312 Commits

Author SHA1 Message Date
Luis Pater
2d5351b3e5 feat(vertex): add support for native gemini interactions api
- Extract shared Gemini Interactions helpers for payload translation, input sanitization, thinking, and SSE streaming
- Add `interactions` configuration option to Vertex credentials
- Support native non-streaming and streaming Interactions API execution in Gemini Vertex executor

Closes: #6445
2026-10-08 12:39:31 +08:00
Luis Pater
0f96f568e4 refactor(translator): update openai and interactions request converters to return errors
- Update OpenAI and OpenAI Responses to Interactions request converters to return `([]byte, error)`
- Register request converters directly in internal translator registry instead of sdktranslator checked requests
2026-10-08 03:00:04 +08:00
Luis Pater
7cd8f7bac7 Merge pull request #6441 from soilSpoon/fix/attachment-parts
fix(translator): stop dropping attachments and empty turns
2026-10-08 02:09:31 +08:00
Luis Pater
e7b22260dd fix(claude): support plain-text and structured response bodies for missing thread errors
- Extend `IsClaudeThreadNotFound` to identify missing thread errors from plain-text error messages in addition to JSON payloads
- Implement `ResponseBody` on executor `claudeThreadNotFoundError` to supply structured JSON error payloads

Closes: #6443
2026-10-07 23:32:21 +08:00
Luis Pater
cd9e5acec7 fix(api): compact json error response bodies for SSE compatibility
- Compact valid upstream JSON error response payloads to single-line formatting to ensure compatibility with SSE streams while preserving error data

Closes: #6434
2026-10-07 21:13:39 +08:00
이대희
3b69068e6c fix(translator): stop dropping attachments and empty turns
An attachment a translator could not represent was dropped without a word, and
a turn whose only content was that attachment went upstream as an empty
messages, parts, or input array. The model then answered as if nothing was
attached, or the upstream rejected a request that never named the attachment.

A base64 document now reaches OpenAI as a file part. A file the target cannot
receive, such as container_upload, an OpenAI file_id, or input_audio sent to
Claude, is reported by name so the route answers 400 instead of forwarding an
empty turn. Text beside it still travels.

One rule, ErrIfNothingLeft, decides when to refuse, and RegisterCheckedRequest
carries the refusal on the request envelope. Every executor that translates
checks it before calling upstream. The exported converters keep their []byte
signature, so no caller or sibling test had to change.
2026-10-07 19:21:32 +09:00
Luis Pater
306c9bd824 fix(routing): restrict speech-only models to speech endpoints and refine xAI error scoping
- Reject speech-only models (such as `grok-tts` and `grok-voice-tts-1.0`) on non-speech entry protocols to prevent invalid chat upstream routing
- Mark upstream 404 errors for xAI speech as request-scoped unless indicating model unavailability, preventing unnecessary credential rotation and model cooldowns
- Align xAI speech payload finalizer protocol with `openai` for consistent payload override rules
2026-10-07 13:46:58 +08:00
luohui1
6a853dce05 feat(xai): expose Grok TTS on /v1/audio/speech
Route OpenAI speech requests to the official xAI /tts endpoint and register grok-tts and grok-voice-tts-1.0.
2026-10-06 02:49:21 -07:00
Luis Pater
97dd9eec62 fix(openai): report error on truncated stream missing finish_reason
- Track `finish_reason` presence across initial and streaming response chunks
- Return a terminal bad gateway error instead of `[DONE]` when upstream stream closes prematurely without a finish reason

Closes: #6371
2026-10-05 06:06:14 +08:00
Luis Pater
5c959cb032 fix(claude): mark missing thread state error for client replay
- Treat Claude missing thread state 404 errors as client errors to bypass credential rotation and cooldown
- Inject `thread_not_found` error code into Claude error response details to signal client-side replay
- Support extracting upstream response bodies across error formatting and classification helpers

Closes: #6344
2026-10-04 21:40:10 +08:00
Luis Pater
c997cbb58a feat(httpwire): introduce error-aware response flushing helper
- Add `FlushResponse` to prefer error-aware flushing and unwrap wrapped response writers
- Bypass Gin's void `Flush` while maintaining header accounting via `WriteHeaderNow` to keep transport errors observable

Closes: #6332
2026-10-04 17:33:19 +08:00
Luis Pater
cbc4cd5532 feat(interactions): support antigravity session continuation and model detail lookup
- Add `InteractionsSessionCache` to preserve Antigravity interaction continuations across tool call rounds
- Automatically restore and inject `previous_interaction_id` and `environment_id` in Gemini interactions executor
- Normalize Antigravity tool identity mappings in OpenAI responses translator
- Add `/v1/models/*model` endpoint to support retrieving individual model details

Closes: #5190
2026-10-04 04:23:31 +08:00
Luis Pater
42d484f9a2 fix(claude): map request timeout status to timeout_error
- Map `http.StatusRequestTimeout` (408) to Claude `timeout_error` response type

Closes: #6298
2026-10-03 15:03:44 +08:00
Luis Pater
d306f2c56d fix(codex): retain template freeform apply_patch capability by default
- Retain `freeform` apply_patch tool type for native template models when `enable-apply-patch` is false
- Update client configuration documentation for `client.codex.enable-apply-patch`

Closes: #6286
2026-10-03 00:01:42 +08:00
hkfires
52d5507dd3 feat(config): add shared upstream provider settings
Move shared Codex, Claude, and xAI provider options under upstream so
they apply consistently to OAuth and API-key credentials. Migrate
historical OAuth paths, preserve OAuth-only header scope, and expose the
new upstream management API path.
2026-10-02 22:36:35 +08:00
Luis Pater
8fbf152b5b fix(executor): preserve top-level responses token usage when service tier is present
- Fall back to top-level token usage when Codex response usage contains only service tier metadata
- Propagate parsed service tier while retaining top-level token counts
- Avoid early return during stream usage observation for chunks with zero token counts

Closes: #6261
2026-10-02 16:01:23 +08:00
Luis Pater
63c04b4bd4 feat(config): introduce client configuration section for codex settings
- Add `ClientConfig` and `CodexClientConfig` structs to `SDKConfig`
- Move `optimize-multi-agent-v2` and add `enable-apply-patch` under `client.codex`
2026-10-02 05:34:30 +08:00
Luis Pater
3ebee06516 fix(interactions): bridge apply_patch tool calls in responses translation
- Handle apply_patch custom tool call streaming deltas and snapshots for Responses API translation
- Track and resolve step indexes, function call identities, and error states across stream events
- Propagate apply_patch tool input errors and upstream failure states in stream and non-stream responses
2026-10-02 03:49:51 +08:00
Luis Pater
9e71c20d01 fix(codex): handle upstream stream disconnect before first payload as bad gateway
- Return Bad Gateway error when Codex upstream stream closes before emitting any payload
- Allow failover to subsequent credentials on premature stream disconnect before output
- Map HTTP 408 Request Timeout status to server_error in base error response handlers

Closes: #6247
2026-10-01 02:51:19 +08:00
Luis Pater
b7f321f2a1 feat(api): support request path overrides and image protocols in model execution
- Add `Path` field to model execution requests and plugin interceptor responses
- Propagate custom request paths through execution metadata
- Allow image models during execution when entry or exit protocol is `openai-image`

Closes: #6196
2026-09-29 22:44:33 +08:00
Luis Pater
4b99d1d6f8 feat(openai): support quality parameter for xAI image requests
- Parse and pass `quality` in xAI image generation and edit requests
- Extract `quality` field from JSON payloads and multipart form data
- Include `quality` in the upstream xAI image request payload when provided

Closes: #6157
2026-09-28 06:22:38 +08:00
Luis Pater
31f4cfab3f feat: migrate CLIProxyAPI to version 8 2026-09-27 14:42:26 +08:00
hkfires
d9922f0589 feat(config): add v8 configuration API
Introduce the v8 management configuration tree with migration-aware reads and
writes, grouped upstream API-key providers, and independent v8 operational
routes.

Preserve legacy configuration compatibility while ensuring successful v8 writes
migrate layouts, redact JSON TURN secrets, and keep OAuth-only provider
settings from affecting API-key credentials.
2026-09-27 14:16:27 +08:00
Luis Pater
c9a06ba6f2 fix(interceptors): avoid cloning request body for read-only interceptors
- Share request payload reference during session identity enrichment when original request is unset
- Avoid cloning request payload when interceptors do not mutate the body
- Pass request body directly to handler and conductor interceptors

Closes: #6101
2026-09-25 00:34:17 +08:00
Luis Pater
673131f574 fix(codex): compact client model catalog and preserve required fields
- Marshal Codex client catalog as compact single-line JSON without HTML escaping
- Use compact base instructions for non-template models to stay within the 1MiB payload limit
- Keep `apply_patch_tool_type`, `upgrade`, and `availability_nux` present as null instead of deleting them
2026-09-23 08:54:52 +08:00
Luis Pater
a962b77d43 feat(server): support trusted proxies configuration for client IP resolution
- Add `trusted-proxies` configuration option with IP and CIDR validation
- Apply trusted proxies to Gin engine to properly resolve forwarded client IPs
- Record `ResolvedClientIP` in request metadata and usage queue details

Closes: #6024
2026-09-23 04:26:45 +08:00
Luis Pater
d582067c06 feat(executor): support execution-scoped request proxy overrides
- Add context helpers to manage execution-scoped proxy overrides
- Prioritize request proxy over credential and global proxy settings across HTTP and uTLS clients
- Propagate request proxy in conductor execution and plugin host adapters
- Isolate Codex WebSocket connection reuse by proxy endpoint

Closes: #6013
2026-09-22 03:54:34 +08:00
Luis Pater
dd013f9e29 fix(responses): filter upstream private and telemetry events in SSE streams
- Filter internal `responsesapi.` telemetry and private `codex.` events from SSE output
- Preserve Codex response metadata for official Codex clients while dropping rate limits
- Discard frames matching filtered event names or payload types in the SSE framer

Closes: #6007
2026-09-21 21:35:48 +08:00
Luis Pater
7b6fafce1b fix(responses): support mid-connection prewarm in websocket handler
- Allow prewarm requests to be handled locally after an existing request turn
- Reset transcript root for mid-connection prewarms that omit `previous_response_id`
- Reuse local prewarm evaluation flag across request normalization and response handling

Closes: #6006
2026-09-21 20:13:05 +08:00
Luis Pater
563865e77a test: fix timing synchronization and channel races in streaming tests
- Wait for bootstrap initialization before advancing mock clock in Codex WebSocket tests
- Reorder data channel closures in OpenAI responses stream error tests
- Drain stream chunks in byte-cap release test to prevent dangling goroutines

Closes: #5981
2026-09-21 00:39:28 +08:00
Luis Pater
42c9680eee feat(executor): support duplex streaming for codex websockets
- Implement `streamCodexDuplex` to handle bidirectional WebSocket interactions for Codex
- Support steering continuations (`response.steer`) and queued creations (`response.create`, `response.append`)
- Preserve response settings and state transitions across steering updates and automatic successors
- Isolate connection-level failures with `codexDuplexConnectionError` to prevent unnecessary credential cooldowns

Closes: #5968
2026-09-20 00:02:10 +08:00
Luis Pater
cb62a6748b fix(openai): classify stream request timeout as server error
- Consolidate stream error code and error type derivations into paired error classes
- Map `StatusRequestTimeout` to `server_error` instead of `invalid_request_error` so interrupted streams remain retryable by clients

Closes: #5931
2026-09-18 23:10:19 +08:00
Luis Pater
05391d7b72 Merge pull request #5919 from Fesaluo/feat/xai-imagine-aspect-ratio-9-20
feat(xai): allow grok imagine aspect_ratio 9:20 and 20:9
2026-09-18 12:49:11 +08:00
Luis Pater
28743473c1 feat(codex): append (Devin) suffix to Devin model display names
- Detect Devin models by ID prefix, type, ownership, model registry metadata, or provider.
- Append `(Devin)` to model display names in Codex client responses when not already present.
- Set model `type` to `devin` in home Codex model formatting when served by the Devin provider.
2026-09-18 10:37:52 +08:00
Fesaluo
f049e00b76 feat(xai): also allow grok imagine aspect_ratio 20:9
Grok Imagine already supports the 20:9 wide phone ratio. Accept it
from aspect_ratio and from size, matching the 9:20 whitelist change.
2026-09-18 04:04:24 +08:00
Fesaluo
75bd6a60eb feat(xai): allow grok imagine aspect_ratio 9:20
Grok Imagine already supports the 9:20 phone ratio, but the OpenAI image
handler whitelist dropped it and fell back to 1:1. Accept 9:20 from
aspect_ratio and from size, and keep unknown ratios on the existing
fallback.
2026-09-18 03:58:11 +08:00
Luis Pater
6724a95851 feat(auth): enhance retry logic with enriched error handling and tests
- Introduce `authUnavailableError` with detailed recovery hints, status codes, and retry-after headers.
- Refactor scheduler logic to incorporate local retry deadlines and classify cooldown states without altering quota assessments.
- Refine error propagation to properly handle upstream errors and enrich context for retryable scenarios.
- Add comprehensive tests for retry deadlines, scheduler behavior, and error handling during credential unavailability.
- Ensure embedded recovery hints in HTTP headers for improved client-side handling and diagnostics.

Closes: #5842
2026-09-16 00:13:37 +08:00
Luis Pater
748d576731 feat(pluginhost): propagate forced provider and auth ID in host model execution
- Add `ForcedProvider` and `AuthID` fields to `HostModelExecutionRequest` and `ModelExecutionRequest`.
- Pin credentials via `WithPinnedAuthID` and forward forced provider options during model execution and streaming.
- Forward forced provider and auth ID from plugin host callbacks to model execution handlers.

Closes: #5814
2026-09-14 21:59:32 +08:00
Luis Pater
ca929459f9 test(openai): add tests for responses websocket compaction replay and routing
- Verify observed compaction response replay and retention across subsequent turns.
- Test plugin route overrides, provider auth pinning, and home runtime auth handling during compaction.

Closes: #5811
2026-09-14 19:36:46 +08:00
Luis Pater
f702bc1ac2 feat(codex): preserve native fidelity for responses-lite requests
- Detect native responses-lite requests via headers and client metadata.
- Skip instructions normalization and synthetic session cloaking for native requests.
- Preserve upstream completion output during websocket response forwarding.

Closes: #5780
2026-09-13 15:05:03 +08:00
Luis Pater
5b2785617d feat(plugins): expose model list responses to plugin interceptors
- Add `WriteModelListResponse` to `BaseAPIHandler` to apply plugin interceptors and record request lifecycles for model catalog responses.
- Update OpenAI, Claude, Gemini, Grok, and Codex model listing endpoints to route responses through the unified interceptor helper.

Closes: #5742
2026-09-12 00:04:11 +08:00
Luis Pater
8f23ad0291 fix(codex): inherit template metadata for model aliases and restrict provider capabilities
- Resolve canonical templates using metadata model IDs for model aliases and prefixed routes.
- Apply descriptions, base instructions, and thinking support overrides to matched templates.
- Restrict protocol capabilities and reasoning levels based on provider support.

Closes: #5699
2026-09-11 01:42:30 +08:00
Luis Pater
638ed7e1cc fix(stream): handle split CRLF across chunk boundaries in SSE validation
- Track trailing carriage returns across chunk boundaries in `sseJSONValidationState`.
- Strip leading newline in subsequent chunks to prevent duplicate newline insertion from split CRLF sequences.
- Reset trailing carriage return state upon stream completion.

Closes: #5657
2026-09-10 17:53:25 +08:00
Luis Pater
259130863d fix(openai): preserve nested error details and sequence numbers in responses stream
- Format streaming error payloads with nested error objects matching official OpenAI Responses SSE specifications.
- Extract and propagate sequence numbers from upstream terminal events and framer states.
- Use `json.Number` to prevent precision loss for large integers and token metrics.
- Sanitize sensitive keys recursively across nested error objects without dropping custom fields.
2026-09-10 11:58:36 +08:00
Luis Pater
bd03aabcf1 fix(openai): preserve prewarm input and allow named tool outputs in responses websocket
- Track pending synthetic prewarm response IDs to merge warmup inputs into subsequent delta followups.
- Normalize transcript replacements when followups do not reference the prewarm parent response ID.
- Validate that the `input` field is an array for `response.create` requests.
- Allow `function_call_output` items without a `call_id` when a non-empty tool name is present.

Closes: #5631
2026-09-10 11:20:49 +08:00
Luis Pater
d1a024e940 feat(codex): add support for gpt-image-2.5 models
- Register builtin model definitions for `gpt-image-2.5`, `gpt-image-2.5-flare`, and `gpt-image-2.5-sunburst`.
- Update OpenAI image handlers and request routing to recognize GPT Image 2.5 models.
- Support direct image generation and edit execution for GPT Image 2.5 variants in the Codex executor.
- Apply client visibility overrides to hide new builtin image models where appropriate.
2026-09-10 10:40:53 +08:00
Luis Pater
aedc9e6a39 fix(auth): classify terminal upstream auth failures as non-retryable errors
- Introduce `IsTerminalAuthError` and `NewTerminalAuthError` to identify permanent upstream authentication failures.
- Return terminal auth errors from candidate selection and scheduling when all available credentials fail with unauthorized errors.
- Support `BuildErrorResponseBodyWithError` to format terminal upstream auth errors as non-retryable `upstream_authentication_required` responses.
- Propagate terminal error classifications and the `retryable` field across HTTP and WebSocket response handlers.

Closes: #5645
2026-09-10 10:02:08 +08:00
Luis Pater
3bf787fc1d feat(auth): propagate canonical session id for custom header expansion
- Initialize `util.SessionIDResolver` to resolve session IDs from request contexts, metadata, and headers.
- Ensure canonical session metadata is injected into execution options across execution flows.
- Propagate session context in executors to support `$CPA-SESSION-ID` expansion in custom headers.
- Sync cleared or updated session identities back to execution contexts during conductor execution.

Closes: #5690
2026-09-10 01:43:37 +08:00
sususu
390589159e feat(session): enhance harness hierarchy recognition and deduplicate selector extraction 2026-09-08 17:04:58 +08:00
sususu
580df36423 feat(usage): propagate session and parent session hierarchy to usage reporting queue
- Reuse coresession.ExtractSessionInfo across HTTP headers and request payloads to unify canonical session prefix namespaces with the scheduler.
- Extract hierarchical session identities in two phases: initial extraction from request headers on entry, and authoritative deep extraction once request payloads and metadata are available.
- Support Claude Code multi-level subagents (X-Claude-Code-Agent-Id, metadata.agent_id) and Codex thread fork lineages.
- Propagate SessionID and ParentSessionID across ClientRequestMetadata, UsageReporter, and coreusage.Record without root_session_id.
- Include session_id and parent_session_id in queuedUsageDetail for Home LPushUsage forwarding and Redis consumption with self-loop guards.
- Add comprehensive test coverage for canonical headers, body extraction, ghost parent elimination, and self-referential loop guards.
2026-09-06 10:45:32 +08:00