- Add `codex.orphan-delegation-compatibility` configuration option and mirror it to SDK configuration.
- Convert orphan Codex delegation outputs into standard user messages for requests with `X-Openai-Subagent: collab_spawn`.
- Integrate orphan delegation rewriting into OpenAI responses request handling pipeline.
Closes: #5401
- Attach candidate upstream errors as causes to scheduler availability and cooldown errors.
- Introduce `errorWithCause` wrapper to extract and display upstream error summaries.
- Enrich auth selection error messages with upstream details and preserve model cooldown errors.
- Forward `Retry-After` response headers for model cooldown errors in Claude Code handler.
Closes: #5365
- Add `ParsePluginExecutorResponseUsage` to extract token usage from non-streaming plugin responses across Claude, Gemini, Interactions, Antigravity, and OpenAI/Codex protocols.
- Add `ObservePluginExecutorStreamUsage` to observe and aggregate token usage across streaming chunks.
Closes: #5340
- Filter `max` and `ultra` reasoning effort levels for Codex client versions prior to `0.144.0`.
- Extract and forward the `client_version` query parameter across model catalog response handlers.
- Add dotted version parsing and comparison utilities to verify extended reasoning level compatibility.
Closes: #5262
- Introduce `WebSocketResponseObserver` capability and bump plugin ABI schema version to 4.
- Forward upstream WebSocket response frames from Codex and xAI executors to configured observers.
- Wire `WebSocketResponseObserver` across API handlers and plugin host dispatchers.
Closes: #5248
- Add compact-specific error classification to mark transient/non-credential failures as availability-neutral instead of triggering cooldown penalties.
- Stop auth fallback immediately on compact request-fault errors (e.g., bad/not-found/unsupported request errors) and return the upstream compact error.
- Preserve existing cooldown behavior for auth/credential faults (`401`, `403`, `429`) while allowing non-auth compact failures to fail fast without tainting normal traffic routing.
Closes: #5031
After remote compaction succeeds, the normalized previous request still contains the consumed compaction_trigger. The next WebSocket-to-HTTP merge replays that trigger before the compaction output and current input, causing the upstream 400 error.
Remove compaction_trigger only from previous request items when the previous response contains compaction or compaction_summary. Add a two-step regression test covering trigger normalization followed by compact replay.
Fixes#5041
- Return buffered pending stream errors from `errChan` when the data channel closes in streaming handlers.
- Emit error response instead of silently falling back to normal SSE completion paths.
- Replace Claude’s local `pendingClaudeStreamError` usage with shared `handlers.PendingStreamError`.
Closes: #4710
- add shared `EnsureResponsesUsageDetails` helper to patch `usage` objects with:
- `output_tokens_details.reasoning_tokens = 0`
- `input_tokens_details.cached_tokens = 0`
- for both plain JSON and SSE `data:` frames, including multi-line frames
- apply the helper to OpenAI Response format outputs in non-stream and stream paths across executors/plugins so translated payloads consistently include required usage details
- update websocket/completion payload builders to emit default `usage` detail fields for prewarm/finish responses
Closes: #4985
- Added `grok-imagine-image-2.0` as a first-class xAI image base model across validation, canonicalization, and routing checks.
- Registered the model in built-in model definitions so it appears in model metadata.
- Updated image model allowlists and request validation error messaging to include the new model.
- Marked the new model as hidden in client visibility override handling.
- Consolidate Responses websocket transcript merging by introducing typed input-item parsing for previous request input, previous response output, and appended input, replacing ad-hoc raw JSON-array string merges.
- Keep deduplication behavior in a single shared pipeline with metadata parsed once (type/id/call_id), then dedupe function-calls and item IDs before reserializing.
- Refactor fallback-turn tool-call repair into a unified prepare path that returns repaired payload + turn context, and only commits request state after successful forwarding to avoid stale per-turn history.
Closes: #4913
- Propagate pending terminal errors when image/response data streams close, emitting `error`/`failed` SSE events (or HTTP error responses when no stream started) instead of dropping them.
- Sanitize and normalize streamed terminal errors before writing, and reuse normalized errors for cancellation.
- Improve SSE parsing/frame handling for multiline and cross-chunk payloads, prioritize payload/event-level failures, and avoid mutating emitted frame buffers by cloning chunks before queueing.
Closes: #4904
- Bump plugin schema to version 3 and introduce `SchemaVersionStreamChunkOmitRequestBody`.
- Treat missing plugin schema versions as legacy during RPC registration (`0 -> 1`) and expose schema on plugin descriptors.
- In stream interception, keep request headers/bodies on header-init chunk and stop re-sending them on payload chunks for schema-v3+ plugins, with per-chunk cloning for legacy plugins.
Closes: #4876
Build the error body with sjson instead of formatting the requested model name into a JSON literal. The name is client supplied and is echoed back verbatim, so a quote in it produced a malformed body and a crafted name could append fields that overwrote the error code clients branch on, for example turning model_not_found into insufficient_quota.
Reported by the Codex reviewer on #4820.
Stop treating an upstream 500 carrying "status":"UNKNOWN" as a request fault. It is an internal upstream failure, so the request now falls through to the next credential instead of failing immediately, and the resulting cooldown lands on the failing credential and model pair only, leaving sibling models on that credential selectable.
Move the store=false item-miss detection into the shared client-error package. The upstream sends that 404 as plain text rather than a JSON error body, so the structured identifiers could never match it and only the conductor recognized it. The proxy now reports it to the client, which is the only party able to rebuild the request without the stale item reference; a reconnect resends the full input and the conversation continues unchanged.
Forward an upstream failure to Responses websocket and SSE clients only when the request itself is at fault. Credential, quota and transport failures now close the stream silently so the client reconnects and retries; a fresh websocket carries no server-side transcript, so reconnecting already implies a full context resend and needs no extra close-code signal.
Classify the failure from the upstream error body instead of the attached status. Codex reports the same cyber_policy rejection as 400 on the stream error path and as 502 through the websocket disconnect channel, so a status-only whitelist hid most of them. Treat cyber_policy as a request error so it stops credential failover without suspending the credential, and treat 413 as request-scoped because a payload that exceeds the upstream frame limit fails identically on every credential and would otherwise burn the whole pool.
Report an unroutable model as 400 invalid_request_error instead of 502 so streaming clients receive an actionable message instead of retrying forever. Keep the upstream reason in the request-log websocket timeline when the client only observes a closed connection, and stop logging expected connection-teardown races as warnings.
- Added `ClientRequestMetadata` struct to capture client IP, `X-Forwarded-For` headers, and user agent.
- Implemented metadata extraction in HTTP handlers and propagation through context.
- Updated Redis queue plugin to include client request metadata in payloads.
- Added tests to validate metadata extraction and inclusion in request contexts.
- Added support for weighted round-robin authentication scheduling strategy.
- Implemented credential weight validation for attributes and metadata, with strict error handling for invalid weights.
- Enhanced scheduler with smooth weighted state handling and proportional selection logic.
- Introduced tests for credential weight parsing, validation, and weighted round-robin behavior.
- Updated configuration to include `weight` field for credentials with range validation.
Closes: #4470
- Implemented a Go-based dynamic library plugin for request lifecycle management.
- Added concurrency controls, keyword-based request termination, and response handling.
- Supported optional capabilities for request interception and active lifecycle termination.
- Included tests for schema compatibility, concurrency limits, and policy-based termination.
- Added build instructions and configuration details in README.
- Updated host support for lifecycle plugin RPC methods.
Closes: #4568
- Introduced `DisableCloakingModelList` in `ClaudeCodeConfig` to control model ID cloaking in Anthropic model list responses.
- Updated relevant APIs and handlers to respect the new configuration.
- Added comprehensive tests for enabling/disabling cloaking behavior and config-driven hot reload scenarios.
- Extended example configuration and documentation to include the new setting.
Closes: #4473
- Removed deprecated interceptor and executor-related methods, including `callRequestInterceptor`, `callResponseInterceptor`, and `callStreamChunkInterceptor`.
- Consolidated unused logic and pruned redundant imports to streamline `adapters.go`.
- No functional changes.
- Introduced a new `models` package for organizing Claude client model templates and building responses.
- Migrated Claude response handling to `claudemodels.BuildResponse`.
- Added comprehensive tests for model ID transformation, sorting, and metadata validation.
- Removed redundant utility functions and simplified integration with the API server.
- Introduced a new `models` package for organizing Codex client model templates and building responses.
- Migrated Codex response handling to `codexmodels.BuildResponse`.
- Added comprehensive tests for model metadata, reasoning levels, and input modalities handling.
- Updated Kimi and Gemini executors to use `TranslateRequestWithCodexMultiAgentV2` for improved multi-agent v2 optimization.
- Enhanced configuration and API server to support `CodexOptimizeMultiAgentV2`.
- Added codex multi-agent V2 optimizations in `config`, `executor`, and `watcher` modules.
