- 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.
Add OAuthModelAlias.ForceMapping to rewrite client-visible model fields in non-stream and SSE stream responses while leaving request-log upstream payloads unchanged.
- Wire config, watcher diff, and conductor execute/stream paths
- Rewrite force-mapped responses in Antigravity credits fallback paths
- Prevent buffered SSE chunks from being emitted by line-wise fallback
- Preserve thinking suffixes for same-base force-mapping aliases
- Cover codex, antigravity, kimi, and xai with live-derived fixtures and regression tests
- Document a conservative antigravity-only force-mapping example in config.example.yaml
Direct OpenAI image calls can inherit downstream User-Agent values from the Gin request context, which may trigger upstream Cloudflare 1010 blocks.
Clone inbound Codex headers for direct image requests and remove only User-Agent before applying defaults. This keeps Version, X-Codex-Turn-Metadata, X-Client-Request-Id, and Originator forwarding intact.
Expand direct image regression coverage for downstream identity headers and align edit endpoint expectations with /images/edits.
- Moved `reportHomePluginStatus` from `cmd/server` to `internal/home` as `ReportPluginStatus`.
- Updated interface and variable names for consistency.
- Adjusted imports and references in `main.go` and test files to align with the changes.
- Improved code structure for better modularity and reuse.
- Introduced `AuthKind` and `AuthSourceKind` methods for improved credential type and source classification.
- Replaced legacy fallback logic with normalized attribute-based handling in `AuthKind`.
- Consolidated metadata inspection for both API key and OAuth attributes.
- Updated calls to replace direct `AccountInfo` usage with `AuthKind` and `AuthSourceKind`.
- Enhanced unit tests to validate explicit and fallback credential resolution scenarios.
- Added NodeID field to HomeConfig for better identification.
- Updated ConfigFromJWT to populate NodeID from claims.
- Introduced new Redis keys for managing plugin status and tasks.
- Implemented RPushPluginStatus and GetPluginTasks methods in the client for handling plugin-related data.
- Enhanced Sync functionality to include detailed reporting on plugin installation and deletion tasks.
- Added error handling and reporting for plugin synchronization failures.
- Created tests for new plugin synchronization and management features.
- Improved the overall structure and readability of the plugin synchronization logic.
Add Grok-native reasoning replay for Claude-sourced xAI Responses requests. Replay state is scoped by model and session, normalized to reasoning/function_call/custom_tool_call items, and injected with the same tool-call alignment semantics used by Codex.
Include the minimal Grok encrypted_content validator needed on upstream/dev so replay cache entries cannot accept Codex/GPT, Gemini, or Claude signature shapes. Cache completed output items from HTTP, streaming, and WebSocket xAI responses.
Cover two-turn Claude replay, tool_result continuity, valid Grok cache storage, and rejection of Codex-shaped encrypted_content.
* Drop foreign encrypted_content before xAI Grok upstream
xAI Grok accepts provider-native encrypted_content as opaque replay state, but GPT/Codex reasoning signatures, Gemini thoughtSignature blobs, and Claude thinking signatures can all travel through OpenAI Responses-style reasoning.encrypted_content while remaining incompatible with xAI. Forwarding those foreign blobs to Grok causes upstream validation failures, especially when the foreign value is high-entropy enough to look ciphertext-like.
Add a Grok encrypted_content transport validator that stays conservative and shape-oriented:
- require unpadded standard base64 with no foreign characters
- reject obvious GPT/Codex gAAAA reasoning signatures before decode
- reject strict Claude thinking signatures in both official E-form and Antigravity R-form
- reject known Gemini thoughtSignature envelopes by reusing the central Gemini validator, covering Gemini 2.5 field-1 and Gemini 3.x field-2 shapes
- require decoded payloads to be long enough and high-entropy enough to look like native Grok ciphertext
- avoid decrypting, protobuf-parsing, or otherwise interpreting native Grok payloads on the hot path
Wire the validator into the xAI Responses request preparation path for reasoning and compaction input items. Invalid encrypted_content fields are deleted before the request is sent upstream, while the surrounding item is preserved and debug logging records only redacted metadata.
Extend coverage with native Grok corpus preservation, Gemini field-1/field-2 rejection, Claude E-form and R-form rejection, invalid-blob sanitizer tests, and compact/websocket replay preservation. The foreign-provider checks are deliberately narrow so high-entropy Grok blobs are not rejected merely because they look random.
* fix(xai): harden encrypted content sanitizer
- Added `ClaudeMessageSystemReminderText` to convert system content into user-readable reminder text.
- Updated translators (Antigravity, Gemini, Codex, OpenAI) to wrap `system` roles as reminders with `<system-reminder>` tags.
- Adjusted related test cases to validate reminder wrapping logic.
- Introduced `ClaudeCodeSessionID` resolution logic, preferring headers over payload metadata.
- Added `ClaudeCodePromptCache` to map sessions to stable prompt cache keys.
- Refactored existing logic to integrate `ClaudeCodePromptCache` for session-based handling.
- Included extensive unit tests to validate session ID extraction, cache reuse, and header prioritization.
- Added tests for `ConvertOpenAIRequestToAntigravity` and `ConvertOpenAIRequestToGemini` to verify skipping of empty text parts while maintaining non-null structure.
- Refactored part index logic to correctly handle placement of replay parts in `antigravity_reasoning_replay`.
- Introduced helper functions `antigravityExistingReplayPartPath` and `antigravityReplayPartWritePath` for consistent replay part path management.
- Added `RefreshAPIKeyModelAlias` for explicit alias table rebuilds.
- Introduced deferred rebuild support with `WithDeferredAPIKeyModelAliasRebuild` and context flag validation.
- Implemented `openAICompatibilityRegistrationCache` to streamline OpenAI compatibility model registrations.
- Updated executor and model registration workflows to utilize cached compatibility data, improving efficiency in batch operations.
- Adjusted max worker limits dynamically based on model categories.
Closes: #3953
- Extracted provider key determination into `apiKeyUsageProviderKey` for reuse and better readability.
- Updated `GetAPIKeyUsage` to utilize the new function.
- Added a new test case to validate compatibility grouping logic via `compat_name` attribute.
Closes: #3940#3941
- Added `rpcPluginError` to encapsulate plugin errors with HTTP status codes.
- Enhanced `decodeEnvelopeResult` to preserve and return detailed plugin errors with status codes.
- Introduced `isPluginErrorEnvelope` to identify plugin error envelopes.
- Updated plugin call logic in Unix and Windows loaders to differentiate plugin errors from system errors.
- Added unit tests to verify error handling and status code preservation.
- Added logic to expand single auth JSON payloads into multiple plugin virtual auth records.
- Updated related API endpoints such as `PatchAuthFileStatus` and `DeleteAuthFile` to handle plugin virtual auths with rollback mechanisms.
- Introduced `NormalizePluginOAuthCallbackProvider` and other normalization functions for better handling of OAuth callbacks.
- Enhanced tests to validate multi-auth parsing, rollback behavior, and API response consistency.
- 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.
- Updated `ConvertOpenAIRequestToGemini` to process `video_url` message types, extracting and embedding video metadata (MIME type and base64 data) into Gemini request parts.
- Added corresponding unit tests to validate `video_url` handling, ensuring proper extraction and data preservation.
Closes: #3920
- Added a new "max" level to model `thinking.levels` for enhanced customization.
- Removed deprecated Gemini 3 Pro (High/Low) models and associated fields from the registry.
- Simplified `thinking` attribute structure for `grok-build-0.1` and `grok-composer-2.5-fast` models.
Closes: #3901
- Updated `ConvertGeminiRequestToClaude`, `ConvertGeminiRequestToCodex`, and their respective response counterparts to include logic for retaining and using tool/call IDs when present from gateway-provided inputs.
- Enhanced pairing logic between function calls and responses to handle custom and auto-generated IDs consistently.
- Introduced tests validating ID preservation and proper behavior in both streaming and non-streaming flows.
Closes: #3878
- Updated `ConvertGeminiRequestToOpenAI` to consume `tool_call_id`s in FIFO order, ensuring consistent mapping between calls and responses.
- Added fallback logic for unmatched or extra function responses to generate unique `tool_call_id`s with a `call_` prefix.
- Introduced comprehensive unit tests to validate order enforcement, distinct ID assignment, and fallback behavior.
Closes: #3874
- Introduced a new `/reset-quota` API endpoint in the management handler to clear quota and cooldown state for auth records.
- Implemented `ResetQuota` method in the auth manager to handle runtime and registry state resets for affected models.
- Added tests to validate quota reset behavior, including proper state updates and registry consistency.
- Refactored utility functions to support deduplication and registered models handling in quota resets.
Closes: #3866
- Applied `CleanJSONSchemaForGemini` to ensure compatibility by removing unsupported fields and cleaning schema requirements.
- Added test cases to validate schema transformation, ensuring only necessary `required` fields are retained.
- Enhanced both request and response flows to consistently clean and sanitize tool parameter schemas.
Closes: #3863
- Replaced internal model-specific constants with exported defaults (`DefaultClaudeMaxInputTokens`, `DefaultClaudeMaxOutputTokens`).
- Refactored Claude model formatting to centralize schema application in `formatHomeClaudeModel`, with fields like `type`, `display_name`, and token limits.
- Added new unit tests for fallback behavior, metadata fields, and token handling in Claude and Gemini models.
- Removed deprecated test coverage for Amp provider model routes.
Closes: #3833
- Introduced `RebuildMidSystemMessage` field in config to move system messages into the top-level Claude system field.
- Updated executor to handle mid-system message rebuilding when enabled via config or auth attributes.
- Added unit tests to verify rebuilding behavior and default behavior when disabled.
- Updated configuration example and API handlers to support the new field.
Closes: #3792
- Introduced `SetOAuthModelAliasesAttribute` and `OAuthModelAliasesFromAttributes` for managing per-auth model aliases.
- Enhanced OAuth model resolution logic to prioritize per-auth aliases over global aliases.
- Updated metadata handling to extract and sanitize per-account model aliases.
- Added tests to validate alias precedence, empty attributes, and conflict scenarios.
Closes: #3764
- Introduced `BenchmarkConvertSystemRoleToDeveloperLargeInput` to evaluate performance on various input sizes and configurations.
- Improved `convertSystemRoleToDeveloper` logic to optimize JSON rebuilding and reduce unnecessary operations.
- Created helper `makeLargeResponsesInputForBenchmark` to generate test data for performance scenarios.
Closes: #3751
- Introduced `xaiRequiresIsolatedConversation` to enforce session ID generation for `grok-composer` models.
- Updated request preparation logic to handle isolated conversations by setting `prompt_cache_key` and `x-grok-conv-id`.
- Added unit tests with coverage for session isolation, stateless models, and explicit `prompt_cache_key` scenarios.
Closes: #3750
- Implemented `applyOpenAIResponsesTextFormatToGemini` to handle `json_object` and `json_schema` formats.
- Updated generation config to set appropriate `responseMimeType` and optional `responseJsonSchema`.
- Introduced unit tests to validate correct handling of `text.format` conversion scenarios.
Closes: #3721
- Added `normalizeCodexParallelToolCallsForTools` to conditionally remove `parallel_tool_calls` when `tools` are missing or empty.
- Integrated normalization into Codex executor workflows for improved request handling.
- Introduced unit tests to validate behavior across different tool scenarios.
Closes: #3903
- Replaced direct `strings.ToLower` usage with `util.OpenAICompatibleProviderKey` for generating provider keys.
- Updated auth and executor workflows to use namespaced keys for OpenAI-compatible providers.
- Adjusted tests to validate namespaced key handling, including new test cases for provider registration and execution logic.
- Added `OpenAICompatibleProviderKey` helper in `util` for consistent key transformations.
Closes: #3600
- Updated JSON schema handling to remove `$comment` and `enumDescriptions` fields during schema transformations.
- Adjusted test cases to validate the removal of these fields both at root and nested levels.
- Expanded unsupported schema keywords to include `$comment` and `enumDescriptions` for Gemini compatibility.
Closes: #3512
- Updated `ConvertCodexResponseToClaude` to delay emitting `function_call` start events until the `name` field is resolved.
- Introduced `pendingCodexFunctionCall` for buffering incomplete function calls.
- Added tests to ensure proper behavior for deferred starts, including argument buffering and finalization.
Closes: #3471
- Updated `ConvertOpenAIRequestToGemini` and `ConvertOpenAIRequestToCodex` to handle `input_audio`, retaining `data` and `format` fields.
- Added helper `openAIInputAudioMimeType` for determining MIME types from audio formats.
- Introduced unit tests to validate correct preservation of `input_audio` data and format.
Closes: #3447
- Enhanced `ConvertOpenAIResponsesRequestToOpenAIChatCompletions` to include `reasoning_content` in assistant and tool call messages.
- Introduced `collectOpenAIResponsesReasoningContent` for aggregating reasoning summaries.
- Added tests to validate reasoning attachment in various scenarios, including empty reasoning, tool calls, and reasoning followed by user messages.
Closes: #3397
- Updated handling in `ConvertOpenAIResponsesRequestToOpenAIChatCompletions` to retain `input_image` detail fields such as `image_url` and `detail`.
- Added `TestConvertOpenAIResponsesRequestToOpenAIChatCompletions_PreservesInputImageDetail` to verify preservation of image details during transformation.
Closes: #3385
- Updated `ConvertOpenAIResponsesRequestToOpenAIChatCompletions` to retain `tool_choice` with raw byte handling.
- Added `TestConvertOpenAIResponsesRequestToOpenAIChatCompletions_PreservesStructuredToolChoice` to ensure function and type fields are preserved in transformations.
Closes: #3384
- Introduced `CooldownStateStore` interface for managing independent cooldown state persistence.
- Implemented `FileCooldownStateStore` for storing cooldown states as per-auth `.cds` files with atomic writes and stale file cleanup.
- Enhanced `Manager` to support restoring state from `CooldownStateStore` and persisting state changes during auth updates.
- Updated tests to validate cooldown state saving, loading, concurrency handling, and error scenarios.
Closes: #3368
- Introduced `SetTransientErrorCooldownSeconds` to enable configurable cooldowns for transient errors (e.g., 408/500/502/503/504).
- Updated retry scheduling logic to use the new `nextTransientErrorRetryAfter` function.
- Modified config parsing to include `transient-error-cooldown-seconds` with support for disabling or defaulting to legacy behavior.
- Expanded tests to validate transient cooldown logic with various configurations and edge cases.
Closes: #3315
- Added `convertResponsesToolToOpenAIChatTools` and helper methods to handle namespace tools during request conversions.
- Enhanced response handling to restore namespace context for function calls using `applyResponsesFunctionCallNamespaceFields` and related utilities.
- Updated tests to validate namespace flattening, function call restoration, and non-stream response handling.
Closes: #3298
- Added logic in `ConvertOpenAIResponsesRequestToClaude` to exclude `apply_patch` custom tools.
- Introduced `isOpenAIResponsesApplyPatchCustomTool` helper function to identify and filter the tool.
- Added `TestConvertOpenAIResponsesRequestToClaude_DropsApplyPatchCustomTool` to validate the behavior.
Closes: #3243
- Refactored `ConfigReloadHook` to use `reloadConfigFromWatcher` for consistency.
- Added async `reloadConfigAfterManagementSaveAsync` to handle post-save operations.
- Introduced `ReloadConfigIfChanged` in watcher for manual trigger support.
- Enhanced config reload paths to separate auth synthesis from standard updates.
- Updated `applyConfigUpdate` logic to allow more granular reload behaviors.
Closes: #3235
- Updated error handling in `RPopAuth` to distinguish `auth_not_found` from transport errors.
- Added a new test, `TestPickNextViaHomeClassifiesTransportErrorsAsHomeUnavailable`, to validate correct error classification and retryable property.
- 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.
- Introduced `TestRequestCodexTokenCompletionKeepsConcurrentSessionPending` to validate proper handling of concurrent OAuth sessions.
- Refactored Codex OAuth logic to use `newCodexOAuthService` for improved testability.
Closes: #3171
- Added `TestConvertClaudeRequestToOpenAI_ToolSchemaAddsMissingObjectProperties` to validate automatic addition of missing `properties` in `object` schemas.
- Introduced `normalizeObjectSchemaProperties` to recursively ensure schemas of type `object` include an empty `properties` field if absent.
- Updated `ConvertClaudeRequestToOpenAI` to apply schema normalization for improved compatibility with OpenAI schema expectations.
Closes: #3165
- Updated Gemini, Gemini CLI, and Antigravity logic to delete `thinkingConfig` when `ModeNone` is set, `Budget=0`, and `Level` is empty.
- Adjusted tests to validate this behavior across multiple scenarios and models with zero-allowed configurations.
- Extended test cases for additional coverage of mixed-model behavior.
Closes: #3138
- Derive replay session from generateStableSessionID when sessionId is absent
- Merge cached thoughtSignature into existing functionCall by call id
- Allow filter to pass function_call_part when only signature replay is needed
- Include native functionCall id in replay dedupe keys
- Add unit tests for signature merge, stable scope, and parallel tool ids
Trim call_id once for matching-function-response checks; use args.Value()
in synthetic model functionCall insertion; guard functionResponse lookup
when call_id is empty.
When HOME replay restores a cached function_call_part and the request
already contains the matching functionResponse, insert a synthetic
role=model content with functionCall (and thoughtSignature) immediately
before that response content instead of writing into the same index.
Add regression tests for user/model functionResponse shapes.
Add executor-scoped replay cache aligned with Codex HOME replay:
Scope, observe SSE/non-stream responses, store normalized thought_signature
and function_call_part items, apply on the next streamGenerateContent
request, and invalidate on invalid signature responses.
Gemini/flash/agent models use HOME replay; native per-part signature
replay is not wired on upstream/dev. Wire non-stream and stream paths
in antigravity_executor and purge expired entries from signature_cache.
Includes unit tests and HOME-provider-replay documentation.
Add executor-scoped replay cache aligned with Codex HOME replay:
Scope, observe SSE/non-stream responses, store normalized thought_signature
and function_call_part items, apply on the next streamGenerateContent
request, and invalidate on invalid signature responses.
Gemini/flash/agent models use HOME replay; native per-part signature
replay is not wired on upstream/dev. Wire non-stream and stream paths
in antigravity_executor and purge expired entries from signature_cache.
Includes unit tests and HOME-provider-replay documentation.
- 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.
- Introduced tests for `ConvertOpenAIRequestToGemini`, `ConvertOpenAIResponsesRequestToGemini`, and related Claude functions to ensure trailing model-prefill turns are removed.
- Enhanced tool call ID handling with `util.SanitizeClaudeToolID` to standardize IDs in Claude-related conversions and tests.
- Updated logic in Gemini and Claude translators to handle edge cases for trailing assistant prefill and tool ID sanitization, ensuring compatibility across input variants.
Closes: #3113
- Added `TestConvertOpenAIChatCompletionsResponseToOpenAIResponses_CompletedOmitsTopLevelOutputText` to ensure `output_text` is excluded in streamed responses.
- Added `TestConvertOpenAIChatCompletionsResponseToOpenAIResponses_ToolCallCompletedOmitsTopLevelOutputText` to validate behavior during tool call completions.
- Introduced `TestConvertOpenAIChatCompletionsResponseToOpenAIResponsesNonStream_OmitsTopLevelOutputText` to confirm the omission of `output_text` in non-streamed responses.
- Expanded test coverage to ensure consistency with native OpenAI responses.
- Implemented `TestUploadAuthFile_PreservesPriorityAttributes` to ensure priority attributes and metadata are preserved during auth file uploads.
- Updated `UploadAuthFile` logic to utilize `SynthesizeAuthFile` for better handling of generated auth attributes and metadata.
Closes: #2924
- Refactored `ConvertOpenAIResponsesRequestToClaude` logic to align tool use with corresponding tool results.
- Introduced helper functions for appending and flushing pending reasoning and tool use messages.
- Expanded tests to validate message order and content consistency when processing tool calls and results.
- 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.
- Introduced `xaiNormalizeReasoningSummaryData` and related functions to normalize `reasoning_text` events into `reasoning_summary` shapes for standardization.
- Updated WebSocket and streaming logic to process normalized reasoning summary events correctly.
- Enhanced tests to validate normalization, order of events, and output structure in both stream and non-stream scenarios.
Use the agy CLI User-Agent family (antigravity/cli/{version} darwin/arm64)
on CPA macOS/arm64 hosts instead of the legacy hub-style antigravity/{version}
string. Resolve the cached version from the CLI auto-updater manifest
(darwin_arm64.json), then the GCS latest pointer, then antigravity-cli GCS
prefix listing, with fallback 1.0.8 when all sources fail.
Update AntigravityUserAgent helpers and executor default UA comment to match.
- Added `isCodexUsageLimitError` to detect and handle `usage_limit_reached` errors from Codex responses.
- Updated `newCodexStatusErr` to treat usage limit errors as HTTP 429 with proper `RetryAfter` handling.
- Enhanced test coverage to validate usage limit error handling, including reset time parsing and retry behavior.
Closes: #2886
- Changed default plugin `Enabled` state from `true` to `false` across configurations, runtime logic, and YAML defaults.
- Added helper function `enabledPluginConfigs` for generating plugin configs with `Enabled` set explicitly.
- Expanded unit tests in `pluginhost`, `config`, and `management` to validate behavior changes for disabled plugins, default settings, and skipped load scenarios.
- Refactored content block start/stop logic into `startCodexTextBlock` and `stopCodexTextBlock` for better readability and reusability.
- Updated logic to ensure proper handling of "output_text" block events to avoid ghost stop emissions.
- Added `TestConvertCodexResponseToClaude_StreamTextBeforeToolCallsDoesNotEmitGhostStop` to validate content block start/stop behavior in streamed responses.
- Introduced `applyResponsesFunctionCallNamespaceFields` to manage name and namespace settings in response items.
- Added `splitResponsesQualifiedFunctionCallFromRequest` for handling qualified names and matching them with namespaces.
- Updated response generation logic to preserve namespace and function call structure in multiple response pathways.
- Expanded unit tests to validate namespace and function call restoration in both stream and non-stream scenarios.
* fix(translator): emit Claude server tool blocks for Codex web_search_call streams
Map Codex Responses streaming web_search_call events to Claude SSE
server_tool_use and web_search_tool_result blocks, with deduplication
and a focused stream regression test.
* fix(translator): stabilize Codex web_search fallback tool_use IDs
Reuse the active fallback web_search tool_use ID across later stream
events so tool_result blocks stay paired when upstream omits item IDs.
This is defensive hardening; live Codex streams already provide ws_* IDs.
* fix(translator): emit Codex web_search blocks from populated items
Wait for output_item.done before emitting Claude web_search tool_use
and tool_result blocks, and avoid deduping early added/completed events
that arrive before action.query is available. Matches live Responses
stream ordering seen in local tmux verification.
* fix(translator): map Codex web_search_call items in non-stream Claude responses
Emit server_tool_use and web_search_tool_result blocks from completed
response.output web_search_call items, matching the streaming translator.
* fix(translator): keep non-stream web_search on end_turn and dedupe output items
Do not treat server web_search_call items as client tool_use for stop_reason.
Skip duplicate or query-less open_page web_search output items in non-stream
translation, matching spark live 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.
- Included CatAPI information in README files (EN, JA, CN) to acknowledge sponsorship.
- Added CatAPI logo and sign-up link with credit claim details.
- Updated project assets to include CatAPI logo.
* 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
Keep RPC streaming executor callback scopes alive until async streams close, detach nested host.model.execute_stream contexts from request cancellation, and clean up the stream bridge on stream completion.
- Added information about exclusive retail availability of Claude Max 200 and GPT Pro 200 premium accounts.
- Enhanced descriptions of VisionCoder's offerings in README files (EN, JA, CN).
- Introduced `disable-claude-cloak-mode` configuration to globally disable Claude cloak mode with credential-level overrides.
- Enhanced `getCloakConfigFromAuth` to support fallback to metadata for cloak settings.
- Updated cloak configuration precedence logic, integrating global, credential, and default modes.
- Updated config and watcher diff handling to include `disable-claude-cloak-mode`.
Closes: #2789
- Added `ConvertClaudeToolResultContent` to standardize Claude tool_result content, preserving JSON structure and splitting out base64-encoded images.
- Updated Gemini and Gemini-CLI translators to use the new utility for generating deterministic function responses and inline image parts.
- Added comprehensive test cases for content types and edge cases, ensuring correct handling of string, JSON, and image blocks.
Closes: #2781
- Added `sanitizeClaudeWebSearchDomains` to remove empty `allowed_domains` and `blocked_domains` fields for built-in web_search tools, addressing ambiguity errors from Anthropic.
- Integrated domain sanitization into the Claude message preparation pipeline.
- Added test cases to validate correct handling of empty and non-empty domain fields across various tool types.
Closes: #2681
- 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.
- Implemented helper methods `IsConfigAPIKeyAuth` and `toggleConfigAPIKeyExcludedAll` for managing config API key exclusions.
- Updated API request handling to support enabling/disabling config API key exclusion patterns.
- Added test coverage to validate exclusion toggling logic and persistence behavior.
- Refactored duplicate code for identifying config API key auth entries into reusable utilities.
- Added methods for managing and tracking WebSocket transcript state, including recording, prepending, and replacing transcript inputs.
- Implemented `executeCompactionTriggerFromWebsocketContext` to support compaction triggers using recorded transcript context.
- Enhanced upstream-downstream ID mapping with additional utilities and state synchronization.
- Expanded test coverage to validate transcript state management, compaction payload generation, and WebSocket response 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 `executeCompact` to handle non-streaming compact responses via the `/responses/compact` endpoint.
- Added `executeCompactionTriggerStream` for streaming responses triggered by `compaction_trigger`.
- Enhanced request preparation with `prepareResponsesRequestTo` for dynamic response formats.
- Updated logic to bypass streaming for `/responses/compact` and added fallback behaviors.
- Added comprehensive tests for compact response handling and event streaming validations.
- Introduced `auth_callbacks` for handling host authentication list, get, runtime, and save operations.
- Added extensive unit tests to validate functionality, including disk fallback and runtime-specific cases.
- Created example implementation in Go to demonstrate host callback integrations.
- Updated Antigravity Credits fallback to handle KV store unavailability as a service error.
- Enhanced signature caching mechanisms with request-time KV access and sliding expiration.
- Added and improved tests for KV client interactions, including error handling and expiration behaviors.
- Introduced `CacheSignatureBestEffort` for non-critical signature caching and clarified function flows with required context.
- Ensured consistent error reporting for missing or unavailable KV stores in various scenarios.
- Replaced direct `homekv` calls with injectable KV client interfaces for `antigravity` and `codex_reasoning_replay` modules.
- Improved error reporting and handling for KV operations, including `KVGet`, `KVSet`, `KVDel`, and `KVExpire`.
- Introduced dedicated fake KV clients for expanded and granular test coverage.
- Added new unit tests to validate KV client behaviors and error scenarios, ensuring robustness and sliding expiration functionality.
/v1/models is shared by the OpenAI and Anthropic surfaces and was
dispatched to the Claude format only for claude-cli User-Agents, so
generic Anthropic API clients received the OpenAI format. Distinguish
Anthropic requests by the Anthropic-Version header (sent by every
Anthropic client, never by OpenAI/Codex clients) in addition to the
existing claude-cli check, in both unifiedModelsHandler and
handleHomeModels. Additive and non-breaking for existing clients.
Anthropic's List Models schema types created_at as an RFC 3339 datetime
string, but the Claude case of convertModelToMap emitted model.Created
as a Unix-timestamp integer. Format it with time.RFC3339 so the listing
matches the documented schema.
Anthropic's List Models response (GET /v1/models) defines each model object
with id, display_name, max_input_tokens, max_tokens, created_at and type.
The Claude case of convertModelToMap emitted an incomplete object: it dropped
max_input_tokens and max_tokens entirely and omitted display_name whenever it
was unset, so the Anthropic-compatible listing did not match the schema it
emulates.
Emit max_input_tokens from ContextLength and max_tokens from
MaxCompletionTokens (the same registry metadata the Gemini case already
surfaces as inputTokenLimit/outputTokenLimit), with fallbacks, and always
emit display_name, falling back to the model ID.
Adds a fourth value for the disable-image-generation setting:
- false: inject image_generation (unchanged)
- true: strip everywhere + 404 on /v1/images/* (unchanged)
- chat: strip on non-images endpoints, keep /v1/images/* (unchanged)
- passthrough: never inject and never strip on non-images endpoints
(the client payload is forwarded unchanged); behaves like
"chat" on /v1/images/* endpoints.
image_generation injection (codex executors) is already gated on the Off
mode, and the /v1/images/* 404 gate is already gated on the All mode, so
passthrough only required a change to the payload strip logic in
payload_helpers.go, now expressed via shouldStripImageGeneration().
Closes#3831
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- Updated `ConvertClaudeRequestToOpenAI` to move mid-conversation `system` messages to the initial system content.
- Added a new test case `TestConvertClaudeRequestToOpenAI_MidConversationSystemMessagesMoveToInitialSystem` to validate functionality.
- Refactored logic for appending system message content for improved readability and maintainability.
Closes: #3815
Add kimi-k2.7-code to the model registry with:
- 262K context length, 65K max completion tokens
- Thinking support (dynamic, 1024-32000 budget)
- zero_allowed=false (K2.7 Code does not support non-thinking mode)
Closes#3826
Cross-platform (Tauri) port of Quotio (Windows / macOS / Linux) that manages an AI account pool through CLIProxyAPI. Added to README.md, README_CN.md and README_JA.md.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Add a native Antigravity WebSearch path for Claude typed WebSearch requests.
Detect Claude Messages requests whose tools are only typed WebSearch tools
(web_search_20250305 / web_search_20260209), and convert them into an
Antigravity requestType=web_search payload instead of sending the request
through the normal tool-calling path.
Preserve the user's requested model. The native path is enabled only when that
Antigravity model is known to support Google Search. Capability data fetched
from Antigravity model info is used only as an enhancement to the local model
registry, not as a replacement for the existing registry fallback behavior.
Unsupported models keep the existing Antigravity request behavior and are not
silently rerouted to another web-search-capable model.
Translate Claude WebSearch request options to the verified Antigravity
googleSearch shape:
- max_uses -> googleSearch.enhancedContent.imageSearch.maxResultCount
- allowed_domains -> googleSearch.includedDomains
Leave blocked_domains and user_location unmapped because the Antigravity
googleSearch request shape has no verified equivalent for them. This avoids
sending speculative fields or pretending unsupported Claude WebSearch options
are enforced upstream.
Translate Antigravity web-search responses back into Claude-compatible output:
server_tool_use blocks, web_search_tool_result blocks, cited text blocks,
grounding URLs, and usage-compatible stream/non-stream responses.
Cover the behavior with tests for request conversion, response conversion,
grounding URL resolution, domain filter mapping, fetched capability hints,
excluded-model handling, and unsupported-model behavior.
The latest release is now the source of truth for plugin versions, so
the registry version only serves as a display fallback. Validate its
format only when present.
List entries now show each plugin's latest release version and compute
update availability against it, falling back to the registry version
when the lookup fails. Lookups run concurrently and are cached per
repository with a short failure TTL to respect API rate limits.
Replace the tag-pinned release lookup with the repository latest
release endpoint. Derive the plugin version from the release tag,
validate it, and attach an optional token to API requests to raise
the rate limit.
- Removed the entire `jshandler` plugin implementation, including `abi.go`, `engine.go`, `config.go`, and associated test files.
- Deleted the `scripts` directory containing JavaScript examples.
- Cleaned up the `go.mod` and `go.sum` dependencies related to `jshandler`.
- Ensured redundant code and files associated with the removed plugin are purged from the repository.
- Introduced `htmlsanitize` package for escaping HTML and handling JSON body sanitization to prevent XSS vulnerabilities.
- Integrated sanitization functions into plugin store, plugin host, and API management handlers to ensure all user-facing content is escaped.
- Added unit tests to verify proper escaping of HTML strings, JSON bodies, and nested data structures.
- Updated existing management and plugin-related tests to validate sanitization implementations.
- Introduced logic to handle plugin unloading during updates to prevent conflicts with loaded plugins.
- Preserved existing plugin configurations during updates, ensuring seamless transitions and maintaining custom fields.
- Added support for reloading the configuration after management saves changes.
- Enhanced unit tests to validate unloading, configuration preservation, and reloading behaviors.
- Introduced `SupportPluginHeaderValue` to indicate CGO build status (`1` for enabled, `0` for disabled).
- Updated API response headers in `handler.go` to include "X-CPA-SUPPORT-PLUGIN".
- Added unit tests to verify proper header behavior under varying conditions.
- Replaced Chinese test strings in `claude_openai-responses_response_test.go` with English equivalents (e.g., "**对比竞品**" -> "**Compare competitors**").
- Updated comments in `config.example.yaml` to English to align with project language standards.
- Introduced `claudeResponsesUsageTokens` to manage detailed token statistics, including input, output, cache read, and cache creation tokens.
- Updated aggregation logic to include cached tokens in total usage calculations.
- Refactored usage processing to simplify token merging and ensure consistent handling across streaming and non-streaming responses.
- Added unit tests (`TestConvertClaudeResponseToOpenAIResponses_ReportsCacheTokens`) to verify correct cache token inclusion in usage metrics.
Closes: #3807
- 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.
- Implemented logic to aggregate text blocks until `message_stop` for improved consistency.
- Introduced support for message annotations like `citations_delta` in content responses.
- Added methods (`finalizeAssistantMessage`, `appendMessageAnnotation`) to handle message grouping and annotation appending cleanly.
- Updated unit tests to verify message aggregation, annotation handling, and suppression of unwanted native events.
Closes: #3801
- Added tests (`TestCliFinishReasonOnlyOnFinalChunk`, `TestGeminiFinishReasonOnlyOnFinalChunk`) to validate correct `finish_reason` and `native_finish_reason` assignment.
- Refactored Gemini and CLI translators to track `SawToolCall` and `UpstreamFinishReason` for accurate final-chunk determination.
- Improved response parsing logic to align with upstream metadata and provide consistent reasoning on chunk outputs.
- 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.
- Updated `README.md`, `README_JA.md`, and `README_CN.md` to include Unity2.ai sponsorship information.
- Highlighted features, benefits, and registration perks offered by Unity2.ai.
- Added Unity2.ai logo (`unity2.jpg`) to the project assets.
- Added new model `Claude Fable 5` to `models.json` with enhanced reasoning and long-horizon capabilities.
- Included detailed parameters such as context length, max completion tokens, and thinking level configurations.
- Added `resources` field in `management.register` for defining browser-accessible resources.
- Updated examples and documentation to reflect resource-based paths under `/v0/resource/plugins/<pluginID>/...`.
- Replaced legacy `GET` menu routes with resource-based implementations for consistent plugin behavior.
- Enhanced request handling for resource paths, including proper response headers and streamlined test coverage.
- Added `HostCallbackID` to request, response, and stream chunk interceptors for enhanced context tracking.
- Updated JavaScript engine to support custom console logging with `HostCallbackID` forwarding.
- Introduced tests verifying proper integration of `HostCallbackID` in all interceptor flows and engine logging.
- Enhanced logging and error handling for consistent callback-related logic implementation.
- Removed `pluginDelegateRoundRobin` and related logic to streamline plugin scheduler management.
- Consolidated scheduler strategies under `builtinSchedulerStrategy` with `pickViaBuiltinScheduler`.
- Introduced new methods `pickSingleWithStrategy` and `pickMixedWithStrategy` for strategy-specific behavior.
- Updated tests to reflect changes, including added coverage for round-robin and mixed-provider scenarios.
- Improved maintainability by unifying scheduling logic and reducing redundant structures.
- 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.
- Added `pluginSchedulerState` interface with `HasScheduler` method for improved plugin scheduler state checks.
- Updated `Manager.hasPluginScheduler` to handle `HasScheduler` logic.
- Implemented and tested fast-path handling for inactive plugin schedulers, including mixed provider scenarios.
- Expanded unit test coverage to ensure correct behavior in various scheduler states.
- Added a Go scheduler plugin demonstrating CLIProxyAPI capabilities, such as `plugin.register`, `plugin.reconfigure`, and `scheduler.pick`.
- Implemented methods for plugin configuration, built-in scheduler delegation (`fill-first`, `round-robin`), dynamic candidate selection, and error handling.
- Extended `pluginhost` with scheduler handling, candidate normalization, and fallback mechanisms.
- Included examples, tests, and detailed documentation for scheduler usage and implementation.
- Introduced `FrontendAuthProviderExclusive` capability to restrict authentication to a single selected provider.
- Added `SetExclusiveProvider` and `ClearExclusiveProvider` methods for managing exclusive providers in the access registry.
- Updated `pluginhost` to prioritize and enforce exclusive providers based on plugin priority and ID.
- Enhanced RPC capabilities schema to include `FrontendAuthProviderExclusive` field.
- Added example plugin and tests for exclusive frontend auth behavior.
- Implemented `RequestInterceptor`, `ResponseInterceptor`, and `StreamChunkInterceptor` using embedded JavaScript.
- Added support for configuring script paths, built-in script resolution, and safe execution.
- Introduced ABI lifecycle management, plugin registration, and execution monitoring.
- Enhanced with extensive test coverage for both plugin behavior and configuration logic.
- 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.
Apply review feedback on codexExtractImageResults: preallocate the results
slice to its known maximum capacity to avoid growth reallocations, and guard
the itemsByIndex index-build/sort with a length check so no empty slice is
allocated or sorted when only the fallback items are present.
The OpenAI images path (/v1/images/*) previously called patchCodexCompletedOutput
to concatenate collected output_item.done items back into the completed event and
then re-parsed that rebuilt JSON to pull out the image results. For multi-megabyte
base64 image payloads this produced two extra full-size copies per request (the
concatenated output array plus the rebuilt completed event), inflating peak memory
under concurrent image generation.
Add codexExtractImageResults, which extracts image_generation_call results directly
from either the completed event's response.output or the collected items, without
the concatenate-and-reparse step. Semantics are preserved: completed output is
preferred and collected items are used only when it is empty, matching the original
patchCodexCompletedOutput behaviour. patchCodexCompletedOutput remains in use by the
text/responses path, which still forwards the patched event downstream.
Adds unit tests covering the completed-output path, the ordered fallback to
collected items, output preference, fallback list, and the wrong-event-type guard.
- Updated `README.md`, `README_JA.md`, and `README_CN.md` with information about RunAPI as a sponsor.
- Included descriptions of RunAPI's features, benefits, and discounts.
- Added `runapi.png` asset to the project.
- Introduced `build-linux-glibc` and `build-linux-no-plugin` workflows for creating Linux release assets with and without plugin support.
- Enhanced release workflow with dynamic update of release notes for Linux assets.
- Improved checksum generation and validation for Linux binaries.
- Updated workflow matrix for better platform coverage and asset handling.
- Added support for processing `signature-only` chunks without opening empty text blocks.
- Refactored chunk handling logic to include `signature_delta` events for improved fidelity.
- Unified logic for emitting final message states, including `message_delta` and `message_stop`, to ensure consistent behavior across different scenarios.
- Enhanced caching mechanism for thought signatures.
- Updated `Dockerfile` base images from `golang:1.26-alpine` and `alpine:3.23` to `golang:1.26-bookworm` and `debian:bookworm`.
- Replaced `apk` with `apt-get` for dependency installation.
- Added `buildvcs=false` flag to Go build command for enhanced reproducibility.
- Introduced a Go-based plugin `codex-service-tier` for normalizing requests to Codex.
- Added functionality to set `service_tier` to `priority` for `gpt-5.5` requests when `fast` mode is enabled.
- Enhanced plugin capabilities with lifecycle configuration and request transformation support.
- Updated documentation with configuration examples and usage instructions in multiple languages.
- Removed redundant `vm_arch` matrix configuration.
- Replaced manual FreeBSD VM setup with `go-cross/cgo-actions` for cross-compilation.
- Improved caching for Go modules and build artifacts.
- Simplified metadata generation and environment variable handling.
- Streamlined binary packaging and archive creation steps.
- Added `GH_REPO` environment variable for repository reference in the workflow.
- Changed exit condition when no release archives are found to avoid workflow failure.
- Added `prepare-release` job for creating/updating GitHub releases.
- Automated asset checksum generation for hosted and FreeBSD builds.
- Introduced release asset uploads, including archives and checksums.
- Refactored release process to include final checksum publishing.
- Deleted `.goreleaser.yml` configuration and migrated functionality to GitHub Actions workflows.
- Replaced `goreleaser` with matrix-based build and archiving process for improved flexibility.
- Enhanced platform and architecture-specific builds, including FreeBSD support and custom runners.
- Streamlined artifact upload, checksum generation, and release publishing.
- Updated `golang.org/x/sys` to v0.38.0 in `go.mod` and replaced `syscall` with `windows` package for memory allocation in `loader_windows.go`.
- Improved cross-compilation in `.goreleaser.yml` using Zig-based toolchains for better platform support.
- Changed GitHub Actions workflow to use macOS runners and added Zig toolchain setup.
- Removed `examples/plugin/main.go` and `internal/pluginhost/loader_plugin.go` after migrating to a more modular system.
- Introduced `streamBridge` in `internal/pluginhost/stream_bridge.go` for efficient stream handling and communication.
- Added examples of `thinking` plugins written in both Rust and Go under `examples/plugin/thinking`.
- Enhanced test coverage for plugin host system changes, including stream chunk translation and thinking logic.
- Improved API compatibility and ensured backward-compatible upgrades for plugin execution.
- Implemented command-line flag registration and execution for plugins with priority-based conflict resolution.
- Enabled plugin-owned command-line flag execution and persistence of plugin-auth data.
- Added new `Host` methods to support command-line capabilities, including flag normalization, validation, and execution state management.
- Introduced unit tests to ensure coverage for command-line plugin functionality, including auth data persistence.
- Updated configs to normalize plugins during initialization.
- 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.
- Removed sections on Amp CLI integration and related management tools from all READMEs (`README.md`, `README_JA.md`, and `README_CN.md`).
- Updated project descriptions for relevance and focus.
- Introduced `publishErrorEvent` in `Manager` to publish error events to Redis.
- Implemented error event structure to capture authentication errors with detailed metadata.
- Added test cases for error event publishing, subscription, and Redis protocol handling.
- Enhanced error and usage queue handling with `SubscribeErrors` and `EnqueueError`.
Closes: #3701
- Introduced `Manager.Remove` to delete runtime auth and unschedule associated tasks.
- Updated handler logic to directly remove auth instead of marking as disabled.
- Added tests to validate removal, unscheduling, and runtime state handling.
- Added a test to validate `skipPersist` behavior during registration.
- Enhanced `Remove` test to verify auto-refresh loop state before and after removal.
Closes: #3690
Introduce Cloudflare challenge detection for 403 errors in the Auth
Manager. Apply a progressive rate-limiting cooldown ladder using the
existing BackoffLevel field instead of a hard 30-minute credentials
suspension. This ensures challenged requests fall through to subsequent
credentials and recover exponentially.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- Updated `NewUtlsHTTPClient` to support context-aware RoundTrippers for protected hosts (e.g., Cloudflare bypass).
- Replaced `anthropicHosts` with `utlsProtectedHosts` to generalize host handling logic.
- Added unit test to validate context-based RoundTripper behavior.
- Replaced `NewProxyAwareHTTPClient` with `NewUtlsHTTPClient` in relevant executors for improved TLS fingerprinting.
Closes: #3680
- Updated links and descriptions for `CPA-Manager-Plus`, replacing outdated `CPA-Manager` references.
- Added `Panopticon`, a multi-agent orchestration tool, to the project list.
Parse Home refresh auth envelopes so refreshed access tokens are used instead of returning missing access token.
Stop retrying when Home dispatch returns an auth that already failed within the same request.
- Cleaned up outdated GPT 5.2 and GPT 5.3 Codex model configurations from `models.json`.
- Simplified registry by removing unused model references across all tiers (`codex-team`, `codex-plus`, `codex-pro`).
- Introduced `grok-composer-2.5-fast` as a new XAI model.
- Updated registry to include display name, description, and configuration details for the new model.
- Enabled support for the model in the Responses API.
- Introduced `NotifyUsageRefresh` in `redisqueue` to notify subscribers of usage refresh events.
- Enhanced `Watcher` logic to trigger usage refresh notifications on client changes (add/update/remove).
- Updated tests to validate proper broadcast of usage refresh messages to subscribers.
- Added support for initial `support_refresh` payload upon subscription initialization.
- Replaced `NewUsageReporter` with `NewExecutorUsageReporter` to include executor type in usage records.
- Updated all executors to use the new reporter implementation.
- Extended `UsageReporter` to track and publish executor type.
- Added tests to validate proper executor type recording and handling.
- Enhanced RedisQueue plugin and payload schema with executor type support.
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.
- Modified `applyCodexIdentityConfuse*` functions to include `turn_id` and `window_id` in metadata transformations.
- Updated test cases to validate the inclusion and restoration of these fields.
- Removed deprecated `Conversation_id` header support and related logic for cleaner implementation.
When Claude Code sends a stop-hook evaluator request (or any request
without tools), the payload includes "tools": [] (empty array). The
claude->codex translator unconditionally emits tools: [] + tool_choice:
"auto" + parallel_tool_calls: true into the Codex Responses shape.
When that payload is routed to xAI, the upstream rejects with HTTP 400:
"A tool_choice was set on the request but no tools were specified."
Fix entirely in the xAI executor (translator package is policy-locked):
add normalizeXAIToolChoiceForTools() after normalizeXAITools() to drop
tool_choice and parallel_tool_calls whenever tools end up absent or
empty (covering both the empty-from-source case and the
all-filtered-out case where every tool was an unsupported type such as
tool_search or image_generation).
Per code-review feedback: always remove parallel_tool_calls when tools
are missing (not gated on tool_choice presence) and existence-check
each key before sjson delete to avoid unnecessary JSON parse/copy.
Verification:
- go build -o test-output ./cmd/server
- go test ./internal/runtime/executor/... -count=1
- 5 new regression tests cover empty / missing / present / orphaned
parallel_tool_calls / no-op-when-both-absent.
- 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.
- Introduced `translateCodexRequestPair` to simplify and reuse translation logic for handling original and modified payloads.
- Updated relevant methods to use the new function.
- Added unit tests to cover payload reuse and differentiation scenarios.
- 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 `TotalTokens` calculation to account for `CacheReadTokens` and `CacheCreationTokens`.
- Added tests to validate accurate token aggregation and fallback behavior for `CachedTokens`.
- Added `assertFileBodySourceCleaned` helper to streamline cleanup validations in tests.
- Introduced handling to recreate missing directories during file source operations.
- Enhanced tests to verify behavior after manual directory removal, ensuring robustness.
- Fixed edge cases in log file merging when parts are missing.
- Introduced Time-To-First-Token (TTFT) measurement and reporting across major executors.
- Added TTFT calculation to `UsageReporter`, including support for HTTP clients and WebSocket communication.
- Updated tests to validate TTFT tracking in streamed and non-streamed scenarios.
- Ensured integration with `usage` plugin and augmented usage records with TTFT data.
- Introduced `SetTranslatedReasoningEffort` method in `UsageReporter` to capture and log reasoning efforts from translated payloads.
- Updated executors to incorporate the new reporting functionality for handling reasoning efforts across various providers.
- Enhanced logging for thinking level extraction with new helper function `ExtractTranslatedReasoningEffort`.
- Introduced support for processing `encrypted_content` reasoning signatures in request and response translations.
- Updated `ConvertOpenAIResponsesRequestToClaude` and `ConvertClaudeResponseToOpenAIResponses` to handle reasoning signatures and summaries.
- Added tests to validate signature preservation and correct reasoning content transformation in both streaming and non-streaming scenarios.
- Refactored processing logic to ensure reasoning content flushing before user messages.
- 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 parsing logic to handle `websockets` field in auth files.
- Extended `PatchAuthFileFields` to update `websockets` and arbitrary nested metadata fields.
- Added tests to validate `websockets` parsing, updating, and persistence.
- 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.
- Included `RequestID` field in `homeRequestLogPayload` for better log categorization.
- Updated `forwardRequestLogToHome` and related components to handle `RequestID`.
- Added new test cases to validate `RequestID` propagation in streaming requests.
- Introduced `fetch_codex_models` CLI command to fetch and save Codex model catalogs in JSON format.
- Supports configuration via flags or `config.yaml` for flexible setup.
- Enhanced `fetch_antigravity_models` with `config.yaml` support and improved auth directory resolution logic.
- Acknowledged APIKEY.FUN as a sponsor with details on their services and exclusive project-specific benefits.
- Updated Japanese (README_JA.md), Chinese (README_CN.md), and English (README.md) documentation.
- Added new sponsorship image (`assets/apikey.png`).
- Added support for advanced RESP commands (`AUTH`, `SUBSCRIBE`, `RPOP`, `LPOP`) with extended functionality.
- Implemented queue operations for usage events via `RPOP` and `LPOP` commands.
- Introduced subscription handling with new Pub/Sub message features and error handling improvements.
- Updated Redis connection logic to enforce authentication requirements and validate inputs.
- Expanded related unit tests to cover new scenarios and edge cases.
- Updated `ConvertClaudeRequestToGemini` to ignore empty `text` entries during processing.
- Added unit tests to ensure empty `text` parts are skipped correctly.
Closes: #3485
- Registered `gemini-3.5-flash` model with dynamic thinking levels and extended token limits.
- Supports multiple generation methods, including cached and batch content creation.
- Added new model `gemini-3.5-flash` to the registry with enhanced intelligence and speed capabilities.
- Supports extended thinking levels (`minimal`, `low`, `medium`, `high`) and dynamic adjustments.
- Expanded generation methods, including content creation and token counting.
- 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.
- Registered new models: `gemini-3-flash-agent` and `gemini-3.5-flash-low` with detailed specifications.
- Includes support for dynamic thinking levels and extended context capabilities.
- Removed obsolete Redis protocol test cases and helper functions that were no longer relevant due to recent architecture changes.
- Streamlined remaining test files to align with updated Redis handling and connection management logic.
- Introduced `homeRedisOperationTimeout` and `homeSubscriptionReceiveTimeout` constants for configurable timeouts.
- Enhanced Redis connection options with operation timeout settings and failover mechanisms.
- Implemented subscription failover logic on heartbeat timeouts to improve resilience.
- Updated message handling to support additional Redis event types, including Pong and Subscription.
- Updated text formatting with bold emphasis for consistent branding.
- Refined wording for VisionCoder's promotion details in Chinese, Japanese, and English README.
- Added support for `ClusterID`, `CAFingerprint`, and `EnrollmentSecret` in Home JWT claims.
- Implemented CA fingerprint normalization and verification for PEM and file-based certificates.
- Improved certificate request validation and error handling.
- Updated server-side logic to include `EnrollmentSecret` in certificate requests.
- 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.
- Implemented `xAI` provider for thinking configurations with support for reasoning.effort levels.
- Registered `xAI` in available providers and updated relevant APIs for compatibility.
- Added unit tests for `xAI` provider functionality, including fallback logic for unsupported levels.
- Integrated `xAI` with executor handling and ensured conformance with OpenAI-compatible standards.
- 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.
- Introduced `-home-jwt` flag and `HOME_JWT` environment variable to provide JWT for mTLS certificate generation.
- Added new APIs to handle certificate requests, validate JWT claims, and manage local certificate files.
- Updated Home TLS configuration to support client certificates, keys, and dynamic server name resolution.
- Simplified test server initialization by removing `newTestServerWithOptions`.
- Deleted `TestManagementLocalPasswordRejectsSpoofedForwardedFor` as spoofed IP handling is no longer applicable.
- Removed trusted proxy configuration from Gin engine setup.
Address review feedback: move HOME_ADDR/HOME_PASSWORD lookup after
godotenv.Load() so .env files work, and use the lookupEnv helper
for case-insensitive key support consistent with PGSTORE_* etc.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Allow configuring the home control plane connection via environment
variables HOME_ADDR and HOME_PASSWORD as an alternative to the --home
and --home-password command-line flags. This enables Docker Swarm stack
deployments without needing docker service update --args.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- Introduced `newTestServerWithOptions` to customize server initialization in tests.
- Added `TestManagementLocalPasswordRejectsSpoofedForwardedFor` to validate security against spoofed `X-Forwarded-For` headers.
- Enabled default WebSocket authentication (`ws-auth`) in `config.example.yaml`.
- Disabled trusted proxy headers in Gin engine with appropriate logging to enhance security.
- Updated variable, function, and struct names from `FormProtocol` to `FromProtocol` for clarity.
- Adjusted related payload matching and normalization logic.
- Updated tests and examples to align with the new naming convention.
- Introduced `resolvePayloadRulePaths` function to dynamically resolve rule paths supporting array queries and complex logic.
- Updated payload processing logic (`apply defaults`, `overrides`, `filters`) to handle resolved paths for better flexibility.
- Added helper functions for path parsing, query matching, and logical resolution to improve modularity and reusability.
- Introduced payload condition match logic, including `match`, `not-match`, `exist`, and `not-exist` rules in `PayloadConfig`.
- Enhanced `payloadModelRulesMatch` function to support conditional checks at various levels.
- Added helper methods for evaluating JSON path conditions and values.
- Updated tests to validate new conditional rules against different payload scenarios.
- Added `namespace` tool type support, enabling nested tools to be normalized and moved to the top level.
- Refactored tool normalization logic into `normalizeXAITool` for reusability and clarity.
- Updated `xai_executor` test cases to validate namespace tool handling and nested tool normalization.
- Added `namespace` tool type support, enabling nested tools to be normalized and moved to the top level.
- Refactored tool normalization logic into `normalizeXAITool` for reusability and clarity.
- Updated `xai_executor` test cases to validate namespace tool handling and nested tool normalization.
- 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`).
- Added `normalizeXAIInputReasoningItems` to clean up `input` reasoning items, removing null `content` and `encrypted_content` fields.
- Updated `xai_executor` test cases to validate input normalization and reasoning item handling.
- 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.
- Implemented xAI OAuth2 integration with PKCE (Proof Key for Code Exchange) support.
- Added logic for token exchange, refresh, and persistent storage in JSON format.
- Created `xai` package with helpers for OAuth discovery, API token handling, and URL building.
- Introduced `XAIExecutor` for integrating xAI credentials into runtime HTTP requests.
- Added unit tests to validate OAuth flow, token persistence, and endpoint validation.
- Added `parseClusterNodesPayload` for streamlined cluster node parsing.
- Introduced `handleSubscriptionPayload` to handle Redis channel payloads, including updates for the new `cluster` channel.
- Updated subscription logic to process and apply cluster node updates seamlessly.
- Added `zstd` decoding support in request logging, including helper functions to process `Content-Encoding` headers.
- Enhanced config diff logic to compare payload-specific rules and track changes in payload configurations.
- Added tests to validate `zstd` decoding and payload diff behavior.
- 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.
- Updated `maybeRunGC` to accept `repoDir` instead of `repo`.
- Moved garbage collection trigger to occur after the push step for improved reliability.
- Added a test to validate the sequence of push and GC operations.
Closes: #3373
- Added Redis Pub/Sub capability to broadcast usage updates to subscribed clients.
- Enhanced `redisqueue` with subscriber management and message broadcasting.
- Updated tests to validate Pub/Sub message handling, subscription behavior, and fallback to the queue after unsubscribing.
- Integrated `project_id` parsing into auth-files logic to include project identifiers in metadata.
Closes: #3027
- Added Redis Pub/Sub capability to broadcast usage updates to subscribed clients.
- Enhanced `redisqueue` with subscriber management and message broadcasting.
- Updated tests to validate Pub/Sub message handling, subscription behavior, and fallback to the queue after unsubscribing.
- Integrated `project_id` parsing into auth-files logic to include project identifiers in metadata.
- Added logic to set `auth.Disabled` and update `auth.Status` to `StatusDisabled` when `disabled` metadata is provided and true.
- Updated `objectstore`, `gitstore`, and `postgresstore` implementations to handle the new metadata attribute.
Closes: #2651
- Introduced `geminiModelsHandler` to dynamically route Gemini model requests based on home configuration.
- Added `handleHomeGeminiModels` and `loadHomeModelEntries` to support home-specific Gemini model handling.
- Refactored and centralized error handling logic for improved maintainability.
- Enhanced response formatting with `formatHomeGeminiModels` for consistent output structure.
- Added `isUnauthorizedError` and `hasUnauthorizedAuthFailure` to classify and handle unauthorized errors.
- Introduced `refreshErrorFromError` to map errors to standardized unauthorized responses.
- Modified refresh logic to stop auto-refresh retries for unauthorized errors.
- Updated tests to verify unauthorized error handling and refresh retry prevention.
- Introduced `CacheReadTokens` and `CacheCreationTokens` to enhance token breakdown.
- Refactored `parseClaudeUsageNode` for cleaner and reusable logic.
- Adjusted helpers and updated token calculations to align with the new fields.
Clear the 10s read deadline before calling handleRedisConnection so
that authenticated Redis clients are not disconnected by an i/o timeout
after 10 seconds of idle time. HTTP paths already clear the deadline
after routing.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- Introduced `logHomeConfigChanges` to compare old and new configs, logging detected differences.
- Leveraged `diff.BuildConfigChangeDetails` for structured change detection.
- Adjusted logging behavior to enable debug-level logs dynamically when required.
- 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.
- Added `homeRuntimeAuthSessions` and `homeRuntimeAuthRefs` for scoped caching of home auths per session.
- Updated `pickNextViaHome` to prevent reuse of already-tried pinned auths during session retries.
- Implemented reference counting for shared auths across multiple sessions to improve memory management.
- Enhanced session cleanup logic to clear cached auths only when all referencing sessions are closed.
- Added unit tests to validate scoped caching, retry logic, and session cleanup behavior.
- Introduced `homeRuntimeAuths` to cache home auths for websocket session reuse.
- Updated `pickNextViaHome` to prioritize cached auths for pinned websocket sessions.
- Implemented automatic clearing of cached home auths when home mode is disabled.
- Added unit tests to validate caching behavior, clearing logic, and fallback scenarios.
Move per-connection protocol detection (TLS handshake, reader.Peek) out
of the accept loop and into a per-connection goroutine. An idle TCP
connection that never sends bytes would previously block Peek(1)
indefinitely, preventing all subsequent connections from being accepted
and making the management/API server unresponsive.
Closes#3267
- Added `count` attribute to `homeAuthCount` requests to improve home message batching.
- Enabled usage statistics for home mode by default and added config-level enforcement.
- Adjusted failure logging to include detailed metadata in `UsageReporter`.
- Updated multiple executors to pass error details to `PublishFailure` for better debugging.
- Enhanced unit tests to validate `count` behavior and usage statistics enforcement across components.
- Introduced `SetHomeEnabled` to enable/disable request-log forwarding to the home control plane.
- Implemented `forwardRequestLogToHome` for non-streaming logs and `homeStreamingLogWriter` for real-time streaming logs.
- Enhanced `FileRequestLogger` to bypass local logging when home forwarding is enabled.
- Updated server configuration to dynamically toggle home request-log forwarding based on changes.
- Added corresponding unit tests to ensure correct forwarding behavior and fallback mechanisms.
- Updated `EnsureIndex` logic to incorporate absolute and cleaned file paths when generating auth indexes.
- Refined metadata handling to include OAuth type in auth index seed.
- Improved compatibility for `json` file paths as sources in auth attributes.
- Added unit tests to validate correct auth index behavior for various path and type scenarios.
- Updated `FileTokenStore` and related stores (`objectstore`, `gitstore`, `postgresstore`) to include the `disabled` flag in metadata for token storage.
- Adjusted `Auth` metadata handling to initialize empty maps when absent.
- Refined logic in `auto_refresh_loop` and `conductor` to exclude `disabled` tokens from refresh checks.
- Added comprehensive unit tests to verify proper handling of the `disabled` flag in storage and retrieval operations.
- Introduced `disable_cooling` metadata field for fine-grained control over cooldown scheduling.
- Updated `Auth` object to include `Metadata` with conditional logic for handling empty states.
- Added YAML configuration support for `disable_cooling` in API key definitions across providers.
- Enhanced unit tests to validate `disable_cooling` behavior in various scenarios.
- Introduced `-home` and `-home-password` flags for specifying home control plane address and authentication.
- Implemented fetching and parsing configuration from the home control plane when `-home` is used.
- Adjusted server configuration handling to bypass local config files when loading from home.
- Ensured compatibility with cloud deploy mode and validation of home configurations.
- Added new helper methods for OAuth session management (`RegisterOAuthSession`, `CompleteOAuthSession`, etc.).
- Introduced `WriteConfig` for persisting management configurations.
- Exported `Handler` type and `NewHandler` constructors for SDK consumers.
When auth-dir is not specified in config.yaml, ResolveAuthDir returns
an empty string which causes os.MkdirAll to fail with no path. Use
the documented default ~/.cli-proxy-api instead.
Fixes#3272
- Updated all references from v6 to v7 for `github.com/router-for-me/CLIProxyAPI`.
- Ensured consistency in imports within core libraries, tests, and integration tests.
- Added missing tests for new features in Redis Protocol integration.
- Introduced `UpstreamDisconnectChan` for Codex WebSocket sessions to notify downstream connections of upstream disconnections.
- Implemented `notifyUpstreamDisconnect` to signal errors and close channels on disconnect events.
- Added integration tests to validate WebSocket session behavior on upstream disconnect.
- Updated OpenAI WebSocket response handlers to properly close connections upon upstream disconnect notifications.
Add CPA-Manager to the Usage Statistics recommendations across English, Chinese, and Japanese READMEs.
Highlight request-level monitoring, cost estimation, LiteLLM price sync, SQLite persistence, and Codex account-pool operations for multi-account maintenance.
- Replaced sponsor `z.ai` with `PackyCode` and updated related descriptions, images, and links in `README.md`, `README_CN.md`, and `README_JA.md`.
- Removed outdated sponsor entries for `Poixe AI` in all README files.
- Added new image assets for PackyCode (`packycode-cn.png` and `packycode-en.png`).
- Added validation so OpenAI-style usage parsing only accepts object payloads with token fields.
- Prevented streaming usage:null chunks from publishing zero-token records before the final usage chunk arrives.
- Reused the shared OpenAI-style parser for stream usage to support both chat completions and responses token field names.
- Added tests covering null usage chunks and input/output token usage fields in streaming responses.
- Renamed handler and test methods for better clarity on functionality.
- Updated route from `/v0/management/usage` to `/v0/management/usage-queue`.
- Adjusted integration and unit tests to reflect new naming and routes.
- Implemented `/v0/management/usage` endpoint for fetching queued usage records from Redis.
- Included validation for `count` parameter to ensure positive integers.
- Added unit tests for queue retrieval and validation, with authentication validation in integration tests.
- Updated management routing to include the new endpoint.
- Introduced methods for setting and retrieving model aliases in execution and usage contexts.
- Enhanced `UsageReporter` and related structures to include client-requested aliases.
- Updated tests to validate alias propagation and ensure correct usage reporting.
- Adjusted metadata handling in CLIProxyAPI executors to address alias integration.
- Added trimming for stream input lines to prevent processing of unnecessary whitespace.
- Improved handling of unsupported prefixes and malformed JSON responses, ensuring errors are recorded and propagated appropriately.
Fixed: #2690
- Integrated `StripVertexOpenAIResponsesToolCallIDs` to remove tool call ID data from request bodies and translated requests.
- Ensures uniformity and avoids unnecessary payload data propagation.
Fixed: #2549
- Introduced `claudeUsageTokens` struct for detailed token usage tracking.
- Replaced `calculateClaudeUsageTokens` with `Merge` and `OpenAIUsage` methods for better modularity.
- Enhanced integration of usage tokens into response processing, enabling more accurate reporting of token details.
Fixed: #2419
- Moved `ApplyThinking` logic earlier in `openai_compat_executor` to align with configuration application sequence.
- Added test to verify payload override precedence over Thinking suffix configuration.
- Added `setToolCallOutputContent` to process various content types, including arrays and fallback cases.
- Implemented robust handling for specific tool output types like text, image URLs, and files, ensuring proper serialization.
- Improved fallback logic to handle unexpected or missing data.
Fixed: #2313Closes: #2349
- Added logic to reset `pinnedAuthID` and replay transcript on unauthorized, forbidden, or throttling errors.
- Enhanced error handling in `forwardResponsesWebsocket` with detailed status inspection.
- Introduced `shouldReleaseResponsesWebsocketPinnedAuth` to determine auth reset conditions.
- Updated state management to preserve prior request and response data during forced replay.
Fixed: #2230
- Implemented `validateClaudeStreamingResponse` to ensure upstream streaming data integrity.
- Added new tests to verify response validation, including empty streams, error events, incomplete streams, and valid streams.
- Integrated validation logic into the Claude executor's streaming handler, returning detailed errors for malformed upstream data.
Fixed: #2193
All streaming executors use bare channel sends (out <- chunk) inside goroutines
that process upstream SSE responses. When the downstream consumer disconnects
(client timeout, network drop, etc.), these sends block indefinitely, causing
the goroutine and all associated resources (HTTP response body, scanner buffers,
translation state) to leak permanently.
Over time, leaked goroutines accumulate monotonically, leading to RSS growth
from ~30MB to 3.7GB+ and eventual OOM kills on resource-constrained VPS hosts.
Fix: Replace all bare 'out <- ...' sends with:
select {
case out <- ...:
case <-ctx.Done():
return
}
This ensures goroutines terminate promptly when the request context is canceled,
allowing GC to reclaim all associated resources.
Affected executors (9 files, 36+ send sites):
- antigravity_executor.go (5 sites)
- gemini_cli_executor.go (6 sites)
- gemini_vertex_executor.go (6 sites)
- aistudio_executor.go (4 sites)
- gemini_executor.go (3 sites)
- openai_compat_executor.go (3 sites)
- claude_executor.go (4 sites)
- codex_executor.go (2 sites)
- kimi_executor.go (3 sites)
- Added `filterKimiEmptyAssistantMessages` to identify and remove empty assistant messages with no content, tool links, or reasoning.
- Integrated logging to track the number of dropped messages.
- Updated tests to validate the filtering logic for both empty and valid assistant messages.
Fixed: #1730
- Introduced `redis-usage-queue-retention-seconds` config parameter with a default of 60 seconds and a max of 3600 seconds.
- Updated logic in `redisqueue` to honor configurable retention periods for enqueued usage data.
- Modified config validation and initialization to support and enforce retention limits.
- Enhanced change tracking in `config_diff` to detect updates to this parameter.
- Moved CPA Usage Keeper from "CLI tools" to a dedicated "Usage Statistics" section.
- Added details on its functionality, periodic data sync, SQLite storage, and built-in dashboard.
- Applied updates across English, Chinese, and Japanese README files for consistency.
- Deleted the `LoggerPlugin` along with associated usage tracking and in-memory statistics logic.
- Removed all related tests (`logger_plugin_test.go`, `usage_tab_test.go`) and external-facing handler (`usage.go`) for usage statistics export/import.
- Cleaned up TUI integration by deleting `usage_tab.go`.
- Introduced `Success` and `Failed` fields in auth records to track request outcomes.
- Updated `/v0/management/auth-files` and `/v0/management/api-key-usage` responses to include success and failure counts.
- Enhanced tests to validate tracking logic and API responses.
- Updated `GetAPIKeyUsage` to group API key usage by "base_url|api_key" composite keys.
- Adjusted logic to handle `base_url` extraction from auth attributes.
- Revised unit tests to validate "base_url|api_key" grouping behavior.
- Implemented `GetAPIKeyUsage` to expose recent request data grouped by provider and API key.
- Added supporting function `mergeRecentRequestBuckets` for bucket aggregation.
- Registered new endpoint `/v0/management/api-key-usage` in the management API.
- Included extensive unit tests for provider and key-based grouping validation.
- Updated `formatRecentRequestBucketLabel` to support configurable bucket duration.
- Implemented `RecentRequestsSnapshot` in `Auth` to capture bucketed recent request data.
- Added new fields and methods to `Auth` for tracking request success and failure counts over time.
- Updated `/v0/management/auth-files` response to include recent request data for each auth record.
- Introduced unit tests to validate request tracking and snapshot generation logic.
- Introduced reusable utilities in `requestmeta` to manage endpoint and response status in request contexts.
- Refactored plugins and handlers to use context-based metadata, removing direct dependency on `gin`.
- Updated tests to validate new context utilities and replaced `gin`-based context handling.
Fixed: #3166
- Introduced a new script `docker-build-local.sh` to build a local Docker image and start services using Docker Compose.
- Updated `docker-compose.yml` to allow dynamic pull policy configuration via the `CLI_PROXY_PULL_POLICY` environment variable.
- Modified `Dockerfile` to support build arguments for Go module proxy settings during the `go mod download` step.
- Introduced a new test file for validating the conversion of OpenAI responses to chat completions.
- Implemented tests to ensure correct merging of consecutive function calls and proper handling of interrupted function calls.
- Enhanced the main conversion function to buffer consecutive function calls and emit them as a single assistant message.
- Updated `ApplyPayloadConfigWithRoot` to prioritize `disable-image-generation` filtering before applying payload rules.
- Ensured payload overrides can explicitly re-enable `image_generation` when required.
- Added unit tests to validate `image_generation` restoration through overrides.
- Introduced `DisableImageGenerationMode` with support for `false`, `true`, and `chat` values.
- Updated payload handling to preserve `image_generation` on images endpoints when `chat` mode is enabled.
- Modified OpenAI image handlers (`ImagesGenerations`, `ImagesEdits`) to respect tri-state logic.
- Added unit tests for `DisableImageGenerationMode` behavior and endpoint-specific handling.
- Enhanced configuration diff logging to support `DisableImageGenerationMode`.
- Added logic to remove `tool_choice` entries of type `image_generation` from payloads when `disable-image-generation` is enabled.
- Updated `ApplyPayloadConfigWithRoot` to handle new removal logic.
- Added unit tests to verify `tool_choice` removal behavior.
- Added `disable-image-generation` configuration flag to disable the `image_generation` tool globally.
- Updated payload handling to remove `image_generation` tools from request payload arrays when the flag is enabled.
- Modified OpenAI image handlers (`ImagesGenerations`, `ImagesEdits`) to return 404 when the feature is disabled.
- Enhanced configuration diff logging to track changes for the `disable-image-generation` flag.
- Added accompanying unit tests for the new feature in payload helpers and image handler logic.
- Introduced tests to ensure unsupported models are rejected in `/images/generations` and `/images/edits`.
- Added `isSupportedImagesModel` and `rejectUnsupportedImagesModel` functions for consistent model validation.
- Enhanced image handler logic to apply validation checks for model compatibility.
The loadCodeAssist polling call hardcoded the User-Agent to
google-api-nodejs-client/9.15.1. Google Cloud Code returns the
paidTier object WITHOUT the availableCredits array for that UA,
so updateAntigravityCreditsBalance always saw "no credits", set the
hint to Available=false for every Google One AI Ultra account, and
the conductor-level credits fallback could never find a candidate.
Switching to resolveUserAgent(auth) (the same UA used for
streamGenerateContent / generateContent) makes the response include
availableCredits, so the credits hint is populated correctly and the
fallback can actually inject enabledCreditTypes:["GOOGLE_ONE_AI"]
when free tier is exhausted.
- Implemented `appendReasoningContent` to support processing of `thinking` signature and text as reasoning input.
- Added test cases to validate reasoning content conversion with and without text.
- Added `buildAdditionalModelRecord` to filter out zero-token usage details.
- Introduced `hasNonZeroTokenUsage` helper function for token usage validation.
- Updated tests to cover scenarios for zero and non-zero token usage.
- Introduced a `Disabled` flag to OpenAI compatibility configurations.
- Updated routing, auth selection, and API handling logic to respect the `Disabled` state.
- Extended relevant APIs, YAML configurations, and data structures to include the `Disabled` field.
- Adjusted all relevant loops and filters to skip disabled providers.
Closes: #3060#3059#2977
GPT-5.5 was correctly removed from codex-free tier in 7b89583c
(since free accounts cannot access it), but the test was not updated
to reflect this. This caused TestCodexStaticModelsIncludeGPT55 to
fail on the free subtest.
Changes:
- Remove free tier from GPT-5.5 inclusion test
- Add new TestCodexFreeModelsExcludeGPT55 to explicitly verify
that free tier does NOT include GPT-5.5
Address Gemini code review suggestion: the reverseMap can contain at
most len(oauthToolRenameMap) entries, so pre-allocating avoids
reallocations as entries are added.
remapOAuthToolNames renames lowercase client-sent tools (e.g. `glob` →
`Glob`) to Claude Code equivalents on OAuth requests to avoid tool-name
fingerprinting. The reverse pass previously ran against a *global*
reverse map and rewrote every tool_use block whose name matched any
value in oauthToolRenameMap — regardless of what the client actually
sent.
For clients that send mixed casing (notably Amp CLI — `Bash`, `Read`,
`Grep`, `Task` alongside `glob`, `skill`, etc.) this corrupted the
response. Any forward rename in the request set the "renamed" flag,
which then unconditionally lowercased every `Bash` in the response to
`bash`. Amp's tool registry has `Bash`, not `bash`, so it rejected the
tool_use with `tool "bash" is not allowed for smart mode` and tool
execution failed.
Fix: `remapOAuthToolNames` now returns a per-request map keyed on the
upstream (TitleCase) name valued with the original client-sent name.
The reverse functions take this map and only touch entries in it.
Names the client sent in TitleCase pass through untouched in both
directions.
- Change remapOAuthToolNames signature from `([]byte, bool)` to
`([]byte, map[string]string)`; populate at every rename site
(tools[], tool_choice.name, message tool_use, tool_reference,
nested tool_reference inside tool_result).
- Change reverseRemapOAuthToolNames and
reverseRemapOAuthToolNamesFromStreamLine to accept and consume the
per-request map; remove the global oauthToolRenameReverseMap.
- Update all three executor call sites (Execute, ExecuteStream direct
passthrough, ExecuteStream translated) + count_tokens.
- Add regression tests for the mixed-case scenario in both the
non-streaming and SSE code paths.
- Updated `buildImagesResponsesRequest` to derive `model` dynamically based on `toolJSON`.
- Adjusted streaming execution to handle dynamic model resolution across multiple contexts.
Closes: #2965
- Added IP ban logic to `AuthenticateManagementKey` and Redis protocol handlers, blocking requests after multiple failed attempts.
- Introduced unit tests to validate IP ban behavior across localhost and remote clients.
- Synchronized Redis protocol's authentication policy with management key validation.
- Added `protocol_multiplexer.go`, enabling support for both HTTP and Redis protocols on a single listener.
- Introduced `redis_queue_protocol.go` to handle Redis-compatible RESP commands for queue management.
- Integrated `redisqueue` package, supporting in-memory queuing with expiration pruning.
- Updated server initialization to manage a shared listener and multiplex connections.
- Adjusted `Handler` to adopt `AuthenticateManagementKey` for modular key validation, supporting both HTTP and Redis flows.
Replace antigravityCreditsAvailableForModel with inline known/unknown
split. Auths whose credit hints are not yet populated are kept as
lower-priority candidates instead of being rejected, breaking the
chicken-and-egg deadlock at cold start.
Remove deferred body optimization and maxErrorLog constants that were
unrelated to credits fallback. Keep only MarkCreditsUsed/CreditsUsed
helpers for flagging requests that consumed AI credits.
- findAllAntigravityCreditsCandidateAuths now filters by PinnedAuthMetadataKey
to prevent credential isolation violations during credits fallback
- Release deferredBody reference on success path to avoid holding large
payloads in memory for the lifetime of the gin context
CountTokens upstream API does not support enabledCreditTypes, so
remove the dead credits fallback path from ExecuteCount and delete
the unused tryAntigravityCreditsExecuteCount method. Fix gofmt on
credits test file.
Move credits handling from executor-level retry to conductor-level
orchestration. When all free-tier auths are exhausted (429/503), the
conductor discovers auths with available Google One AI credits and
retries with enabledCreditTypes injected via context flag.
Key changes:
- Add AntigravityCreditsHint system for tracking per-auth credits state
- Conductor tries credits fallback after all auths fail (Execute/Stream/Count)
- Executor injects enabledCreditTypes only when conductor sets context flag
- Credits fallback respects provider scope (requires antigravity in providers)
- Add context cancellation check in credits fallback to avoid wasted requests
- Remove executor-level attemptCreditsFallback and preferCredits machinery
- Restructure 429 decision logic (parse details first, keyword fallback)
- Expand shouldAbort to cover INVALID_ARGUMENT/FAILED_PRECONDITION/500+UNKNOWN
- Support human-readable retry delay parsing (e.g. "1h43m56s")
Codex CLI gates the built-in image_generation tool behind
AuthMode::Chatgpt (OAuth only). When clients connect via API key
auth through CPA, the tool is absent from requests, making image
generation unavailable through the reverse proxy.
Changes:
1. Inject image_generation tool (codex_executor.go):
Add ensureImageGenerationTool() that appends
{"type":"image_generation","output_format":"png"} to the tools
array if not already present. Applied to all three execution
paths: Execute, executeCompact, and ExecuteStream.
2. Route aliases for Codex CLI direct access (server.go):
Add /backend-api/codex/responses routes that map to the same
OpenAI Responses API handlers as /v1/responses. This allows
Codex CLI to connect via chatgpt_base_url config while keeping
AuthMode::Chatgpt, which enables the built-in image_generation
tool on the client side.
3. Unit tests (codex_executor_imagegen_test.go):
Cover no-tools, existing tools, already-present, empty array,
and mixed built-in tool scenarios.
- Added `GPT-Image-2` as a built-in model to avoid dependency on remote updates for Codex.
- Updated model tier functions (`CodexFree`, `CodexTeam`, etc.) to include built-in models via `WithCodexBuiltins`.
- Introduced new handlers for image generation and edit operations under `OpenAIAPIHandler`.
- Extended tests to validate 503 response for unsupported image model requests.
- Refactored `/healthz` handler to support `HEAD` requests alongside `GET`.
- Updated tests to include validation for `HEAD` requests with expected status and empty body.
Closes: #2929
- Introduced `refreshIneffectiveBackoff` to prevent tight-looping in auto-refresh when token refresh fails to update expiry.
- Adjusted refresh logic to apply backoff when `shouldRefresh` evaluates true.
Closes: #2830
- Added VisionCoder sponsorship information to `README.md`, `README_CN.md`, and `README_JA.md`.
- Updated external links to include `target="_blank"` for improved user experience.
- Added new logo asset `visioncoder.png` for README use.
Anthropic has moved the 1M-context-window feature to General Availability,
so the context-1m-2025-08-07 beta flag is no longer accepted and now causes
400 Bad Request errors when forwarded upstream.
Remove the X-CPA-CLAUDE-1M detection and the corresponding injection of the
now-invalid beta header. Also drop the unused net/textproto import that was
only needed for the header-key lookup.
- Introduced `LastImageHashByItemID` in Codex-GPT and `LastImageHashByID` in Codex-Gemini for deduplication of generated images.
- Added support for handling `partial_image` and `image_generation_call` types, with inline data embedding for Gemini and URL payload conversion for GPT.
- Extended unit tests to verify image handling in both streaming and non-streaming modes.
Addressing the P1 note from the Codex reviewer: applyCustomHeaders is
also called with a synthetic &http.Request{Header: ...} from the
websockets executors (aistudio_executor.go, codex_websockets_executor.go),
which forward only the header map. The previous continue meant a custom
Host was dropped from that map, regressing virtual-host overrides on
those flows. Mirror the value to both r.Host (for real net/http) and
r.Header (for header-map-only consumers).
- Deleted `iflow` provider implementation, including thinking configuration (`apply.go`) and authentication modules.
- Removed iFlow-specific tests, executors, and helpers across SDK and internal components.
- Updated all references to exclude iFlow functionality.
- Introduced `WithProxyURL` variants for `CodexAuth`, `ClaudeAuth`, `IFlowAuth`, and `DeviceFlowClient`.
- Updated executors to use proxy-aware constructors for improved configurability.
- Added unit tests to validate proxy override precedence and functionality.
Closes: #2823
- Refactored `requestExecutionMetadata` to handle empty `Idempotency-Key` gracefully.
- Added test to validate metadata inclusion of execution session without idempotency key.
Custom headers configured under openai-compatibility (and any other
provider passing through applyCustomHeaders) were silently dropped for
the Host key, because Go's net/http reads the wire Host from
req.Host, not req.Header["Host"]. As a result, virtual-host routed
upstreams (e.g. LiteLLM behind an ingress) saw the base-url's host
instead of the user-configured override and returned 404.
Detect the Host key with http.CanonicalHeaderKey and assign it to
req.Host so it is actually written on the wire. Other headers continue
to use Header.Set as before.
Fixes#2833
The x-anthropic-billing-header block in the Claude system array is
client-internal metadata and should not be forwarded to the Gemini
upstream as part of systemInstruction.parts.
When multiple auth credentials are configured, requests from the same
session are now routed to the same credential, improving upstream prompt
cache hit rates and maintaining context continuity.
Core components:
- SessionAffinitySelector: wraps RoundRobin/FillFirst selectors with
session-to-auth binding; automatic failover when bound auth is
unavailable, re-binding via the fallback selector for even distribution
- SessionCache: TTL-based in-memory cache with background cleanup
goroutine, supporting per-session and per-auth invalidation
- StoppableSelector interface: lifecycle hook for selectors holding
resources, called during Manager.StopAutoRefresh()
Session ID extraction priority (extractSessionIDs):
1. metadata.user_id with Claude Code session format (old
user_{hash}_session_{uuid} and new JSON {session_id} format)
2. X-Session-ID header (generic client support)
3. metadata.user_id (non-Claude format, used as-is)
4. conversation_id field
5. Stable FNV hash from system prompt + first user/assistant messages
(fallback for clients with no explicit session ID); returns both a
full hash (primaryID) and a short hash without assistant content
(fallbackID) to inherit bindings from the first turn
Multi-format message hash covers OpenAI messages, Claude system array,
Gemini contents/systemInstruction, and OpenAI Responses API input items
(including inline messages with role but no type field).
Configuration (config.yaml routing section):
- session-affinity: bool (default false)
- session-affinity-ttl: duration string (default "1h")
- claude-code-session-affinity: bool (deprecated, alias for above)
All three fields trigger selector rebuild on config hot reload.
Side effect: Idempotency-Key header is no longer auto-generated with a
random UUID when absent — only forwarded when explicitly provided by the
client, to avoid polluting session hash extraction.
- Deleted `QwenAuthenticator`, internal `qwen_auth`, and `qwen_executor` implementations.
- Removed all Qwen-related OAuth flows, token handling, and execution logic.
- Cleaned up dependencies and references to Qwen across the codebase.
Claude models on antigravity have a 64000 token output limit but
max_tokens from downstream requests was passed through uncapped,
causing 400 INVALID_ARGUMENT from Google when clients sent 128000.
The strict bypass test used testGeminiSignaturePayload() which produces
a base64 string starting with 'C'. Since StripInvalidSignatureThinkingBlocks
now strips all non-E/R signatures unconditionally, the test payload was
stripped before reaching ValidateClaudeBypassSignatures, causing the test
to pass the request through instead of rejecting it with 400.
Replace with testFakeClaudeSignature() which produces a base64 string
starting with 'E' (valid at the lightweight check) but with invalid
protobuf content (no valid field 2), so strict mode correctly rejects
it at the deep validation layer.
Proxy-generated thinking blocks may carry hex hashes or other non-Claude
signatures (e.g. "d5cb9cd0823142109f451861") from Gemini responses. These
are now discarded alongside empty-signature blocks during the strip phase,
before validation runs. Valid Claude signatures always start with 'E' or 'R'
(after stripping any cache prefix).
Thinking blocks with empty signatures come from proxy-generated
responses (Antigravity/Gemini routed as Claude). These should be
silently dropped from the request payload before forwarding, not
rejected with 400. Fixes 10 "missing thinking signature" errors.
- Introduced `auth-auto-refresh-workers` config option to override default concurrency.
- Updated `authAutoRefreshLoop` to support customizable worker counts.
- Enhanced token refresh scheduling flexibility by aligning worker pool with runtime configurations.
- Replaced `filepath.Walk` with `os.ReadDir` for cleaner directory traversal.
- Fixed `isAuthJSON` check to use `filepath.Dir` for directory comparison.
- Updated auth hash cache generation and file synthesis to improve readability and maintainability.
Avoid whole-payload schema sanitization when translated Antigravity requests have no actual tool schemas, including missing and empty tools arrays. Add regression coverage so image-heavy no-tool requests keep bypassing the old memory amplification path.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Antigravity wraps empty thinking text into a prompt-caching-scope
object that omits the required inner "thinking" field, causing 400
"messages.N.content.0.thinking.thinking: Field required" when Claude
Max requests are routed through Antigravity in bypass mode.
- Introduced `authAutoRefreshLoop` to handle token refresh scheduling.
- Replaced semaphore-based refresh logic in `Manager` with the new loop.
- Added unit tests to verify refresh schedule logic and edge cases.
Raise the local bypass-signature ceiling so long Claude thinking signatures are not rejected before request translation, and keep the oversized-signature test cheap to execute.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
- Added proper parsing of `Retry-After` headers for 429 responses.
- Set default retry duration when "disable cooling" is active on quota exhaustion.
- Updated tests to verify `Retry-After` handling and default behavior.
- Use buildTextBlock for billing header to avoid raw JSON string interpolation
- Fix empty array edge case in prependToFirstUserMessage
- Allow remapOAuthToolNames to process messages even without tools array
- Move claude_system_prompt.go to helps/ per repo convention
- Export prompt constants (ClaudeCode* prefix) for cross-package access
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
A/B testing confirmed that Anthropic uses tool name fingerprinting to detect
third-party clients on OAuth traffic. OpenCode-style lowercase names like
'bash', 'read', 'todowrite' trigger extra-usage billing, while Claude Code
TitleCase names like 'Bash', 'Read', 'TodoWrite' pass through normally.
Changes:
- Add oauthToolRenameMap: maps lowercase tool names to Claude Code equivalents
- Add oauthToolsToRemove: removes 'question' and 'skill' (no Claude Code counterpart)
- remapOAuthToolNames: renames tools, removes blacklisted ones, updates tool_choice and messages
- reverseRemapOAuthToolNames/reverseRemapOAuthToolNamesFromStreamLine: reverse map for responses
- Apply in Execute(), ExecuteStream(), and CountTokens() for OAuth token requests
Only for Claude OAuth requests, sanitize forwarded system-prompt context before
it is prepended into the first user message. This preserves neutral task/tool
instructions while removing OpenCode branding, docs links, environment banners,
and product-specific workflow sections that still triggered Anthropic extra-usage
classification after top-level system[] cloaking.
sjson treats 'cache_control.type' as nested path, creating
{ephemeral: {scope: org}} instead of {type: ephemeral, scope: org}.
Pass the whole map to sjson.SetBytes as a single value.
The previous commit used fmt.Sprintf with %s to insert multi-line string
constants into JSON strings. Go raw string literals contain actual newline
bytes, which produce invalid JSON (control characters in string values).
Replace with buildTextBlock() helper that uses sjson.SetBytes to properly
escape text content for JSON serialization.
Previous fix only injected billing header + agent identifier (2 blocks).
Anthropic's updated detection now validates system prompt content depth:
- Block count (needs 4-6 blocks, not 2)
- Cache control scopes (org for agent, global for core prompt)
- Presence of known Claude Code instruction sections
Changes:
- Add claude_system_prompt.go with extracted Claude Code v2.1.63 system prompt
sections (intro, system instructions, doing tasks, tone & style, output efficiency)
- Rewrite checkSystemInstructionsWithSigningMode to build 5 system blocks:
[0] billing header (no cache_control)
[1] agent identifier (cache_control: ephemeral, scope=org)
[2] core intro prompt (cache_control: ephemeral, scope=global)
[3] system instructions (no cache_control)
[4] doing tasks (no cache_control)
- Third-party client system instructions still moved to first user message
Follow-up to 69b950db4c
Three changes to avoid Anthropic's content-based system prompt validation:
1. Fix identity prefix: Use 'You are Claude Code, Anthropic's official CLI
for Claude.' instead of the SDK agent prefix, matching real Claude Code.
2. Move user system instructions to user message: Only keep billing header +
identity prefix in system[] array. User system instructions are prepended
to the first user message as <system-reminder> blocks.
3. Enable cch signing for OAuth tokens by default: The xxHash64 cch integrity
check was previously gated behind experimentalCCHSigning config flag.
Now automatically enabled when using OAuth tokens.
Related: router-for-me/CLIProxyAPI#2599
After a Codex CLI compact, the client sends a full conversation
transcript (with compaction items or assistant messages) as input.
Previously, normalizeResponseSubsequentRequest() unconditionally
merged this with stale lastRequest/lastResponseOutput, breaking
function_call/function_call_output pairings and causing 400 errors
("No tool output found for function call").
Add inputContainsFullTranscript() heuristic that detects compaction
items (type=compaction/compaction_summary) or assistant messages in
the input array, and bypasses the merge when a full transcript is
present.
Fixes#2207
ensureAmpSignature injects signature:"" into tool_use blocks so the
Amp TUI does not crash on P.signature.length. when Amp sends the
conversation back, Claude rejects the extra field with 400:
tool_use.signature: Extra inputs are not permitted
strip the proxy-injected signature from tool_use blocks in
SanitizeAmpRequestBody before forwarding to the upstream API.
Added comprehensive tests to ensure key order is maintained when modifying payloads in `normalizeCacheControlTTL` and `enforceCacheControlLimit` functions. Removed unused helper functions and refactored implementations for better readability and efficiency.
Added comprehensive support for resolving proxy URLs from configuration based on API key and provider attributes. Introduced new helper functions and extended the test suite to validate fallback mechanisms and compatibility cases.
Added Poixe AI sponsorship information, including referral bonuses and platform capabilities, to README files in English, Japanese, and Chinese. Updated assets to include Poixe AI logo.
Introduce `StartAntigravityVersionUpdater` to periodically refresh the cached Antigravity version using a non-blocking background process. Updated main server flow to initialize the updater.
Fetch the latest version from the antigravity auto-updater releases
endpoint and cache it for 6 hours. Falls back to 1.21.9 if the API
is unreachable or returns unexpected data.
The review asked for the builtin tool registry helper to live with the rest
of executor support utilities. This moves the registry code into the helps
package, exports the minimal surface executor needs, and keeps behavior tests
with the executor while leaving registry-focused checks with the helper.
Constraint: Requested layout keeps executor helper utilities centralized under internal/runtime/executor/helps
Rejected: Keep the files in executor and reply with rationale | conflicts with requested package organization
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Keep executor behavior tests near applyClaudeToolPrefix and keep pure registry tests in helps
Tested: go test ./internal/runtime/executor/helps ./internal/runtime/executor -run 'Claude|Builtin|Tool'; go test ./test/...; go test ./...
Not-tested: End-to-end Claude Code direct-connect/session runtime behavior
Follow-up review found two real framing hazards in the handler-layer
framer: it could flush a partial `data:` payload before the JSON was
complete, and it could inject an extra newline before chunks that
already began with `\n`/`\r\n`. This commit tightens the framer so it
only emits undelimited events when the buffered `data:` payload is
already valid JSON (or `[DONE]`), skips newline injection for chunks
that already start with a line break, and avoids the heavier
`bytes.Split` path while scanning SSE fields.
The regression suite now covers split `data:` payload chunks,
newline-prefixed chunks, and dropping incomplete trailing data on
flush, so the original Responses fix remains intact while the review
concerns are explicitly locked down.
Constraint: Keep the follow-up limited to handler-layer framing and tests
Rejected: Ignore the review and rely on current executor chunk shapes | leaves partial data payload corruption possible
Rejected: Build a fully generic SSE parser | wider change than needed for the identified risks
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Do not emit undelimited Responses SSE events unless buffered `data:` content is already complete and valid
Tested: /tmp/go1.26.1/go/bin/go test ./sdk/api/handlers/openai -count=1
Tested: /tmp/go1.26.1/go/bin/go test ./sdk/api/handlers -count=1
Tested: /tmp/go1.26.1/go/bin/go vet ./sdk/api/handlers/...
Not-tested: Full repository test suite outside sdk/api/handlers packages
Line-oriented upstream executors can emit `event:` and `data:` as
separate chunks, but the Responses handler had started terminating
each incoming chunk as a full SSE event. That split `response.created`
into an empty event plus a later data block, which broke downstream
clients like OpenClaw.
This keeps the fix in the handler layer: a small stateful framer now
buffers standalone `event:` lines until the matching `data:` arrives,
preserves already-framed events, and ignores delimiter-only leftovers.
The regression suite now covers split event/data framing, full-event
passthrough, terminal errors, and the bootstrap path that forwards
line-oriented openai-response streams from non-Codex executors too.
Constraint: Keep the fix localized to Responses handler framing instead of patching every executor
Rejected: Revert to v6.9.7 chunk writing | would reintroduce data-only framing regressions
Rejected: Patch each line-oriented executor separately | duplicates fragile SSE assembly logic
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Do not assume incoming Responses stream chunks are already complete SSE events; preserve handler-layer reassembly for split `event:`/`data:` inputs
Tested: /tmp/go1.26.1/go/bin/go test ./sdk/api/handlers/openai -count=1
Tested: /tmp/go1.26.1/go/bin/go test ./sdk/api/handlers -count=1
Tested: /tmp/go1.26.1/go test ./sdk/api/handlers/... -count=1
Tested: /tmp/go1.26.1/go/bin/go vet ./sdk/api/handlers/...
Tested: Temporary patched server on 127.0.0.1:18317 -> /v1/models 200, /v1/responses non-stream 200, /v1/responses stream emitted combined `event:` + `data:` frames
Not-tested: Full repository test suite outside sdk/api/handlers packages
This change stops short of broader Claude Code runtime alignment and instead
hardens two safe edges: builtin tool prefix handling and source-informed
sentinel coverage for future drift checks.
Constraint: Must preserve existing default behavior for current users
Rejected: Implement control-plane/session alignment now | too much runtime risk for a first slice
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Treat the new fixtures as compatibility sentinels, not a full Claude Code schema contract
Tested: go test ./test/...; go test ./sdk/translator/...; go test ./internal/runtime/executor -run 'Claude|Builtin|Tool'; go test ./...
Not-tested: End-to-end Claude Code direct-connect/session runtime behavior
- Introduced new logging functions for websocket requests, handshakes, errors, and responses in `logging_helpers.go`.
- Updated `CodexWebsocketsExecutor` to utilize the new logging functions for improved clarity and consistency in websocket operations.
- Modified the handling of websocket upgrade rejections to log relevant metadata.
- Changed the request body key to a timeline body key in `openai_responses_websocket.go` to better reflect its purpose.
- Enhanced tests to verify the correct logging of websocket events and responses, including disconnect events and error handling scenarios.
delegate schema sanitization to util.CleanJSONSchemaForGemini and drop the top-level eager_input_streaming key to prevent validation errors when sending claude tools to the gemini api
Add ProxyPal (https://github.com/buddingnewinsights/proxypal) to the
community projects list in all three README files (EN, CN, JA).
Placed after CCS, restoring its original position.
ProxyPal is a cross-platform desktop app (macOS, Windows, Linux) that
wraps CLIProxyAPI with a native GUI, supporting multiple AI providers,
usage analytics, request monitoring, and auto-configuration for popular
coding tools.
Closes#2420
- Narrow websocket transcript replacement detection to assistant outputs and function calls
- Preserve existing merge behavior for follow-up developer messages without previous_response_id
- Add a regression test covering mid-session developer message updates
- Add shouldReplaceWebsocketTranscript() to detect historical model output in input
- Add normalizeResponseTranscriptReplacement() for full transcript reset handling
- Prevent duplicate stale turn-state when clients replace local history post-compaction
- Avoid orphaned function_call items from incremental append on compact transcripts
- Add unit tests for transcript replacement detection and state reset behavior
Reverts the streaming thinking suppression introduced in b15453c.
rewriteStreamEvent should only inject signatures and rewrite model
names — suppressing thinking blocks in streaming mode breaks SSE
index alignment and causes the Amp TUI to render empty responses
on the second message onward (especially with model-mapped
non-Claude providers like GPT-5.4).
Non-streaming responses still suppress thinking when tool_use is
present via rewriteModelInResponse.
When a Claude assistant message contains [text, tool_use, text], the
Antigravity API internally splits the model message at functionCall
boundaries, creating an extra assistant turn between tool_use and the
following tool_result. Claude then rejects with:
tool_use ids were found without tool_result blocks immediately after
Fix: extend the existing 2-way part reordering (thinking-first) to a
3-way partition: thinking → regular → functionCall. This ensures
functionCall parts are always last, so Antigravity's split cannot
insert an extra assistant turn before the user's tool_result.
Fixes#989
- Call suppressAmpThinking in rewriteStreamEvent for streaming path
- Handle nil return from suppressAmpThinking to skip suppressed events
- Narrow looksLikeSSEChunk to line-prefix detection (HasPrefix vs Contains)
- Initialize suppressedContentBlock map in test
- Simplify project ID selection to always use the backend project ID returned by Gemini onboarding
- Update Gemini CLI version from 0.31.0 to 0.34.0
- Add 'terminal' to User-Agent string for better client identification
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Emit signature only when non-empty in both streaming content_block_start
and non-streaming thinking blocks. Avoids turning 'missing signature'
into 'empty/invalid signature' which Claude clients may reject.
Address two blocking issues from PR review:
- Auth file now named vertex-{prefix}-{project}.json so importing the
same project with different prefixes no longer overwrites credentials
- Prefix containing "/" is rejected at import time instead of being
silently ignored at runtime
- Add prefix to in-memory metadata map for consistency
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add Manager.ReconcileRegistryModelStates to clear stale per-model runtime failures for models currently registered in the global model registry. The method finds models supported for an auth, resets non-clean ModelState entries, updates aggregated availability, persists changes, and pushes a snapshot to the scheduler. Introduce modelStateIsClean helper to determine when a model state needs resetting. Call ReconcileRegistryModelStates from Service paths that register/refresh models (applyCoreAuthAddOrUpdate and refreshModelRegistrationForAuth) to keep the scheduler and global registry aligned after model re-registration.
When adjustedBudget < minBudget, the previous fix blindly set
max_tokens = budgetTokens+1 which could exceed MaxCompletionTokens.
Now: cap max_tokens at MaxCompletionTokens, recalculate budget, and
disable thinking entirely if constraints are unsatisfiable.
Add unit tests covering raise, clamp, disable, and no-op scenarios.
1. Always include interleaved-thinking-2025-05-14 beta header so that
thinking blocks are returned correctly for all Claude models.
2. Remove status-code guard in AMP reverse proxy ModifyResponse so that
error responses (4xx/5xx) with hidden gzip encoding are decoded
properly — prevents garbled error messages reaching the client.
3. In normalizeClaudeBudget, when the adjusted budget falls below the
model minimum, set max_tokens = budgetTokens+1 instead of leaving
the request unchanged (which causes a 400 from the API).
- `CLIProxyAPI_<version>_linux_<arch>.tar.gz` is the default Linux build. It supports dynamic library plugins and is built against a GLIBC 2.17 baseline.
- `CLIProxyAPI_<version>_linux_<arch>_no-plugin.tar.gz` is the portable Linux build for musl-based or older systems such as OpenWrt. It does not support dynamic library plugins.
## FreeBSD release assets
- `CLIProxyAPI_<version>_freebsd_aarch64_no-plugin.tar.gz` is the FreeBSD arm64 build. It is built without CGO and does not support dynamic library plugins.
<!-- cliproxyapi-linux-release-assets:end -->
EOF
git fetch --force --tags
previous_tag=""
if previous_tag_value="$(git describe --tags --abbrev=0 "${GITHUB_REF_NAME}^" 2>/dev/null)"; then
-`internal/thinking/` — Main thinking/reasoning pipeline. `ApplyThinking()` (apply.go) parses suffixes (`suffix.go`, suffix overrides body), normalizes config to canonical `ThinkingConfig` (`types.go`), normalizes and validates centrally (`validate.go`/`convert.go`), then applies provider-specific output via `ProviderApplier`. Do not break this "canonical representation → per-provider translation" architecture.
- If editing code that already contains non-English comments, translate them to English (don’t add new non-English comments)
- For user-visible strings, keep the existing language used in that file/area
- New Markdown docs should be in English unless the file is explicitly language-specific (e.g. `README_CN.md`)
- As a rule, do not make standalone changes to `internal/translator/`. You may modify it only as part of broader changes elsewhere.
- If a task requires changing only `internal/translator/`, run `gh repo view --json viewerPermission -q .viewerPermission` to confirm you have `WRITE`, `MAINTAIN`, or `ADMIN`. If you do, you may proceed; otherwise, file a GitHub issue including the goal, rationale, and the intended implementation code, then stop further work.
-`internal/runtime/executor/` should contain executors and their unit tests only. Place any helper/supporting files under `internal/runtime/executor/helps/`.
- Follow `gofmt`; keep imports goimports-style; wrap errors with context where helpful
- Do not use `log.Fatal`/`log.Fatalf` (terminates the process); prefer returning errors and logging via logrus
- Shadowed variables: use method suffix (`errStart := server.Start()`)
- Use logrus structured logging; avoid leaking secrets/tokens in logs
- Avoid panics in HTTP handlers; prefer logged errors and meaningful HTTP status codes
- Timeouts are allowed only during credential acquisition; after an upstream connection is established, do not set timeouts for any subsequent network behavior. Intentional exceptions that must remain allowed are the Codex websocket liveness deadlines in `internal/runtime/executor/codex_websockets_executor.go`, the wsrelay session deadlines in `internal/wsrelay/session.go`, the management APICall timeout in `internal/api/handlers/management/api_tools.go`, and the `cmd/fetch_antigravity_models` utility timeouts
<a href="https://x.com/Finessse377721"><img src="https://img.shields.io/badge/Follow-%F0%9D%95%8F%2F%40Finessse377721-1c9bf0" alt="Follow on 𝕏"></a>
<a href="https://github.com/Finesssee/ProxyPilot"><img src="https://img.shields.io/github/stars/Finesssee/ProxyPilot.svg?style=social&label=Star%20this%20repo" alt="Star this repo"></a>
</p>
A proxy server that provides OpenAI/Gemini/Claude/Codex/Grok compatible API interfaces for CLI.
<p align="center">
<strong>Stop juggling API keys.</strong> ProxyPilot is a powerful local API proxy that lets you use your existing Claude Code, Codex, Gemini, Kiro, and Qwen subscriptions with any AI coding tool – no separate API keys required.
</p>
It now also supports OpenAI Codex (GPT models) and Claude Code via OAuth.
<p align="center">
Built in Go, it handles OAuth authentication, token management, and API translation automatically. One server to route them all.
</p>
So you can use local or multi-account CLI access with OpenAI(include Responses)/Gemini/Claude-compatible clients and SDKs.
PackyCode is a reliable and efficient API relay service provider, offering relay services for Claude Code, Codex, Gemini, and more.
PackyCode provides special discounts for our software users: register using <a href="https://www.packyapi.com/register?aff=cliproxyapi">this link</a> and enter the "cliproxyapi" promo code during recharge to get 10% off.
---
> [!TIP]
> 📣 **Latest models supported:**
> Claude Opus 4.5 / Sonnet 4.5 with extended thinking, GPT-5.2 / GPT-5.2 Codex, Gemini 3 Pro/Flash, and Kiro (AWS CodeWhisperer)! 🚀
<td>Thanks to AICodeMirror for sponsoring this project! AICodeMirror provides official high-stability relay services for Claude Code / Codex / Gemini, with enterprise-grade concurrency, fast invoicing, and 24/7 dedicated technical support. Claude Code / Codex / Gemini official channels at 38% / 2% / 9% of original price, with extra discounts on top-ups! AICodeMirror offers special benefits for CLIProxyAPI users: register via <a href="https://www.aicodemirror.com/register?invitecode=TJNAIF">this link</a> to enjoy 20% off your first top-up, and enterprise customers can get up to 25% off!</td>
<td>Huge thanks to BmoPlus for sponsoring this project! BmoPlus is a highly reliable AI account provider built strictly for heavy AI users and developers. They offer rock-solid, ready-to-use accounts and official top-up services for ChatGPT Plus / ChatGPT Pro (Full Warranty) / Claude Pro / Super Grok / Gemini Pro. By registering and ordering through <a href="https://shop.bmoplus.com/?utm_source=github">BmoPlus - Premium AI Accounts & Top-ups</a>, users can unlock the mind-blowing rate of <b>10% of the official GPT subscription price (90% OFF)</b>!</td>
<td>Thanks to VisionCoder for supporting this project. <a href="https://coder.visioncoder.cn">VisionCoder Developer Platform</a> is a reliable and efficient API relay service provider, offering access to mainstream AI models such as Claude Code, Codex, and Gemini. It helps developers and teams integrate AI capabilities more easily and improve productivity. Additionally, VisionCoder now offers retail channels for <b>Claude Max 200 and GPT Pro 200 premium accounts</b>, providing users with instant access to top-tier AI computing power and features.</td>
<td>Thanks to APIKEY.FUN for sponsoring this project! APIKEY.FUN is a professional enterprise-grade AI relay platform dedicated to providing stable, efficient, and low-cost AI model API access for enterprises and individual developers. The platform supports popular mainstream models such as Claude, OpenAI, and Gemini, with prices as low as 7% of the official price. Register through this project's <a href="https://apikey.fun/register?aff=CLIProxyAPI">exclusive link</a> to enjoy a special <b>permanent 5% top-up discount</b>.</td>
<td>RunAPI is an efficient and stable API platform—an alternative to OpenRouter. A single API Key gives you access to 150+ leading models, including OpenAI, Claude, Gemini, DeepSeek, Grok, and more, at prices as low as 10% of the original (up to 90% off), with exceptional stability. It's seamlessly compatible with tools like Claude Code, OpenClaw, and others. RunAPI offers an exclusive perk for CPA users: <a href="https://runapi.co/register?aff=FivD">register</a> and contact an administrator to claim ¥7 in free credit.</td>
<td>Thanks to Unity2.ai for sponsoring this project! Unity2.ai is a high-performance AI model API relay platform for individual developers, teams, and enterprises. It has long served leading domestic enterprises, handles more than 30 billion token calls per day, and supports high concurrency at the 5000 RPM level. It supports balance billing, first top-up bonuses, bundled subscriptions, enterprise invoicing, and dedicated integration support. Register through <a href="https://unity2.ai/register?source=cliproxyapi">this link</a> to receive a $2 balance, then join the official group to get another $10 balance, for up to $12 in free credit.</td>
<td>Cat API is an AI model aggregation platform built for individual developers and teams, integrating leading large language models into a single simple, stable, and easy-to-use entry point. It provides an API fully compatible with OpenAI, Claude, and Gemini that plugs seamlessly into mainstream AI IDEs and coding tools such as Claude Code, Cursor, Windsurf, Cline, Roo Code, Continue, Codex, and Trae, and features dedicated CN2 high-speed routing for low-latency, highly reliable access. <a href="https://catapi.ai/sign-up">Sign up</a> to claim 1$ in free credits.</td>
OAuth tokens are stored locally and auto-refreshed before expiry.
### Security Defaults (Auth + CORS)
- Proxy requests require API keys by default. To allow unauthenticated access (not recommended), set `allow-unauthenticated: true` in `config.yaml`.
- CORS is enabled for non-management endpoints by default (wildcard `*`). Management endpoints **do not** emit CORS headers unless you explicitly allow origins under `cors.management-allow-origins`.
Example:
```yaml
allow-unauthenticated:false
cors:
allow-origins:
- "http://localhost:5173"
management-allow-origins:
- "http://localhost:5173"
```
### Configure Your Tools
**Claude Code** (`~/.claude/settings.json`):
```json
{
"env":{
"ANTHROPIC_BASE_URL":"http://127.0.0.1:8317",
"ANTHROPIC_AUTH_TOKEN":"your-api-key"
}
}
```
**Codex CLI** (`~/.codex/config.toml`):
```toml
[openai]
api_base_url="http://127.0.0.1:8317"
```
**Factory Droid** (`~/.factory/settings.json`):
```json
{
"customModels":[{
"name":"ProxyPilot",
"baseUrl":"http://127.0.0.1:8317"
}]
}
```
---
- OpenAI/Gemini/Claude/Grok compatible API endpoints for CLI models
- OpenAI Codex support (GPT models) via OAuth login
- Claude Code support via OAuth login
-Grok Build support via OAuth login
-Streaming, non-streaming, and WebSocket responses where supported
-Function calling/tools support
-Multimodal input support (text and images)
-Multiple accounts with round-robin load balancing (Gemini, OpenAI, Claude, Grok)
| `/v0/management/prompt-cache/clear` | POST | Clear prompt cache |
| `/v0/management/prompt-cache/enabled` | PUT | Enable/disable at runtime |
| `/v0/management/prompt-cache/top` | GET | Top 10 most-hit prompts |
Since v6.10.0, CLIProxyAPI and [CPAMC](https://github.com/router-for-me/Cli-Proxy-API-Management-Center) no longer ship built-in usage statistics. If you need usage statistics, use:
Standalone persistence and visualization service for CLIProxyAPI, with periodic data sync, SQLite storage, aggregate APIs, and a built-in dashboard for usage and statistics.
For low‑memory or high‑throughput setups, you can disable heavier features:
Full CLIProxyAPI management center with request-level monitoring and cost estimates. CPA-Manager tracks collected requests by account, model, channel, latency, status, and token usage; estimates cost with editable model prices and one-click LiteLLM price sync; persists events in SQLite; and provides Codex account-pool operations with batch inspection, quota detection, unhealthy account discovery, cleanup suggestions, and one-click execution for day-to-day multi-account maintenance.
A cross-platform desktop and web app to translate and validate SRT subtitles using your existing LLM subscriptions (Gemini, ChatGPT, Claude, etc.) via CLIProxyAPI - no API keys needed.
ProxyPilot automatically backs up the previous version during updates and can restore it if something goes wrong.
CLI wrapper for instant switching between multiple Claude accounts and alternative models (Gemini, Codex, Antigravity) via CLIProxyAPI OAuth - no API keys needed
- **Crash Detection** - Tracks rapid restarts within a 30-second window
- **Auto-Rollback** - After 3 rapid failures, automatically restores previous version
- **Health Marking** - After 30 seconds of stable operation, clears the failure counter
Native macOS menu bar app that unifies Claude, Gemini, OpenAI, and Antigravity subscriptions with real-time quota tracking and smart auto-failover for AI coding tools like Claude Code, OpenCode, and Droid - no API keys needed.
From the tray menu:
- **Settings → Rollback to Previous Version** - Restore the previous version
VSCode extension for quick switching between Claude Code models, featuring integrated CLIProxyAPI as its backend with automatic background lifecycle management.
| `proxypilot` | Main CLI with server and config switching |
| `proxypilot-tray` | System tray app |
Windows desktop app built with Tauri + React for monitoring AI coding assistant quotas via CLIProxyAPI. Track usage across Gemini, Claude, OpenAI Codex, and Antigravity accounts with real-time dashboard, system tray integration, and one-click proxy control - no API keys needed.
A lightweight web admin panel for CLIProxyAPI with health checks, resource monitoring, real-time logs, auto-update, request statistics and pricing display. Supports one-click installation and systemd service.
- **Claude Code** - Auto-configure via settings.json
- **Codex CLI** - Auto-configure via config.toml
- **Factory Droid** - Auto-configure via settings.json
- **Cursor IDE** - Manual endpoint configuration
- **Continue** - Manual endpoint configuration
A Windows tray application implemented using PowerShell scripts, without relying on any third-party libraries. The main features include: automatic creation of shortcuts, silent running, password management, channel switching (Main / Plus), and automatic downloading and updating.
---
### [霖君](https://github.com/wangdabaoqq/LinJun)
## Requirements
霖君 is a cross-platform desktop application for managing AI programming assistants, supporting macOS, Windows, and Linux systems. Unified management of Claude Code, Gemini, OpenAI Codex, and other AI coding tools, with local proxy for multi-account quota tracking and one-click configuration.
A modern web-based management dashboard for CLIProxyAPI built with Next.js, React, and PostgreSQL. Features real-time log streaming, structured configuration editing, API key management, OAuth provider integration for Claude/Gemini/Codex, usage analytics, container management, and config sync with OpenCode via companion plugin - no manual YAML editing needed.
## Author
### [All API Hub](https://github.com/qixing-jk/all-api-hub)
ProxyPilot is developed and maintained by [@Finesssee](https://github.com/Finesssee). Some contributors shown in the git history are from upstream [CLIProxyAPI](https://github.com/router-for-me/CLIProxyAPI) merges. Direct contributors to ProxyPilot will be listed here as the project grows.
Browser extension for one-stop management of New API-compatible relay site accounts, featuring balance and usage dashboards, auto check-in, one-click key export to common apps, in-page API availability testing, and channel/model sync and redirection. It integrates with CLIProxyAPI through the Management API for one-click provider import and config sync.
- **[CLIProxyAPI](https://github.com/router-for-me/CLIProxyAPI)** - The original unified proxy server that inspired this project
- **[VibeProxy](https://github.com/automazeio/vibeproxy)** - Native macOS menu bar app showcasing clean proxy UX
Cross-platform desktop app (macOS, Windows, Linux) wrapping CLIProxyAPI with a native GUI. Connects Claude, ChatGPT, Gemini, GitHub Copilot, and custom OpenAI-compatible endpoints with usage analytics, request monitoring, and auto-configuration for popular coding tools - no API keys needed.
Long-context features are inspired by research from the AI community:
- **[Factory.ai](https://factory.ai/news/evaluating-compression)** - Context compression techniques for long-running coding agents
- **[Anthropic](https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents)** - Effective harnesses for long-running agents
Ready-to-use cross-platform quota inspector for CLIProxyAPI, supporting per-account codex 5h/7d quota windows, plan-based sorting, status coloring, and multi-account summary analytics.
Special thanks to these teams for sharing their work and insights.
### [CLIProxy Pool Watch](https://github.com/murasame612/CLIProxyPoolWidget)
---
Native macOS SwiftUI app for monitoring ChatGPT/Codex account quotas in CLIProxyAPI pools. Displays account availability, Plus-base capacity, 5-hour and weekly quota bars, plan weights, and restore forecasts through the Management API.
Multi-agent orchestration for AI coding assistants. Runs CLIProxyAPI as a local sidecar so its agents can drive GPT models through a ChatGPT subscription, pointing Claude Code at an Anthropic-compatible endpoint with no OpenAI API key required.
Windows desktop UI that manages CLIProxyAPI and Perplexity WebUI Scraper from a single interface, inspired by Quotio and VibeProxy. Connect OAuth providers (Claude, Gemini, Codex, Kimi, Antigravity), custom API keys, and Perplexity session accounts, then point any coding agent at the local endpoint.
Cross-platform (Tauri) port of Quotio for Windows, macOS and Linux. Manages a pool of AI accounts (Codex, Claude Code, GitHub Copilot, Gemini, Antigravity, Kiro, Cursor, Trae, GLM) through CLIProxyAPI, with per-account 5-hour/weekly quota bars, Codex rate-limit reset credits with one-click reset, smart scheduling, usage statistics, and multi-instance Codex — no API keys needed.
> [!NOTE]
> If you developed a project based on CLIProxyAPI, please open a PR to add it to this list.
## More choices
Those projects are ports of CLIProxyAPI or inspired by it:
### [9Router](https://github.com/decolua/9router)
A Next.js implementation inspired by CLIProxyAPI, easy to install and use, built from scratch with format translation (OpenAI/Claude/Gemini/Ollama), combo system with auto-fallback, multi-account management with exponential backoff, a Next.js web dashboard, and support for CLI tools (Cursor, Claude Code, Cline, RooCode) - no API keys needed.
Never stop coding. Smart routing to FREE & low-cost AI models with automatic fallback.
OmniRoute is an AI gateway for multi-provider LLMs: an OpenAI-compatible endpoint with smart routing, load balancing, retries, and fallbacks. Add policies, rate limits, caching, and observability for reliable, cost-aware inference.
### [Playful Proxy API Panel (PPAP)](https://github.com/daishuge/playful-proxy-api-panel)
A public CLIProxyAPI-compatible fork and bundled management panel. It keeps upstream-style usage while restoring built-in usage statistics, adding cache hit rate, first-byte latency, TPS tracking, and Docker-oriented self-hosted installation docs.
This is a tool built with Tauri 2 + Vue 3 for managing multiple OpenAI Codex desktop accounts. Switch between saved ChatGPT/Codex certification profiles, check 5-hour and weekly quota usage in real time, verify token health, view active account details, and import or save auth.json files without manual copying.
> [!NOTE]
> If you have developed a port of CLIProxyAPI or a project inspired by it, please open a PR to add it to this list.
<td>感谢 BmoPlus 赞助了本项目!BmoPlus 是一家专为AI订阅重度用户打造的可靠 AI 账号代充服务商,提供稳定的 ChatGPT Plus / ChatGPT Pro(全程质保) / Claude Pro / Super Grok / Gemini Pro 的官方代充&成品账号。 通过<a href="https://shop.bmoplus.com/?utm_source=github" target="_blank">BmoPlus AI成品号专卖/代充</a>注册下单的用户,可享GPT <b>官网订阅一折</b> 的震撼价格!</td>
<td>感谢 VisionCoder 对本项目的支持。<a href="https://coder.visioncoder.cn">VisionCoder 开发平台</a> 是一个可靠高效的 API 中继服务提供商,提供 Claude Code、Codex、Gemini 等主流 AI 模型,帮助开发者和团队更轻松地集成 AI 功能,提升工作效率。此外,VisionCoder 还提供 <b>Claude Max 200 与 GPT Pro 200 高级成品号</b>的独家售卖渠道,助力体验全网顶配 AI 的算力与体验。</td>
<td>Cat API 是一家面向个人开发者与团队的 AI 大模型聚合平台,致力于将主流大模型能力整合到一个简单、稳定、易用的入口中。平台提供完全兼容 OpenAI、Claude、Gemini 的 API,可无缝接入 Claude Code、Cursor、Windsurf、Cline、Roo Code、Continue、Codex、Trae 等主流 AI IDE 与编程工具,并主打 CN2 高速线路,为用户带来低延迟、高稳定的访问体验。<a href="https://catapi.ai/sign-up">注册</a>即可领取 1$ 的免费额度。</td>
</tr>
</tbody>
</table>
## 功能特性
- 为 CLI 模型提供 OpenAI/Gemini/Claude/Codex/Grok 兼容的 API 端点
<td>本プロジェクトにご支援いただいた BmoPlus に感謝いたします!BmoPlusは、AIサブスクリプションのヘビーユーザー向けに特化した信頼性の高いAIアカウントサービスプロバイダーであり、安定した ChatGPT Plus / ChatGPT Pro (完全保証) / Claude Pro / Super Grok / Gemini Pro の公式代行チャージおよび即納アカウントを提供しています。こちらの<a href="https://shop.bmoplus.com/?utm_source=github">BmoPlus AIアカウント専門店/代行チャージ</a>経由でご登録・ご注文いただいたユーザー様は、GPTを <b>公式サイト価格の約1割(90% OFF)</b> という驚異的な価格でご利用いただけます!</td>
### [All API Hub](https://github.com/qixing-jk/all-api-hub)
New API互換リレーサイトアカウントをワンストップで管理するブラウザ拡張機能。残高と使用量のダッシュボード、自動チェックイン、一般的なアプリへのワンクリックキーエクスポート、ページ内API可用性テスト、チャネル/モデルの同期とリダイレクト機能を搭載。Management APIを通じてCLIProxyAPIと統合し、ワンクリックでプロバイダーのインポートと設定同期が可能
flag.StringVar(&vertexImport,"vertex-import","","Import Vertex service account key JSON file")
flag.StringVar(&vertexImportPrefix,"vertex-import-prefix","","Prefix for Vertex model namespacing (use with -vertex-import)")
flag.StringVar(&password,"password","","")
flag.BoolVar(&launchTUI,"tui",false,"Start with terminal management UI")
flag.StringVar(&homeJWT,"home-jwt","","Home control plane JWT for mTLS certificate bootstrap and connection")
flag.BoolVar(&homeDisableClusterDiscovery,"home-disable-cluster-discovery",false,"Disable Home CLUSTER NODES discovery and keep using the configured -home-jwt address")
flag.BoolVar(&tuiMode,"tui",false,"Start with terminal management UI")
flag.BoolVar(&standalone,"standalone",false,"In TUI mode, start an embedded local server")
flag.BoolVar(&localModel,"local-model",false,"Use embedded model catalog only, skip remote model fetching")
flag.BoolVar(&showVersion,"version",false,"Show ProxyPilot version and exit")
flag.BoolVar(&showStatus,"status",false,"Show ProxyPilot status and exit")
flag.BoolVar(&listAccounts,"list-accounts",false,"List all configured accounts and exit")
flag.BoolVar(&cleanupExpired,"cleanup-expired",false,"Remove expired tokens and exit")
flag.StringVar(&removeAccount,"remove-account","","Remove a specific account by name and exit")
flag.StringVar(&refreshTokens,"refresh","","Force token refresh (all, or email/id to refresh specific)")
flag.BoolVar(&jsonOutput,"json",false,"Output in JSON format (overrides --quiet)")
flag.BoolVar(&quietMode,"quiet",false,"Run in quiet mode (overrides --verbose)")
flag.BoolVar(&verboseMode,"verbose",false,"Run in verbose mode")
flag.BoolVar(&listModels,"list-models",false,"List available models per provider and exit")
flag.StringVar(&exportAccounts,"export-accounts","","Export accounts to JSON file (use - for stdout)")
flag.StringVar(&importAccounts,"import-accounts","","Import accounts from JSON file")
flag.BoolVar(&includeTokens,"include-tokens",false,"Include sensitive tokens in export (use with -export-accounts)")
flag.BoolVar(&forceImport,"force",false,"Force overwrite existing accounts on import")
flag.BoolVar(&showUsage,"usage",false,"Show token usage statistics and exit")
flag.BoolVar(&showLogs,"logs",false,"View recent proxy logs and exit")
flag.IntVar(&logLines,"n",50,"Number of log lines to show (used with -logs)")
// Windows service flags
flag.BoolVar(&runAsService,"service",false,"Run as Windows service (internal)")
# Per-entry proxy-url also supports "direct" or "none" to bypass both the global proxy-url and environment proxies explicitly.
proxy-url:""
@@ -87,30 +116,93 @@ max-retry-credentials: 0
# Maximum wait time in seconds for a cooled-down credential before triggering a retry.
max-retry-interval:30
# When true, disable auth/model cooldown scheduling globally (prevents blackout windows after failure states).
disable-cooling:false
# When true, persist per-auth cooldown status as .cds files next to auth files.
# Default is false; when false, cooldown status is kept in memory only.
save-cooldown-status:false
# Cooldown duration in seconds for transient upstream errors (408/500/502/503/504).
# Set to 0 to keep the legacy 60-second cooldown; set to -1 to disable transient error cooldowns.
transient-error-cooldown-seconds:0
# When true, globally disable Claude request cloaking (the Claude Code CLI disguise and
# system prompt replacement), so the original system prompt is passed through to Claude as-is.
# Individual credentials can still override this: a claude-api-key entry via its "cloak.mode",
# or a Claude OAuth/token file via a "cloak_mode" value. Default false keeps the per-client
# "auto" behavior (cloak only non-Claude-Code clients).
disable-claude-cloak-mode:false
# disable-image-generation supports: false (default), true, "chat", or "passthrough".
# - true: disable image_generation everywhere (also returns 404 for /v1/images/generations and /v1/images/edits).
# - "chat": disable image_generation injection on non-images endpoints, but keep /v1/images/generations and /v1/images/edits enabled.
# - "passthrough": never inject or strip image_generation on non-images endpoints (forward the client payload unchanged); behaves like "chat" on /v1/images/* endpoints.
disable-image-generation:false
# Base model used by the legacy hosted image_generation tool path when a Codex image request is not proxied directly through the Image API.
# Must start with "gpt-" (case-insensitive). If unset or invalid, defaults to "gpt-5.4-mini".
# gpt-image-2-base-model: "gpt-5.4-mini"
# How long video IDs returned by /openai/v1/videos and xAI video creation stay bound
# to the credential that created them. Default: 3h.
# rebuild-mid-system-message: false # optional: default is false; when true, move messages with role "system" into the top-level Claude system field
# cloak: # optional: request cloaking for non-Claude-Code clients
# mode: "auto" # "auto" (default): cloak only when client is not Claude Code
# # "always": always apply cloaking
# # "never": never apply cloaking
# # This "cloak" block applies to this claude-api-key entry only. For Claude OAuth
# # credentials, set the same options in the auth/token JSON file via "cloak_mode" /
# # "cloak_strict_mode" / "cloak_sensitive_words" / "cloak_cache_user_id". The top-level
# # "disable-claude-cloak-mode: true" disables cloaking for all Claude credentials at once.
# strict-mode: false # false (default): prepend Claude Code prompt to user system messages
# # true: strip all user system messages, keep only Claude Code prompt
# sensitive-words: # optional: words to obfuscate with zero-width characters
# - "API"
# - "proxy"
# cache-user-id: true # optional: default is false; set true to reuse cached user_id per API key instead of generating a random one each request
# experimental-cch-signing: false # optional: default is false; when true, sign the final /v1/messages body using the current Claude Code cch algorithm
# # keep this disabled unless you explicitly need the behavior, so upstream seed changes fall back to legacy proxy behavior
# Default headers for Claude API requests. Update when Claude Code releases new versions.
# In legacy mode, user-agent/package-version/runtime-version/timeout are used as fallbacks
- Avoid Claude Code “Auth conflict”: do **not** set both `ANTHROPIC_AUTH_TOKEN` and `ANTHROPIC_API_KEY` at the same time.
- Restart Claude Code after editing settings so the new env vars take effect.
## Account risk warning
Claude/Anthropic OAuth, Google/Gemini OAuth, Gemini CLI OAuth, and Antigravity OAuth are unofficial compatibility paths. Providers may treat proxy, automation, shared-token, or third-party OAuth traffic as abnormal usage or a policy violation. These flows can risk quota loss, account restriction, or account suspension.
Do not use production, billing-critical, school/work, or irreplaceable personal accounts with these OAuth paths unless you accept that risk. Prefer official API keys or officially supported developer access for important accounts.
## Claude OAuth quota limitation
Anthropic currently treats third-party app traffic differently from regular Claude.ai or Claude Code subscription usage. If a Claude OAuth request fails with:
```text
Third-party apps now draw from your extra usage, not your plan limits.
Add more at claude.ai/settings/usage and keep going.
```
that response is coming from Anthropic, not ProxyPilot. It means the OAuth credential is valid, but Anthropic is requiring paid extra usage for this third-party API path. ProxyPilot cannot make those requests draw from normal Claude.ai subscription quota.
For Claude through ProxyPilot, either add extra usage in Anthropic settings, use a supported API-key billing path, or route the client to another provider/model alias such as Antigravity, Codex, Gemini, or Kiro.
## Server-side model aliasing (Claude handler)
CLIProxyAPI rewrites common Claude Code model aliases to locally-available models before routing:
@@ -57,12 +57,16 @@ proxypilot --codex-login # Login to Codex using OAuth
proxypilot --claude-login # Login to Claude using OAuth
proxypilot --qwen-login # Login to Qwen using OAuth
proxypilot --antigravity-login # Login to Antigravity using OAuth
proxypilot --kiro-login # Login to Kiro using Google OAuth
proxypilot --kiro-aws-login # Login to Kiro using AWS Builder ID
proxypilot --kiro-login # Login to Kiro using AWS Builder ID
proxypilot --kiro-aws-login # Login to Kiro using AWS Builder ID device code
proxypilot --minimax-login # Add MiniMax API key
proxypilot --zhipu-login # Add Zhipu AI API key
```
Account risk warning: `--claude-login`, `--login` / Gemini, Gemini CLI OAuth, and `--antigravity-login` are unofficial compatibility login paths. Providers may treat proxy, automation, shared-token, or third-party OAuth traffic as abnormal usage or a policy violation. These flows can risk quota loss, account restriction, or account suspension. Prefer official API-key or officially supported developer access for accounts you cannot afford to lose.
Kiro Google/GitHub OAuth is not currently supported because AWS Cognito rejects third-party localhost callbacks. Use AWS Builder ID or import a token from the official Kiro IDE instead.
Account risk warning: Antigravity, Gemini/Gemini CLI, and Claude login launchers use unofficial compatibility OAuth paths. Providers may treat proxy, automation, shared-token, or third-party OAuth traffic as abnormal usage or a policy violation. These flows can risk quota loss, account restriction, or account suspension. Use disposable or non-critical accounts only if you accept that risk; prefer official API keys or officially supported developer access for important accounts.
Merged upstream CLIProxyAPI release `v6.9.7` into ProxyPilot on a dedicated sync branch, carrying forward ProxyPilot branding and local-manual release workflow choices while absorbing the upstream changes from `v6.9.6` and `v6.9.7`.
Re-established a fully local Windows installer build path on Linux using a repo-scoped Wine prefix plus Inno Setup so the `Setup.exe` can be built without CI/CD.
## Upstream Releases Included
-`v6.9.6` - intermediate upstream changes now included through the `v6.9.7` merge
-`v6.9.7` - Codex executor/cache behavior updates, Amp response rewriting improvements, scheduler/auth updates, and related tests
## Conflict Resolution Notes
- Kept the ProxyPilot README and removed upstream `README_CN.md` and `README_JA.md` revivals because this fork intentionally does not ship those translation files.
- Followed upstream on the Codex continuity revert by deleting `internal/runtime/executor/codex_continuity.go` and aligning the Codex cache tests with `v6.9.7`, since upstream explicitly reverted that helper rather than evolving it.
- Preserved the existing fork policy of local/manual releases instead of changing CI or workflow behavior as part of this sync.
## Repo State Updates
- Updated `UPSTREAM_VERSION` to `v6.9.7`.
- Updated `features.json` upstream marker to `CLIProxyAPI v6.9.7`.
- Prepared a local Windows installer toolchain using Wine + Inno Setup for the upcoming `v0.3.0-dev-0.47` release build.
## Pending Verification
-`mise exec go@1.26.0 -- go build ./cmd/server ./cmd/proxypilot-tray ./cmd/proxypilotpack`
-`mise exec go@1.26.0 -- go vet ./...`
-`mise exec go@1.26.0 -- go test ./...`
- full local release asset build for `v0.3.0-dev-0.47`
-`gh release list -R Finesssee/ProxyPilot --limit 5`
Merged upstream CLIProxyAPI release `v6.9.10` into ProxyPilot on a dedicated sync branch and preserved the fork's local/manual release workflow.
Reconciled upstream's executor helper-package move with ProxyPilot's existing executor call sites by keeping the new `internal/runtime/executor/helps/` layout while restoring compatibility entrypoints in `internal/runtime/executor/`.
## Upstream Releases Included
-`v6.9.8` - intermediate upstream changes now included through the `v6.9.10` merge
-`v6.9.9` - intermediate upstream changes now included through the `v6.9.10` merge
-`v6.9.10` - latest upstream sync target for this release cycle
## Conflict Resolution Notes
- Kept the ProxyPilot README and continued to omit upstream `README_CN.md` and `README_JA.md` revivals because this fork does not ship those translation files.
- Preserved ProxyPilot's auth-file persistence behavior, including `prefix`, `proxy_url`, `priority`, and last-refresh handling, while also bringing in upstream custom-header hydration and patch support.
- Kept upstream's `internal/runtime/executor/helps/` reorganization, but restored executor-package compatibility wrappers/files so existing fork-specific executors still compile without a larger refactor in the same release pass.
- Continued to omit the upstream TUI translation/usage-tab files because ProxyPilot's current TUI surface does not carry those forked files.
## Repo State Updates
- Updated `UPSTREAM_VERSION` to `v6.9.10`.
- Updated `features.json` upstream marker to `CLIProxyAPI v6.9.10`.
- Recorded the merge commit `chore: merge upstream CLIProxyAPI v6.9.10` before starting validation and release assembly.
## Pending Verification
-`mise exec go@1.26.0 -- go build ./cmd/server ./cmd/proxypilot-tray ./cmd/proxypilotpack`
-`mise exec go@1.26.0 -- go vet ./...`
-`mise exec go@1.26.0 -- go test ./...`
- full local release asset build for `v0.3.0-dev-0.48`
-`gh release list -R Finesssee/ProxyPilot --limit 5`
Merged upstream CLIProxyAPI release `v6.9.12` into ProxyPilot on a dedicated sync branch and kept the existing local/manual release workflow unchanged.
This catch-up pull included the upstream delta from `v6.9.11` through `v6.9.12` and merged cleanly without any fork-specific conflict resolution work.
## Upstream Releases Included
-`v6.9.11` - intermediate upstream changes now included through the `v6.9.12` merge
-`v6.9.12` - latest upstream sync target for this release cycle
## Merge Notes
- The merge applied cleanly with upstream changes concentrated in `config.example.yaml`, `internal/config/sdk_config.go`, `internal/runtime/executor/qwen_executor.go`, and `sdk/api/handlers/gemini/gemini-cli_handlers.go`.
- No additional ProxyPilot compatibility shims were needed beyond the executor-wrapper structure restored in the prior sync.
Merged upstream CLIProxyAPI release `v6.9.15` into ProxyPilot on a dedicated sync branch based on the latest `origin/main`.
Kept the local management-asset security fix from `origin/main`, preserved ProxyPilot branding and local/manual release workflow choices, and absorbed the upstream delta from `v6.9.13` through `v6.9.15`.
## Upstream Releases Included
-`v6.9.13` - vertex credential namespacing support, websocket custom tool-call repair, and model catalog refreshes
-`v6.9.14` - antigravity version refresh updates and additional upstream maintenance changes
- Kept the ProxyPilot README branding and continued to omit upstream `README_CN.md` and `README_JA.md` revivals because this fork does not ship those translated files.
- Kept the existing local/manual release workflow and combined the fork's broader `.gitignore` with upstream's additional local-tool entries.
- Preserved the local `internal/managementasset/updater.go` security behavior that removes the unverified fallback download path while accepting the rest of the upstream sync.
- Merged `cmd/server/main.go` semantically so ProxyPilot keeps its wider CLI surface while also adding upstream `--vertex-import-prefix` support.
## Repo State Updates
- Updated `UPSTREAM_VERSION` to `v6.9.15`.
- Updated `features.json` upstream marker to `CLIProxyAPI v6.9.15`.
- Prepared the repo for the next clean release tag: `v0.3.0-dev-0.51`.
- kept ProxyPilot branding and docs flow in `README.md`
- did not revive upstream locale README files (`README_CN.md`, `README_JA.md`)
- preserved ProxyPilot `qwen` and `iflow` auth/runtime/config/model support while taking upstream auth proxy-override support and Claude Opus 4.7 model catalog updates
- kept local synthetic idempotency-key behavior in `sdk/api/handlers/handlers.go` and updated the new upstream metadata test to match fork behavior
- Validation:
-`mise exec go@1.26.0 -- go build ./cmd/server ./cmd/proxypilot-tray ./cmd/proxypilotpack`
- no textual conflicts in the upstream merge; existing ProxyPilot fork surfaces carried forward cleanly
- corrected stale upstream marker files from the prior `v6.9.30` sync so `.upstream-sync-tag` and `.upstream-sync-sha` now match the merged upstream release
- kept the existing fork behavior around local provider support while taking upstream Codex image-generation, Antigravity credits fallback, logging, and `/healthz` improvements
-`management-api/`: Management API and resource capability only.
-`host-callback/`: minimal plugin resource that demonstrates host callbacks.
-`host-callback-auth-files/`: Go-only plugin resource that calls host auth file callbacks.
-`host-model-callback/`: Go-only plugin resource that calls the host model execution callbacks.
Most standard capability examples contain `go/`, `c/`, and `rust/` subdirectories. Specialized examples may provide only the implementation language they need.
## Codex Service Tier
`codex-service-tier` declares the request normalization capability. When `fast` is `true`, it sets `service_tier` to `priority` for requests where `req.ToFormat` is `codex` and `req.Model` is `gpt-5.5`.
```yaml
plugins:
configs:
codex-service-tier:
enabled:true
priority:1
fast:false
```
## Host Auth Files Callback
`host-callback-auth-files` declares the Management API capability and exposes a browser resource named `Host Auth Files`. The resource demonstrates `host.auth.list`, `host.auth.get` (physical JSON file), `host.auth.get_runtime`, and `host.auth.save`.
```yaml
plugins:
configs:
host-callback-auth-files:
enabled:true
priority:1
```
See `host-callback-auth-files/README.md` for URL examples.
## Host Model Callback
`host-model-callback` declares the Management API capability and exposes a browser resource named `Host Model Callback`. The resource calls `host.model.execute` for non-streaming requests and `host.model.execute_stream` plus `host.model.stream_read` for streaming requests. It demonstrates explicit stream close with `host.model.stream_close` and an `implicit_close=true` option for RPC-scope host cleanup.
When the resource forwards its `host_callback_id`, CPA identifies the plugin that initiated the host model callback and skips that same plugin's interceptors for the nested execution. This makes host model callbacks non-recursive for the caller while allowing other plugins to intercept the nested request.
```yaml
plugins:
configs:
host-model-callback:
enabled:true
priority:1
```
The default example model is `gpt-5.5`, but the request succeeds only when the current CPA model and auth configuration can route that model.
## Scheduler
`scheduler` declares the scheduler capability. It can select a configured auth ID from the candidate list, delegate to the built-in `fill-first` or `round-robin` scheduler, or reject picks when `deny` is `true`.
```yaml
plugins:
configs:
scheduler:
enabled:true
priority:1
auth_id:""
delegate:""
deny:false
```
`auth_id` selects a matching candidate when `delegate` is empty. `delegate` accepts `""`, `fill-first`, or `round-robin`; other non-empty values leave the pick unhandled. `deny` returns a scheduler error.
## Build All Examples
```bash
make -C examples/plugin list
make -C examples/plugin build
```
Artifacts are written to `examples/plugin/bin`.
## Notes
`protocol-format` uses a minimal executor because format declarations belong to executor capabilities.
`host-callback` uses a minimal plugin resource because host callbacks are invoked from plugin methods and are not standalone capabilities.
Menu resources returned by `management.register` through the `resources` field are exposed by CPA under `/v0/resource/plugins/<pluginID>/...`. Authenticated plugin Management API routes remain under `/v0/management/...`.
# Claude Code Web Search Router (ModelRouter example)
This plugin demonstrates **ModelRouter** on Claude Code built-in `web_search` requests (see `temp/1.json` in the repo root for a captured request/response).
## What it detects
- Inbound protocol `claude` / `anthropic`
-`tools[]` with `type``web_search_20250305` or `web_search_20260209`
- Optional Claude Code heuristics: system text like “web search tool use”, or user text
| `fallback` (**default**) | Plugin **executor** runs **antigravity → codex → xai → tavily** (built-ins via `host.model.*`, Tavily in-plugin). On **429/503/502**, tries the next backend in the same request. Backends that fail often are **deprioritized on later requests** (in-memory penalty; no extra config). |
| `antigravity_google` / `codex_web_search` / `xai_web_search` / `tavily` | Same orchestration for that backend’s chain member(s): execution retry + penalty apply when multiple backends are eligible. |
Routing for `fallback` requires at least one runnable backend (providers in `AvailableProviders` where needed, resolvable antigravity model, or `tavily_api_keys`).
### xAI web search notes (aligned with upstream docs)
- **Model**: xAI documents `grok-4.3` for server-side `web_search`. This example sets `TargetModel` to **`grok-4.3`** when `xai_model` is empty (do not forward `claude-sonnet-4-6` to xAI).
- **Request shape**: Responses API `input` + `tools[]` with `"type": "web_search"`. Optional `filters.allowed_domains` / `filters.excluded_domains` (max 5 each, mutually exclusive).
- **Claude mapping today**: `internal/translator/codex/claude` copies Claude `allowed_domains` → `filters.allowed_domains`. Claude `blocked_domains` is **not** mapped to `excluded_domains` yet.
- **Executor**: `xai_executor` normalizes tools (drops unsupported `external_web_access` if present) and posts to `/responses`.
- **Response**: Citations / server tool metadata come back through OpenAI Responses SSE and are converted toward Claude `server_tool_use` / `web_search_tool_result` where the response translator supports it.
## Configuration
Plugin config lives under `plugins.configs.claude-web-search-router` (key must match the plugin name). Load the shared library via `plugins.path`.
### Recommended: fallback chain (default)
Tries **antigravity → codex → xai → tavily**; configure `tavily_api_keys` so the last step can succeed when built-in providers are missing or unavailable.
},Description:"Backend for Claude Code web_search. fallback (default): antigravity → codex → xai → tavily."},
{Name:"antigravity_model",Type:pluginapi.ConfigFieldTypeString,Description:"Antigravity googleSearch model (empty: registry lookup, then first supports_web_search)."},
{Name:"codex_model",Type:pluginapi.ConfigFieldTypeString,Description:"Codex Responses model for web_search (empty defaults to gpt-5.4, never client Claude model)."},
{Name:"xai_model",Type:pluginapi.ConfigFieldTypeString,Description:"xAI Responses model with web_search (empty uses grok-4.3, not the client Claude model)."},
{Name:"default_provider",Type:pluginapi.ConfigFieldTypeString,Description:"Built-in provider key when route=default_provider."},
{Name:"default_provider_model",Type:pluginapi.ConfigFieldTypeString,Description:"Optional execution model on default_provider route."},
{Name:"tavily_api_keys",Type:pluginapi.ConfigFieldTypeArray,Description:"Tavily API keys (round-robin) when route=tavily."},
{Name:"require_web_search_only",Type:pluginapi.ConfigFieldTypeBoolean,Description:"Require tools to be exclusively typed web_search (matches antigravity-only path)."},
// Override client by patching: executeStream uses loadedConfig keys + real URL.
// Test runTavilyClaudeStreamWithClient directly instead; for execute() we need config + mock URL.
// Use executor path with injected client via runTavilyClaudeStreamWithClient already covered.
_=server
claudeBody:=[]byte(`{"messages":[{"role":"user","content":"Perform a web search for the query: q"}],"tools":[{"type":"web_search_20250305","name":"web_search"}]}`)
write_response(response,"{\"ok\":true,\"result\":{\"Flags\":[{\"Name\":\"example-cli-c-command\",\"Usage\":\"Run the example plugin command\",\"Type\":\"bool\"}]}}");
write_response(response,r#"{"ok":false,"error":{"code":"invalid_method","message":"method is required"}}"#);
return1;
}
letmethod=matchCStr::from_ptr(method).to_str(){
Ok(value)=>value,
Err(_)=>{
write_response(response,r#"{"ok":false,"error":{"code":"invalid_method","message":"method is not utf-8"}}"#);
return1;
}
};
let_=request;
let_=request_len;
matchmethod{
"plugin.register"=>{write_response(response,"{\"ok\":true,\"result\":{\"schema_version\":1,\"metadata\":{\"Name\":\"example-cli-rust\",\"Version\":\"0.1.0\",\"Author\":\"router-for-me\",\"GitHubRepository\":\"https://github.com/router-for-me/CLIProxyAPI\",\"Logo\":\"https://example.invalid/example-cli-rust.png\",\"ConfigFields\":[]},\"capabilities\":{\"command_line_plugin\":true}}}");0},"plugin.reconfigure"=>{write_response(response,"{\"ok\":true,\"result\":{\"schema_version\":1,\"metadata\":{\"Name\":\"example-cli-rust\",\"Version\":\"0.1.0\",\"Author\":\"router-for-me\",\"GitHubRepository\":\"https://github.com/router-for-me/CLIProxyAPI\",\"Logo\":\"https://example.invalid/example-cli-rust.png\",\"ConfigFields\":[]},\"capabilities\":{\"command_line_plugin\":true}}}");0},"command_line.register"=>{write_response(response,"{\"ok\":true,\"result\":{\"Flags\":[{\"Name\":\"example-cli-rust-command\",\"Usage\":\"Run the example plugin command\",\"Type\":\"bool\"}]}}");0},"command_line.execute"=>{write_response(response,"{\"ok\":true,\"result\":{\"Stdout\":\"ImV4YW1wbGUtY2xpLXJ1c3QgY29tbWFuZCBleGVjdXRlZFxcbiI=\",\"ExitCode\":0}}");0},
This example registers a frontend auth provider with `frontend_auth_provider_exclusive: true`.
When enabled and selected, this provider becomes the only request authentication provider. Built-in config API keys and other frontend auth providers do not authenticate requests while this provider is active.
The example accepts requests that include:
```http
X-Example-Frontend-Auth: exclusive
```
Build:
```bash
cd examples/plugin/frontend-auth-exclusive/go
go build -buildmode=c-shared -o /tmp/cliproxy-frontend-auth-exclusive.dylib .
```
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.