- Exclude known credential quota and cooldown errors from recoverable duplex error preservation in forwardResponsesWebsocket so opts.suppressError and terminal error handling still apply after response.created.
- Add regression tests verifying usage_limit_reached and model_cooldown consult the replay guard while request and client rate-limit errors stay on the duplex path.
Closes: #7586
- Strip thinking suffixes from `advisor_*` tool `model` fields inside `sanitizeClaudeMessagesForClaudeUpstreamWithDebugDoc` before payload config rules run.
- Preserve each advisor tool's own base model and leave non-advisor tool entries untouched.
- Add regression tests covering API key and OAuth flows across `Execute`, `ExecuteStream`, `CountTokens`, payload overrides, and edge cases.
Closes: #7591
- Close text content blocks in Gemini-to-Claude streaming and non-streaming responses only when the part carries a thought signature or at a non-text boundary.
- Coalesce consecutive unsigned text chunks into a single text block while keeping explicitly signed text parts isolated and preserving delayed signature carriers.
Closes: #7587
- Unpin and exclude the failed credential when a full response.create on a persistent Responses WebSocket fails with a pre-commit quota or auth error.
- Propagate excluded auth IDs through handler metadata into mixed and Home stream selection while blocking replay once any downstream frame is committed.
- Add regression tests for pre-commit 429 failover, post-commit non-replay, and Home repeated excluded-auth rejection.
Closes: #7585
- Route OpenAI Chat Completions response_format and Responses text.format json_schema payloads to Claude output_config.format via ojson.Doc while keeping system-prompt fallback for legacy Claude models and non-schema formats.
- Preserve optional schema name and description in a short system instruction without repeating the JSON schema body.
- Include output_config.format.schema in local Claude input token estimation and add translator and executor regression tests.
Closes: #7576
- Tag Gemini-family zero-output HTTP 502 errors and translated Claude MALFORMED_FUNCTION_CALL error payloads with ErrorCodeTransientTransport across Antigravity, Gemini, Vertex, and AI Studio executors so Conductor skips credential cooldown while preserving per-request rotation and cross-provider failover.
- Update existing Claude MALFORMED_FUNCTION_CALL conductor tests to assert failed execution results and failed usage metrics without placing credentials into cooldown.
- Add unit and HTTP handler regression tests verifying uncooled rotation, cross-provider failover, and groundingChunks-only Claude fallback paths across Gemini-family executors.
Closes: #7571
- Convert Gemini inlineData image parts to Responses image_generation_call output items in both streaming and non-streaming paths so /v1/responses returns generated images instead of dropping them.
- Exclude thought images, gate on supported image mime types, dedupe streamed image parts by sha256, and preserve thought signatures attached to image parts.
Closes: #7569
- Add Builder.WithExecutorWrapper applied in the centralized registerExecutor gate so embedder wrappers survive startup sync, auth, and model refresh paths that bypass OnConfigApplied.
- Track the service-owned underlying executor per provider with manager revisions to preserve Claude WithConfig reuse and Codex/XAI session sharing across wrapping without double-wrapping.
- Harden replacement lifecycle for wrapped executors, including shared-session preservation, stale-ownership invalidation, and safe traversal of opaque or cyclic wrappers.
Closes: #7568
- Skip inlineData and inline_data parts marked with thought=true when translating Gemini and Antigravity responses to OpenAI chat completions so intermediate draft images do not leak into images[].
- Suppress empty streaming deltas for standalone thought image chunks while preserving tool signature boundaries and empty-stream guards.
Closes: #7566
- Reconcile v8 credential uploads through SynthesizeAuthFile without redundant local store rewrites, preserving plugin-assigned IDs, FileName values, multi-record expansions, and symlinked destinations while retiring stale records from overwritten files.
- Pass synthesis fallback AuthDir out-of-band during plugin parsing so omitted IDs resolve relative to AuthDir without mutating AuthParseRequest.Host or overriding explicit path-based IDs.
- Remove all in-memory auth records backed by a deleted file in v8 credential deletion and snapshot handler config under lock for race-free synthesis.
Closes: #7557
- Preserve ModeLevel in normalizeUserDefinedConfig for native Gemini/Interactions requests and user-defined models with explicit thinking levels.
- Enforce strict provider scoping in ModelRegistry.GetModelInfo and prioritize channel-specific static catalog fallback in LookupModelInfo.
- Add unit and Vertex executor regression tests covering user-defined Gemini thinkingLevel preservation and cross-provider shadowing.
Closes: #7558
- Add ExcludeCandidates with PascalCase and snake_case ojson decoding to pluginapi.SchedulerPickResponse and preserve normalized exclusions in pluginhost when unhandled or delegated.
- Filter excluded auth IDs per selection pass in Manager before priority tiering and built-in selector evaluation so healthy lower-priority credentials can promote without mutating caller tried state.
- Add unit tests covering JSON/RPC compatibility, host normalization, priority promotion, session affinity, and cooldown/empty-pool errors.
Closes: #7535
- Add sensitive-patterns-replace configuration rules with load-time RE2 validation, comment-preserving YAML persistence, config diffing, and bounded matcher caching across Antigravity, Devin, and Claude cloak paths.
- Apply ordered non-cascading regex replacements against original text boundaries while preserving Devin original-line drop ownership and existing sensitive-words-replace semantics.
Closes: #7540
- Stop counting signature-only empty-text parts as thought output in InspectGeminiZeroOutputPayload so leading signature-only frames stay buffered until real content arrives.
- Fail buffered candidate-bearing zero-output streams with a retryable 502 on EOF in GeminiZeroOutputStreamGuard.Finalize and harden Antigravity OpenAI streaming translation against all-null delta emission.
- Add unit, executor, and HTTP failover regression tests covering signature-only zero-output streams across downstream formats and credential rotation.
Closes: #7536
- Resolve and validate the target Codex credential proxy_url in StartSIWCBind and construct the OAuth client via codex.NewCodexAuthWithProxyURL so account proxy takes precedence over global proxy without falling back on failure.
- Update siwcOAuthFactory to pass the resolved account proxy URL and add regression tests covering account proxy precedence, global proxy inheritance, direct bypass, unreachable proxy failure, and credential field preservation.
Closes: #7531
- Detect the 403 PERMISSION_DENIED ErrorInfo reason=TOS_VIOLATION signature and mark the credential StatusDisabled + Disabled so it is excluded from rotation and persisted across restarts, while OAuth refresh stays intact; carry appeal_url/appeal_url_link_text through Error.Metadata to auth.Metadata and the management API.
- Add an optional pool-wide protective pause (antigravity.tos-pause-window, default 6h) armed only by TOS results, never by transient 429s, covering all Antigravity request paths including SSE mid-stream error frames and CountTokens.
- Distinguish terminal TOS results from stale/superseded results using a new Result.RefreshToken account hint so a same-account OAuth refresh applies the suspension while a genuine credential replacement discards it safely.
Closes: #7515
- Wrap the final 429 in a poolCooldownTerminalError at the Execute/ExecuteCount/ExecuteStream boundaries when every candidate credential for the model is blocked and at least one is in a timed cooldown, preserving the upstream error body and status while marking IsModelCooldown so the Claude handler appends the reset time.
- Compute the Retry-After from the earliest auto-recovery across all blocked candidates (including non-cooldown timed blocks) so the client sees the pool's real recovery instead of the last attempt's hint.
- Add regression coverage for both cooldown variants across the three execution paths, the available-candidate guard, mixed-block earliest deadlines, the sub-floor hint clamp, and the Claude handler end-to-end.
Closes: #7521
- Build interceptor metadata in WriteModelListResponse from the authenticated gin context (caller_scope, access_provider, frontend_auth_metadata) instead of always passing nil.
- Reuse requestCallerScope so model-list requests share the same irreversible caller handle as execution paths, enabling per-key catalog filtering including ?key= credentials.
- Forward the same metadata to the request lifecycle tracker and add regression tests for identity forwarding, metadata isolation, and unauthenticated nil metadata.
Closes: #7524
- Add Priority *int to pluginListEntry, populated from the host RegisteredPlugins snapshot so clients can verify effective ordering, including zero and negative values.
- Gate exposure to the maintained v8 route while leaving the deprecated v0 response shape unchanged, and add RegisterPluginWithPriorityForTest to cover non-default priorities in tests.
Closes: #7522
- Cache verified management secret HMAC-SHA256 digests bound to the active bcrypt hash for a one-hour TTL while coalescing concurrent cold-cache verifications.
- Invalidate cached verification entries on management secret changes in SetConfig and ConfigV8 while preserving failure counting, IP ban checks, and non-caching of invalid keys.
- Add deterministic unit tests, a ConfigV8 HTTP integration test, and a benchmark covering TTL expiration, rotation, concurrency coalescing, and ban preservation.
Closes: #7519
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
- Detect MALFORMED_FUNCTION_CALL, UNEXPECTED_TOOL_CALL, and MALFORMED_RESPONSE with zero visible output before bootstrap commit, reasoning replay caching, or usage finalization across Antigravity, Gemini, Vertex, and AI Studio executors.
- Withhold only contentless leading shell frames while keeping thought chunks unbuffered for TTFT, and align Claude response error handling and stream completion flags while preserving valid partial outputs.
- Add unit, executor, bootstrap failover, and cross-module HTTP regression tests covering credential rotation and HTTP 502 exhaustion.
Closes: #7513
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
- Sequence the WebSocket close frame ahead of socket teardown by waiting on the writer in finishClose with a bounded grace window, closing the 1006-vs-1002 race.
- Add waitServersVisible to drain the topology stream until expected servers are observable, fixing empty server_list and stale server_online reads in client tests.
- Make the backpressure test deterministic via a gated transport plus tighter byte budgets, and route background-read errors through bounded barrier channels to prevent hangs.
Closes: #7504
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
- Add Builder.WithPluginInterceptorHost so embedders can install a custom PluginInterceptorHost that survives startup and reload; the server wraps it to keep plugin model routing, executor dispatch, lifecycle, and websocket observers delegated to the internal plugin host.
- Add Hooks.OnConfigApplied invoked after each successful config apply so embedders can reinstall executor wrappers and other caller-owned runtime state.
- Cover the delegated interceptor host with nil-safety, skip-forwarding, capability-detection, and real execute-chain regression tests.
Closes: #7499
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
- Add a lightweight per-request in-flight tracker on the auth manager that covers selection, upstream calls, retry waits, and the full stream lifetime; it stays disabled in Home mode where the execution registry is authoritative.
- Register GET /v8/management/observability/requests/in-flight returning counts only (in_flight, oldest_started_at, by_provider) with no request bodies or credential identifiers.
Closes: #7476
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
- Add server.shutdown-timeout config (default 0 = immediate close, preserving #6094 behavior); positive values drain in-flight HTTP requests via http.Server.Shutdown bounded by the configured seconds, then force-close the rest.
- Bound the drain by the configured timeout even when the caller's context is more generous, while a tighter parent deadline still wins; hijacked WebSocket connections remain managed by their own handlers.
- Cover drain completion, budget-expiry fallback, tighter parent ctx, zero default, and v8/legacy config parsing in tests.
Closes: #7475
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
- Prefer /v8/management endpoints for config, credentials, api-keys, logs, and OAuth flows, normalizing the v8 config tree to the TUI's flat view and falling back to /v0/management only when a route is genuinely unimplemented.
- Read access.api-keys from the same versioned root-config snapshot and write back with If-Match, refusing unconditional replaces and stale-index edits/deletes so concurrent changes are not lost.
- Return a non-zero exit via CheckManagementSupport when a server definitively exposes neither contract, while keeping transient probe failures and wrong-password retries non-fatal.
Closes: #7462
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
- Restore Claude signature carriers onto their original Gemini parts with message and semantic boundaries.
- Return Gemini tool signatures in streaming and non-streaming Chat Completions responses without weakening provider compatibility.
- Cover delayed signatures, metadata, unsupported payloads, and payload-rule precedence with regression tests.
Closes: #7484
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
- Run the reauthorization regression test with request logging both enabled and disabled.
- Drain WebSocket handlers and verify logging leaves no temporary files and records the revoked credential.