For downstream websocket with CPA-mediated HTTP/SSE upstream (non-passthrough),
always merge the full conversation transcript instead of sending incremental
previous_response_id turns. Release pinned websocket auths after timeout and
gateway failures, and after WS bootstrap failover pin the successful SSE
credential so the next turn keeps merged context instead of retrying a
suspended websocket auth.
Fixes#4048
- Introduced `model` field in `videoAuthBinding` for model tracking.
- Enhanced binding store with `setWithModel` and `getBinding` methods for binding models.
- Updated handlers to propagate execution models during video processing.
- Added tests to verify model binding, retrieval, and propagation logic.
- Added `applyCodexClientNonTemplatePriorities` to assign higher priorities to non-template Codex client models dynamically.
- Implemented `maxCodexClientTemplatePriority` to set base priority for non-template models relative to template models.
- Updated unit tests to validate priority calculation for custom models.
- Introduced a new "max" level for reasoning depth in Codex client model configuration, providing maximum problem-solving capability.
- Added `service_tiers` field to model responses for better tier categorization.
- Updated unit tests to validate the inclusion and default behavior of `service_tiers` and the new "max" reasoning depth.
- Introduced the `gpt-image-2` model in Codex built-ins and updated visibility logic in the registry.
- Added direct proxy support for OpenAI image generation and editing endpoints.
- Implemented new execution paths for `/images/generations` and `/images/edit`, ensuring seamless handling for both JSON and multipart payloads.
- Expanded test coverage to validate the new model and direct proxy features, including streaming scenarios and error handling.
- Deleted `geminicli` provider and related `Apply` logic.
- Removed all translator packages specific to Gemini CLI (Claude, Codex integrations).
- Purged associated test files for Gemini CLI translation.
- Removed `GeminiAuthenticator` and all associated authentication logic (OAuth flows, token handling, refresh logic).
- Deleted internal/executor Gemini OAuth support, including bearer token handling and runtime API logic.
- Purged all tests, configs, and command-line flags specific to Gemini OAuth flows.
- Updated documentation and aliases to reflect Gemini removal.
- Renamed `parseRetryDelay` to `ParseRetryDelay` and `deleteJSONField` to `DeleteJSONField`.
- Updated references in `antigravity_executor` and tests to use the new `helps` package.
- Adjusted import paths and test cases to ensure compatibility with the new location.
- Updated README files to reflect changes in the retry logic references.
- Updated `.github/ISSUE_TEMPLATE/bug_report.md` to remove deprecated Gemini CLI mention.
- Added auth binding logic to tie video requests to specific authentication IDs.
- Enhanced video content handlers to support proxy configuration based on selected auth.
- Introduced helper functions for creating HTTP clients with direct or global proxy fallback.
- Expanded unit tests to validate auth binding, proxy usage, and fallback behavior.
- Updated `openai_videos_handlers` to extract and set `video_url` from payloads when available.
- Enhanced unit tests to validate correct `video_url` extraction and inclusion in responses.
* feat(plugin): add ModelRouter before auth with single-slot routing targets
## Motivation
Plugins that need to change execution based on the **original inbound request**
(protocol format, raw body, headers, query, stream flag, metadata, etc.) often
resorted to virtual/trampoline models or routing inside interceptors. This
commit adds **ModelRouter**: a pluggable layer **before** model-to-provider
resolution and AuthManager credential selection, so plugins can declare who
executes a request without spoofing the client model name.
This is a **new capability**, not a bugfix on the existing chain. With no
ModelRouter plugins loaded, behavior matches upstream.
## Pipeline placement
- `execute`, `stream`, and `count` (and image paths via AuthManager) call
`applyModelRouter()` before building `coreexecutor.Request`.
- Routing runs **before** the request interceptor (before auth), so routers see
the client’s original context. After a plugin executor is chosen, the existing
**after-auth interceptor → response/stream interceptor** chain still applies.
- Internal `ExecuteModel` / `ExecuteModelStream` (host callbacks) support
`SkipRouterPluginID` so nested calls do not re-enter the same router.
## Routing API (single slot, mutually exclusive)
`ModelRouteResponse` uses **one target slot** to avoid ambiguity when both
`TargetExecutorPluginID` and `TargetProvider` were set and the host ignored one:
| Field | Meaning |
|-------|---------|
| `Handled` | `false`: this router declines; try the next router or default path |
| `TargetKind` | `self` \| `executor` \| `provider` (pick one) |
| `Target` | `self`/`executor`: plugin ID; `provider`: built-in provider key |
| `TargetModel` | Optional on `provider` only; empty keeps client `RequestedModel` |
| `Reason` | Optional diagnostic text |
- **self**: the router plugin’s own executor (`Target` normalized to the router’s plugin ID).
- **executor**: another plugin’s executor; host pre-checks with `executorPluginReady()`
(executor declared and provider identifier resolvable) to avoid handled routes that 500 at execution.
- **provider**: skip registry model resolution; fixed built-in AuthManager path; optional
`TargetModel` for execution model only—**does not** change outward requested-model metadata.
Routers run in **descending plugin priority** (tie-break: ascending plugin ID). Panic, error,
invalid target, or unavailable executor/provider → log and **fall through to the next router**;
if none handle, use the original provider+auth flow.
## Context exposed to routers
`ModelRouteRequest` includes:
- `SourceFormat`, `RequestedModel`, `Stream`
- `Headers`, `Query`, `Body` (defensive copies)
- `Metadata` (best-effort read-only context snapshot)
- `AvailableProviders`: built-in provider keys with at least one **non-disabled** auth
(`AuthManager.AvailableProviders()`). **Does not** reflect per-model cooldown or transient
unavailability—treat as an optimistic snapshot.
Adds `AuthManager.HasProviderAuth()` and `AvailableProviders()`, excluding `Disabled` and
`StatusDisabled` auths consistently with credential selection.
## Host and RPC
- Go plugins: `pluginapi.ModelRouter` + `RouteModel()`.
- RPC plugins: `pluginabi.MethodModelRoute` (`model.route`), capability flag `model_router`.
- `pluginhost.Host` implements `RouteModel` / `RouteModelExcept`; handlers use
`SetModelRouterHost` or a `PluginHost` type assertion; **direct executor** paths use
`ExecutePluginExecutor*` / `CountPluginExecutor`.
- No bundled example ModelRouter plugin; capability is active only when a third-party plugin
declares `model_router` and loads.
## Plugin RPC schema (policy A, upstream-aligned)
- `pluginabi.SchemaVersion` stays **1**: capability additions (`model_router`, `model.route`)
do not bump the number; increment only on breaking RPC JSON changes.
- Host sends `schema_version` at register; reject only if the plugin declares a **higher**
version than the host.
- No unpublished “ModelRouter requires schema ≥ 3” gate (v3 single-slot API was never public).
- Existing plugins and examples without `model_router` (`schema_version: 1`) need no changes.
- RPC ModelRouter: `schema_version: 1` + `model_router: true` + implement `model.route`.
## Path consistency within this commit
- Provider routes reuse image-only model checks (e.g. `gpt-image-2`) on the normalized model,
same as the default AuthManager path.
- `count` aligned with execute/stream: `SkipRouterPluginID`, query/headers injection,
interceptor skip semantics.
- Handlers: `modelRoutersEnabled` treats hosts without `HasModelRouters` as disabled
(same as before ModelRouter existed); `pluginhost.Host` implements the detector.
- API docs: `ModelRouter` explicitly includes built-in **provider** targets (in addition to
plugin executors and the router’s own executor).
## Testing
go test ./internal/pluginhost ./sdk/api/handlers ./sdk/pluginapi ./sdk/pluginabi ./sdk/cliproxy/auth
go build -o test-output ./cmd/server && rm test-output
go test ./...
* fix(handlers): address ModelRouter review feedback
- Use modelExecutionQuery for plugin executor and AuthManager paths so
inbound URL query matches router/header behavior
- Guard queryFromContext when gin Request.URL is nil
- Read plugin executor stream chunks via nextStreamChunk to exit on cancel
- Drop redundant clonePluginMetadata on capability record meta
Tests cover query propagation, stream cancel, and nil URL safety.
* feat(plugin): add Claude web search router example
Add a Claude Code web_search ModelRouter example that can route matching Claude requests through Antigravity, Codex, xAI, or Tavily.
The plugin includes executor orchestration, backend fallback/penalty handling, Tavily API key support, Claude-compatible response assembly, stream forwarding, and focused unit coverage for detection, fallback routing, model resolution, penalties, stream forwarding, and Tavily behavior.
Verification: go test -count=1 ./... in examples/plugin/claude-web-search-router/go; go build -buildmode=c-shared for the plugin; go build ./cmd/server; live local CPA curl coverage for plugin load, four explicit routes, fallback, and Codex spark routing.
* fix(pluginhost): validate executor routes before fallback
* fix(pluginhost): skip oauth-only executor routes
- Introduced `videoAuthBindingStore` for managing mappings of video IDs to credentials with TTL support.
- Updated video creation and retrieval handlers to bind and utilize credentials for authentication.
- Enhanced response models to include upstream models and adjusted request preparation logic.
- Added test coverage for video auth binding, TTL configuration, and expiration handling.
- Developed `XAIWebsocketsExecutor` for handling xAI Responses via WebSocket transport.
- Introduced session and state management with `codexWebsocketSessionStore` and `xaiWebsocketIDStateStore`.
- Added robust ID mapping for upstream and downstream request/response sequences.
- Enhanced error propagation and handling of WebSocket terminal events.
- Included utility methods for WebSocket request preparation, connection management, and state tracking.
- Added foundational support for compact and streamed responses via enhanced session tracking.
- Implemented `websocketDirectCaptureExecutor` for Codex websocket passthrough functionality.
- Added logic to bypass incremental state handling for passthrough models.
- Updated normalization, compaction, and replay handling to support passthrough mode.
- Introduced `responsesWebsocketUsesCodexWebsocketPassthrough` utility for model-specific passthrough determination.
- Expanded test coverage for websocket passthrough scenarios, including compaction and response validation.
- Introduced `/openai/v1/videos` endpoint to support OpenAI-specific video generation.
- Added error normalization and handling for OpenAI video resources, including detailed error propagation.
- Enhanced response structure to include OpenAI-specific fields for status, progress, and model mappings.
- Implemented new handlers for video content retrieval and error scenarios.
- Expanded test coverage to validate OpenAI video support, error handling, and backend compatibility.
- Enhanced Codex Websockets Executor to capture `response.done` as a terminal event, alongside `response.completed` and `error`.
- Improved error propagation for upstream websocket errors with comprehensive message handling.
- Introduced utility functions for recognizing terminal events and extracting error messages.
- Expanded tests to validate new websocket event logic, including terminal event handling and upstream error propagation.
- Introduced test scenarios to validate `previous_response_id` injection during incremental and non-incremental requests.
- Verified behavior for pending tool calls, including proper inclusion or exclusion in websocket requests.
- Updated websocket handling logic to track `lastResponseID` and `pendingToolCallIDs`.
- Added utility functions for pending tool call validation and cleanup.
- Updated host model callback logic to skip originating plugin's interceptors during nested model executions.
- Added `SkipInterceptorPluginID` field to plugin API structs for controlling interceptor bypass behavior.
- Introduced supporting logic in host API handlers, plugin host registry, and callback contexts to identify and skip specific plugins.
- Enhanced unit tests across plugin host, API handlers, and execution paths to verify interceptor skipping behavior and plugin isolation.
- Revised documentation to clarify non-recursive behavior of host model callbacks and the use of `SkipInterceptorPluginID`.
- Added an example plugin `host-model-callback` in Go to summarize host model callbacks.
- Implemented `cliproxy_plugin_init`, `cliproxyPluginCall`, and other plugin functions for callback handling.
- Introduced API handlers for `ModelExecution` and `ModelExecutionStream` with support for both streaming and non-streaming requests.
- Included unit tests (`model_execution_test.go`) to validate execution logic and streaming responses.
- Introduced `applyRequestAfterAuthInterceptor` to modify requests after credential selection and before executor translation.
- Added `InterceptRequestAfterAuth` method across plugin adapters with corresponding tests for context validation.
- Enhanced format resolution logic (`requestToFormat`) to support additional providers and formats.
- Updated JavaScript handler to include a new `on_after_auth_request` hook for post-auth request handling.
- Refactored interceptor methods for clarity and better encapsulation of request/response lifecycles.
- Added `opts.OriginalRequest` handling to `applyResponseInterceptors` for improved context passing.
- Introduced new test `TestApplyJSBeforeRequestUsesReturnedCtxBody` to validate JavaScript interceptor behavior.
- Updated JavaScript-based handler to safely rewrite sensitive content and headers in requests.
- Refined interceptor logic to ensure consistent state retention across request processing.
- Implemented `RequestInterceptor`, `ResponseInterceptor`, and `StreamChunkInterceptor` capabilities.
- Added `sanitizePluginMetadata` to clean metadata for RPC compatibility.
- Enhanced interceptor chaining, error handling, and test coverage.
- Updated plugin configuration to register and dispatch interceptor methods.
- Introduced support for file-backed logging of API requests and responses to handle large payloads efficiently.
- Refactored `attachWebsocketLogSources` to `attachRequestLogSources` for broader request and response handling.
- Added new methods for appending request/response data to file-backed sources and updated existing logging workflows for compatibility.
- Improved cleanup and merge logic for file-backed sources during request processing.
- Updated tests to cover newly introduced file-backed logging functionality.
Address review feedback: parse each item's type/id/call_id once with
gjson.GetManyBytes and reuse it across the dedupe loops instead of
rescanning every item up to five times. Behavior is unchanged.
The input item ID dedupe added in #3620 keeps only the last occurrence of
each item id. When an upstream reuses the same item id across a re-sent or
repaired tool call (so two function_call items share an id but carry
different call_ids), the last-wins rule can drop the function_call whose
call_id still has a matching function_call_output. The upstream then rejects
the request with HTTP 400 "No tool call found for function call output with
call_id ...", breaking every subsequent turn over the Codex WebSocket path.
Make the dedupe orphan-aware: when several input items share an id, never
replace an item whose call_id is still referenced by a tool-call output with
one that is not. This keeps a single item per id (preserving the original
intent) while ensuring retained tool calls stay paired with their outputs.
Adds a regression test covering two function_call items that share an id
where only the earlier call_id has a surviving output.
- Updated session handling to replace `Session_id` and `Conversation_id` headers with new logic ensuring consistent use of `Cache.ID` and prompt keys.
- Restored `Session_id` as a priority extraction source for `ExtractSessionID`.
- Added tests to validate case-sensitive and case-insensitive headers, canonical account header usage, and session key preservation.
- Removed legacy support for deprecated `Conversation_id` header to clean up API.
- Introduced `grok-imagine-video-1.5-preview` as a new XAI video model.
- Updated handlers, registry, and validation logic to include support for the new model.
- Enhanced test coverage to validate integration and functionality of the preview model.
- Added `applyCodexIdentityConfuse*` functions for remapping request and response payloads and headers to enhance security.
- Updated WebSocket and HTTP logic to handle identity state transformations seamlessly.
- Introduced unit tests to verify remapping and restoration of identity-related fields.
- Added `sanitizeDownstreamWebsocketFallbackRequest` to clean `generate` from payload for HTTP fallback requests.
- Implemented tests to validate payload handling logic in WebSocket-to-HTTP transitions.
Closes: #3556
- Introduced `service_tier` metadata key to capture client-requested service tiers.
- Updated usage records, context propagation, and plugins to include service tier data.
- Added default handling logic for cases where `service_tier` is absent.
- Implemented tests for `service_tier` extraction, defaults, and updates across components.
- Updated WebSocket response repair tests to validate incremental preservation of response calls and outputs.
- Added new test cases for custom tool responses ensuring accurate handling of output cache and call cache.
- Refactored `repairResponsesWebsocketToolCallsWithCaches` to handle orphan outputs more consistently.
- Adjusted input filtering logic for clearer incremental repair behavior.
Closes: #3569
- Introduced `GPTImage2BaseModel` configuration for hosted image generation tools with validation for "gpt-" prefix.
- Added logic to dynamically resolve and apply the base model in Codex executor workflows.
- Enhanced server-sent events (SSE) implementation with keep-alive tickers and error events for stream reliability.
- Updated configuration file examples and internal documentation.
- Introduced `FileBodySource` to support large request log sections stored in temp files.
- Added file-backed support for WebSocket timeline and API WebSocket timeline logging.
- Updated `LogRequest` and middleware to integrate optional file-backed sources.
- Implemented clean-up mechanisms to manage temporary log files after processing.
- Added new reasoning levels: `none`, `minimal`, and `unsupported` to Codex model configurations.
- Introduced metadata sanitization and normalization for reasoning levels in API response.
- Extended unit tests to cover reasoning levels validation and metadata sanitation logic.
- Introduced OpenAI-compatible image model support in the API, enabling integration through image generation and editing endpoints.
- Added registry type for OpenAIImageModelType to classify and validate compatibility.
- Implemented request handling for OpenAI-compatible image models, including JSON and multipart formats.
- Enhanced executor methods to support OpenAI-compatible image streaming and non-streaming requests.
- Included tests to validate model registration, streaming behavior, and multipart payload formatting.
- Added APIs to store, retrieve, and clone upstream response headers in context for detailed logging.
- Updated `RecordAPIResponseMetadata`, `RecordAPIWebsocketHandshake`, and related methods to capture response headers.
- Extended `UsageReporter` to include response headers in published usage records.
- Enhanced payload tests to validate response headers' integrity and persistence.
- Refactored `usage.Record` to support optional `ResponseHeaders` field.
- Relocated Codex client model JSON and related logic from `openai` package to `registry` for better modularity.
- Updated references to use `registry.GetCodexClientModelsJSON()` in loading logic.
- Extended test cases to cover additional field removals (`upgrade`, `availability_nux`).
- Introduced Codex client models framework in `openai` package.
- Added JSON-based model definitions (`codex_client_models.json`) for Codex, including metadata, reasoning levels, and configuration options.
- Implemented handlers to load, clone, and build Codex client models with support for visibility overrides and metadata application.
- Enabled sorting and prioritization of models based on configuration or runtime criteria.
- Added utility functions for managing and validating model attributes.
- Introduced new xAI `grok-imagine-video` model for video generation with configurable options (e.g., duration, size, resolution).
- Implemented video-specific API endpoints (`/v1/videos`, `/v1/videos/generations`, `/v1/videos/edits`, `/v1/videos/extensions`), including request validation and model handling.
- Enhanced model registry with `xaiBuiltinVideoModelID` and metadata for video capabilities.
- Added unit tests to validate video model support, request structures, and API response handling.
- Extended `XAIExecutor` to integrate video generation and retrieval via runtime requests.
- Added new xAI Grok image models (`grok-imagine-image`, `grok-imagine-image-quality`) with high-fidelity and aspect ratio configurations.
- Extended `isSupportedImagesModel` logic to validate xAI models.
- Implemented API request builders for image generation/editing with customizable options (e.g., resolution, aspect ratio, response format).
- Enhanced `/v1/images` endpoints to handle xAI model capabilities, including response normalization and model-specific handlers.
- Updated unit tests to validate xAI model validation, request structure, and API integration.
- Introduced `ReadRequestBody` helper function to support decoding request bodies based on "Content-Encoding" (e.g., `zstd`).
- Replaced `c.GetRawData()` with `ReadRequestBody` across handlers to enable decoding.
- Added test case to validate `zstd` decoding for compact responses.
- Consolidated `homeRuntimeAuths` to store a map of session-scoped auth maps, replacing `homeRuntimeAuthSessions` and `homeRuntimeAuthRefs`.
- Adjusted session cleanup logic to directly remove session-scoped auths without reference counting.
- Added `GetExecutionSessionAuthByID` to retrieve auths scoped to a specific execution session.
- Updated tests to reflect the new session-scoped caching behavior.
