
caller saves this record at points where its in-memory copy is still
empty (right after sign-in, before a checkout session exists); a
concurrent peer running the same intent can have already elected and
recorded a real token in that window, and the unconditional spread
was overwriting it with "", stranding the peer's chargeable checkout.
- The exchange lease is sized for a single POST (EXCHANGE_LEASE_STALE_MS,
75s) but a resumed wait-exchange holder can sit in a read-only poll
for up to POLL_TIMEOUT_MS (20 minutes) before ever reaching that POST.
Without refreshing, a peer would see the lease go stale mid-wait,
reclaim it, and risk a second concurrent /exchange on the same
one-shot session. Add refreshAimlapiExchangeLeaseAsync and call it
every poll iteration.
- When a peer finishes /exchange and records the settled key WHILE this
process holds the lease and is polling/exchanging, the poll seeing
the session flip to 'exchanged' threw a hard failure instead of
resuming from that peer's settled receipt. Re-check for a settled
receipt before releasing the lease and rethrowing.
- claimAimlapiTopupState's abandonExisting no longer drops an
already-minted (but not yet paid) existing-account key when
overwriting a retained checkout for a different amount/auto-top-up -
it now merges apiKey/apiKeyId/model in, matching
resetAimlapiCheckoutSession's retain-key pattern. A fully settled
(paid + exchanged) credential is refused unconditionally regardless
of abandonExisting, since that confirms giving up an UNPAID checkout,
never an already-paid one.
* fix(aimlapi): guard GUI checkout abandonment and receipt recovery
- The abandon-ack gate only armed once a checkout URL surfaced
(aimlapiOpenedCheckoutRef), but resolveTopupSession can already elect
and persist a resumeSessionToken before that point. Backing out in
that window then editing the amount hit claimAimlapiTopupState's
generic refusal instead of the same confirm-to-abandon flow. Extend
the gate to also cover a persisted (not yet opened) intent.
- Persist an existing-account key minted at sign-in into the top-up
receipt itself (mirrors the CLI), not just the separate sign-in-key
cache, so a restart before settlement can resume from one
self-contained record instead of depending on two files staying
consistent.
- reportSession's terminal branch (a cancelled/expired/dead session)
always fully wiped the receipt; mirror the CLI's persistSession,
which retains an already-minted key (fresh payment session, dead
token dropped) and only falls back to a full clear when there's no
key to keep.
- Submitting the email screen unconditionally reset the whole
onboarding identity, silently abandoning a chargeable checkout on an
accidental Esc-back-and-resubmit of the same email. Require the same
explicit confirmation an amount edit does when a resumable checkout
exists.
- "Set up a new key or switch account" only cleared in-memory fields,
leaving a durable receipt from an earlier interrupted top-up (this
mount's refs were never populated for it, since it may be from an
earlier process) to hit the same refusal on the next onboarding
attempt with no way to recover short of deleting the file by hand.
Force the next claim to override it once.
- existingAimlapiCredential() rejected saved-profile discovery whenever
the AMBIENT AIMLAPI_INFERENCE_URL wasn't canonical, even for a
profile that was itself saved against the canonical endpoint. Narrow
the canonical requirement to what it's actually protecting: reading
the ambient env key, and sending a saved key to a non-canonical
endpoint (the existing per-profile check).
- The post-signup success screen claimed a magic link was emailed; this
flow is passwordless email-code sign-in, no magic link is ever sent.
Point at the dashboard instead.
* docs(aimlapi): note the interactive/CLI auto-top-up default mismatch
The guided GUI flow pre-selects auto-top-up on; the CLI's --auto-top-up
only enrolls when explicitly passed. Left both defaults as-is (auto-top-up
is a real billing behavior, not something to flip unilaterally) and
documented the asymmetry so it's not a surprise either way.
* test(aimlapi): sync on the settled frame before confirming switch-account
A fixed sleep doesn't prove the Select's focus actually moved to the
second option; on a loaded runner the following Enter could land on
"Continue with your saved API key" instead and assert against the
wrong branch. Wait for the frame to stop changing, matching the
settle-poll pattern already used elsewhere in this file.
* fix(aimlapi): stop the exchange poll when a peer reclaims the lease
The periodic lease refresh added to pollUntilExchangeSettled discarded
its result (`.catch(() => false)`), so a peer reclaiming the lease
mid-wait was silently ignored: the poll kept going, returned normally
once the session left 'exchanging', and the caller walked straight
into the non-idempotent /exchange POST with no ownership check of its
own — racing whatever the peer was doing with the same one-shot
session. The comment claiming this was safe ("resolves on this
function's next outer retry") was simply wrong: there is no outer
retry on the success path, control goes directly to the POST.
Distinguish a thrown refresh (transient lock contention — best-effort,
retry next iteration) from an explicit `false` result (the lease is
definitively no longer ours) and bail out on the latter, so the
caller's existing catch block re-checks for the peer's settled
receipt (or fails the run, requiring a re-run) instead of racing it.
* test(aimlapi): require the settle-wait frame to actually differ from before the keypress
waitForCondition polls every 10ms; on a loaded runner two consecutive
polls can both land before Ink has processed the keypress at all, so
the "stable frame" check was satisfied by the unchanged PRE-keypress
frame, sending Enter before focus ever moved to the second option.
Snapshot the frame before the keypress and require the settled frame
to differ from it, not just be internally stable.
* fix(aimlapi): elect the retained key atomically, stop blocking Ink on claim
- Two concurrent sign-ins for the same intent could each mint their own
existing-account key before either save landed, and saveAimlapiTopupState
(last-writer-wins) let whichever saved last silently overwrite the
other's key on disk while both runs kept using their own in-memory
copy. Elect apiKey/apiKeyId first-writer-wins (same as
resumeSessionToken already is), re-check the receipt right before
minting so a losing run adopts the winner's key instead of minting a
second, and re-check again after a save that lost the election so the
run's own in-memory key matches what's actually on disk. Apply the
same first-writer-wins election to the separate GUI sign-in-key cache
(saveAimlapiSignInKey), which had the identical last-writer-wins gap.
- The GUI called the sync claimAimlapiTopupState directly from an event
handler; its lock retry blocks the whole event loop (Atomics.wait) for
up to LOCK_TIMEOUT_MS on contention, freezing Ink rendering, Esc, and
SIGINT — exactly what resetAimlapiCheckoutSessionAsync already exists
to avoid for the same reason. Add claimAimlapiTopupStateAsync (sharing
the same claim logic via an extracted operation function) and switch
the GUI to it, making startAimlapiTopup async.
recordAimlapiCheckoutSession (the reportSession/onSession path) has the
same sync-lock exposure but is called from a callback whose return value
AimlapiProvisionOptions.onSession drives synchronous control flow in
several places across both the CLI and GUI provisioning paths; making it
async is a larger, riskier contract change deliberately left out of this
pass.
* fix(aimlapi): never pair a new key with a stale or unrelated apiKeyId
saveAimlapiTopupState's apiKeyId fallback still read current.apiKeyId
even when current.apiKey was empty (the id-without-a-key case) or when
state carried a genuinely new apiKey with its own empty-id sentinel,
letting a fresh key get silently tagged with an unrelated leftover id.
Gate apiKeyId on the same winner apiKey came from instead of falling
back to current independently.
* fix(aimlapi): stop cross-account key leaks, lease key-minting, keep GUI CAS async
- claimAimlapiTopupState's abandonExisting carried a retained apiKey into
ANY differing intent, including a switch from account A to account B
(the GUI's forceAbandonExisting path). A B-flow restart before the
profile write could then initialize from the receipt and call the B
checkout with A's credential — crediting A while B's flow saves A's
key. Gate the carry-over on the intent's account/key identity
(`email`) matching, not just abandonExisting.
- The key-choice screen (I am a new user / I already have a key) reset
the whole onboarding identity unconditionally on either choice, even
when Esc had backed all the way out from the amount screen past an
already-opened, still-chargeable checkout. Apply the same
abandon-confirmation gate startAimlapiEmailOnboarding already uses.
- POST /v1/keys (minting an existing-account key) had no cross-process
serialization: two concurrent runs for the same intent could each
observe no retained key and both mint, orphaning whichever key lost
the first-writer-wins receipt race. Add a key-mint lease (mirroring
the exchange lease's acquire/release shape) so exactly one process
ever mints; a peer backs off and adopts the winner's recorded key.
- The interactive flow already claimed asynchronously, but still called
the synchronous saveAimlapiTopupState and recordAimlapiCheckoutSession
directly from an event handler and the onSession callback — either
could block the whole event loop for up to LOCK_TIMEOUT_MS under lock
contention, freezing rendering, Esc, and SIGINT while a payment
session is being created. Add async CAS variants and await them; this
needed widening AimlapiProvisionOptions.onSession to allow returning a
promise, since its return value drives resolveTopupSession's session
election.
- An ambient AIMLAPI_API_KEY takes the by-key route with
aimlapiExistingUsesEnv, so the eventual profile intentionally stays
keyless. The settled-receipt save before that write unconditionally
copied the env value into aimlapi-topup.json regardless, expanding a
secret's on-disk exposure surface for no recovery benefit (a restart
re-reads the same env var). Keep an env-backed receipt credential-free.
* fix(aimlapi): preserve the key-mint lease across unrelated CAS writes
saveTopupStateOperation and recordCheckoutSessionOperation merged the
exchange lease but not the key-mint lease added in the previous commit:
AimlapiCheckoutState (what every caller spreads checkoutState from)
carries neither lease pair, so an unrelated write - persisting the
exchange flag, or electing a checkout session - silently dropped an
in-flight peer's key-mint lease. A third process would then see the
slot as free and mint its own key, reopening the exact double-mint race
the lease exists to close. Fall back to the current lease the same way
the exchange lease already does.
Also: add a future-dated key-mint lease reclaim test mirroring the
exchange lease's, and align the default saveAimlapiTopupStateAsync test
mock with the real CAS (match on intent + payment id, keep the first
writer's resumeSessionToken/apiKey) so it no longer accepts a write the
real store would reject.
* test(aimlapi): preserve the key-mint/exchange lease in the mocked GUI CAS writes
saveAimlapiTopupStateAsync's and recordAimlapiCheckoutSessionAsync's
default mocks spread { ...state } as their write's base, same gap as
the real saveTopupStateOperation/recordCheckoutSessionOperation had
before the previous commit: neither lease pair survived a write whose
state didn't carry them (which is every real caller, since
AimlapiCheckoutState exposes neither).
Fixing the merge alone wasn't enough — the same two mocks' "does this
write still belong to this slot" check also compared lease fields as
if they were part of the intent identity, so a write that seeded a
lease value failed to match the just-claimed record and silently
no-op'd instead of persisting anything. Exclude both lease pairs from
that comparison too, matching the real matchingStateOrNull (which only
ever compares INTENT_KEYS + paymentSessionId).
* fix(aimlapi): recover ambiguous key-mint/exchange outcomes before releasing leases
createKey and /exchange are both non-idempotent with no server-side retrieval
path, so a lost response after the request actually committed left three
races: a retry could exchange (or mint) a second time and orphan the first
credential, or the CLI's exchange caller would surface a generic network
error instead of the accurate "already exchanged, rotate the key" guidance.
exchangeKeyWithLease now distinguishes a genuinely ambiguous transport
failure of the /exchange POST itself from other doExchange failures (a
pre-POST bail on a reclaimed lease, or a definite rejection): only the
former re-checks the session status directly, surfaces the already-exchanged
error when confirmed, and otherwise leaves the lease held instead of
releasing it into a race. mintExistingAccountKeyWithLease applies the same
ambiguous/definite split before deciding whether to release its lease.
The GUI sign-in flow had an equivalent gap one step earlier: two concurrent
code-verification races could each see an empty key cache and both mint
before either save elected a winner, so the loser never adopted the winner's
key. completeAimlapiCodeSignIn now serializes the cache lookup and mint
behind a new email-scoped lease in topupState.ts, so a losing process waits
and adopts the winner's cached credential instead of minting its own.
* fix(aimlapi): treat caller-aborted mutations as ambiguous and dedupe the transport helpers
client.request rethrows a caller-driven abort as the raw abort error instead
of wrapping it in AimlapiApiError, so the ambiguous-outcome checks added for
createKey and /exchange missed it: cancelling client-side does not stop a
non-idempotent POST from completing server-side, but the lease was still
released as if the request definitely failed, leaving the door open to a
retry racing a second mint/exchange. All three call sites (the checkout-time
key-mint lease, the exchange lease, and the sign-in key-mint lease) now also
hold the lease when the caller's own signal fired.
Extracted the duplicated abortError/sleep/isAmbiguousTransportApiError
helpers shared between topup.ts and onboarding.ts into transport.ts so the
ambiguity rule can't drift between the CLI and GUI paths. Switched the GUI
sign-in flow's cache save to the async, lock-yielding variant and logged its
lease-release failures for parity with the other leases.
* fix(aimlapi): close six checkout-state races found across the claim, lease, and recovery paths
claimAimlapiTopupState's in-progress check only looked at
resumeSessionToken/settled/apiKey, so a receipt claimed just before its
non-idempotent POST (/v1/keys or /exchange) still looked blank and
replaceable to a different intent. A competing claim could overwrite it
mid-flight, leaving the in-flight request's eventual CAS save with no
matching record to land in and orphaning the credential it was about to
mint or exchange. The claim now also refuses (unconditionally, even under
abandonExisting) while either lease is live.
The sign-in key-mint lease's 75s stale window exactly matched createKey's
worst-case duration (60s) plus the async lock's own timeout (15s) for the
cache write that follows, with zero margin for anything else. A legitimately
still-working holder could lose the lease to a peer moments before its
result was cached. It's now refreshed right after createKey succeeds, giving
the cache-write phase its own fresh window.
ProviderManager's code-verification path called the synchronous
saveAimlapiSignInKey, whose lock retry blocks the whole event loop for up to
five seconds on contention — freezing Ink rendering, timers, Esc, and SIGINT
right after a sign-in. Switched to the async variant, exported through
providerManagerAimlapi.ts alongside the other async cache operations.
The three session polling helpers typed onSession as returning void and
never awaited it, even though ProviderManager's callback is async and starts
receipt cleanup before returning. A terminal session (cancelled/expired/
failed, or a dead session) could let the UI reach the amount screen before
the durable receipt was actually reset, so an immediate retry still saw the
stale resume token and got rejected as "not yet abandoned." Both sides now
await through to completion.
The confirmed email-switch flow cleared the in-memory checkout intent and
fired an un-awaited, error-swallowing state clear, but derived its later
claim's abandonExisting only from refs that clear had just wiped — so a
slow or failed clear left the user's explicit confirmation unenforced at the
claim itself. It now sets the same one-shot force-abandon signal the
"switch account" flow already uses for exactly this kind of on-disk,
this-mount-invisible conflict.
A cached sign-in key that the server had revoked was indistinguishable from
one that was merely unreachable: both collapsed into balanceStatus:
'unknown', which re-cached the same dead key and sent the user to manual-key
entry with no way back into the guided flow short of deleting local state.
A definite 401/403 against a cached (not freshly minted) key now invalidates
the stale cache entry and mints one replacement before falling back to the
generic unknown-balance path; every other (ambiguous) failure still leaves
the cache untouched.
Extracted a shared claim/lease-liveness helper in topupState.ts and added
regression coverage for each race — including two that hold a mocked
createKey/reset call open to prove the competing operation actually waits
instead of just asserting on the end state.
* fix(aimlapi): clear the stale force-abandon flag on a fresh preset entry
aimlapiForceAbandonExistingRef is armed when the user confirms abandoning a
checkout during an email switch, then consumed by the next claim. If that
claim never runs — the switch's own onboarding fails and the user backs all
the way out to preset selection instead of retrying — the flag stayed armed.
Re-entering the aimlapi preset with an unrelated email then passed
abandonExisting: true on its first claim with no confirmation for that flow,
silently overwriting whatever unpaid checkout was still on disk.
startCreateFromPreset now resets the flag alongside the other per-flow refs
it already clears on fresh entry.
Also swapped a fixed 20ms sleep in the cross-intent concurrency test for a
signal fired from the held-open /v1/keys handler, so the test can't flake
under CI load waiting for the run to reach the point it needs to race.
* fix(aimlapi): close the remaining confirmation, cleanup, and lease gaps in checkout state
The API-key-choice screen's own confirm-abandon gate (Enter twice to accept
"a checkout from this account is still pending") reset the onboarding
identity but never armed the force-abandon signal the email-switch and
switch-account flows already use. A contended or failed pre-clear left the
next claim to hit the CAS's unconfirmed-conflict refusal despite the user
having just confirmed abandonment through this exact screen.
reportSession('')'s terminal-session handler discarded the persisted intent
ref before its reset/clear attempt settled, and swallowed any failure as
success. A lock timeout or I/O error then left the durable receipt exactly
as it was, but with no ownership left in memory to retry cleanup or to route
a later conflicting claim through the normal confirmation gate — the CAS
just rejected it outright. Ownership now only drops once the transition
actually commits; a failure is logged and the ref stays populated so the
existing gate covers the next claim.
The sign-in key-mint lease's stale window already had zero margin for its
own refresh call's lock wait (up to 15s) on top of createKey's own worst
case (60s) and the cache save's lock wait (another 15s) — 90s with nothing
left over. Widened it to 150s and lengthened the losing side's patience to
match, and stopped silently ignoring a refresh that reports lost ownership:
it's now logged for diagnosability even though the save itself stays safe
to attempt regardless (first-writer-wins makes a losing write a no-op).
Both onSaved completion paths (persistExistingAimlapi and persistAimlapiKey)
called the synchronous clearAimlapiSignInKey from Ink's synchronous save
callback, whose lock retry blocks the event loop for up to five seconds on
contention — freezing rendering, timers, Esc, and SIGINT right at
completion, the same class of bug already fixed for the sign-in save path.
Re-exported the async variant through providerManagerAimlapi.ts and switched
both call sites to fire-and-forget it instead.
* fix(aimlapi): stop the flow instead of risking a stranded key on a receipt-write failure
/exchange (and the by-key top-up) is a one-shot operation: once it succeeds,
the issued key exists only in memory until a durable copy lands somewhere.
Both the CLI and the GUI wrote the local recovery receipt right after that,
but treated a failure there as best-effort and proceeded straight into the
provider-profile write regardless. If the receipt write failed and the
profile write then also failed — or the process was interrupted between the
two — the key was gone: nothing durable ever recorded it, and a retry can't
re-exchange an already-spent session to get it back.
Both paths now treat the receipt as a required checkpoint rather than an
optional resume aid: a failure here stops the flow with a clear error
pointing at the one real recovery path (rotating the key from the aimlapi.com
dashboard) instead of silently continuing. This shouldn't cost much in
practice — the underlying CAS write already retries substantially on lock
contention before giving up, so a failure this deep signals a real problem
rather than a transient blip a fallback write would likely have hit too.
Added failure-injection coverage for both paths: the CLI test breaks the
config directory (a file where a directory is expected) right as the
exchange response lands, so the post-exchange save fails deterministically
without relying on OS-specific permission semantics; the GUI test mocks the
save to reject directly and asserts the profile write is never reached.
* test(aimlapi): strengthen receipt-write-failure coverage and document the recovery path
Both the CLI and interactive-flow tests for the post-exchange receipt-write
failure only asserted the generic error text, which would still pass if the
issued key id — the actual recovery handle the error exists to surface — got
dropped from the message later. Both now assert the id appears too. The
interactive test also confirms the screen stays usable after the error: a
retry reaches the amount-submission path again instead of the flow being
stuck.
Documented the resulting behavior in the setup guide: since the key exchange
is one-shot, a receipt-write failure after a successful payment now stops
both flows with an error naming the issued key, rather than continuing
silently — recovery is manual, via rotating that key on the aimlapi.com
dashboard.
* test(aimlapi): move to end-of-line before clearing the email field after Esc
Rebasing onto current main picked up the input layer's DEL-coalescing fix,
which now correctly respects the cursor position for a backspace run instead
of dropping it. These three tests backspaced assuming the cursor sat at the
end of the retained email text, but cursorOffset is a single state shared
across every screen's text field and was last set for the amount screen (its
default "25" is 2 chars) — going back via Esc never resets it, so the cursor
was actually stuck mid-string. Sending an explicit end-of-line sequence
before the backspaces makes the clear correct regardless of where the stale
cursor was left.
* fix(aimlapi): close six checkout/onboarding gaps from the latest review pass
Treats a malformed-but-2xx key-mint response as ambiguous (not proof of
failure) so an unusable receipt no longer releases the mint lease and risks
an orphaned credential; fences startAimlapiTopup's cancellation to an
epoch created before the state-lock await so Esc/unmount during that wait
can no longer barge back in; makes the checkout-receipt read fail closed on
a permission/IO/parse/schema failure instead of silently claiming over it;
completes (or reconciles) a settled by-key receipt instead of stranding it
at the post-payment model picker; retires a sign-in mint lease together
with its cache entry so it can't resurface as held once the cache is later
cleared; and adds a --code-stdin path plus a deprecation warning so the
passwordless code no longer has to travel through shell history or argv.
* fix(aimlapi): reconcile env-credential receipts and stop endorsing AIMLAPI_CODE as safe
reconcileSettledAimlapiTopupStateAsync matched a stale settled receipt by
its stored apiKey, but an env-sourced credential's receipt never persists
one, so that path stayed permanently stranded; it now matches on the
absence of a stored key when the caller is reusing an env credential.
Also stops recommending AIMLAPI_CODE as an equivalently safe alternative
to the deprecated --code flag, since typing it inline still lands in
shell history, and adds a lock-release assertion to the fail-closed
receipt-read tests.
* fix(aimlapi): await stale-receipt reconciliation and stop overclaiming --code-stdin's history safety
Reconciling a stale settled receipt matches by the by-key credential's
apiKey, which a genuinely new top-up for that same credential can also
produce — firing the reconcile call without waiting for it left a window
where a fresh settlement landing in that gap could be swept up by it.
Await it before moving on so the two can no longer interleave.
Also narrows the --code-stdin messaging: it only guarantees the code stays
out of this process's argv/`ps` output, not shell history in general,
since that still depends on how the caller feeds stdin.
* fix(aimlapi): keep the configured screen locked until reconciliation finishes
Clearing isAimlapiKeyValidating before the reconcile await let the
aimlapi-configured screen's Select (and its Esc binding) become
interactive while that reconcile was still running in the background —
it carries no abort signal of its own, so aborting the surrounding
controller only stops this flow from acting on the result, not the
reconcile itself. That left a window where the user could start a
competing top-up for the same credential and have its fresh settlement
caught by the still-in-flight reconcile. Both now stay gated on
isAimlapiKeyValidating through the whole wait.
* fix(aimlapi): fail closed on the sign-in cache, bind env receipts by identity, and commit minted keys
Makes the sign-in key cache and its mint lease match the checkout
receipt's fail-closed contract: only ENOENT means no record, so a
permission/IO/parse failure can no longer be mistaken for "nothing
cached, no lease held" and authorize a second createKey call or a
concurrent lease acquisition.
Reworks reconcileSettledAimlapiTopupStateAsync to match on the by-key
checkout intent's non-secret key fingerprint (already carried in the
persisted email field) instead of the raw stored apiKey or its mere
absence — an env-backed receipt never stores its key, so absence alone
couldn't tell two different env credentials' receipts apart, letting one
credential's balance check discard another's still-unrecovered payment.
Treats persisting a freshly minted existing-account key as a commit
point in the CLI's mint-with-lease path: a write failure now stops the
flow with a recovery-oriented error and leaves the lease held, instead
of continuing with the key only in memory where an interruption before
the later checkout/profile save would orphan it once the lease goes
stale.
Adds a shared isValidAimlapiSignInCode check so both the CLI and the
interactive flow reject a malformed passwordless code (empty,
non-numeric, wrong length) before it ever reaches verifySignInCode.
* fix(aimlapi): reject an array-shaped sign-in cache/lease file instead of degrading to empty
typeof [] === 'object' and [] !== null, so readJsonObjectFile's shape
check let a JSON array through as if it were a valid store. Both readers
then found no matching entries and returned {}, exactly the "no cached
key, no live lease" outcome the fail-closed contract exists to prevent —
authorizing a second createKey call or a lease acquisition over a
possibly-live one.
* fix(aimlapi): commit the sign-in key as a checkpoint and retire a completed mint's lease
mintOrAdoptSignInKey swallowed a failed cache commit and returned the
minted key only in memory — the same non-idempotent-mutation gap already
closed for the CLI's mintExistingAccountKeyWithLease. A commit failure
now stops the flow with a recovery-oriented error and leaves the lease
held, instead of risking the key becoming unrecoverable once the lease
ages out and a retry mints a second one.
Also retires the checkout key-mint lease in the same save that elects a
freshly minted key, mirroring how the exchange lease is already cleared
on settle. Without it, backing out of an unpaid checkout and confirming
a different amount right away still hit the "minting or exchanging"
refusal for the full 75s stale window even though the mint had already
completed.
* fix(aimlapi): make key-mint lease retirement owner-checked, preserve error causes
Retiring the checkout key-mint lease on a successful mint (the previous
commit's fix) cleared it unconditionally, with no check that the save
still belonged to the owner that acquired it. createKey has no refresh
mechanism, so a slow response can let the lease go stale and be
reclaimed by a peer before the original owner's save lands — clearing
the lease then would drop that peer's still-live one and let a
differently-amounted claim proceed as though minting were done while
the peer's mint was still genuinely in flight.
Replaces the raw saveAimlapiTopupState call in
mintExistingAccountKeyWithLease with a dedicated
recordAimlapiMintedKeyAsync that takes the acquiring owner and only
retires the lease while it's still theirs — mirroring how
recordAimlapiSettledKeyAsync already handles the exchange lease.
Also adds `cause` to the three recovery-oriented errors thrown on a
receipt-write failure, so the underlying persistence error stays
diagnosable instead of being replaced by the wrapper message alone.
* test(aimlapi): assert a stale owner's minted key is still persisted
The reclaimed-peer-lease regression test only pinned the lease
bookkeeping, so a variant regression that skipped the write entirely for
a non-owning caller (e.g. an early return on lease-owner mismatch) would
still pass while silently discarding a real, non-idempotently minted
key. Asserts the receipt retains it regardless of who currently holds
the lease.
* fix(aimlapi): persist and charge the endpoint a manually-entered key was actually validated against
persistExistingAimlapi's no-existing-profile fallback saved the profile
with resolveEndpoints().inferenceBaseUrl (the current ambient endpoint)
instead of aimlapiInferenceBaseUrl (the endpoint this flow actually
validated the key and will charge against). The two diverge for a
manually-entered key: after "Set up a new key or switch account" resets
aimlapiInferenceBaseUrl to the ambient default, draft.baseUrl (what
validateAndPersistAimlapiKey actually calls the balance/top-up endpoints
with) keeps the OLD profile's endpoint if it differs (e.g. a canonical
saved profile while AIMLAPI_INFERENCE_URL currently points at a proxy).
Now captures the validated endpoint into aimlapiInferenceBaseUrl as soon
as the low-balance branch is reached, and the fallback save uses that
state instead of re-resolving the ambient endpoint — so the top-up
charge and the persisted profile both follow the endpoint that was
actually validated.
* fix(aimlapi): reject stale key-mint results, make the exchange checkpoint mandatory, validate lease pairs
recordAimlapiMintedKeyAsync previously let a stale owner's delayed
createKey result land beside a peer's reclaimed, still-live lease: since
no key was recorded yet, first-writer-wins accepted the stale result
outright, so the reclaiming peer's own (equally real, non-idempotent)
mint got silently discarded once its own save landed — turning one lost
credential into two. It now rejects a result whose ownership was already
lost when nothing is recorded yet to adopt instead, surfacing a
recovery-oriented error naming the issued key id rather than risking a
second orphan. The caller now also returns whichever credential is
actually durably recorded, not always its own.
exchangeKeyWithLease's own settled-receipt commit — the only durable
record of a one-shot /exchange result until the caller's later,
separate save runs — was only logged on failure. A crash in that
window left the paid session exchanged with its key absent from local
recovery state, so a retry could only report the session was already
exchanged with no way to recover automatically. The commit is now a
required checkpoint: its failure stops the flow with the existing
recovery guidance and leaves the exchange lease held, exactly as the
analogous key-mint checkpoint already does.
The receipt schema validated the exchange lease pair but not the newer
key-mint one, and even the exchange check only verified each field in
isolation — a one-sided pair (an owner with no timestamp, or vice versa)
passed either way. A shared validator now enforces both lease pairs are
either fully present or fully absent, so a malformed or partial lease
can no longer be silently accepted as "not currently live" and let a
claim replace it out from under an in-flight mint or exchange.
* fix(aimlapi): fail the exchange when the settled-receipt commit no-ops, not just when it throws
recordAimlapiSettledKeyAsync silently returned without writing whenever the
CAS no longer matched (checkout cleared/reset mid-flight) or no credential
could be resolved to settle with. exchangeKeyWithLease only caught thrown
errors, so both no-op paths let a successfully exchanged key return with no
durable local receipt. The function now returns a boolean, and the caller
treats false exactly like a thrown save error.
Also fixes recordAimlapiMintedKeyAsync returning the raw untrimmed apiKeyId
instead of the trimmed value it actually persisted.
---------
Co-authored-by: Lookoff123 <bataryshkinairina@gmail.com>
|
||
|
JATMNandGitHub
|
7cae4089d6 |
feat(xai): add Grok 4.6/4.5 to catalog, xAI provider, and gateways (#2117)
* feat(xai): add Grok 4.6/4.5 and hybrid catalog discovery xAI's current flagship is Grok 4.6; keep shared capability flags so gateways can reference the new models, and let /v1/models surface later Grok IDs without another catalog bump. * fix(xai): authenticate hybrid discovery for OAuth and keep gateway aliases aligned OAuth xAI sessions had no /v1/models credential, so hybrid refresh failed; also drop curated alias IDs from discovery and map grok-build-latest on Atlas/Hicap to Grok 4.5. * fix(xai): align OAuth hybrid discovery cache with runtime metadata OAuth-only xAI sessions hashed the access token into discovery writes, but runtime limit lookups only used env credentials, so uncataloged Grok IDs fell back to default windows. Mirror stored OAuth on cache reads and isolate discovery tests from the shared config home. * fix(xai): keep Grok 4.6 PR on catalog and hybrid discovery Move OAuth /v1/models auth and cache-key alignment out of this branch so the catalog, xAI hybrid vendor, and gateway references stay reviewable on their own. * fix(xai): read discovered model context length * fix(xai): preserve OAuth discovery metadata * fix(xai): tolerate malformed discovery models * fix(discovery): harden credential cache partitions * fix(xai): unify discovery OAuth cache handling * fix(xai): preserve OAuth discovery cache identity * fix(discovery): use native cache namespace hashing * fix(xai): keep OAuth discovery nonblocking * fix(discovery): use opaque cache fingerprints |
||
 OpenClaude
|
6277bfadbc | fix: Ling 3.0 Tiny :free window back to Aug 13 (official promo end) | ||
|
OpenClaude
|
ee64d80c2e | fix: extend Ling 3.0 Tiny :free availability window to Aug 17 | ||
|
|
7b03ad19a4 |
feat(opengateway): add Ling 3.0 Tiny :free — Day-0 launch, free until August 13 (#2112)
* feat(opengateway): add Ling 3.0 Tiny :free — Day-0 launch, free until Aug 13 inclusionai/ling-3.0-tiny:free (7.9B MoE, ~1.3B active, 262k ctx) joins the picker via the gateway's OpenRouter wiring. The gateway time-boxes it (free through Aug 13, rate limited) and delists it server-side when the window closes. * test(opengateway): Ling Tiny gateway mapping test + explicit window note Addresses CodeRabbit review on #2112: - new ling-tiny.test.ts (macaron.test.ts pattern) asserting the opengateway-ling-3.0-tiny-free entry maps both apiName and modelDescriptorId to inclusionai/ling-3.0-tiny:free, plus descriptor capabilities and runtime limits - catalog note now dated explicitly ('Free through August 13, 2026') and the entry's lifecycle documented: the gateway time-boxes the id server-side and 400s after the window; this static catalog has no expiry mechanism (Ling Flash precedent), so the entry is removed or updated at window close * feat(integrations): availableUntil catalog-entry expiry + Tiny lifecycle guard Addresses CodeRabbit round 2 on #2112: - new optional ModelCatalogEntry.availableUntil (ISO-8601): entries past the cutoff are dropped in getCatalogEntriesForRoute, the single choke point behind the model picker, gateway catalogs, and runtime limits; the pre-existing (previously unenforced) hidden flag is honored in the same filter; unparseable dates fail open - the Ling Tiny entry sets availableUntil to the gateway's window end (2026-08-13T10:00:00Z), so the picker drops it the instant the gateway starts rejecting the id — no client release needed - boundary regression test on both sides of the cutoff, and the picker expected-list test pins the clock inside the window (setSystemTime) so it stays deterministic after the date passes - ling-tiny.test.ts now also asserts supportsPreciseTokenCount: false * test(integrations): exact-cutoff + hidden + malformed-date coverage; fix stale lifecycle comment Addresses CodeRabbit round 3 on #2112: - ling-tiny.test.ts asserts the boundary at exactly 2026-08-13T10:00:00Z (cutoff is exclusive: entry already gone at that instant) - registry.test.ts covers the two previously-untested filter branches: hidden entries dropped, availableUntil expiry (before / at / after cutoff), and a malformed availableUntil failing open - the catalog comment above the Ling Tiny entry no longer claims the static catalog has no expiry mechanism — availableUntil is the guard Validation commands run locally: bun run integrations:generate bun test src/integrations src/commands/model/model.test.tsx src/utils/model bunx tsc --noEmit 558 tests pass, typecheck clean. * fix(model): route static picker entries through the availability filter Addresses jatmn's P1 on #2112: model.tsx read catalog.models directly, bypassing the availableUntil/hidden filter that only lived in getCatalogEntriesForRoute — so after 2026-08-13T10:00Z the /model picker would still offer inclusionai/ling-3.0-tiny:free and selecting it would persist an id the gateway 400s. - registry.ts exports filterAvailableCatalogEntries (shared with getCatalogEntriesForRoute) - model.tsx filters the static entries AND the static+discovery merged list, so discovery-sourced entries with their own markers are covered - routeMetadata.ts getRouteDefaultModel's catalog fallback filters too, so an expired entry can never become the implicit default - new picker regression test pinned just past the cutoff asserts the expired entry is gone while the rest of the catalog is untouched Validation: bun run integrations:generate; bun test src/integrations src/commands/model/model.test.tsx src/utils/model (559 pass); bunx tsc --noEmit (clean). * fix(model): merge raw static entries so expired ones mask cached duplicates Addresses CodeRabbit round 4 on #2112: filtering static entries before mergeRouteCatalogEntries let a cached discovery entry with the same apiName (and no availableUntil marker) re-enter the merged list, where the post-merge filter could not remove it. The merge now takes the RAW static list — the expired static entry wins the apiName dedup and the post-merge filter then drops it, so neither copy survives. The filtered list still drives the non-discovery path. Regression tests in routeCatalogOptions.test.ts cover the cached duplicate after the cutoff (including documenting the buggy pre-filter order) and the masking inside the window. Validation: bun run integrations:generate; bun test src/integrations src/commands/model/model.test.tsx src/utils/model (561 pass); bunx tsc --noEmit (clean). * test(integrations): default-model fallback skips hidden and expired entries Addresses CodeRabbit round 5 on #2112: getRouteDefaultModel's catalog fallback changed in the availability-filter fix but had no focused coverage. New routeMetadata.test.ts case (self-contained registry mutation with the shared lock, mirroring registry.test.ts) verifies a hidden default-marked entry and a past-cutoff availableUntil entry are both skipped in favor of the remaining valid entry, and that a catalog with nothing valid yields undefined rather than a rejected id. Validation: bun test ./src/integrations/routeMetadata.test.ts (63 pass); bun run integrations:generate; bun test src/integrations src/commands/model/model.test.tsx src/utils/model (562 pass); bunx tsc --noEmit (clean). * test(integrations): release shared mutation lock even if registry restore throws Addresses CodeRabbit round 6 on #2112: the fallback test's finally block ran _clearRegistryForTesting/ensureIntegrationsLoaded before releaseSharedMutationLock, so a throw there would leave the lock held and block later tests. Nested try/finally, matching registry.test.ts's afterEach shape. Validation: bun test ./src/integrations/routeMetadata.test.ts (63 pass); full related suites 562 pass; tsc clean. --------- Co-authored-by: OpenClaude <openclaude@gitlawb.com> |
||
|
BogdanandGitHub
|
16e332e108 |
fix(query): use monotonic watchdog deadlines (#2110)
Wall-clock corrections can otherwise manufacture an immediate timeout or postpone an already-scheduled one. Keep lifecycle timestamps in wall time while measuring deadline state and elapsed duration from a monotonic clock.\n\nRefs #1830 |
||
|
JATMNandGitHub
|
ff91642364 |
feat(integrations): add ApiSmart OpenAI-compatible gateway provider (#2109)
* feat(integrations): add ApiSmart OpenAI-compatible gateway provider
Add a hybrid-catalog ApiSmart gateway with dedicated APISMART_API_KEY/APISMART_MODEL
env wiring, route detection, profile persistence, and regression tests so the
provider works via --provider, env-only setup, and saved profiles.
* fix(apismart): protect dedicated credentials
* fix(apismart): enforce route credential boundaries
* fix(apismart): honor explicit competing route models
* fix(apismart): validate credentials and default profiles
* test(apismart): isolate env-only client tests
* fix(apismart): align routing and validation contracts
* fix(apismart): centralize route capability contracts
* Revert "fix(apismart): centralize route capability contracts"
This reverts commit
|
||
|
|
54b9cd8389 |
feat(opengateway): free retirement — paid Ling id, dual Nemotron, Macaron Venti (#2108)
The gateway retired its free models on 2026-08-10, keeping Nemotron 3 Ultra :free as the one free model (rate-limited by OpenRouter's shared pool) and adding its paid throttle-free sibling as a separate entry. Ling 3.0 Flash moves to its paid id (the :free id is aliased server-side for older clients), Macaron V1 Tall is now paid, and Macaron V1 Venti (748B MoL on GLM-5.2, 1M ctx) joins the catalog. The ling entry id keeps its historical -free suffix so saved selections resolve; HY3's stale Free label removed. Co-authored-by: OpenClaude <openclaude@gitlawb.com> |
||
|
JATMNandGitHub
|
93dbc72cbd |
refactor(openai-shim): extract Codex dispatch (#2074)
* refactor(openai-shim): extract Codex dispatch * test(openai-shim): cover Codex dispatch guards |
||
|
JATMNandGitHub
|
7fae0ffee0 |
refactor(openai-shim): extract request preparation (#2073)
* refactor(openai-shim): extract request preparation * test(openai-shim): move request preparation regressions * fix(openai-shim): rebase request preparation extraction * test(openai-shim): assert converted preparation tools |
||
|
95409464f3 |
feat(codex): move codexplan default to GPT-5.6 Sol (#2051)
* feat(codex): default codexplan to GPT-5.6 Sol
Preserve existing reasoning and routing behavior while updating the default model, labels, documentation, and focused coverage.
* test(codex): lock fallback and routing behavior
* make credential-step test self-contained
* fix(codex): default unset teammate fallback to GPT-5.6 Sol
The changes to the inert codex config keys are known to have no functional effect, but we updated them to ensure the defaults are correct and consistent across the table.
* fix codexplan gateway defaults after model resolution
* Revert "fix codexplan gateway defaults after model resolution"
This reverts commit
|
||
|
0xfandomandGitHub
|
eb1de5b576 |
fix(bash): convert BRE interval braces when previewing sed edits (#1955)
* fix(bash): convert BRE interval braces when previewing sed edits
convertBrePatternToJs rewrites a POSIX BRE sed pattern into a JS regex so the
permission dialog can preview what a 'sed -i s/.../.../' edit will do. It
unescapes the BRE metacharacters that flip escaping between BRE and JS, but the
membership sets listed only +?|() and omitted { }. In BRE '\{n,m\}' is the
interval quantifier and a bare '{' is literal — the reverse of JS — so both
were handled backwards: '\{2\}' was emitted as a JS literal (matched nothing)
and a bare '{2}' became a JS quantifier.
The result is a misleading diff at an approval gate: 'sed -i s/a\{2\}/X/'
previews as no change while the command the user approves rewrites the file.
Add { } to both sets. Add coverage for escaped intervals, escaped ranges, and
bare-brace literals.
* fix(bash): only unescape sed interval braces when they form a valid count
\{,m\}, \{\} and \{n,m,k\} are literal brace runs in sed, not interval
quantifiers. Emitting them as JS braces produced a bogus quantifier (or a
literal that matched nothing), so the sed-edit preview showed no change while
real sed rewrote the file. Detect the enclosed count and only convert legal
BRE intervals (n, n,, n,m, and the GNU ,m extension, normalized to {0,m});
otherwise keep the braces escaped as literals. Extract the shared metachar set
and cover ? | ( ) and the ERE brace path.
* fix(bash): decline to simulate sed edits that cannot be reproduced faithfully
The preview is what the user approves, so it must either match what sed writes
or not be rendered at all. Three cases could not match:
- Zero-minimum quantifiers under g. sed and JS advance differently past an empty
match: s/a\{0,3\}/X/g turns aaaab into XXbX in sed but XXXbX in JS, and the
same holds for the pre-existing s/a*/X/g (XbX vs XXbX).
- Bracket expressions. \{ and \} are ordinary members inside [...], not an
interval, and a backslash is a literal member in POSIX brackets but an escape
in a JS character class, so [\{,3\}] cannot be mapped across.
- Illegal interval bodies. sed rejects \{\} and \{1,2,3\} outright (Invalid
content of \{\}) and leaves the file untouched, so they are not literal braces
and there is no edit to show.
parseSedEditCommand now returns null for these, falling back to ordinary bash
rendering. The same gate catches patterns whose translation is not a valid JS
regex, which previously threw and was swallowed into a silent no-change diff.
Verified differentially against GNU sed 4.10: of 22 expressions, the 15 still
simulated match sed byte-for-byte and the 7 divergent ones now decline.
* fix(bash): restrict the sed preview to portable, per-line-faithful patterns
Tighten the faithful-simulation gate on every axis where the preview could
disagree with what sed writes on the user's platform:
- Apply the substitution once per line, as sed does: without g, sed replaces
the first match on EVERY line, so a whole-buffer replace previewed
s/a\{2\}/X/ on 'aa\naa\n' as 'X\naa\n' where sed writes 'X\nX\n'. This also
makes ^ and $ anchor per line, matching sed.
- Decline GNU-only operators: \+ \? \| and the \{,m\} interval are extensions
that BSD/macOS sed treats as literals (or rejects outright), and this parser
explicitly supports macOS through its -i '' handling — one platform's
operator is the other's literal, so no single preview can be right for both.
Alternation is additionally unfaithful even on GNU: POSIX selects the
leftmost-longest branch where JavaScript takes the first that matches.
- Decline unterminated bracket expressions (an error in sed, not a literal)
and POSIX [:class:]/[=equiv=]/[.collate.] constructs, which JavaScript would
silently read as plain character sets. ERE patterns, which previously carried
over verbatim, are screened for the same constructs.
Verified differentially against GNU sed 4.10 and macOS BSD sed across 27
expressions including multi-line inputs: every still-simulated pattern matches
both implementations byte-for-byte, and every declined pattern demonstrably
differs between platforms, differs from JavaScript, or errors in sed.
* fix(bash): keep empty files empty in the per-line sed simulation
An empty file has no lines, so sed never runs the substitution and the
output stays empty. Splitting '' fabricated one empty line, letting
anchored patterns like s/^/X/ preview an edit the real command does not
make. Return early before splitting; verified against GNU sed 4.10 and
BSD/macOS sed (both leave the file at 0 bytes).
* fix(bash): only simulate the sed subset that translates faithfully
The preview replaces the command once approved, so every accepted pattern
must produce exactly what sed writes. Move from screening known-bad
constructs to admitting only ones with matching semantics:
- flags: accept g/i/I only. 1-9 select the Nth match per line (the
simulator always rewrites the first, so s/a\{2\}/X/2 on "aaaa" previewed
"Xaa" where sed writes "aaX"); p prints; m/M redefine ^ and $.
- replacements: require literal text. \1-\9, &, \n and \U are sed syntax the
simulator passes through verbatim, so s/\(a\)\{2\}/\1/ wrote the literal
characters \1 where sed writes a.
- escapes: allow only the portable set. \< and \> are word boundaries in GNU
sed but literal angle brackets in JS; \d is the converse.
- anchors: bare ^ and $ only anchor at a BRE boundary, so s/a^b/X/ previewed
no change while sed rewrote the literal text.
- ERE intervals: validate the body there too — JS reads a{,3} as literal
braces while GNU sed -E rewrites "aaaab" to "XXbX".
- character semantics: compile with u, so a quantifier counts characters as
sed does rather than UTF-16 code units.
- CRLF: compile with s, so . matches the carriage return the pattern space
holds.
- an empty pattern declines: sed has no previous regexp to reuse and errors.
Verified against GNU sed 4.10 and BSD/macOS sed: all 12 accepted expressions
match both byte-for-byte.
* fix(bash): decline bracket expressions opening with a ] member
POSIX treats the first ] in [] ] / [^] ] as an ordinary member, so GNU sed
rewrites "a]b" to "aXb". JavaScript reads it as the class terminator and
matches nothing, so the preview showed no change while sed rewrote the file.
findBracketEnd already skipped the leading ] to locate the real terminator,
but the body was then carried into the JS regex verbatim.
Decline on both the BRE and ERE paths.
* fix(bash): close three sed preview divergences before approval
All three let an approved preview differ from what the command writes,
which is the failure this simulator exists to avoid -- the preview is
persisted directly once the user approves it.
Dollar tokens: $ is an ordinary character in a sed replacement but a
substitution token to String.replace, so s/\(a\)/$1/ previewed the matched
text where sed writes the two characters $1. Double each $ for the JS
replacement.
ERE escapes: the ERE screen skipped every backslash escape and then used
the source verbatim, so -E 's/\d/X/g' on "1d2" previewed "XdX" while sed
writes "1X2" -- GNU sed reads \d as a literal d. \w, \s and \u{...} diverge
the same way. Admit only the escapes that are the same literal in both
dialects, mirroring the BRE allowlist.
Case-insensitive matching: the emitted regex needs u for the quantifier
fix, and u + i selects ECMAScript Unicode case folding rather than sed's
locale matching, so s/k/X/I rewrote a Kelvin sign that GNU sed under
C.UTF-8 leaves alone. Decline i/I until that can be modeled.
Verified the accepted set against GNU sed 4.10: 11 expressions, including
each dollar case above, byte-identical.
* fix(bash): gate the sed preview on locale and bound its matching
Three follow-ups to the preview-fidelity work.
The emitted regex always carries the u flag so a quantifier counts
characters, but sed inherits the process locale and counts bytes in a byte
locale: LC_ALL=C 's/.\{2\}/X/' on an emoji consumes two of its bytes and
leaves the rest in the file. Claim a sed edit only when the resolved locale
(LC_ALL, then LC_CTYPE, then LANG, per POSIX) names a UTF-8 codeset.
Interval support also made nested quantifiers translatable:
\(a\{1,\}\)\{1,\}b becomes (a{1,}){1,}b, which backtracks
exponentially on a run of a's with no b. applySedSubstitution runs
synchronously while the permission request renders, so that stalls the
approval UI before the user can decide. Decline a quantified group that
already contains a quantifier.
The replacement gate rejected every backslash, including \/ and \&, which
the translation right below already handles faithfully -- so ordinary
commands like s/foo/path\/to/ lost their file diff for no reason. Admit
those two, keep declining backreferences, case folding and a bare &.
Verified against GNU sed 4.10: the newly readmitted escapes and the
still-accepted single-quantifier groups all match byte-for-byte.
* fix(bash): decline a repeated s/// g flag the way sed does
GNU sed rejects a duplicated flag ("multiple `g' options to `s' command"),
so tighten the accepted-flags pattern from /^g*$/ to /^g?$/. A preview that
rendered `s/a/X/gg` as a successful global rewrite would diverge from the
command sed refuses to run.
* test(bash): scope the sed preview test to the CRLF-normalized gate
The permission path normalizes CRLF to LF before calling applySedSubstitution,
so the approved preview never sees a raw carriage return. Replace the
raw-\r\n assertion (which claimed a fidelity the gate does not exercise) with
one over LF content, and document that raw-CR bytes are out of scope.
* fix(bash): decline ERE (?...) groups sed does not implement
ereHasUnfaithfulConstructs screened escapes, alternation, anchors, intervals
and bracket bodies but treated grouping as implicitly safe. POSIX/GNU sed -E
only supports plain capturing (...); a (? opens JavaScript-only syntax --
(?:), lookaround, named groups -- that new RegExp compiles but GNU sed rejects.
The preview would render a concrete edit for a command sed refuses to run, so
decline as soon as an unescaped ( is followed by ?.
|
||
|
0xfandomandGitHub
|
41d2f3b831 |
fix(repomap): resolve file language by real extension, own-property only (#2100)
getLanguageForFile computed the extension as substring(lastIndexOf('.')). For a
path with no dot, lastIndexOf returns -1 and substring(-1) clamps to
substring(0), so the whole filename became the lookup key against the plain
SUPPORTED_EXTENSIONS object. That misclassifies extensionless files, and a root
file named after an Object.prototype member (constructor, __proto__, toString,
…) resolves to an inherited value that the ?? null guard accepts as a supported
language -- so isSupportedFile returns true and the file enters the repo-map
graph with a bogus language. Return null when there is no dot and gate the
lookup on Object.hasOwn.
|
||
|
JATMNandGitHub
|
deb91941e1 |
refactor(openai-shim): extract response adapters (#2072)
* refactor(openai-shim): extract response adapters * test(openai-shim): cover response adapter stream wrappers Add focused regression tests for geminiSseToAnthropic and openaiStreamToAnthropic through the responseAdapters facade wiring. Validated with: bun test src/services/api/openaiShim/responseAdapters.test.ts * test(openai-shim): assert Gemini tool-use stream blocks in adapter test Extend the responseAdapters geminiSseToAnthropic wrapper test to cover tool_use content_block_start, input_json_delta, and content_block_stop. Remove stale post-extraction imports from the openaiShim facade. * test(openai-shim): cover facade parser re-exports Add a focused openaiShim.test.ts case that imports parseTextToolCalls and parseXmlToolCalls through the public facade and asserts shared sequencing. |
||
|
0xfandomandGitHub
|
c327805e1d |
fix(cost): guard model-cost lookup against prototype-member model ids (#2064)
* fix(cost): guard model-cost lookup against prototype-member ids MODEL_COSTS is a plain object, so `MODEL_COSTS[shortName]` inherits Object.prototype members. A model id of `constructor` or `__proto__` -- both valid arbitrary ids for custom/OpenAI-compatible providers, and already lowercase so getCanonicalName returns them unchanged -- resolved to a truthy prototype value (the Object constructor / Object.prototype), so the `!costs` unknown-model guard was skipped: trackUnknownModelCost never fired and tokensToUSDCost read undefined rate fields, producing a NaN cost that permanently poisons the running session total (total + NaN stays NaN) and surfaces as "$NaN". getModelPricingString had the same defect and rendered "$NaN/$NaN per Mtok". Match on own properties via Object.hasOwn, mirroring resolveOutputStyle in constants/outputStyles.ts. Add a regression test asserting proto-name ids take the unknown-model path and yield a finite, positive cost. * fix(cost): guard per-model usage tracking against prototype-member ids getModelCosts was hardened, but the sibling per-model accounting kept the same latent hole. STATE.modelUsage is a plain object, so a model id of `constructor` / `__proto__` (arbitrary for custom/OpenAI-compatible providers) reaches both getUsageForModel's read and the `STATE.modelUsage[model] = ...` write. On the read, an absent proto-name key resolves to an inherited Object.prototype member; addToTotalModelUsage then does `modelUsage.inputTokens += ...` on that inherited object, and for `__proto__` that lands on Object.prototype itself -- process-wide pollution (every object gains inputTokens = NaN, etc.). On the write, bracket-setting `__proto__` invokes the prototype setter. Back modelUsage with a null-prototype map (emptyModelUsage) at init, reset, and restore, so both operations act on ordinary own keys, and read through Object.hasOwn to match the getModelCosts guard. Restore re-keys a persisted breakdown (which can carry an own `__proto__` from JSON) into the null-proto map. Regression test asserts no Object.prototype pollution and correct own-key round-trip for proto-name ids. * test(cost): tighten the proto-name model-cost regression Assert Number.isFinite(cost) (rejects Infinity too, not just NaN) and that the unknown-model detection flag fires, so a regression that dropped trackUnknownModelCost while keeping the fallback tier would fail. Reset the process-wide cost state afterward to avoid leaking into other suites, and correct the comment: getModelPricingString has no production callers and pre-fix threw a TypeError rather than rendering "$NaN/$NaN per Mtok". * fix(cost): guard the /cost per-model aggregation against prototype-member ids formatModelUsage accumulates per-model usage into a plain object keyed by canonical short name. An unrecognised custom-provider id that canonicalizes to `__proto__` / `constructor` (unchanged, since it matches no Claude pattern) made the `!usageByShortName[shortName]` check read an inherited Object.prototype member, skip initialization, and increment it in place -- for `__proto__` that mutation lands on Object.prototype process-wide, and the model is dropped from the displayed /cost breakdown. Use a null-prototype accumulator and an Object.hasOwn guard, matching the getModelCosts / getUsageForModel fixes. Regression drives the real addToTotalSessionCost -> formatTotalCost path for `__proto__` and `constructor` ids, asserting no prototype pollution and that both appear in the breakdown. * test(cost): tidy the /cost proto-pollution regression harness Load addToTotalSessionCost via a lazy ESM import instead of require (drops the eslint suppression) and snapshot the guarded Object.prototype descriptors so cleanup restores pre-existing state instead of unconditionally deleting keys a sibling module might legitimately own. |
||
|
BogdanandGitHub
|
d834904e5a |
fix(session): make transcript replacements crash-safe (#2094)
* fix(session): make transcript replacements crash-safe Complete transcript rewrites could truncate live JSONL files before preserved data was durable, risking unrecoverable resume history after an interrupted write. Commit replacements through exclusive sibling temp files and serialize them with all transcript append paths so readers observe either the old file or the complete replacement. * fix(session): preserve concurrent transcript updates Abort tombstone commits when the scanned transcript changes before replacement, and keep existing local history when remote foreground hydration returns no entries. Harden the associated portability, option coverage, queue timing, and diagnostics. * test(session): match hydration reader signature Pass the explicit optional subagent reader in the empty-hydration regression so a fresh TypeScript build sees the complete helper signature. * fix(session): coordinate transcript writers across processes Hold a same-directory cooperative lock across transcript replacement and final-line truncation, and make session plus SDK append paths participate. Exercise the post-validation/pre-rename race deterministically so external appends land after the complete commit. * test(session): provide empty hydration subagent reader * fix(session): scope transcript lock ownership Separate async and synchronous lock ownership so unrelated sync appends cannot bypass an in-flight replacement. Route aliased in-process appends through the queue, propagate lock compromise through AbortSignal, and cover both symlink-alias and rename-boundary races. |
||
|
BogdanandGitHub
|
6465a516f2 |
fix(mcp): serialize OAuth and XAA refresh across processes (#2093)
* fix(mcp): serialize OAuth and XAA refresh across processes Normal OAuth refresh, reactive 401 recovery, and silent XAA exchange can otherwise race shared secure-storage writes between processes. Coordinate them on one server-scoped lock and re-read storage so waiters reuse persisted winners. * fix(mcp): harden refresh follow-up paths Use asynchronous cache-bypass reads on request paths while preserving the adjacent final record merge and write. Make the XAA concurrency fixtures independent of module import order and extend abort, redaction, and retry coverage. * fix(mcp): honor aborts after credential reads Check the active cancellation signal after asynchronous secure-storage reads so fresh-token fast paths cannot return credentials to an aborted request. Cover cancellation while a cache-bypassing read is pending. |
||
|
JATMNandGitHub
|
bac012f70b |
refactor(openai-shim): extract transport lifecycle (#2071)
* refactor(openai-shim): extract transport lifecycle * refactor(openai-shim): rebase transport extraction and address review Rebase onto current main and clean up the transport extraction follow-ups: drop stale facade imports left after the move and restore the full API timeout parser negative-case coverage in transport.test.ts. * test(openai-shim): address CodeRabbit review findings Use path.join in the architecture guard, require transport.ts in the mandatory extraction slice, strengthen Gemini stream conversion coverage, and add transport deadline/cancellation regression tests with fake timers. * test(openai-shim): assert manual signal cleanup after body cancel Exercise the combineRequestSignals fallback without AbortSignal.any so early body cancellation removes caller listeners and a later caller.abort does not abort the combined fetch signal. * test(openai-shim): restore AbortSignal.any when initially absent Delete the temporary AbortSignal.any override when the runtime did not define an own property, so transport and facade signal-cleanup tests leave global AbortSignal state unchanged for later cases. |
||
|
BogdanandGitHub
|
1bf8076d48 |
fix(input): preserve text in DEL-coalesced chunks (#2091)
* fix(input): preserve text in DEL-coalesced chunks Some terminal transports deliver replacement input as raw DEL bytes and printable text in one read. The raw-DEL workaround previously applied only the deletions and returned, dropping the replacement text and leaving same-event cursor and mode state stale. Process filtered chunks in source order through the existing cursor semantics, preserve coalesced submission and Vim state, and cover grapheme, token, filter, mode, and batching cases. * test(input): harden DEL regression coverage * test(input): clean up harnesses after timeouts * fix(input): preserve coalesced consumer state * fix(input): synchronize coalesced mode state |
||
|
மனோஜ்குமார் பழனிச்சாமிandGitHub
|
95eeb0bde3 |
feat(cli): add --yolo alias for --dangerously-skip-permissions (#2097)
Register the alias on the main command and the ssh stub. Recognize it in the cc:// and ssh raw-argv scans, and in both skills pre-parse boolean sets (leading and trailing), so and route correctly. Update the web flags docs. Includes source-scan + help-text tests proving the alias is wired through. The SSH/argv refactor remains on the existing feat/yolo-flag branch for a separate follow-up PR. |
||
|
JATMNandGitHub
|
b0cbfe1100 |
fix(repl): make local interactive max-turns configurable (#2086)
* fix(repl): make interactive max-turns configurable Wire --max-turns into interactive sessionConfig and honor OPENCLAUDE_MAX_TURNS / CLAUDE_CODE_MAX_TURNS so long autonomous REPL sessions can raise the default 50-turn per-prompt cap (fixes #2079). * fix(repl): forward --max-turns on connect/ssh/remote launches sessionConfig covered the normal interactive paths; connect, SSH, assistant, and --remote built REPL props without spreading it, so the CLI override was dropped despite help advertising interactive support. * fix(repl): scope interactive max-turns to local query loops Remote-backed sessions bypass local query(), so forwarding --max-turns into those REPL props over-claimed enforcement. Clarify help/docs and match OPENCLAUDE_MAX_RETRIES precedence when OPENCLAUDE_MAX_TURNS is set but invalid. * feat(config): add interactive max turns under /config Expose replMaxTurns in the Config panel (50/100/200/500) and resolve it after CLI/env so local interactive sessions can raise the per-prompt cap without restarting. Resolve at query time so mid-session /config changes apply on the next prompt. * docs(repl): clarify invalid OPENCLAUDE_MAX_TURNS precedence Match the OPENCLAUDE_MAX_RETRIES contract: a set-but-invalid primary env var uses the default and does not fall through to legacy or /config. * fix(repl): address PR review on max-turns help and web version gate Share the --max-turns Commander description via an imported constant so help and tests stay in sync without breaking the CLI bundle, replace source-only help assertions with Commander behavior coverage, and add the published 0.27.0 entry so web verify-dist passes. * fix(repl): typecheck Commander maxTurns opts and warn on invalid env Avoid TS2339 on untyped Commander opts, log invalid OPENCLAUDE_MAX_TURNS like MAX_RETRIES, and clarify that /config shows the persisted preference. * fix(repl): warn when max turns is unlimited * fix(repl): scope unlimited-turn warning locally * fix(repl): preserve interactive turn caps across backgrounding * fix(repl): preserve turn caps when backgrounding * fix(repl): share turn budget across background handoff * fix(repl): reserve turns at provider dispatch * fix(repl): snapshot background handoff transcript * fix(tasks): avoid phantom background session task * fix(repl): preserve handoff lifecycle state * fix(repl): own pending background handoffs * test(tasks): isolate background session task storage * fix(repl): refresh background task title and test cleanup * test(repl): cover max-turn CLI dispatch paths * test(queue): cover prepend notification and priority * fix(repl): skip background handoff after foreground query throws Rebased onto main and gate Ctrl+B continuation on !didThrow so a faulted foreground turn cannot start a background session from partial state. * fix(repl): address PR review findings on notifications and handoff Dedupe background task notifications by embedded task id, gate background continuation on preflight veto, scope queue removal to main-thread notifications, and forward maxTurns through all launchRepl entry points. * fix(repl): resolve latest CodeRabbit inline review findings Dedupe claimed notification batches by task id, restore notifications on pre-registration abort, tighten test isolation, and replace remaining brittle source-text assertions with behavioral coverage. * fix(repl): keep notification restore active until provider dispatch Stop clearing notification ownership when preparation succeeds so pre-dispatch aborts can restore claimed queue items, and commit ownership once the provider starts. Add regression coverage for the abort path and headless max-turns zero. * test(repl): cover post-dispatch ownership and headless max-turns 0 Add regression tests for notification restore after provider dispatch commits ownership, and assert headless --max-turns 0 reaches query() without interactive resolution stripping the value. * fix(repl): restore only embeddable notifications on Ctrl+B handoff abort Track the deduped successor subset when restoring claimed main-thread task notifications so items already in the settled foreground transcript are not re-queued. Clarify that agent-scoped notifications intentionally stay on their owner drain path (issue #2079 scope is interactive turn caps only). * fix(repl): address review findings on background handoff Commit notification ownership when background sessions complete without provider dispatch, forward all task notifications on Ctrl+B again, and restore deferred max-turn cap attachments when continuation is cancelled. * fix(repl): guard deferred cap restore and skip remote turn limits Anchor deferred max-turn restoration to the handed-off transcript tail so a cancelled Ctrl+B handoff cannot attach the prior prompt's cap to a newer turn. Apply the interactive turn cap only in local sessions and align remote-session docs/help wording. * fix(repl): use messagesRef for deferred cap transcript anchor persistentMessages is block-scoped inside onQuery try; read the settled tail from messagesRef in finally so typecheck passes. * test: harden context fallback warning assertion after max-turns tests Scope the unknown-model context test to [context] warnings only so unrelated import-time debug logs do not fail CI, and clear turn env vars in both that test and replMaxTurnsProp setup to avoid cross-file pollution. * test: address PR review findings on headless max-turns boundary Add a runHeadless-to-ask regression that asserts maxTurns 0 is forwarded through the headless print path, and restore OPENCLAUDE_MAX_TURNS env vars in context.test.ts after the unknown-model fallback test mutates them. * test: tidy headless max-turns boundary test and env isolation Mock headless stdout so runHeadless completes cleanly without leaking output, restore spies in finally, and centralize turn-env cleanup in context.test beforeEach. * fix: address PR review findings for max-turns background handoff Separate model-request lifecycle from provider dispatch acceptance so interruption correction arms before async prep, notification ownership commits only after dispatch, deferred turn caps restore on every abort path, and foreground work stays blocked while handoff preparation runs. |
||
|
0xfandomandGitHub
|
2c42a325d9 |
fix(permissions): anchor the session plan-file match on its exact shape (#1994)
* fix(permissions): anchor the session plan-file match on its exact shape
isSessionPlanFile auto-allows the current session's plan file for both
read (checkReadableInternalPath) and un-prompted write
(checkEditableInternalPath). It matched with a bare
normalizedPath.startsWith(join(plansDir, planSlug)), which also accepts
any sibling whose name merely begins with the slug — {slug}nova.md,
{slug}-other.md, or a newly-created {slug}dir/ subtree. Those are not this
session's plan yet were silently readable and writable without a prompt.
Anchor on the two shapes getPlanFilePath actually emits: {slug}.md exactly,
or a {slug}-agent- prefix for subagent plans. Extract the decision into a
pure isPlanFilePath(plansDir, slug, path) helper so it can be unit-tested
without session state. normalize() still runs first, so traversal segments
can't escape the plans directory.
Same missing-separator class as the path-containment fix in #1974.
* fix(permissions): restrict the agent-plan branch to a single filename
The -agent- prefix check still matched any path beneath a lookalike
sibling directory: {plansDir}/{slug}-agent-evil/anything.md passed
startsWith and ended in .md, so both permission carve-outs granted
unprompted read and write to arbitrary files below it. The malformed
{slug}-agent-.md, which getPlanFilePath never emits, was accepted too.
Require the remainder after the prefix to be exactly one nonempty agent id
followed by .md — no path separators.
* fix(plans): keep separator-carrying agent ids in one filename component
The anchored predicate rejected any agent id containing a path separator,
but producers can emit one: TeamCreateTool accepts any nonblank team name
and teammate spawning only strips `@` from the teammate name, so a team
called `a/b` yields the path {plansDir}/{slug}-agent-writer@a/b.md. That
is a file in a subdirectory, not a plan file, so the teammate lost the
carve-out for its own plan and was blocked in plan mode.
Escape the separators where the path is built instead. Percent-escaping is
reversible, so two teammates can never collide on one plan file, and ids
without those characters are untouched -- existing plan files keep their
paths.
* fix(plans): recover plans written under the unescaped agent id
Escaping changes the pathname for teammates whose id already contains a
separator, and team names have always accepted arbitrary nonblank text --
so plans for ids like writer@a/b or writer@100% are already on disk under
the raw name. Every reader now builds the escaped name, so on upgrade the
teammate's plan reads as missing and a second file is created beside it.
getPlan falls back to the unescaped path on ENOENT and moves the file to
the escaped name. Moving rather than copying is what makes it stick: the
escaped name is the one the permission carve-out recognizes, so a plan left
at the old path would keep falling through to ordinary permission handling
on every later write. A failed move is not fatal, the content is already
read.
The recovery takes explicit paths so it is covered against a real temporary
directory rather than a mocked filesystem.
* fix(plans): confine legacy plan recovery to the plans directory
readLegacyUnescapedPlan builds the pre-escape path from the raw, unescaped
agent id so an existing file can be found. Team/agent names accept arbitrary
nonblank text, so a traversal-shaped id (`../../../etc/passwd`) collapses to
a path outside the plans directory -- which readAndMigrateLegacyPlan then
reads and renames, moving an arbitrary file. Refuse any resolved path the
plans directory does not contain before delegating.
* fix(plans): give escaped agent plans a collision-free namespace and harden recovery
The escaped filename shared a directory with legacy plans, so two distinct
teammates could map onto one file: `writer@a/b` writes the escaped
`{slug}-agent-writer@a%2Fb.md` while `writer@a%2Fb` already owns that exact
name as its raw legacy plan -- a cross-agent read and clobber. Store escaped
agent plans under a dedicated `agents/` subdirectory: a real path separator
is the one thing a raw single-component legacy name can never contain, so
the two namespaces are provably disjoint. The permission carve-out
(isPlanFilePath) recognizes the new location.
Harden legacy recovery, which reads then renames a file built from the raw
(unescaped) agent id:
- Reject any `..` segment before building the path, so `a/../{slug}` can no
longer collapse onto the main plan (or `a/../{slug}-agent-victim` onto a
sibling) and have recovery move another agent's file.
- Make migration no-clobber: never rename a legacy file over a plan already
present at the escaped path.
- Export readLegacyUnescapedPlan (with injectable plansDir/slug) so the guard
is covered through the recovery flow, not just isPathWithinPlansDir alone.
* test(plans): cover getPlan's ENOENT recovery wiring end to end
The recovery helpers are unit-tested, but nothing drove getPlan() itself
through the ENOENT fallback -- the whole user-visible fix. Add a test that
plants a legacy plan under a temp config dir and asserts getPlan() returns
its contents and migrates it into the agents/ subdirectory, serialized
under the shared mutation lock since it swaps OPENCLAUDE_CONFIG_DIR.
* fix(plans): anchor plan-file matching on the canonical encoding and harden recovery
Addresses review on the agent-plan permission carve-out.
isPlanFilePath accepted any `{slug}-agent-<x>.md` whose `<x>` had no raw
`/` or `\`, but getPlanFilePath emits only the canonical output of
encodeAgentIdForPlanFile (escapes `%`->`%25`, `/`->`%2F`, `\`->`%5C`). So a
raw-percent sibling such as `{slug}-agent-writer@100%.md` (canonical form
`...writer@100%25.md`) was auto-allowed for unprompted read/write even though
the producer never writes it. Add decodeAgentIdForPlanFile and
isCanonicalPlanFileEncoding (a component is canonical iff re-encoding its
decode reproduces it byte-for-byte) and anchor the agent branch on it. This
accepts every path the encoder can emit and rejects raw-`%`/raw-separator
lookalikes, subsuming the previous separator-only check.
Also harden legacy recovery, which reads and renames a path built from the
raw agent id:
- getPlan now treats an empty/whitespace escaped file as not-a-plan and falls
through to legacy recovery. isPlanFilePath permits a direct FileWrite/FileEdit
to the canonical escaped path before migration runs; such a stub would
otherwise permanently shadow a legacy plan that still holds content. Recovery's
no-clobber guard returns the legacy contents without renaming over the stub,
so a genuine concurrent escaped write is never lost.
- readAndMigrateLegacyPlan lstat-checks the legacy slot and refuses anything
that is not a regular file, so a symlink planted there cannot make recovery
read and rename an arbitrary target outside the plans directory.
Tests: canonical-vs-lookalike pairs for `%`/separator ids, getPlan driven
end-to-end for a separator id and for the empty-stub fallthrough, and a
symlinked legacy slot. The getPlan integration tests acquire the shared
mutation lock inside try/finally and clear the plan slug on teardown.
* fix(plans): close symlink and race gaps in plan-file recovery and the carve-out
Second review pass on the agent-plan hardening.
- Symlinked path components no longer bypass the lexical carve-out. The plan-file
permission grant (isSessionPlanFile) now resolves the deepest existing ancestor
of the target and requires it to stay within the *resolved* plans directory, so
a symlinked `agents` subdir (or plans dir) that redirects the real file outside
the plans directory is refused instead of auto-allowed. Legacy recovery gets the
same containment check, closing the slash-bearing-id case where a symlinked
intermediate `{slug}-agent-writer@a` parent passed the prefix checks and leaf
lstat.
- Migration is now a genuine no-clobber move: linkSync (atomic, fails EEXIST)
replaces the existsSync-then-renameSync check-then-act race that could replace a
concurrently-created live plan on POSIX. The escaped hard link pins the inode we
lstat'd, and we read through it, so a symlink swap of the legacy pathname cannot
redirect the read. Reads verify the inode/device are unchanged across the read.
- Traversal validation uses the host platform's real separators: on POSIX `\` is a
legal filename character, so a legacy id like `a\..\b` (persisted as one flat
filename) recovers again instead of being wrongly rejected; Windows still treats
both `/` and `\` as separators.
Tests: symlinked intermediate directory rejection (helper + recovery), POSIX
literal-backslash recovery, genuine-move semantics. All fail on the pre-fix code.
* refactor(permissions): reuse the shared plans-dir containment helper
Drop the duplicate isResolvedWithinPlansDir in the permission layer and route
the session plan-file carve-out through the exported isResolvedPathWithinPlansDir
from plans.ts, keeping the symlink-containment logic in one place. Guard the two
symlink-based tests on non-Windows so they skip where symlinkSync needs
privileges.
|
||
 keyarvsfandGitHub
|
248424ffe3 |
fix(model-picker): eliminate O(n²) catalog rebuild lag in /model (#2078)
* fix(model-picker): eliminate O(n²) catalog rebuild lag in /model getModelOptions() ran an O(n²) optionMatchesModel loop (catalog scan per option) plus an O(n²) duplicate-apiName filter, costing ~43ms per call on catalogs with hundreds of models (e.g. Fireworks' ~280 entries). The picker also rebuilt the full options list on every keystroke via isGenuineSwitchProfileValue, so arrow-key navigation lagged badly. - hoist catalog lookup out of the per-option loop (hasOptionValue) - precompute duplicate apiNames into a Set - short-circuit isGenuineSwitchProfileValue for non-switch values getModelOptions(): 43.5ms -> 2.0ms on a 277-entry catalog * perf(model-options): share route-catalog context across getModelOptions checks getRouteCatalogModelOption re-resolved the active route, fetched the catalog entries, and rebuilt the duplicate-apiName set on every call — getModelOptions() invoked it up to 3x per build (env custom model, each scoped additional option, active custom model + fallback), so large catalogs (Fireworks ~280 entries) paid O(n) context rebuilds repeatedly. Build the RouteCatalogContext lazily once per options build and pass it through findRouteCatalogOption/hasOptionValue. Behavior unchanged; the catalog-miss path measures 6.1ms -> 4.1ms on a 277-entry catalog. * test(model-picker): add regression tests for catalog dedup and switch-profile guard * test(model-picker): gate process-wide mocks in regression tests * test(model-picker): reuse mocked modelOptions instance in switch-profile test * test(model-picker): prevent mock leakage * test(model-picker): drop dead env overrides overwritten by catalog dedup helper OPENAI_BASE_URL and OPENAI_MODEL assigned in the scoped-cache test were immediately overwritten by getRouteCatalogModelOptions, so they never affected the exercised path. Remove the dead assignments; keep OPENAI_API_KEY to preserve the helper's auth path. * test(model-picker): assert getModelOptions skipped for ordinary ids isGenuineSwitchProfileValue short-circuits on the switch-profile prefix, skipping the getModelOptions() rebuild for ordinary model ids. Track the gated getModelOptions binding ModelPicker captures (opt-in call-through mock in importFreshModelPicker) and assert it is never invoked for non-prefixed ids, alongside the existing false-result assertions. * test(model-picker): address review feedback on spies, fetch bounds, and alias dedup |
||
|
|
5844d1fe8a |
Feat/ultracode blue spinner (#2096)
* feat(ultracode): add blue/cyan spinner and effort visual treatment - Add EFFORT_ULTRACODE (◆) figure for effort display surfaces - Add ultracode/ultracodeShimmer theme colors across all 6 theme variants - Wire ultracode case into effortLevelToSymbol() for icon rendering - Use blue-cyan RGB shimmer for "thinking" text when ultracode is active - Set spinner color override in REPL when displayed effort is ultracode * feat(ultracode): tint prompt border and unify shimmer to theme tokens Add a persistent cyan-blue prompt border whenever ultracode is the active effort, reacting immediately to /effort and ranking below bash/teammate overrides. Derive the spinner thinking-shimmer from the ultracode/ ultracodeShimmer theme tokens (with an ANSI/daltonized fallback) instead of a divergent hardcoded cyan, so border, spinner, and shimmer share one source of truth. Co-Authored-By: OpenClaude <openclaude@gitlawb.com> * test(spinner): cover ultracode shimmer color selection and ANSI fallback Extracts the thinking-shimmer color computation into an exported getThinkingShimmerColor helper (renderToString strips ANSI color, so the selection logic is only observable through a direct call) and adds focused tests for ultracode rgb() token interpolation, the ansi:* fallback endpoints, and the non-ultracode gray interpolation. Addresses CodeRabbit review on #2096. Co-Authored-By: OpenClaude <openclaude@gitlawb.com> --------- Co-authored-by: OpenClaude <openclaude@gitlawb.com> |
||
|
JATMNandGitHub
|
b3735bedb3 |
refactor(openai-shim): extract request executor helpers (#2011)
* refactor(openai-shim): extract request execution * fix(openai-shim): rebase executor extraction * test(openai-shim): preserve local stream options coverage * test(openai-shim): isolate Azure compatibility state * fix(openai-shim): preserve executor retry contracts * fix(openai-shim): retain route credential isolation * fix(openai-shim): preserve executor transport behavior * fix(openai-shim): avoid duplicate local retries * fix(openai-shim): preserve LongCat credential routing * fix(openai-shim): retain executor abort contracts * fix(openai-shim): preserve fallback cancellation * fix(openai-shim): preserve executor retry and transport contracts * fix(openai-shim): stabilize extracted executor smoke coverage * test(openai-shim): cover extracted executor retry contracts * test(openai-shim): assert redacted HTTP errors * test(openai-shim): isolate Azure executor configuration * fix(openai-shim): preserve executor recovery retries * test(openai-shim): remove migrated executor duplicates * docs(openai-shim): clarify extracted façade budget * test(openai-shim): enforce extraction modules * fix(openai-shim): stop retrying cooled GitHub keys * fix(openai-shim): avoid concurrent cooled-key retries * test(openai-shim): stabilize pooled-key retry coverage * fix(openai-shim): preserve newer credential cooldowns * docs(openai-shim): explain stale auth eviction |
||
 
|
5cac15cbda |
fix(minimax): mark MiniMax-M2.7 as text-only input (#2068)
Co-authored-by: octo-patch <266937838+octo-patch@users.noreply.github.com> |
||
|
JATMNandGitHub
|
8df37c78f4 |
fix(agents): allow subagents from multi-repo parent sessions (#2063)
* fix(agents): allow subagents from multi-repo parent sessions Expose Agent cwd in the open build, let cwd select the child repo for worktree isolation, and fall back instead of hard-failing when the session itself is outside a git repository. * fix(agents): persist cwd on resume and forward it to worktree hooks Address final-head review: store explicit Agent cwd in metadata for resume, pass cwd into WorktreeCreate hooks, reject relative cwd in the schema, and make the multi-repo parent regression sandbox portable. * fix(agents): keep child-repo cwd across worktree cleanup and resume Persist explicit Agent cwd even when a worktree is created, preserve it when unchanged worktrees are removed, and base fork worktree notices on the child-repo cwd for multi-repo parent sessions. * fix(agents): re-persist child-repo cwd on every resume Always forward persisted Agent cwd through resume metadata writes so a mid-life resume cannot drop the multi-repo fallback path, and tighten prompt wording to match the missing-git fallback contract. * fix(agents): validate cwd directories and recover from worktree hook failures Require Agent cwd to be an existing directory, always re-persist the original resume metadata cwd, and fall through from failed WorktreeCreate hooks to git when the selected cwd is a git repository. * fix(agents): keep WorktreeCreate hooks authoritative Revert silent git fallback after hook failure. Treat WorktreeCreate hook errors as recoverable in AgentTool so multi-repo cwd overrides still work without bypassing configured hooks at the worktree layer. * fix(agents): only soft-fallback missing-git worktree errors Keep WorktreeCreate hook failures hard-failing so configured hooks stay authoritative in normal git sessions. Soft-fallback remains limited to the missing-git path that #2052 needs. * docs(agents): clarify missing-git cwd fallback wording Align AgentTool prompt and resume debug logs with the missing-git-only soft-fallback contract for multi-repo parent sessions. * fix(agents): keep fork worktree notices on session cwd Inherited fork context paths are relative to the parent session, so the worktree notice must use getCwd() even when isolation used a child-repo cwd. * docs(agents): align runAgent cwd JSDoc with resume persistence * fix(agents): address CodeRabbit cwd validation review notes Use afterAll for schema-test temp cleanup, and preserve the underlying stat failure reason when Agent cwd validation rejects a path. * fix(agents): surface worktree isolation fallback visibly Make the missing-cwd schema test path platform-neutral, and record a user/model-visible notice plus tool-result flag when worktree isolation soft-falls back outside a git repository. * fix(agents): surface worktree fallback when sync agents background Share async_launched payload construction so the sync-to-background path includes worktreeIsolationFallback when worktree isolation soft-falls back. |
||
|
JATMNandGitHub
|
871bf28568 |
refactor(openai-shim): extract typed request body planning (#2010)
* refactor(openai-shim): extract request planning * test(openai-shim): cover Bankr route credential base * test(openai-shim): retain empty Responses fallback coverage * fix(openai-shim): address planner review findings * test(openai-shim): cover serializeBody transport routing Add planner tests that exercise serializeBody() for responses, anthropic_messages, and gemini transports, including omit-flag rebuilds. Remove the vacuous Gemini tool_choice assertion that never guarded behavior. |
||
|
|
e636f7d1cb |
feat(opengateway): add Macaron V1 Tall to the gateway catalog (#2067)
* feat(opengateway): add Macaron V1 Tall to the gateway catalog Served by opengateway via direct Novita (model is not on OpenRouter). Free launch window; the gateway delists it 2026-08-10. Adds the model and brand descriptors and regenerates integration artifacts. * test(opengateway): add Macaron regression coverage + picker expectation Adds macaron.test.ts (descriptor capabilities/limits, gateway catalog apiName/modelDescriptorId wiring, runtime limits — tencent.test.ts pattern) and includes mindai/macaron-v1-tall in the /model picker's expected opengateway option list. --------- Co-authored-by: OpenClaude <openclaude@gitlawb.com> |
||
|
JATMNandGitHub
|
ae634cdef3 |
refactor(openai-shim): extract stream lifecycle and response dispatch (#2009)
* refactor(openai-shim): extract client dispatch * fix(openai-shim): preserve max reasoning effort dispatch * test(openai-shim): cover injected Codex dispatch |