- 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.
Drop the last affinity-related executor artifacts so the PR stays focused on the minimal Codex continuity fix set: stable prompt cache identity, stable session_id, and the executor-only behavior that was validated to restore cache reads.
Drop the chat-completions translator edits from this PR so the branch complies with the repository policy that forbids pull-request changes under internal/translator. The remaining PR stays focused on the executor-level Codex continuity fix that was validated to restore cache reuse.
Remove the experimental auth-affinity routing changes from this PR so it stays focused on the validated Codex continuity fix. This keeps the prompt-cache repair while avoiding unrelated routing-policy concerns such as provider/model affinity scope, lifecycle cleanup, and hard-pin fallback semantics.
Keep sticky auth affinity limited to matching providers and stop persisting execution-session IDs as long-lived affinity keys so provider switching and normal streaming traffic do not create incorrect pins or stale affinity state.
Stop using one-shot idempotency keys as long-lived auth-affinity identifiers and remove raw affinity-key values from debug logs so sticky routing keeps its continuity benefits without creating avoidable memory growth or credential exposure risks.
Restore Claude continuity after the continuity refactor, keep auth-affinity keys out of upstream Codex session identifiers, and only persist affinity after successful execution so retries can still rotate to healthy credentials when the first auth fails.
Align websocket continuity resolution with the HTTP Codex path, make auth-affinity principal keys use a stable string representation, and extract small helpers that remove duplicated continuity and affinity logic without changing the validated cache-hit behavior.
Prompt caching on Codex was not reliably reusable through the proxy because repeated chat-completions requests could reach the upstream without the same continuity envelope. In practice this showed up most clearly with OpenCode, where cache reads worked in the reference client but not through CLIProxyAPI, although the root cause is broader than OpenCode itself.
The proxy was breaking continuity in several ways: executor-layer Codex request preparation stripped prompt_cache_retention, chat-completions translation did not preserve that field, continuity headers used a different shape than the working client behavior, and OpenAI-style Codex requests could be sent without a stable prompt_cache_key. When that happened, session_id fell back to a fresh random value per request, so upstream Codex treated repeated requests as unrelated turns instead of as part of the same cacheable context.
This change fixes that by preserving caller-provided prompt_cache_retention on Codex execution paths, preserving prompt_cache_retention when translating OpenAI chat-completions requests to Codex, aligning Codex continuity headers to session_id, and introducing an explicit Codex continuity policy that derives a stable continuity key from the best available signal. The resolution order prefers an explicit prompt_cache_key, then execution session metadata, then an explicit idempotency key, then stable request-affinity metadata, then a stable client-principal hash, and finally a stable auth-ID hash when no better continuity signal exists.
The same continuity key is applied to both prompt_cache_key in the request body and session_id in the request headers so repeated requests reuse the same upstream cache/session identity. The auth manager also keeps auth selection sticky for repeated request sequences, preventing otherwise-equivalent Codex requests from drifting across different upstream auth contexts and accidentally breaking cache reuse.
To keep the implementation maintainable, the continuity resolution and diagnostics are centralized in a dedicated Codex continuity helper instead of being scattered across executor flow code. Regression coverage now verifies retention preservation, continuity-key precedence, stable auth-ID fallback, websocket parity, translator preservation, and auth-affinity behavior. Manual validation confirmed prompt cache reads now occur through CLIProxyAPI when using Codex via OpenCode, and the fix should also benefit other clients that rely on stable repeated Codex request continuity.
The Codex/OpenAI Responses API does not support the stream_options
parameter. When clients (e.g. Amp CLI) include stream_options in their
requests, CLIProxyAPI forwards it as-is, causing a 400 error:
{"detail":"Unsupported parameter: stream_options"}
Strip stream_options alongside the other unsupported parameters
(previous_response_id, prompt_cache_retention, safety_identifier)
in Execute, ExecuteStream, and CountTokens.
- Read maxAssetDownloadSize+1 bytes and error if exceeded, preventing
silent truncation that could write a broken management.html to disk
- Log explicit warning when fallback URL is used without digest
verification, so users are aware of the reduced security guarantee
- Abort update when SHA256 digest mismatch is detected instead of
logging a warning and proceeding (prevents MITM asset replacement)
- Cap asset download size to 10 MB via io.LimitReader (defense-in-depth
against OOM from oversized responses)
- Add `auto-update-panel` config option (default: false) to make the
periodic background updater opt-in; the panel is still downloaded
on first access when missing, but no longer silently auto-updated
every 3 hours unless explicitly enabled
Apply SanitizeFunctionName on request and RestoreSanitizedToolName on
response for: gemini/claude, gemini/openai/chat-completions,
gemini/openai/responses, antigravity/openai/chat-completions,
gemini-cli/openai/chat-completions.
Also update SanitizedToolNameMap to handle OpenAI format
(tools[].function.name) in addition to Claude format (tools[].name).
Claude Code and MCP clients may send tool names containing characters
invalid for Gemini's function_declarations (e.g. '/', '@', spaces).
Sanitize on request via SanitizeFunctionName and restore original names
on response for both antigravity/claude and gemini-cli/claude translators.
- Introduced a new method `buildRecord` in `usageReporter` to encapsulate record creation, improving code readability and maintainability.
- Added latency tracking to usage records, ensuring accurate reporting of request latencies.
- Updated tests to validate the inclusion of latency in usage records and ensure proper functionality of the new reporting structure.
When Claude sends redacted thinking with empty text, the translator
was omitting the "text" field from thought parts. Google Antigravity
API requires this field, causing 500 "Unknown Error" responses.
Verified: 129/129 error logs with empty thought → 500, 0/97 success
logs had empty thought. After fix: 0 new "Unknown Error" 500s.
- Log a warning instead of silently ignoring sjson.SetBytes errors in the TranslateRequest fallback path
- Add registry_test.go with tests covering the fallback model normalization and verifying registered transforms take precedence
When no request translator is registered for a format pair (e.g.
openai-response → openai-response), TranslateRequest returned the raw
payload unchanged. This caused client-side model prefixes (e.g.
"copilot/gpt-5-mini") to leak into upstream requests, resulting in
"The requested model is not supported" errors from providers.
The fallback path now updates the "model" field in the payload to
match the resolved model name before returning.
When enabled, the server uses only the embedded models.json loaded at
init() and skips registry.StartModelsUpdater(), disabling the initial
remote fetch and 3-hour periodic refresh. The management panel
auto-updater (managementasset.StartAutoUpdater) is unaffected.
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>
gjson.Parse() marks any string starting with { or [ as gjson.JSON type,
even when the content is not valid JSON (e.g. macOS plist format, truncated
tool results). This caused sjson.SetRaw to embed non-JSON content directly
into the Gemini API request payload, producing 400 errors.
Add json.Valid() check before using SetRaw to ensure only actually valid
JSON is embedded raw. Non-JSON content now falls through to sjson.Set
which properly escapes it as a JSON string.
Fixes#2161
The Claude-to-Gemini translator derived function names by splitting
tool_use_id on "-", which produced empty strings for IDs with exactly
2 segments (e.g. toolu_tool-<uuid>). Replace the string-splitting
heuristic with a lookup map built from tool_use blocks during the
main processing loop, with fallback to the raw ID on miss.
Only emit note in listAuthFilesFromDisk when the JSON value is actually
a string (gjson.String), matching the synthesizer/buildAuthFileEntry
behavior. Non-string values like numbers or booleans are now ignored
instead of being coerced via gjson.String().
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
buildAuthFileEntry now falls back to reading priority/note from
auth.Metadata when Attributes lacks them. This covers auths registered
via UploadAuthFile which bypass the synthesizer and only populate
Metadata from the raw JSON.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Read note from Attributes (consistent with priority) in buildAuthFileEntry,
fixing missing note on Gemini multi-project virtual auth cards.
- Propagate note from primary to virtual auths in SynthesizeGeminiVirtualAuths,
mirroring existing priority propagation.
- Sync note/priority writes to both Metadata and Attributes in PatchAuthFileFields,
with refactored nil-check to reduce duplication (review feedback).
- Validate priority type in fallback disk-read path instead of coercing all values
to 0 via gjson.Int(), aligning with the auth-manager code path.
- Add regression tests for note synthesis, virtual-auth note propagation, and
end-to-end multi-project Gemini note inheritance.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Gemini API rejects uniqueItems in tool schemas with 400. Add it to
unsupportedConstraints alongside minItems/maxItems where it belongs.
Same class of fix as #1424 and #1531.
When assistant has tool_calls but no text content, the translator
emitted an empty message into the Responses API input array before
function_call items. The API then couldn't match function_call_output
to its function_call by call_id, returning:
No tool output found for function call ...
Only emit assistant messages that have content parts. Tool-call-only
messages now produce function_call items directly.
Added 9 tests for tool calling translation covering single/parallel
calls, multi-turn conversations, name shortening, empty content
edge cases, and call_id integrity.
When an auth file is deleted and re-created with the same path/ID, the
new auth could inherit stale ModelStates (cooldown/backoff) from the
previously disabled entry, preventing it from being routed.
Gate runtime state inheritance (ModelStates, LastRefreshedAt,
NextRefreshAfter) on both existing and incoming auth being non-disabled
in Manager.Update and Service.applyCoreAuthAddOrUpdate.
Closes#2061
The list endpoint previously omitted priority and note, which are stored
inside each auth file's JSON content. This adds them to both the normal
(auth-manager) and fallback (disk-read) code paths, and extends
PATCH /auth-files/fields to support writing the note field.
Co-Authored-By: Claude Opus 4.6 <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.
1. Claude translator: add CleanJSONSchemaForGemini() to sanitize tool
input schemas (removes $schema, anyOf, const, format, etc.) and
delete eager_input_streaming from tool declarations. Remove fragile
bytes.Replace for format:"uri" now covered by schema cleaner.
2. Gemini native translator: filter out content entries with empty or
missing parts arrays to prevent Gemini API 400 error "required
oneof field 'data' must have one initialized field".
Both fixes align gemini-cli with protections already present in the
antigravity translator.
when Amp or Claude Code sends functionResponse with an empty name in Gemini
conversation history, the Gemini API rejects the request with 400
"Name cannot be empty". this fix backfills empty names from the
corresponding preceding functionCall parts using positional matching.
covers all three Gemini translator paths:
- gemini/gemini (direct API key)
- antigravity/gemini (OAuth)
- gemini-cli/gemini (Gemini CLI)
also switches fixCLIToolResponse pending group matching from LIFO to
FIFO to correctly handle multiple sequential tool call groups.
fixes#1903
feat(proxy): centralize proxy handling with `proxyutil` package and enhance test coverage
- Added `proxyutil` package to simplify proxy handling across the codebase.
- Refactored various components (`executor`, `cliproxy`, `auth`, etc.) to use `proxyutil` for consistent and reusable proxy logic.
- Introduced support for "direct" proxy mode to explicitly bypass all proxies.
- Updated tests to validate proxy behavior (e.g., `direct`, HTTP/HTTPS, and SOCKS5).
- Enhanced YAML configuration documentation for proxy options.
test(auth-scheduler): add benchmarks and priority-based scheduling improvements
- Added `BenchmarkManagerPickNextMixedPriority500` for mixed-priority performance assessment.
- Updated `pickNextMixed` to prioritize highest ready priority tiers.
- Introduced `highestReadyPriorityLocked` and `pickReadyAtPriorityLocked` for better scheduling logic.
- Added unit test to validate selection of highest priority tiers in mixed provider scenarios.
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.
When new OAuth auth files are added while the service is running,
`applyCoreAuthAddOrUpdate` calls `coreManager.Register()` (which upserts
into the scheduler) BEFORE `registerModelsForAuth()`. At upsert time,
`buildScheduledAuthMeta` snapshots `supportedModelSetForAuth` from the
global model registry — but models haven't been registered yet, so the
set is empty. With an empty `supportedModelSet`, `supportsModel()`
always returns false and the new auth is never added to any model shard.
Additionally, when all existing accounts are in cooldown, the scheduler
returns `modelCooldownError`, but `shouldRetrySchedulerPick` only
handles `*Error` types — so the `syncScheduler` safety-net rebuild
never triggers and the new accounts remain invisible.
Fix:
1. Add `RefreshSchedulerEntry()` to re-upsert a single auth after its
models are registered, rebuilding `supportedModelSet` from the
now-populated registry.
2. Call it from `applyCoreAuthAddOrUpdate` after `registerModelsForAuth`.
3. Make `shouldRetrySchedulerPick` also match `*modelCooldownError` so
the full scheduler rebuild triggers when all credentials are cooling
down — catching any similar stale-snapshot edge cases.
The Gemini v1internal (cloudcode-pa) and Antigravity Manager endpoints
require camelCase "systemInstruction" in request JSON. The current
snake_case "system_instruction" causes system prompts to be silently
ignored when routing through these endpoints.
Replace all "system_instruction" JSON keys with "systemInstruction" in
chat-completions and responses request translators.
- Added comprehensive unit tests for `authScheduler` and related components.
- Implemented `authScheduler` with support for Round Robin, Fill First, and custom selector strategies.
- Improved tracking of auth states, cooldowns, and recovery logic in scheduler.
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).
test(websocket): add tests for incremental input and prewarm handling logic
- Added test cases for incremental input support based on upstream capabilities.
- Introduced validation for prewarm handling of `response.create` messages locally.
- Enhanced test coverage for websocket executor behavior, including payload forwarding checks.
- Updated websocket implementation with prewarm and incremental input logic for better testability.
test(translator): add unit tests for OpenAI to Claude requests and tool result handling
- Introduced tests for converting OpenAI requests to Claude with text, base64 images, and URL images in tool results.
- Refactored `convertClaudeToolResultContent` and related functionality to properly handle raw content with images and text.
- Updated conversion logic to streamline image handling for both base64 and URL formats.
- Simplified connection logic by removing `connCreateSent` and related state handling.
- Updated `buildCodexWebsocketRequestBody` to always use `response.create`.
- Added unit tests to validate `response.create` behavior and beta header preservation.
- Dropped unsupported `response.append` and outdated `response.done` event types.
- Add model to GetGeminiModels()
- Add model to GetGeminiVertexModels()
- Add model to GetGeminiCLIModels()
- Add model to GetAIStudioModels()
- Add to AntigravityModelConfig with thinking levels
- Update gemini-3-flash-preview description
Registers the new lightweight Gemini model across all provider
endpoints for cost-effective high-volume usage scenarios.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
SetOAuthSessionError previously sent generic messages to the management
panel (e.g. "Failed to complete Gemini CLI onboarding"), hiding the
actual error returned by Google APIs. The specific error was only
written to the server log via log.Errorf, which is often inaccessible
in headless/Docker deployments.
Include the upstream error in all 8 OAuth error paths so the
management panel shows actionable messages like "no Google Cloud
projects available for this account" instead of a generic failure.
normalizeCacheControlTTL unconditionally re-serializes the entire request
body through json.Unmarshal/json.Marshal even when no TTL normalization
is needed. Go's json.Marshal randomizes map key order and HTML-escapes
<, >, & characters (to \u003c, \u003e, \u0026), producing different raw
bytes on every call.
Anthropic's prompt caching uses byte-prefix matching, so any byte-level
difference causes a cache miss. This means the ~119K system prompt and
tools are re-processed on every request when routed through CPA.
The fix adds a bool return to normalizeTTLForBlock to indicate whether
it actually modified anything, and skips the marshal step in
normalizeCacheControlTTL when no blocks were changed.
Add util.SanitizeClaudeToolID() to replace non-conforming characters in
tool_use.id fields across all five response translators (gemini, codex,
openai, antigravity, gemini-cli).
Upstream tool names may contain dots or other special characters
(e.g. "fs.readFile") that violate Claude's ID validation regex.
The sanitizer replaces such characters with underscores and provides
a generated fallback for empty IDs.
Fixes#1872, Fixes#1849
Made-with: Cursor
- Add `TestTriggerServerUpdateCancelsPendingTimerOnImmediate` to verify proper handling of server update debounce and timer cancellation.
- Fix logic in `triggerServerUpdate` to prevent duplicate timers and ensure proper cleanup of pending state.
The instructions restore logic was originally needed when the proxy
injected custom instructions (per-model system prompts) into requests.
Since ac802a46 removed the injection system, the proxy no longer
modifies instructions before forwarding. The upstream response's
instructions field now matches the client's original value, making
the restore a no-op.
Also removes unused sjson import.
Closesrouter-for-me/CLIProxyAPI#1868
fix(gemini): add `deprecated` to unsupported schema keywords
Add `deprecated` to the list of unsupported schema metadata fields in Gemini and update tests to verify its removal.
- Set Accept-Encoding: identity for SSE streams; upstream must not compress
line-delimited SSE bodies that bufio.Scanner reads directly
- Re-enforce identity after ApplyCustomHeadersFromAttrs to prevent auth
attribute injection from re-enabling compression on the stream path
- Add peekableBody type wrapping bufio.Reader for non-consuming magic-byte
inspection of the first 4 bytes without affecting downstream readers
- Detect gzip (0x1f 0x8b) and zstd (0x28 0xb5 0x2f 0xfd) by magic bytes
when Content-Encoding header is absent, covering misbehaving upstreams
- Remove if-Content-Encoding guard on all three error paths (Execute,
ExecuteStream, CountTokens); unconditionally delegate to decodeResponseBody
so magic-byte detection applies consistently to all response paths
- Add 10 tests covering stream identity enforcement, compressed success bodies,
magic-byte detection without headers, error path decoding, and
auth attribute override prevention
Fixes#5 - The 'tui' flag was registered twice via flag.BoolVar(),
causing a 'panic: flag redefined: tui' crash on startup.
Removed the duplicate at line 208, keeping the original at line 181.
Claude's Tool Search feature (advanced-tool-use-2025-11-20 beta) adds
defer_loading field to tool definitions. When proxying Claude requests
to Codex or Gemini, this unknown field causes 400 errors upstream.
Strip defer_loading (and cache_control where missing) in all three
Claude-to-upstream translation paths:
- codex/claude: defer_loading + cache_control
- gemini-cli/claude: defer_loading
- gemini/claude: defer_loading
Fixes#1725, Fixes#1375
Add support for Claude's "adaptive" and "auto" thinking modes using `output_config.effort`. Introduce support for new effort level "max" in adaptive thinking. Update thinking logic, validate model capabilities, and extend converters and handling to ensure compatibility with adaptive modes. Adjust static model data with supported levels and refine handling across translators and executors.
## Problem
When using Antigravity Claude models through CLIProxyAPI, the thinking
chain (reasoning content) does not display in the Amp client.
## Root Cause
The Amp client sends `thinking: {"type": "auto"}` in its requests,
but `ConvertClaudeRequestToAntigravity` only handled `"enabled"` and
`"adaptive"` types in its switch statement. The `"auto"` type was
silently ignored, resulting in no `thinkingConfig` being set in the
translated Gemini request. Without `thinkingConfig`, the Antigravity
API returns responses without any thinking content.
Additionally, the Antigravity API for Claude models does not support
`thinkingBudget: -1` (auto mode sentinel). It requires a concrete
positive budget value. The fix uses 128000 as the budget for "auto"
mode, which `ApplyThinking` will then normalize to stay within the
model's actual limits (e.g., capped to `maxOutputTokens - 1`).
## Changes
### internal/translator/antigravity/claude/antigravity_claude_request.go
1. **Add "auto" case** to the thinking type switch statement.
Sets `thinkingBudget: 128000` and `includeThoughts: true`.
The budget is subsequently normalized by `ApplyThinking` based
on model-specific limits.
2. **Add "auto" to hasThinking check** so that interleaved thinking
hints are injected for tool-use scenarios when Amp sends
`thinking.type="auto"`.
### internal/registry/model_definitions_static_data.go
3. **Add Thinking configuration** for `claude-sonnet-4-6`,
`claude-sonnet-4-5`, and `claude-opus-4-6` in
`GetAntigravityModelConfig()` -- these were previously missing,
causing `ApplyThinking` to skip thinking config entirely.
## Testing
- Deployed to Railway test instance (cpa-thinking-test)
- Verified via debug logging that:
- Amp sends `thinking: {"type": "auto"}`
- CPA now translates this to `thinkingConfig: {thinkingBudget: 128000, includeThoughts: true}`
- `ApplyThinking` normalizes the budget to model-specific limits
- Antigravity API receives the correct thinkingConfig
Amp-Thread-ID: https://ampcode.com/threads/T-019ca511-710d-776d-a07c-4b750f871a93
Co-authored-by: Amp <amp@ampcode.com>
Captured and compared outgoing requests from CLIProxyAPI against real
Claude Code 2.1.63 and fixed all detectable differences:
Headers:
- Update anthropic-beta to match 2.1.63: replace fine-grained-tool-streaming
and prompt-caching-2024-07-31 with context-management-2025-06-27 and
prompt-caching-scope-2026-01-05
- Remove X-Stainless-Helper-Method header (real Claude Code does not send it)
- Update default User-Agent from "claude-cli/2.1.44 (external, sdk-cli)" to
"claude-cli/2.1.63 (external, cli)"
- Force Claude Code User-Agent for non-Claude clients to avoid leaking
real client identity (e.g. curl, OpenAI SDKs) during cloaking
Body:
- Inject x-anthropic-billing-header as system[0] (matches real format)
- Change system prompt identifier from "You are Claude Code..." to
"You are a Claude agent, built on Anthropic's Claude Agent SDK."
- Add cache_control with ttl:"1h" to match real request format
- Fix user_id format: user_[64hex]_account_[uuid]_session_[uuid]
(was missing account UUID)
- Disable tool name prefix (set claudeToolPrefix to empty string)
TLS:
- Switch utls fingerprint from HelloFirefox_Auto to HelloChrome_Auto
(closer to Node.js/OpenSSL used by real Claude Code)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Public Google OAuth client IDs and secrets from upstream CLIProxyAPI.
These are intentionally embedded (installed/CLI app OAuth flow) and
identical to the upstream public repo. Allowlisting prevents GitHub
push protection from blocking merges.
Guard the openai-response streaming path against truncated/invalid SSE data payloads by validating data: JSON before forwarding; surface a 502 terminal error instead of letting clients crash with JSON parse errors.
Move base64 image data from Claude tool_result into functionResponse.parts
as inlineData instead of outer sibling parts, preventing context bloat.
Unify all inlineData field naming to camelCase mimeType across Claude,
OpenAI, and Gemini translators. Add comprehensive edge case tests and
Gemini-side regression test for functionResponse.parts preservation.
CI blocks PRs that modify internal/translator. Revert translator edits and keep only the /v1/responses streaming error-chunk fix; file an issue for translator conformance work.
Ensure response.created and response.completed chunks produced by the OpenAI/Gemini/Claude translators always include required fields (response.model and response.usage) so clients validating Responses SSE do not fail schema validation.
When /v1/responses streaming fails after headers are sent, we now emit a type=error chunk instead of an HTTP-style {error:{...}} payload, preventing AI SDK chunk validation errors.
- Add 60 requests/minute rate limiting per credential using sliding window
- Detect insufficient_quota errors and set cooldown until next day (Beijing time)
- Map quota errors (HTTP 403/429) to 429 with retryAfter for conductor integration
- Cache Beijing timezone at package level to avoid repeated syscalls
- Add redactAuthID function to protect credentials in logs
- Extract wrapQwenError helper to consolidate error handling
- force http/1.1 instead of http/2
- explicit connection close
- strip proxy headers X-Forwarded-For and X-Real-IP
- add project id to fetch models payload
Changes the RoundRobinSelector to use two-level round-robin when
gemini-cli virtual auths are detected (via gemini_virtual_parent attr):
- Level 1: cycle across credential groups (parent accounts)
- Level 2: cycle within each group's project auths
Credentials start from a random offset (rand.IntN) for fair distribution.
Non-virtual auths and single-credential scenarios fall back to flat RR.
Adds 3 test cases covering multi-credential grouping, single-parent
fallback, and mixed virtual/non-virtual fallback.
Default to generating a fresh random user_id per request instead of
reusing cached IDs. Add cache-user-id config option to opt in to the
previous caching behavior.
- Add CacheUserID field to CloakConfig
- Extract user_id cache logic to dedicated file
- Generate fresh user_id by default, cache only when enabled
- Add tests for both paths
console.anthropic.com is now protected by a Cloudflare managed challenge
that blocks all non-browser POST requests to /v1/oauth/token, causing
`-claude-login` to fail with a 403 error.
Switch to api.anthropic.com which hosts the same OAuth token endpoint
without the Cloudflare managed challenge.
Fixes#1659
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Non-spark codex models (gpt-5.3-codex, gpt-5.2-codex) stream function call
arguments via multiple delta events followed by a done event. The done handler
unconditionally emitted the full arguments, duplicating what deltas already
streamed. This produced invalid double JSON that Claude Code couldn't parse,
causing tool calls to fail with missing parameters and infinite retry loops.
Add HasReceivedArgumentsDelta flag to track whether delta events were received.
The done handler now only emits arguments when no deltas preceded it (spark
models), while delta-based streaming continues to work for non-spark models.
Some Codex models (e.g. gpt-5.3-codex-spark) send function call arguments
in a single "done" event without preceding "delta" events. The streaming
translator only handled "delta" events, causing tool call arguments to be
lost — resulting in empty tool inputs and infinite retry loops in clients
like Claude Code.
Emit the full arguments from the "done" event as a single input_json_delta
so downstream clients receive the complete tool input.
- Introduced `passthrough-headers` option in configuration to control forwarding of upstream response headers.
- Updated handlers to respect the passthrough headers setting.
- Added tests to verify behavior when passthrough is enabled or disabled.
sjson.SetRaw with an empty string produces malformed JSON (e.g. "result":}).
This happens when a Claude tool_result block has no content field, causing
functionResponseResult.Raw to be "". Guard against this by falling back to
sjson.Set with an empty string only when .Raw is empty.
- Implemented `--standalone` mode to launch an embedded server for TUI.
- Enhanced TUI client to support API-based log polling when log hooks are unavailable.
- Added authentication gate for password input and connection handling.
- Improved localization and UX for logs, authentication, and status bar rendering.
- Implemented `--standalone` mode to launch an embedded server for TUI.
- Enhanced TUI client to support API-based log polling when log hooks are unavailable.
- Added authentication gate for password input and connection handling.
- Improved localization and UX for logs, authentication, and status bar rendering.
- Introduced unit tests for request logging middleware to enhance coverage.
- Added WebSocket-based Codex executor to support Responses API upgrade.
- Updated middleware logic to selectively capture request bodies for memory efficiency.
- Enhanced Codex configuration handling with new WebSocket attributes.
The OpenAI Chat Completions translator was silently dropping
response.function_call_arguments.delta and
response.function_call_arguments.done Codex SSE events, meaning
tool call arguments were never streamed incrementally to clients.
Add proper handling mirroring the proven Claude translator pattern:
- response.output_item.added: announce tool call (id, name, empty args)
- response.function_call_arguments.delta: stream argument chunks
- response.function_call_arguments.done: emit full args if no deltas
- response.output_item.done: defensive fallback for backward compat
State tracking via HasReceivedArgumentsDelta and HasToolCallAnnounced
ensures no duplicate argument emission and correct behavior for models
like codex-spark that skip delta events entirely.
Update hardcoded X-Stainless-* and User-Agent defaults to match
Claude Code 2.1.44 / @anthropic-ai/sdk 0.74.0 (verified via
diagnostic proxy capture 2026-02-17).
Changes:
- X-Stainless-Os/Arch: dynamic via runtime.GOOS/GOARCH
- X-Stainless-Package-Version: 0.55.1 → 0.74.0
- X-Stainless-Timeout: 60 → 600
- User-Agent: claude-cli/1.0.83 (external, cli) → claude-cli/2.1.44 (external, sdk-cli)
Add claude-header-defaults config section so values can be updated
without recompilation when Claude Code releases new versions.
CPA-internal thinking levels like 'xhigh' and 'minimal' are not accepted
by OpenAI-format providers (MiniMax, etc.). The OpenAI applier now maps
non-standard levels to the nearest valid reasoning_effort value before
writing to the request body:
xhigh → high
minimal → low
auto → medium
Allow disabling the proxy_ tool name prefix on a per-account basis.
Users who route their own Anthropic account through CPA can set
"tool_prefix_disabled": true in their OAuth auth JSON to send tool
names unchanged to Anthropic.
Default behavior is fully preserved — prefix is applied unless
explicitly disabled.
Changes:
- Add ToolPrefixDisabled() accessor to Auth (reads metadata key
"tool_prefix_disabled" or "tool-prefix-disabled")
- Gate all 6 prefix apply/strip points with the new flag
- Add unit tests for the accessor
The proxy_ prefix logic correctly skips built-in tools (those with a
non-empty "type" field) in tools[] definitions but does not skip them
in messages[].content[] tool_use blocks or tool_choice. This causes
web_search in conversation history to become proxy_web_search, which
Anthropic does not recognize.
Fix: collect built-in tool names from tools[] into a set and also
maintain a hardcoded fallback set (web_search, code_execution,
text_editor, computer) for cases where the built-in tool appears in
history but not in the current request's tools[] array. Skip prefixing
in messages and tool_choice when name matches a built-in.
- Collect built-in tool names (those with a "type" field like
web_search, code_execution) and skip prefixing tool_reference
blocks that reference them, preventing name mismatch.
- Refactor if-else if chains to switch statements in all three
prefix functions for idiomatic Go style.
tool_reference blocks can appear nested inside tool_result.content[]
arrays, not just at the top level of messages[].content[]. The prefix
logic now iterates into tool_result blocks with array content to find
and prefix/strip nested tool_reference.tool_name fields.
applyClaudeToolPrefix, stripClaudeToolPrefixFromResponse, and
stripClaudeToolPrefixFromStreamLine now handle "tool_reference" blocks
(field "tool_name") in addition to "tool_use" blocks (field "name").
Without this fix, tool_reference blocks in conversation history retain
their original unprefixed names while tool definitions carry the proxy_
prefix, causing Anthropic API 400 errors: "Tool reference 'X' not found
in available tools."
Co-authored-by: Kirill Turanskiy <kt@novamedia.ru>
Upstream changes:
- feat: add Google One login and improve Gemini CLI auto-discovery
- feat: add gpt-5.3-codex-spark model definition
- feat: add 'kimi' channel support in model definitions
- feat: pass cache usage from codex to openai chat completions
- fix: normalize Gemini credential file prefix for consistency
- refactor: replace manual pointer assignments with new()
- chore: update Go to 1.26, update Codex client version
Fork fixes:
- Bump mise Go pin to 1.26.0
- Remove stale .syso resource files (incompatible with Go 1.26 linker)
Adds explicit handling for context.Canceled errors in the reverse proxy error handler to return 499 status code without logging, which is more appropriate for client-side cancellations during polling.
Also adds a test case to verify this behavior.
- Added unit tests for combining OAuth excluded models across global and attribute-specific scopes.
- Implemented priority attribute parsing with support for different formats and trimming.
Upstream changes (v6.8.0–v6.8.11):
- feat: add Kimi (Moonshot AI) provider support with OAuth
- feat: add iFlow provider with OAuth and cookie auth
- feat: support Claude thinking type adaptive
- feat: capture cached token count in usage metadata
- fix: correct max completion tokens for opus 4.6 thinking
- fix: improve content handling for system and user messages
- fix: rewrite model name in response.model for Responses API SSE
- refactor: simplify provider lifecycle and registration logic
- refactor: migrate config-access to internal package
Fork integration:
- Migrate configaccess from sdk/access/config to internal/access/config_access
- Update reconcile.go to use internalconfig types directly
- Add Kimi and iFlow login flags to ProxyPilot CLI
- Integrate managementasset auto-updater
- Keep all ProxyPilot fork features (TUI, agent setup, service, etc.)
Add Google One personal account login to Gemini CLI OAuth flow:
- CLI --login shows mode menu (Code Assist vs Google One)
- Web management API accepts project_id=GOOGLE_ONE sentinel
- Auto-discover project via onboardUser without cloudaicompanionProject when project is unresolved
Improve robustness of auto-discovery and token handling:
- Add context-aware auto-discovery polling (30s timeout, 2s interval)
- Distinguish network errors from project-selection-required errors
- Refresh expired access tokens in readAuthFile before project lookup
- Extend project_id auto-fill to gemini auth type (was antigravity-only)
Unify credential file naming to geminicli- prefix for both CLI and web.
Add extractAccessToken unit tests (9 cases).
Sanitize tool schemas by stripping prefill, enumTitles, $id, and patternProperties to prevent Gemini INVALID_ARGUMENT 400 errors, and add unit and executor-level tests to lock in the behavior.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Added support for single and array-based `content` cases.
- Enhanced `system_instruction` structure population logic.
- Improved handling of user role assignment for string-based `content`.
Silences logging for client cancellations during polling to reduce noise in logs.
Client-side cancellations are common during long-running operations and should not be treated as errors.
The `ConvertOpenAIResponsesRequestToGemini` function had code that attempted
to uppercase JSON Schema type values (e.g. "string" -> "STRING") for Gemini
compatibility. This broke nullable types because when `type` is a JSON array
like `["string", "null"]`:
1. `gjson.Result.String()` returns the raw JSON text `["string","null"]`
2. `strings.ToUpper()` produces `["STRING","NULL"]`
3. `sjson.Set()` stores it as a JSON **string** `"[\"STRING\",\"NULL\"]"`
instead of a JSON array
4. The downstream `CleanJSONSchemaForGemini()` / `flattenTypeArrays()`
cannot detect it (since `IsArray()` returns false on a string)
5. Gemini/Antigravity API rejects it with:
`400 Invalid value at '...type' (Type), "["STRING","NULL"]"`
This was confirmed and tested with Droid Factory (Antigravity) Gemini models
where Claude Code sends tool schemas with nullable parameters.
The fix removes the uppercasing logic entirely and passes the raw schema
through to `parametersJsonSchema`. This is safe because:
- Antigravity executor already runs `CleanJSONSchemaForGemini()` which
properly handles type arrays, nullable fields, and all schema cleanup
- Gemini/Vertex executors use `parametersJsonSchema` which accepts raw
JSON Schema directly (no uppercasing needed)
- The uppercasing code also only iterated top-level properties, missing
nested schemas entirely
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The ResponseRewriter's modelFieldPaths was missing 'response.model',
causing the mapped model name to leak through SSE streaming events
(response.created, response.in_progress, response.completed) in the
OpenAI Responses API (/v1/responses).
This caused Amp CLI to report 'Unknown OpenAI model' errors when
model mapping was active (e.g., gpt-5.2-codex -> gpt-5.3-codex),
because the mapped name reached Amp's backend via telemetry.
Also sorted modelFieldPaths alphabetically per review feedback
and added regression tests for all rewrite paths.
Fixes#1463
fix(translator): restructure message content handling to support multiple content types
- Consolidated `input_text` and `output_text` handling into a single case.
- Added support for processing `input_image` content with associated URLs.
- Updated `KimiAPIBaseURL` to remove versioning from the root path.
- Integrated `ClaudeExecutor` fallback in `KimiExecutor` methods for compatibility with Claude requests.
- Simplified token counting by delegating to `ClaudeExecutor`.
- Standardized the handling of `stop_reason` and `finish_reason` across Codex and Gemini responses.
- Restricted pass-through of specific reasons (`max_tokens`, `stop`) for consistency.
- Enhanced fallback logic for undefined reasons.
- Added support to extract and include `cachedContentTokenCount` in `usage.prompt_tokens_details`.
- Logged warnings for failures to set cached token count for better debugging.
- Introduced `RequestKimiToken` API for Kimi authentication flow.
- Integrated device ID management throughout Kimi-related components.
- Enhanced header management for Kimi API requests with device ID context.
Changes (v6.7.49 - v6.7.53):
- feat(registry): add Claude 4.6 (Opus) model
- feat(registry): add GPT 5.3 Codex model
- fix(registry): correct Claude Opus 4.6 model metadata
- fix: enable extended thinking support for Claude Haiku 4.5
- refactor(executor): centralize Codex client version and user agent
- refactor(translator, executor): remove redundant bytes.Clone calls
- refactor(util): optimize JSON schema processing
Upstream: https://github.com/router-for-me/CLIProxyAPI/releases/tag/v6.7.53
- OAuth2 device authorization grant flow (RFC 8628) for authentication
- Streaming and non-streaming chat completions via OpenAI-compatible API
- Models: kimi-k2, kimi-k2-thinking, kimi-k2.5
- CLI `--kimi-login` command for device flow auth
- Token management with automatic refresh
- Thinking/reasoning effort support for thinking-enabled models
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Replaced all instances of `bytes.Clone` with direct references to enhance efficiency.
- Simplified payload handling across executors and translators by eliminating unnecessary data duplication.
- Consolidated path-finding logic into a new `findPathsByFields` helper function.
- Refactored repetitive loop structures to improve readability and performance.
- Added depth-based sorting for deletion paths to ensure proper removal order.
Changes:
- feat(registry): add Kimi-K2.5 model to static data
- refactor(util, executor): optimize payload handling and schema processing
- fix(thinking): support user-defined includeThoughts setting (camelCase/snake_case)
- fix(thinking): ensure includeThoughts is false for ModeNone
- fix(gemini): support snake_case thinking config fields from Python SDK
- feat(gemini-cli): support image content in Claude request conversion
- fix(test): upstream fixed the builtin tools test we also fixed
Upstream: https://github.com/router-for-me/CLIProxyAPI/releases/tag/v6.7.48
Claude Haiku 4.5 (claude-haiku-4-5-20251001) supports extended thinking
according to Anthropic's official documentation:
https://docs.anthropic.com/en/docs/build-with-claude/extended-thinking
The model was incorrectly marked as not supporting thinking in the static
model definitions. This fix adds ThinkingSupport with the same parameters
as other Claude 4.5 models (Sonnet, Opus):
- Min: 1024 tokens
- Max: 128000 tokens
- ZeroAllowed: true
- DynamicAllowed: false
- Replaced repetitive string operations with a centralized `escapeGJSONPathKey` function.
- Streamlined handling of JSON schema cleaning for Gemini and Antigravity requests.
- Improved payload management by transitioning from byte slices to strings for processing.
- Removed unnecessary cloning of byte slices in several places.
Changes from v6.7.43-v6.7.47:
- fix(logging): expand tilde in auth-dir and log resolution errors
- feat(pprof): add configurable pprof HTTP debug server
- feat(watcher): log auth field changes on reload
- fix(cliproxy): update auth before model registration
- docs: README updates, AICodeMirror sponsorship
Fixed upstream test bug: TestOpenAIResponsesToOpenAI now correctly expects
built-in tools to be dropped (upstream intentionally changed this behavior).
Upstream: https://github.com/router-for-me/CLIProxyAPI/releases/tag/v6.7.47
Google official Gemini Python SDK sends thinking_level, thinking_budget,
and include_thoughts (snake_case) instead of thinkingLevel, thinkingBudget,
and includeThoughts (camelCase). This caused thinking configuration to be
ignored when using Python SDK.
Changes:
- Extract layer: extractGeminiConfig now reads snake_case as fallback
- Apply layer: Gemini/CLI/Antigravity appliers clean up snake_case fields
- Translator layer: Gemini->OpenAI/Claude/Codex translators support fallback
- Tests: Added 4 test cases for snake_case field coverage
Fixes#1426
- Add logic to handle `image` content type during request translation.
- Map Claude base64 image data to Gemini's `inlineData` structure.
- Support automatic extraction of `media_type` and `data` for image parts.
- Introduced a new `pprof` server to enable/debug HTTP profiling.
- Added configuration options for enabling/disabling and specifying the server address.
- Integrated pprof server lifecycle management with `Service`.
#1287
This merge brings in upstream changes from CLIProxyAPI v6.7.42 while
preserving ProxyPilot-specific customizations:
- Updated API server and executor modules
- New OAuth model alias functionality
- Enhanced thinking provider for iflow
- Updated model definitions and registry
- Improved docker build scripts
Conflicts were resolved by keeping ProxyPilot branding and merging
upstream improvements for translator and runtime components.
- Use util.ResolveAuthDir to properly expand ~ to user home directory
- Fixes issue where logs were created in literal "~/.cli-proxy-api" folder
- Add warning log when auth-dir resolution fails for debugging
Bug introduced in 62e2b67 (refactor(logging): centralize log directory
resolution logic), where strings.TrimSpace was used instead of
util.ResolveAuthDir to process auth-dir path.
MEDIUM: Return 400 on body read error instead of passing empty body
- Previously, on io.ReadAll error, body was consumed but c.Next()
was called, causing downstream handlers to see empty body
- Now returns http.StatusBadRequest on read errors
MEDIUM: Recompute token analysis after scaffold injection
- Token analysis was computed before scaffold state was injected
- If scaffold pushed request over token threshold, trimming was skipped
- Now recomputes analyzeTokenBudget() after injection
LOW: Always strip X-CLIProxyAPI-Todo header
- Header was only stripped when memory store was available
- If memory disabled, internal header leaked upstream
- Now stripped immediately regardless of memory store state
Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
The trimming loop condition `for keep >= minKeep` was never true because
`keep` started at 20 while `minKeep` defaults to 25. Added clamp to ensure
`keep >= minKeep` at initialization, fixing prompt budget enforcement.
Affected functions:
- trimOpenAIChatCompletions
- trimOpenAIResponses
- trimOpenAIChatCompletionsWithMemory
- trimOpenAIResponsesWithMemory
- trimClaudeMessagesWithMemory
Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
Split the 3,891 line kiro_executor.go into focused modules:
- kiro_executor.go (966 lines): Main executor, public interface
- kiro_auth.go (462 lines): Authentication/credential logic
- kiro_request.go (422 lines): Request transformation and retry logic
- kiro_response.go (1,765 lines): Response handling/streaming
Fix: Corrected isRetryableError to use errors.As for EventStreamError
type assertion instead of errors.Is on string constants.
Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
Split the 2,280-line conductor.go into three focused files:
- conductor.go (1,416 lines): Core types, Manager struct, execution
- conductor_oauth.go (383 lines): OAuth/API key model alias resolution
- conductor_token.go (501 lines): Token refresh and HTTP request handling
This is a pure refactor with no logic changes.
Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
Replace `for i, part := range` with `for _, part := range` since the
index variable was captured but never used (just discarded with `_ = i`).
Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
Remove the V1 RouteModule interface which was marked as deprecated.
All modules now use RouteModuleV2 exclusively. The RegisterModule
function signature is simplified to accept RouteModuleV2 directly
instead of interface{}.
Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
Remove TODO marker and update comment to indicate the stub is
intentional for API compatibility, not incomplete work.
Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
Update FileVersion and ProductVersion in versioninfo.json files
from 0.1.6 to 0.3.0 for both proxypilot-tray and server commands.
Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
Cherry-picked from upstream 6d8609e4
Allows configuring rules to remove specific JSON paths from request/response payloads.
Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
Cherry-picked from upstream 7ff3936e
Adds multi-turn cache control tests.
Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
Cherry-picked from upstream 6b6d030e
Adds uTLS-based HTTP transport to mimic browser TLS fingerprints for Claude API.
Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
Cherry-picked from upstream ca796510
Uses post-order traversal and DeleteBytes for better performance.
Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
Cherry-picked from upstream 2666708c
When Claude API sends an assistant message with empty text content,
the translator was creating an empty part, causing Gemini API to return
"required oneof field 'data' must have one initialized field" error.
Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
Introduce `Filter` rules in the payload configuration to remove specified JSON paths from the payload. Update related helper functions and add examples to `config.example.yaml`.
- Add ErrorLogsMaxFiles config field with default value 10
- Support hot-reload via config file changes
- Add Management API: GET/PUT/PATCH /v0/management/error-logs-max-files
- Maintain SDK backward compatibility with NewFileRequestLogger (3 params)
- Add NewFileRequestLoggerWithOptions for custom error log retention
When request logging is disabled, forced error logs are retained up to
the configured limit. Set to 0 to disable cleanup.
Introduce a custom HTTP client utilizing utls with Firefox TLS fingerprinting to bypass Cloudflare fingerprinting on Anthropic domains. Includes support for proxy configuration and enhanced connection management for HTTP/2.
Tool outputs like "[1,2,3]\n\n[Process exited with code 0]" were being
partially parsed by gjson.Parse() which would extract just "[1,2,3]" and
lose the trailing text. This caused invalid JSON in the Gemini request.
Fix: Use gjson.Valid() to verify the ENTIRE string is valid JSON before
treating it as raw JSON. If validation fails, treat as a string with
proper escaping via sjson.Set().
Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
Tests were failing with "auth_not_found: no auth available" because the
conductor.pickNextMixed() function checks ClientSupportsModel() against
the global registry. Test auths weren't registered with their models.
Changes:
- sdk/cliproxy/auth/conductor_test.go: Add registry.RegisterClient calls
- internal/translator/gemini/.../gemini_openai-responses_request.go:
Skip empty text parts to avoid invalid Gemini content
Note: Some pre-existing flaky tests remain in test/integration and
internal/translator/gemini (NonJSON tool output test).
Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
- Add SupportedEndpoints field to ModelInfo
- Add GetMiniMaxModels, GetZhipuModels stub functions
- Add GetGitHubCopilotModels, GetKiroModels, GetAmazonQModels
- Update model registry with new providers
Cherry-picked and merged from plus remote.
Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
When all oauth-model-alias entries are deleted, ensure an empty map
is persisted to config file rather than being omitted entirely.
Fixes#1305
Cherry-picked from upstream: a709e5a1
Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
- Add firstChunkTimestamp field to ResponseWriterWrapper for sync capture
- Capture TTFB in Write() and WriteString() before async channel send
- Add SetFirstChunkTimestamp() to StreamingLogWriter interface
- Make requestTimestamp/apiResponseTimestamp required in LogRequest()
- Remove timestamp capture from WriteAPIResponse() (now via setter)
- Fix Gemini handler to set API_RESPONSE_TIMESTAMP before writing response
This ensures accurate TTFB measurement for all streaming API formats
(OpenAI, Gemini, Claude) by capturing timestamp synchronously when
the first response chunk arrives, not when the stream finalizes.
Cherry-picked from upstream: 295f34d7
Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
Previously:
- REQUEST INFO timestamp was captured at log write time (not request arrival)
- API RESPONSE had NO timestamp at all
This fix:
- Captures REQUEST INFO timestamp when request first arrives
- Adds API RESPONSE timestamp when upstream response arrives
- Add Timestamp field to RequestInfo, set at middleware initialization
- Set API_RESPONSE_TIMESTAMP in appendAPIResponse() and gemini handler
- Pass timestamps through logging chain to writeNonStreamingLog()
- Add timestamp output to API RESPONSE section
Cherry-picked from upstream: c41ce77e
Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
When using Gemini API format with Antigravity backend, the executor
renames usageMetadata to cpaUsageMetadata in non-terminal chunks.
The Gemini translator was returning this internal field name directly
to clients instead of the standard usageMetadata field.
Add restoreUsageMetadata() to rename cpaUsageMetadata back to
usageMetadata before returning responses to clients.
Cherry-picked from upstream: 9dc0e6d0
Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
Add support for Gemini's code_execution and url_context tools in the
request translators, enabling:
- Agentic Vision: Image analysis with Python code execution for
bounding boxes, annotations, and visual reasoning
- URL Context: Live web page content fetching and analysis
Tools are passed through using the same pattern as google_search:
- code_execution: {} -> codeExecution: {}
- url_context: {} -> urlContext: {}
Tested with Gemini 3 Flash Preview agentic vision successfully.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Removes x-* extension fields from JSON schemas to ensure compatibility with the Gemini API.
These fields, while valid in OpenAPI/JSON Schema, are not recognized by the Gemini API and can cause issues.
The change recursively walks the schema, identifies these extension fields, and removes them, except when they define properties.
Amp-Thread-ID: https://ampcode.com/threads/T-019c0cd1-9e59-722b-83f0-e0582aba6914
Co-authored-by: Amp <amp@ampcode.com>
- Add ensureCacheControl() to auto-inject cache breakpoints
- Cache tools (last tool), system (last element), and messages (2nd-to-last user turn)
- Add prompt-caching-2024-07-31 beta header
- Return original payload on sjson error to prevent corruption
- Include verification test for caching logic
Enables up to 90% cost reduction on cached tokens.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add firstChunkTimestamp field to ResponseWriterWrapper for sync capture
- Capture TTFB in Write() and WriteString() before async channel send
- Add SetFirstChunkTimestamp() to StreamingLogWriter interface
- Make requestTimestamp/apiResponseTimestamp required in LogRequest()
- Remove timestamp capture from WriteAPIResponse() (now via setter)
- Fix Gemini handler to set API_RESPONSE_TIMESTAMP before writing response
This ensures accurate TTFB measurement for all streaming API formats
(OpenAI, Gemini, Claude) by capturing timestamp synchronously when
the first response chunk arrives, not when the stream finalizes.
Add migration logic for converting oauth-model-mappings to oauth-model-alias
with comprehensive test coverage.
Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
Add empty auth provider for handling requests that don't require authentication.
Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
Add complete Amp module for routing requests through the Amp CLI:
- Core module with lifecycle management
- Gemini bridge for model translation
- Model mapping configuration
- Proxy handler for request forwarding
- Response rewriter for format conversion
- Secret management for API keys
- Route definitions and fallback handlers
- Comprehensive test coverage
Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
Previously:
- REQUEST INFO timestamp was captured at log write time (not request arrival)
- API RESPONSE had NO timestamp at all
This fix:
- Captures REQUEST INFO timestamp when request first arrives
- Adds API RESPONSE timestamp when upstream response arrives
Changes:
- Add Timestamp field to RequestInfo, set at middleware initialization
- Set API_RESPONSE_TIMESTAMP in appendAPIResponse() and gemini handler
- Pass timestamps through logging chain to writeNonStreamingLog()
- Add timestamp output to API RESPONSE section
This enables accurate measurement of backend response latency in error logs.
Cherry-picked changes from CLIProxyAPI v6.7.28:
- feat(handlers): add test to verify no retries after partial stream response (4eb1e60)
- fix(config): prune oauth-model-alias when preserving config (d0bada7)
Note: fix(api): update amp module only on config changes (8510fc3) was skipped
as ProxyPilot does not have the Amp feature.
Co-Authored-By: Claude (gemini-claude-opus-4-5-thinking) <noreply@anthropic.com>
Introduce `TestExecuteStreamWithAuthManager_DoesNotRetryAfterFirstByte` to validate that stream executions do not retry after receiving partial responses. Implement `payloadThenErrorStreamExecutor` for test coverage of this behavior.
When using Gemini API format with Antigravity backend, the executor
renames usageMetadata to cpaUsageMetadata in non-terminal chunks.
The Gemini translator was returning this internal field name directly
to clients instead of the standard usageMetadata field.
Add restoreUsageMetadata() to rename cpaUsageMetadata back to
usageMetadata before returning responses to clients.
When Claude API sends an assistant message with empty text content like:
{"role":"assistant","content":[{"type":"text","text":""}]}
The translator was creating a part object {} with no data field,
causing Gemini API to return error:
"required oneof field 'data' must have one initialized field"
This fix:
1. Skips empty text parts (text="") during translation
2. Skips entire messages when their parts array becomes empty
This ensures compatibility when clients send empty assistant messages
in their conversation history.
Optimize channel operations by introducing reusable context-aware send functions (`send` and `sendErr`) across `wsrelay`, `handlers`, and `cliproxy`. Ensure graceful handling of canceled contexts during stream operations.
Cherry-picked changes from CLIProxyAPI:
- fix(gemini): force type to string for enum fields (fixes Antigravity Gemini API error)
- feat(auth): add request_retry and disable_cooling per-auth overrides
- feat(auth): add skip persistence context key for file watcher events
Manually added RequestRetryOverride/DisableCoolingOverride methods to
types.go to preserve ProxyPilot's conductor.go compatibility while
gaining new functionality.
Implement `request_retry` and `disable_cooling` metadata overrides for authentication management. Update retry and cooling logic accordingly across `Manager`, Antigravity executor, and file synthesizer. Add tests to validate new behaviors.
- Antigravity retry logic with improved error handling and capacity management
- Added request_id to error logs for better debugging
- Export OAuth constants from auth packages (antigravity, claude, codex, gemini)
- Added Antigravity AuthService in internal/auth/antigravity
- Updated Claude executor test expectations for system message handling
- Skip built-in tools in OAuth tool prefix
- Preserve displayName and description in Gemini models list
- Added Embed stubs for ProviderExecutor interface compliance
Introduce `WithSkipPersist` to disable persistence during Manager Update/Register calls, preventing write-back loops caused by redundant file writes. Add corresponding tests and integrate with existing file store and conductor logic.
- Updated all executors with context cancellation handling
- Added payload rules using requested model
- Filter out Top_P when Temperature is set on Claude
- Remove empty system messages in translators
- Handle quota cooldown in retry logic
- Include requested model in executor metadata
- Normalize plan type filenames to lowercase
- Added Embed stubs for ProviderExecutor interface compliance
- Added payloadRequestedModel helper function
Fixes#1082
When all Antigravity accounts are unavailable, the error response now returns
HTTP 502 (Bad Gateway) instead of HTTP 400 (Bad Request). This ensures that
NewAPI and other clients will retry the request on a different channel,
improving overall reliability.
Previously GeminiModels handler unconditionally overwrote displayName
and description with the model name, losing the original values defined
in model definitions (e.g., 'Gemini 3 Pro Preview').
Now only set these fields as fallback when they are missing or empty.
Major changes from upstream v6.7.16:
- Remove sessionID from signature caching API entirely
- CacheSignature(modelName, text, sig) instead of 4 params
- GetCachedSignature(modelName, text) instead of 3 params
- HasValidSignature(modelName, sig) instead of 1 param
- Add Gemini fallback: returns "skip_thought_signature_validator" on cache miss
- Add sliding expiration (TTL refresh on cache access)
- Add GetModelGroup() for grouping cache keys by model family
- Simplify antigravity executor by removing project switch logic
- Fix OpenAI Responses request handler to skip empty assistant text
- Fix OpenAI Responses request to validate full JSON before parsing
Local fixes for compatibility:
- Add Embed stub method to AntigravityExecutor for interface compliance
- Update test to clear cache for isolation (ThinkingBlockWithoutSignature)
- Update Gemini test to expect thinking blocks to be annotated not removed
- Fix gjson.Valid check before treating tool output as raw JSON
Port features from upstream CLIProxyAPI:
v6.7.13:
- Raw JSON payload rules (DefaultRaw, OverrideRaw)
- OpenCode instructions support with user agent detection
v6.7.14:
- Improve signature handling by associating with model name
v6.7.15:
- Unify model group references with GetModelGroup helper function
Features ported from upstream:
- feat(claude): add native request cloaking support
- feat(translator): add candidate count (n param) support for Gemini
- fix(translator): consolidate multiple system messages into single message (#1064)
- feat(codex): add config toggle for codex instructions injection
- feat(auth): add hashed account ID to credential filenames for team plans
- feat(config): add support for raw JSON payload rules (default-raw, override-raw)
- feat(codex): add OpenCode instructions based on user agent
Also includes minor whitespace cleanup and code organization.
The checkSystemInstructions was being called on every request but the
cloaking/system prompt handling is now done elsewhere. This removes
redundant processing.
Cherry-picked from CLIProxyAPI: 7831cba9
Extract session ID from metadata.user_id field when available, using
the "session_" prefix marker. Falls back to first user message hash.
Cherry-picked from CLIProxyAPI: 6184c433 (Fixed: #1109)
Update tests to reflect the new signature handling behavior where only
cached signatures are used, not client-provided ones. This prevents
"Corrupted thought signature" errors when switching between Claude and
Gemini models.
Tests now properly cache signatures before testing conversion functions.
Add support for Imagen 3.0 and 4.0 image generation models in Vertex AI:
- Add 5 Imagen model definitions (4.0, 4.0-ultra, 4.0-fast, 3.0, 3.0-fast)
- Implement :predict action routing for Imagen models
- Convert Imagen request/response format to match Gemini structure
- Transform prompts to Imagen's instances/parameters format
- Convert base64 image responses to Gemini-compatible inline data
Cherry-picked from CLIProxyAPI: 8734d4cb
Add InfoByProvider map to ModelRegistration to store provider-specific
ModelInfo, enabling different capabilities for the same model across
providers (e.g., direct API vs OpenRouter).
Changes:
- Add InfoByProvider field to ModelRegistration struct
- Update GetModelInfo to accept provider parameter for provider-specific lookup
- Update LookupModelInfo to accept variadic provider parameter
- Add LookupStaticModelInfo for fallback to static model definitions
- Update ApplyThinking to pass providerKey for registry lookups
- Update all GetModelInfo callers to use new signature
- Remove ensureMaxTokensForThinking test (function moved to thinking package)
Ported from CLIProxyAPI e641fde2
Move ensureMaxTokensForThinking logic from claude_executor to
thinking/provider/claude/apply.go. This centralizes Claude-specific
thinking budget constraints in the thinking package.
Cherry-picked from c421d653.
Add 6th parameter 'original' to applyPayloadConfigWithRoot to support
checking defaults against the original payload. This enables proper
default rule validation when translating between formats.
Based on upstream 2a663d5c.
- Comment out client signature extraction (incompatible across model families)
- Use only cached signatures for thinking blocks
- Switch to thinking.GetThinkingText for text extraction
- Add explanatory comment about cross-model signature issues
Cherry-picked from d4bb4e66.
- Remove static Name mapping from AntigravityModelConfig
- Add new model entries: claude-sonnet-4-5, gpt-oss-120b-medium, tab_flash_lite_preview
- Add model skip list for unlisted models
- Update thinking limits (Max: 128000, ZeroAllowed: true)
Cherry-picked from c175821c.
Add support for Imagen 3.0 and 4.0 image generation models in Vertex AI:
- Add 5 Imagen model definitions (4.0, 4.0-ultra, 4.0-fast, 3.0, 3.0-fast)
- Implement :predict action routing for Imagen models
- Convert Imagen request/response format to match Gemini structure like gemini-3-pro-image
- Transform prompts to Imagen's instances/parameters format
- Convert base64 image responses to Gemini-compatible inline data
Add new PATCH /v0/management/auth-files/status endpoint that allows
toggling the disabled state of auth files without deleting them.
This enables users to temporarily disable credentials from the
management UI.
Rename include_thoughts to includeThoughts across all translator files
for consistency with the Gemini API field naming convention.
Cherry-picked key change from d5ef4a6d.
Port the internal/thinking package from CLIProxyAPI for unified thinking
configuration processing across all AI providers.
Features:
- Core types: ThinkingConfig, ThinkingMode, ThinkingLevel, SuffixResult
- Suffix parsing: model-name(16384) or model-name(high) syntax
- Validation: auto-conversion between budget/level formats, clamping
- Provider appliers: claude, gemini, antigravity, openai, codex
- Config extraction: extract thinking config from various request formats
- Stripping: remove thinking config for non-supporting models
Registry updates:
- Add UserDefined field to ModelInfo for passthrough behavior
- Add LookupModelInfo function for model capability lookup
- Add ResolveLogDirectory() for consistent log path resolution
- Add SetLogLevel() for string-based log level configuration
- Update ConfigureLogOutput() to take *config.Config parameter
- Update all callers to use simplified API
Cherry-picked from CLIProxyAPI with adaptations.
Gemini API requires enum values to be strings. This adds NormalizeEnumValues
to convert numeric or boolean enum values to their string representations.
Cherry-picked from CLIProxyAPI.
- Introduced `ResolveLogDirectory` function in `logging` package to standardize log directory determination across components.
- Replaced redundant logic in `server`, `global_logger`, and `handlers` with the new utility function.
Update ApplyThinking signature to accept fromFormat and toFormat parameters
instead of a single provider string. This enables:
- Proper level-to-budget conversion when source is level-based (openai/codex)
and target is budget-based (gemini/claude)
- Strict budget range validation when source and target formats match
- Level clamping to nearest supported level for cross-format requests
- Format alias resolution in SDK translator registry for codex/openai-response
Also adds ErrBudgetOutOfRange error code and improves iflow config extraction
to fall back to openai format when iflow-specific config is not present.
Refactor thinking configuration tests by separating model name suffix-based
scenarios from request body parameter-based scenarios into distinct test
functions with independent case numbering.
Architectural improvements:
- Extract thinkingTestCase struct to package level for shared usage
- Add getTestModels() helper returning complete model fixture set
- Introduce runThinkingTests() runner with protocol-specific field detection
- Register level-subset-model fixture with constrained low/high level support
- Extend iflow protocol handling for glm-test and minimax-test models
- Add same-protocol strict boundary validation cases (80-89)
- Replace error responses with clamped values for boundary-exceeding budgets
Gemini API requires all enum values in function declarations to be
strings. Some MCP tools (e.g., roxybrowser) define schemas with numeric
enums like `"enum": [0, 1, 2]`, causing INVALID_ARGUMENT errors.
Add convertEnumValuesToStrings() to automatically convert numeric and
boolean enum values to their string representations during schema
transformation.
- Add Auto-Updates and Rollback Support features to Features list
- Add Auto-Updates section with configuration options
- Add Rollback Support section explaining crash detection and recovery
- Document tray menu options for updates and rollback
Tray app integration:
- Health check on startup with auto-rollback trigger
- Background update polling with configurable interval
- One-click update menu item (shown when available)
- Manual rollback menu item in Settings
- Mark healthy after 30s of stable operation
- Graceful cleanup on exit (stop engine, stop poller)
New rollback module for version recovery:
- Version-aware backup metadata tracking
- Platform-specific restore (Windows batch, Unix swap)
- Crash loop detection via startup health monitoring
- Auto-rollback after 3 rapid failures in 30s window
- MarkHealthy() clears failure counter after stable run
Install module updated to save rollback info on update.
New UpdateBanner component for dashboard:
- Auto-checks for updates on mount with 2s delay
- Shows dismissible banner when update available
- Session-based dismissal persistence
- Download progress bar during update
- Integrated into App.tsx main layout
New poller module for periodic update checks:
- Configurable polling interval
- Channel support (stable/prerelease)
- Callback-based notification system
- Global singleton for tray integration
- Graceful start/stop with context cancellation
Cherry-pick from CLIProxyAPI v6.7.7 (f8f3ad8).
Fixes issue where only the last system/developer message was preserved
when multiple were provided. Added systemPartIndex counter to accumulate
parts across all system messages instead of overwriting at index 0.
Also fixed path inconsistency in gemini_openai_request.go where the
array branch incorrectly used request.systemInstruction instead of
system_instruction.
Fixes: router-for-me/CLIProxyAPI#1064
feat(translator): improve system message handling and content indexing across translators
- Updated logic for processing system messages in `claude`, `gemini`, `gemini-cli`, and `antigravity` translators.
- Introduced indexing for `systemInstruction.parts` to ensure proper ordering and handling of multi-part content.
- Added safeguards for accurate content transformation and serialization.
- Introduced `payloadModelAliases` and `payloadModelCandidates` functions to support model aliases for improved flexibility.
- Updated rule matching logic to handle multiple model candidates.
- Refactored variable naming in executor to improve code clarity and consistency.
- Enhanced ID matching in `cliproxy` by adding additional conditions to better handle ID equality cases.
- Updated `gemini` handlers to include `displayName` and `description` in normalized models for enriched metadata.
- Added conditional logic for Codex instruction injection based on configuration.
- Updated role terminology from "user" to "developer" for better alignment with context.
- Added logic to transform `inputResults` into structured JSON for improved processing.
- Removed redundant `safety_identifier` field in executor payload to streamline requests.
Add check to ensure 'instructions' field exists in Execute, ExecuteStream,
and CountTokens functions before sending request to Codex API.
Cherry-picked from:
- CLIProxyAPI v6.7.4 (902bea2)
Change conditional check from gemini-3-pro-preview (alias) to
gemini-3-pro-high (internal name) for system instruction injection.
Cherry-picked from:
- CLIProxyAPI v6.7.3 (c3ef46f)
When switching from Claude models (e.g., Opus 4.5) to Gemini models
(e.g., Flash) mid-conversation via Antigravity OAuth, the client-provided
thinking signatures from Claude would cause "Corrupted thought signature"
errors since they are incompatible with Gemini API.
Changes:
- Remove fallback to client-provided signatures in thinking block handling
- Only use cached signatures (from same-session Gemini responses)
- Skip thinking blocks without valid cached signatures
- tool_use blocks continue to use skip_thought_signature_validator when
no valid signature is available
This ensures cross-model switching works correctly while preserving
signature validation for same-model conversations.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add Claude 4.5 model variants (opus, sonnet, haiku)
- Add Gemini 2.0/2.5 Flash and Pro pricing
- Add OpenAI o3/o4-mini pricing
- Update date reference from Dec 2024 to Jan 2026
- GET /v0/management/rate-limits - detailed per-credential status
- GET /v0/management/rate-limits/summary - availability overview
- Shows available, cooling_down, disabled counts and next recovery time
- Bubbletea-based TUI with 5 tabs: Status, Accounts, Rate Limits, Usage, Logs
- Industrial control room aesthetic with orange/green color scheme
- Double-line borders (╔═╗), active tab indicator 【】
- 3-column stat boxes on Status, 4-column on Usage
- Visual gauge bar for rate limit availability
- Config-optional mode allows TUI to run without config.yaml
- Full-width frame with properly aligned borders
New Accounts submenu:
- Copy Account List (-list-accounts)
- Cleanup Expired (-cleanup-expired)
- Export Accounts... (-export-accounts)
- Import Accounts... (-import-accounts)
All menu items harness CLI binary for single source of truth.
Add menu items to copy CLI output to clipboard:
- Copy Account Status (account health summary)
- Copy Usage Stats (token usage by provider)
- Copy Model List (available models)
- Copy Recent Logs (last 100 log entries)
Uses stdout capture to get formatted CLI output.
- Add -usage flag (token usage stats per provider)
- Add -logs flag (view recent logs, -n for line count)
- Add -refresh flag (force token refresh)
- Add -list-models flag (show available models)
- Add -export-accounts/-import-accounts (backup/restore)
- Add --include-tokens and --force flags for export/import
- install.ts: read version from package.json (auto-sync)
- release.yml: manual dispatch only (no auto-trigger on tags)
- proxypilot-release.yml: add checksums.txt generation
- Add 26 tests for SetLogLevel() in logging package
- Add 6 tests for AppError in errors package
- Add 10 tests for SDKConfig in config package
- Add 3 tests for EmailRequiredError in sdk/auth
- Remove dead code: GeminiCLIToken type alias, LoadGeminiCLIToken,
LoadGeminiCLITokenFromPath (no callers found)
- Add tests for gemini auth (CredentialFileName, SaveTokenToFile)
Cherry-picked from e8e3bc86. Adds HttpRequest method to ProviderExecutor
interface for injecting credentials into arbitrary HTTP requests.
- Added HttpRequest to conductor.go interface
- Added HttpRequest stubs to kiro, minimax, zhipu executors
- Added http-request example
- Updated mock executors in tests
Also kept our Embed method and CountTokens implementations.
- feat(executor): enhance Antigravity payload with user role and dynamic system instructions
- feat(executor): add model-specific support for "gemini-3-pro" in execution
- feat(executor): update system instruction handling for Claude and Gemini-3-Pro models
- fix(executor): update gemini model identifier to gemini-3-pro-preview
- feat(executor): centralize systemInstruction handling
Cherry-picked: 67985d82, bda04eed, 1b2f9076, b6a0f7a0, 59a448b6
- fix(logging): improve request/response capture
- fix(handlers): match raw error text before JSON body for duplicate detection
- feat(logging): disambiguate OAuth credential selection in debug logs
- Various logging refinements for auth selection
Cherry-picked from upstream: a091d12f, 3ca5fb10, 0e4148b2, 79fbcb3e, 48f6d7ab, 48f19aab, cb3bdffb, a95428f2
- Add internal/auth/antigravity package with token loading from ~/.gemini/oauth_creds.json
- Add ImportFromGeminiCLI method to AntigravityAuthenticator
- Add DoAntigravityImport CLI command
- Add --antigravity-import flag to server binary
Usage: proxypilot --antigravity-import
Routes requests to the account with lowest daily output tokens.
Spreads load across accounts to avoid hitting quota limits.
Config: routing.strategy = "usage-aware" or "least-used"
Initialize response/prompt caches in Service.Run from config.
Add cache lookup to executor payload helpers.
Document cache config and management API in README.
ProviderLogins table now shows:
- Priority column with up/down reorder buttons
- Expires column with color-coded status (green/yellow/red)
API exposes token_expires_at for WebUI consumption.
When streaming responses with tool calls, the finish_reason was being
overwritten. The upstream sends functionCall in chunk 1, then
finishReason: STOP in chunk 2. The old code would set finish_reason
from every chunk, causing "tool_calls" to be overwritten by "stop".
This broke clients like Claude Code that rely on finish_reason to
detect when tool calls are complete.
Changes:
- Add SawToolCall bool to track tool calls across entire stream
- Add UpstreamFinishReason to cache the finish reason
- Only emit finish_reason on final chunk (has both finishReason + usage)
- Priority: tool_calls > max_tokens > stop
Includes 5 unit tests covering:
- Tool calls not overwritten by subsequent STOP
- Normal text gets "stop"
- MAX_TOKENS without tool calls gets "max_tokens"
- Tool calls take priority over MAX_TOKENS
- Intermediate chunks have no finish_reason
Fixes streaming tool call detection for Claude Code + Gemini models.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Previously, metadataEqualIgnoringTimestamps() ignored access_token for all
providers, which prevented refreshed tokens from being persisted to disk/database.
This caused tokens to be lost on server restart for providers like iFlow.
This change makes the behavior provider-specific:
- Providers like gemini/gemini-cli that issue new tokens on every refresh and
can re-fetch when needed will continue to ignore access_token (optimization)
- Other providers like iFlow will now persist access_token changes
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
integrate claude-cloak functionality to disguise api requests:
- add CloakConfig with mode (auto/always/never) and strict-mode options
- generate fake user_id in claude code format (user_[hex]_account__session_[uuid])
- inject claude code system prompt (configurable strict mode)
- obfuscate sensitive words with zero-width characters
- auto-detect claude code clients via user-agent
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Fixes issue where free tier users cannot access Gemini 3 preview models
due to frontend/backend project ID mapping.
## Problem
Google's Gemini API uses a frontend/backend project mapping system for
free tier users:
- Frontend projects (e.g., gen-lang-client-*) are user-visible
- Backend projects (e.g., mystical-victor-*) host actual API access
- Only backend projects have access to preview models (gemini-3-*)
Previously, CLIProxyAPI ignored the backend project ID returned by
Google's onboarding API and kept using the frontend ID, preventing
access to preview models.
## Solution
### CLI (internal/cmd/login.go)
- Detect free tier users (gen-lang-client-* projects or FREE/LEGACY tier)
- Show interactive prompt allowing users to choose frontend or backend
- Default to backend (recommended for preview model access)
- Pro users: maintain original behavior (keep frontend ID)
### Web UI (internal/api/handlers/management/auth_files.go)
- Detect free tier users using same logic
- Automatically use backend project ID (recommended choice)
- Pro users: maintain original behavior (keep frontend ID)
### Deduplication (internal/cmd/login.go)
- Add deduplication when user selects ALL projects
- Prevents redundant API calls when multiple frontend projects map to
same backend
- Skips duplicate project IDs in activation loop
## Impact
- Free tier users: Can now access gemini-3-pro-preview and
gemini-3-flash-preview models
- Pro users: No change in behavior (backward compatible)
- Only affects Gemini CLI OAuth (not antigravity or API key auth)
## Testing
- Tested with free tier account selecting single project
- Tested with free tier account selecting ALL projects
- Verified deduplication prevents redundant onboarding calls
- Confirmed pro user behavior unchanged
- Add Priority field to Auth for per-provider account ordering
- Add UsageStats struct tracking total/daily tokens and requests
- Track usage in MarkResult with daily reset logic
- Add TokenExpiresAt for proactive refresh (5min buffer)
- Sort available auths by priority in selector
Remove os.RemoveAll() call in syncAuthFromBucket() that was causing
a race condition with the file watcher.
Problem:
1. syncAuthFromBucket() wipes local auth directory with RemoveAll
2. File watcher detects deletions and propagates them to remote store
3. syncAuthFromBucket() then pulls from remote, but files are now gone
Solution:
Use incremental sync instead of delete-then-pull. Just ensure the
directory exists and overwrite files as they're downloaded.
This prevents the watcher from seeing spurious delete events.
COMPLETED:
- Added ViewWithSize(width, height) pattern to all submodels
- login.go: responsive provider rows with adaptive widths
- switch.go: responsive agent rows without card borders
- mappings.go: responsive table columns with calculateColumnWidths()
- usage.go: responsive stat cards (2x2 grid layout)
- logs.go: responsive log entries with message truncation
- Fixed main View() layout calculation in tui.go
- Properly accounts for border (2) + padding (2) = 4 chars per panel
- sidebarWidth now represents content width (20/14 for normal/narrow)
- contentWidth = m.width - sidebarWidth - 9 (accounts for both panels)
- Added new screen files:
- integrations.go: setup/integration screen
- logs.go: real-time log viewer with filtering
- mappings.go: model alias mappings table
- usage.go: usage statistics with charts
PENDING TEST:
- Verify sidebar displays correctly alongside content (was overflowing)
- Test all screens at various terminal widths (60, 80, 100+ cols)
KNOWN ISSUE BEING FIXED:
- Sidebar was showing only "[8] Setup" at top due to width overflow
- Content panel was too wide, causing horizontal wrap
Cherry-picked fixes:
- fix(antigravity): inject required placeholder when properties exist without required
- fix(translators): correct key path for system_instruction.parts in Claude request logic
- Add package.json with bun postinstall script
- Add install.ts for binary download
- Add bin wrapper script
- Add README with usage instructions
- Version 0.1.0
Add 'Shell' button per agent that opens modal displaying environment
variables and shell profile configuration snippets. Includes copy-to-
clipboard functionality for easy shell integration.
Add live/history toggle, date range filtering, model/provider/status
filters, pagination, export/import/clear buttons, and statistics display.
Fetches from persistent /request-history endpoint.
Add standalone ppswitch binary for fast agent configuration switching
without server logging overhead. Usage:
- ppswitch Show all agent statuses
- ppswitch <agent> Show specific agent status
- ppswitch <agent> <mode> Switch agent to proxy/native mode
Add --switch and --mode flags plus subcommand-style 'proxypilot switch'
syntax for quick agent configuration switching. Supports both flag style
(--switch claude --mode proxy) and subcommand style (proxypilot switch
claude proxy).
Add DoSwitch() and DoSwitchStatusAll() for switching agent configs
between proxy mode (routed through ProxyPilot) and native mode (direct
API access). Supports claude, gemini, codex, opencode, droid, cursor,
kilo, and roocode agents with backup/restore functionality.
Add GET/PUT /thinking-budget endpoint for configuring extended
thinking token budgets. Supports preset levels (Low 2048, Medium 8192,
High 32768) and custom values with enable/disable toggle.
Add management endpoints for request history:
- GET /request-history - list entries with pagination
- GET /request-history/stats - aggregate statistics
- DELETE /request-history - clear all entries
- POST /request-history/export - export to JSON
- POST /request-history/import - import from JSON
- POST /request-history/save - force save to disk
Integrate RequestHistoryManager with request logging middleware.
Add RequestHistoryManager with file-based persistence at
~/.cli-proxy-api/request-history.json. Features:
- Max 500 entries with automatic pruning
- Auto-save every 30 seconds
- Thread-safe with mutex protection
- In-memory ring buffer for performance
Add GetShellConfig() to AgentHandler interface returning ShellConfigInfo
with environment variables and shell profile snippets. Implement for all
agents: Claude Code, Codex, Gemini CLI, Cursor, OpenCode, Factory Droid,
and Amazon Q CLI.
Major overhaul of agent integration system:
- Add support for additional agent types
- Improve configuration detection and management
- Better error handling and validation
- Add --minimax-login, --zhipu-login for API key providers
- Add --amazonq-import for Amazon Q CLI token import
- Add --kiro-import for Kiro IDE token import
- Add --kiro-aws-login for AWS Builder ID flow
- Improve agent detection logic for multiple CLI tools
- Add support for detecting Amazon Q CLI, OpenCode
- Better path resolution and state management
Add React-based UI for the custom installer:
- Clean modern installation wizard interface
- Progress tracking and status display
- TypeScript + Vite build
Document the migration from iFlow to MiniMax and Zhipu AI providers.
Includes:
- Summary of changes
- Files deleted/created/modified
- New model definitions
- API details for new providers
- Auth file format examples
- Migration notes for existing users
Remove the iFlow OAuth and cookie-based authentication implementation.
This provider is being replaced with simpler API key-based providers.
Deleted files:
- internal/auth/iflow/cookie_helpers.go
- internal/auth/iflow/iflow_auth.go
- internal/auth/iflow/iflow_token.go
- internal/auth/iflow/oauth_server.go
Includes:
- Vision base64 parsing fix for OpenAI-to-Claude translation
- Memory API localhost authentication with API keys
- Global model mapping SDK hook for cross-provider aliases
- Comprehensive unit tests for auth, config, memory, and runtime
Adds GlobalModelMapperFunc type and hook to SDKConfig, allowing
SDK-level handlers to access Config-level global model mappings.
This enables cross-provider model aliasing (e.g., gpt-4o → claude-sonnet).
This release removes the need for a separate proxypilot-engine.exe binary.
The ProxyPilot.exe tray app now runs the proxy service in-process using
the cliproxy SDK builder pattern.
Changes:
- Add internal/embedded package for in-process server management
- Update desktopctl to support embedded mode alongside subprocess mode
- Clean up vestigial -exe flag and engine binary references
- Update package scripts to build only single binary
- Bump version to 0.1.2
The embedded engine in cmd/cliproxytray was already implemented; this
commit cleans up the remaining references to the old two-binary architecture.
Prepare release v0.1.1 with new features:
- Model-specific pricing for cost estimation
- Auto-update with download, verify, and install flow
- Cost savings display in Analytics
- Logo branding assets
Update Header with logo display, improve AgentSetup and ProviderLogins
components. Update App.tsx and index.html for better structure.
Adjust Vite config for development.
Add complete update workflow with stages: checking, available, downloading,
ready, installing. Show download progress bar, version info, and release
notes. Add Install & Restart button for applying updates.
Add Cost Savings hero card showing proxy cost vs direct API cost with
visual comparison bars. Add Cost column to Model Breakdown table.
Display savings percentage and total amount saved.
Add handlers for update status, download, verify, and install operations.
Register new routes: GET /updates/status, POST /updates/download,
POST /updates/verify, POST /updates/install. Track download progress
with background goroutine and mutex-protected state.
Add install.go with archive extraction (zip, tar.gz) and binary replacement
logic. Windows uses batch script for safe replacement of running executable.
Unix directly replaces binary with backup. Includes cleanup for old versions.
Add DownloadUpdate function to download platform-specific binaries from
GitHub releases with progress tracking. Add verify.go with SHA256 checksum
verification for downloaded files. Fix GitHub repo URL and add 404 handling
for repositories without releases.
Add comprehensive pricing table for Claude, GPT, Gemini, Qwen, and DeepSeek
models with per-million-token rates. Update cost calculation to use actual
model pricing instead of hardcoded estimates. Add new cost fields to
UsageStats for tracking actual cost, direct API cost, and savings.
- Add agent detection and configuration bindings
- Add update check and download bindings
- Add usage and request monitoring bindings
- Update useProxyContext with new desktop API hooks
- Refactor EngineControl with new status indicators
- Update Integrations with provider cards
- Enhance LogsViewer with better filtering and display
- Improve MemoryManager with modern UI patterns
- Update ModelMappings with collapsible sections
- Refactor ProviderLogins with OAuth flow improvements
- Update SemanticMemory styling
- Add versioninfo.json for goversioninfo in tray and server
- Generate resource.syso files with embedded icon
- Update ico.go to embed actual icon.ico for tray
- All exes now show ProxyPilot logo in File Explorer
- Embed React dashboard assets in tray binary
- Open dashboard in WebView2 window from tray
- Remove need for separate proxypilotui.exe
- Simplifies distribution to just ProxyPilot.exe + proxypilot-engine.exe
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove logo and test files from tracking
- Keep files locally but exclude from repo
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Credits Factory.ai and Anthropic for their research on context
compression and building effective agents.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Cleaner centered branding with star badge
- Bold tagline with concise value prop
- GitHub tip callout for latest models
- Emoji bullet feature list
- Simplified sections
- Setup guide links
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Removed dead code (commented-out ErrTokenExpired error constant) from
both claude/errors.go and codex/errors.go.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Removed redundant `_ "embed"` import as `embed` is already imported
and used for embed.FS.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove desktop-ui-spec.md and windows-ui-spec.md which reference
deleted cliproxyctl CLI that no longer exists.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Type was defined but never used anywhere in codebase.
Keep EmailRequiredError which is actively used.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Document Factory.ai context compression and Anthropic agentic harness
implementations with architecture diagrams and configuration reference.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Test context compression adapter and harness middleware work together
without conflicts.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Removed feature not present in original Factory.ai or Anthropic sources.
Keep implementation pure to research references.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Enable Anthropic-style INITIALIZER/CODING mode prompts for long-running
agentic clients.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add coreManagerWrapper to adapt auth manager types and initialize
LLM-based summarization after server creation.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Enables Factory.ai-style LLM summarization by wiring the summarizer
executor to the core auth manager.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Bridge type differences between coreauth.Manager and memory.AuthExecutor
to enable LLM-based context compression through the auth pipeline.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Centered logo and badges
- Catchy tagline "Stop juggling API keys"
- Emoji-styled feature list
- Latest models callout section
- Cleaner installation/usage sections
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add downloadBlob helper to reduce duplication
- Refactor export functions to use helper
- Fix model mapping edit to use controlled React state
instead of DOM getElementById manipulation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Delete input.tsx, progress.tsx, tabs.tsx - none were imported
or used anywhere in the codebase.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Complete rewrite with:
- ProxyPilot branding and badges
- Feature list and architecture overview
- Quick start and configuration guide
- API endpoints documentation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove internal/letta/ package (unused memory bridge)
- Remove Letta references from run.go and start-cliproxy.ps1
- Move docker-build scripts to scripts/
- Move TROUBLESHOOTING_ANTIGRAVITY.md and WARP.md to docs/
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Update droid.go to use ~/.factory/settings.json (runtime config)
- Add /healthz endpoint for Droid health checks
- Add root-level API routes (/responses, /messages, etc.)
- Fix detection in proxypilotui to check settings.json
- Use thinking models with provider: "openai" for Responses API
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add WebView2 JavaScript bindings:
- pp_detect_agents: List installed CLI agents
- pp_configure_agent: Configure agent for ProxyPilot
- pp_get_model_mappings: Get global mappings
- pp_save_model_mappings: Save global mappings
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove bloated React bundle (~500KB) in favor of
simple embedded HTML (~15KB). Update embed.go to
only include index.html and vite.svg.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Generate config files to point CLI agents at ProxyPilot:
- Claude Code: ~/.claude/settings.json
- Codex CLI: ~/.codex/config.toml
- Factory Droid: ~/.factory/config.json
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Detect installed CLI agents (Claude Code, Codex, Droid, Gemini)
by checking binaries and config files.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add global-model-mappings section to config.example.yaml
showing smart/rush/think aliases.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add API handler for managing global model mappings
stored in ~/.proxypilot/model-mappings.json.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add GlobalModelMapping struct and LookupGlobalModelMapping()
for routing friendly model names to actual models.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add CRUD operations for harness files:
- GET /v0/management/harness/files - list files
- GET /v0/management/harness/file - read file
- PUT /v0/management/harness/file - write file
- GET /v0/management/harness/export - export all
- POST /v0/management/harness/import - import files
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Improve INITIALIZER and CODING prompts based on Anthropic guidance:
- Structured feature_list.json format
- GET BEARINGS workflow for coding mode
- Puppeteer MCP detection for browser testing
- Session-aware state detection
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add utilities for estimating token counts using tiktoken
to support token-aware compression decisions.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implement proactive compression based on token count rather than bytes:
- Uses tiktoken for accurate token estimation
- Compresses at 75% threshold before hitting limits
- Reserves tokens for output generation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Update file_store.go with BuildAnchoredSummaryWithLLM() for
generating context-aware summaries during compression.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add structured summary generation for context compression:
- structured_summary.go: Types and parsing for summaries
- summarizer.go: LLM summarization logic
- summarizer_executor.go: Routes to LLM pipeline
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add Kiro OAuth handling in management API:
- Fix ExpiresAt field name in KiroTokenStorage
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add KiroAuthenticator for AWS Builder ID device flow:
- Client registration with AWS SSO OIDC
- Device authorization with user code display
- Token polling with timeout handling
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add Kiro support in SnapshotCoreAuths():
- Synthesize auth entries from KiroKey config
- Support token-file and direct access-token modes
- Handle profile-arn, region, agent-task-type
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add KiroExecutor for AWS CodeWhisperer API:
- AWS Event Stream binary format parsing
- Kiro payload building with origin field
- Token refresh with mutex protection
- Quota fallback: AI_EDITOR -> CLI on 429
- Auto-refresh on 401/403 errors
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove dead code that was never used:
- toolCallIDToName map: built but never read from
- seenToolCallIDs: declared but never populated, only suppressed with _
Fix three issues in Kiro OpenAI translator that caused "Improperly formed request"
errors when processing LiteLLM-translated requests with tool_use/tool_result:
1. Skip merging tool role messages in MergeAdjacentMessages() to preserve
individual tool_call_id fields
2. Track pendingToolResults and attach to the next user message instead of
only the last message. Create synthetic user message when conversation
ends with tool results.
3. Insert synthetic user message with tool results before assistant messages
to maintain proper alternating user/assistant structure. This fixes the case
where LiteLLM translates Anthropic user messages containing only tool_result
blocks into tool role messages followed by assistant.
Adds unit tests covering all tool result handling scenarios.
- Handle errors in promptInput instead of ignoring them
- Improve promptSelect to provide feedback on invalid input and re-prompt
- Use sentinel errors (ErrAuthorizationPending, ErrSlowDown) instead of
string-based error checking with strings.Contains
- Move hardcoded x-amz-user-agent header to idcAmzUserAgent constant
Addresses code review feedback from Gemini Code Assist.
Add persistRefreshedAuth function to write refreshed tokens back to the
auth file after inline token refresh. This prevents repeated token
refreshes on every request when the token expires.
Changes:
- Add persistRefreshedAuth() to kiro_executor.go
- Call persist after all token refresh paths (401, 403, pre-request)
- Remove unused log import from sdk/auth/kiro.go
Implements a new middleware to handle agentic headers and dynamically inject system prompts for 'Initializer' and 'Coding' agents. Also registers this middleware in the server setup.
Fixes a critical bug where rate limit errors were only updating the parent Auth object and not the specific ModelState. This caused the selector to incorrectly view the model as active and retry the same account immediately. Also hardens the selector to respect timestamps even if availability flags are desynchronized.
Currently, the executor ignores upstream retry-after headers, causing the manager to default to a 1s backoff. This change parses standard HTTP Retry-After headers (seconds or date) and passes them to the error handler.
- Add claude-cli detection to isAgenticCLI and mustKeepTools checks
- Add /v1/messages Claude Messages API format support
- Implement trimClaudeMessagesWithMemory with tool_use/tool_result adjacency preservation
- Add extractLastUserTextFromClaude, extractTextFromClaudeMessage, truncateClaudeMessageContent helpers
- Add claude case to prependToLastUserText, appendToLastUserText, extractPinnedContext
- Add response headers for localhost diagnostics:
- X-ProxyPilot-Session: session ID
- X-ProxyPilot-Request-Shape: detected format (chat/responses/claude)
- X-ProxyPilot-Memory-Stored: dropped message count
- X-ProxyPilot-Memory-Retrieved: injected snippet count
- Document Windows Claude Code settings for using CLIProxyAPI (base URL, auth token, default model mapping)
- Add Claude alias remapping for opus/sonnet/haiku to Gemini-backed models
- Improve auth unavailability reporting (429 cooldown vs 503 blocked) and fallback provider inference
- **Thinking Support**:
- Enabled thinking support for all Kiro Claude models, including Haiku 4.5 and agentic variants.
- Updated `model_definitions.go` with thinking configuration (Min: 1024, Max: 32000, ZeroAllowed: true).
- Fixed `extended_thinking` field names in `model_registry.go` (from `min_budget`/`max_budget` to `min`/`max`) to comply with Claude API specs, enabling thinking control in clients like Claude Code.
- **Kiro Executor Fixes**:
- Fixed `budget_tokens` handling: explicitly disable thinking when budget is 0 or negative.
- Removed aggressive duplicate content filtering logic that caused truncation/data loss.
- Enhanced thinking tag parsing with `extractThinkingFromContent` to correctly handle interleaved thinking/text blocks.
- Added EOF handling to flush pending thinking tag characters, preventing data loss at stream end.
- **Performance**:
- Optimized Claude stream handler (v6.2) with reduced buffer size (4KB) and faster flush interval (50ms) to minimize latency and prevent timeouts.
## Changes Overview
This commit includes multiple improvements to the Kiro executor for better
stability, API compatibility, and code quality.
## Detailed Changes
### 1. Output Token Calculation Improvement (lines 317-330)
- Replace simple len(content)/4 estimation with tiktoken-based calculation
- Add fallback to character count estimation if tiktoken fails
- Improves token counting accuracy for usage tracking
### 2. Stream Handler Panic Recovery (lines 528-533)
- Add defer/recover block in streamToChannel goroutine
- Prevents single request crashes from affecting the entire service
### 3. Struct Field Reordering (lines 670-673)
- Reorder kiroToolResult struct fields: Content, Status, ToolUseID
- Ensures consistency with API expectations
### 4. Message Merging Function (lines 778-780, 2356-2483)
- Add mergeAdjacentMessages() to combine consecutive messages with same role
- Add helper functions: mergeMessageContent(), blockToMap(), createMergedMessage()
- Required by Kiro API which doesn't allow adjacent messages from same role
### 5. Empty Content Handling (lines 791-800)
- Add default content for empty history messages
- User messages with tool results: "Tool results provided."
- User messages without tool results: "Continue"
### 6. Assistant Last Message Handling (lines 811-830)
- Detect when last message is from assistant
- Create synthetic "Continue" user message to satisfy Kiro API requirements
- Kiro API requires currentMessage to be userInputMessage type
### 7. Duplicate Content Event Detection (lines 1650-1660)
- Track lastContentEvent to detect duplicate streaming events
- Skip redundant events to prevent duplicate content in responses
- Based on AIClient-2-API implementation for Kiro
### 8. Streaming Token Calculation Enhancement (lines 1785-1817)
- Add accumulatedContent buffer for streaming token calculation
- Use tiktoken for accurate output token counting during streaming
- Add fallback to character count estimation with proper logging
### 9. JSON Repair Enhancement (lines 2665-2818)
- Implement conservative JSON repair strategy
- First try to parse JSON directly - if valid, return unchanged
- Add bracket balancing detection and repair
- Only repair when necessary to avoid corrupting valid JSON
- Validate repaired JSON before returning
### 10. HELIOS_CHK Filtering Removal (lines 2500-2504, 3004-3039)
- Remove filterHeliosDebugInfo function
- Remove heliosDebugPattern regex
- HELIOS_CHK fields now handled by client-side processing
### 11. Comment Translation
- Translate Chinese comments to English for code consistency
- Affected areas: token calculation, buffer handling, message processing
* feat(api): add comprehensive ampcode management endpoints
Add new REST API endpoints under /v0/management/ampcode for managing
ampcode configuration including upstream URL, API key, localhost
restriction, model mappings, and force model mappings settings.
- Move force-model-mappings from config_basic to config_lists
- Add GET/PUT/PATCH/DELETE endpoints for all ampcode settings
- Support model mapping CRUD with upsert (PATCH) capability
- Add comprehensive test coverage for all ampcode endpoints
* refactor(api): simplify request body parsing in ampcode handlers
* feat(logging): add upstream API request/response capture to streaming logs
* style(logging): remove redundant separator line from response section
* feat(antigravity): enforce thinking budget limits for Claude models
* refactor(logging): remove unused variable in `ensureAttempt` and redundant function call
---------
Co-authored-by: hkfires <10558748+hkfires@users.noreply.github.com>
- Remove custom stringContains and findSubstring helper functions
- Use standard library strings.Contains for better maintainability
- No functional change, just cleaner code
Addresses Gemini Code Assist review feedback
- Added setKiroIncognitoMode() helper function to handle Kiro auth incognito mode setting
- Replaced 3 duplicate code blocks (21 lines) with single function calls (3 lines)
- Kiro auth defaults to incognito mode for multi-account support
- Users can override with --incognito or --no-incognito flags
This addresses the code duplication noted in PR #1 review.
- Add --kiro-aws-login flag for AWS Builder ID device code flow
- Add DoKiroAWSLogin function for AWS SSO OIDC authentication
- Complete Kiro integration with AWS, Google OAuth, and social auth
- Add kiro executor, translator, and SDK components
- Update browser support for Kiro authentication flows
- Updated README files to reflect the new 'Plus' variant with detailed third-party provider support information.
- Adjusted Dockerfile, `docker-compose.yml`, and build configurations to align with the `CLIProxyAPIPlus` naming convention.
- Added information about GitHub Copilot OAuth integration contributed by the community.
- Updated Docker and release workflows to use `cli-proxy-api-plus` as the Docker repository name and adjusted tag generation logic.
- Renamed artifacts in Goreleaser configuration to align with the new 'plus' variant naming convention.
- Updated release and Docker workflows to ensure the `-plus` suffix is added to build versions when missing.
- Adjusted Goreleaser configuration to include `-plus` suffix in `main.Version` during build process.
- Add Unwrap() to AuthenticationError for proper error chain handling with errors.Is/As
- Extract hardcoded header values to constants for maintainability
- Replace verbose status code checks with isHTTPSuccess() helper
- Remove unused ExtractBearerToken() and BuildModelsURL() functions
- Make buildChatCompletionURL() private (only used internally)
- Remove unused 'strings' import
Add complete GitHub Copilot support including:
- Device flow OAuth authentication via GitHub's official client ID
- Token management with automatic caching (25 min TTL)
- OpenAI-compatible API executor for api.githubcopilot.com
- 16 model definitions (GPT-5 variants, Claude variants, Gemini, Grok, Raptor)
- CLI login command via -github-copilot-login flag
- SDK authenticator and refresh registry integration
Enables users to authenticate with their GitHub Copilot subscription and
use it as a backend provider alongside existing providers.
2025-11-27 20:14:30 +01:00
1368 changed files with 271636 additions and 31748 deletions
- `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
This project is sponsored by Z.ai, supporting us with their GLM CODING PLAN.
Thanks to PackyCode for sponsoring this project!
GLM CODING PLAN is a subscription service designed for AI coding, starting at just $3/month. It provides access to their flagship GLM-4.7 model across 10+ popular AI coding tools (Claude Code, Cline, Roo Code, etc.), offering developers top-tier, fast, and stable coding experiences.
PackyCode is a reliable and efficient API relay service provider, offering relay services for Claude Code, Codex, Gemini, and more.
Get 10% OFF GLM CODING PLAN:https://z.ai/subscribe?ic=8JVLJQFSKB
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.
<td>Thanks to PackyCode for sponsoring this project! 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.</td>
<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>Thanks to Cubence for sponsoring this project! Cubence is a reliable and efficient API relay service provider, offering relay services for Claude Code, Codex, Gemini, and more. Cubence provides special discounts for our software users: register using <a href="https://cubence.com/signup?code=CLIPROXYAPI&source=cpa">this link</a> and enter the "CLIPROXYAPI" promo code during recharge to get 10% 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>
</tr>
</tbody>
</table>
## Overview
- OpenAI/Gemini/Claude compatible API endpoints for CLI models
- OpenAI/Gemini/Claude/Grok compatible API endpoints for CLI models
- OpenAI Codex support (GPT models) via OAuth login
- Claude Code support via OAuth login
-Qwen Code support via OAuth login
-iFlow support via OAuth login
- Amp CLI and IDE extensions support with provider routing
- Streaming and non-streaming responses
-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, Qwen and iFlow)
see [MANAGEMENT_API.md](https://help.router-for.me/management/api)
## Amp CLI Support
## Usage Statistics
CLIProxyAPI includes integrated support for [Amp CLI](https://ampcode.com) and Amp IDE extensions, enabling you to use your Google/ChatGPT/Claude OAuth subscriptions with Amp's coding tools:
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:
- Provider route aliases for Amp's API patterns (`/api/provider/{provider}/v1...`)
- Management proxy for OAuth authentication and account features
- Smart model fallback with automatic routing
- **Model mapping** to route unavailable models to alternatives (e.g., `claude-opus-4.5` → `claude-sonnet-4`)
- Security-first design with localhost-only management endpoints
Standalone persistence and visualization service for CLIProxyAPI, with periodic data sync, SQLite storage, aggregate APIs, and a built-in dashboard for usage and statistics.
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.
## SDK Docs
@@ -104,23 +120,15 @@ Native macOS menu bar app to use your Claude Code & ChatGPT subscriptions with A
Browser-based tool to translate SRT subtitles using your Gemini subscription via CLIProxyAPI with automatic validation/error correction - no API keys needed
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.
CLI wrapper for instant switching between multiple Claude accounts and alternative models (Gemini, Codex, Antigravity) via CLIProxyAPI OAuth - no API keys needed
Native macOS menu bar app that unifies Claude, Gemini, OpenAI, Qwen, 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.
### [CodMate](https://github.com/loocor/CodMate)
Native macOS SwiftUI app for managing CLI AI sessions (Codex, Claude Code, Gemini CLI) with unified provider management, Git review, project organization, global search, and terminal integration. Integrates CLIProxyAPI to provide OAuth authentication for Codex, Claude, Gemini, Antigravity, and Qwen Code, with built-in and third-party provider rerouting through a single proxy endpoint - no API keys needed for OAuth providers.
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.
@@ -130,7 +138,62 @@ Windows-native CLIProxyAPI fork with TUI, system tray, and multi-provider OAuth
VSCode extension for quick switching between Claude Code models, featuring integrated CLIProxyAPI as its backend with automatic background lifecycle management.
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.
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)
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.
### [All API Hub](https://github.com/qixing-jk/all-api-hub)
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.
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.
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.
### [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
@@ -141,7 +204,21 @@ Those projects are ports of CLIProxyAPI or inspired by it:
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>
@@ -36,23 +56,20 @@ GLM CODING PLAN 是专为AI编码打造的订阅套餐,每月最低仅需20元
## 功能特性
- 为 CLI 模型提供 OpenAI/Gemini/Claude/Codex 兼容的 API 端点
- 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
The following versions of ProxyPilot are currently supported with security updates:
| Version | Supported |
| ------- | ------------------ |
| latest | :white_check_mark: |
| < 1.0 | :x: |
## Reporting a Vulnerability
We take the security of ProxyPilot seriously. If you discover a security vulnerability, please report it responsibly.
### How to Report
You can report a vulnerability through one of the following methods:
1.**GitHub Security Advisory (Preferred)**: Open a private security advisory through [GitHub Security Advisories](https://github.com/smat-dev/ProxyPilot/security/advisories/new). This allows for private discussion and coordination.
2.**Email**: Send an email to the project maintainers with details of the vulnerability. Please include:
- A description of the vulnerability
- Steps to reproduce the issue
- Potential impact of the vulnerability
- Any suggested fixes (if available)
### What to Expect
After submitting a vulnerability report:
- **Initial Response**: You will receive an acknowledgment within **48 hours** confirming we have received your report.
- **Assessment**: We will investigate and assess the vulnerability within **7 days**.
- **Resolution Timeline**: We aim to release a fix for confirmed vulnerabilities within **30 days**, depending on complexity.
- **Disclosure**: Once a fix is released, we will coordinate with you on public disclosure timing.
We will keep you informed throughout the process and credit you for the discovery (unless you prefer to remain anonymous).
## Responsible Disclosure Guidelines
To protect our users, we ask that you:
- **DO NOT** disclose the vulnerability publicly until a fix has been released.
- **DO NOT** exploit the vulnerability beyond what is necessary to demonstrate the issue.
- **DO NOT** access, modify, or delete data belonging to other users.
- **DO** provide us with reasonable time to address the issue before any public disclosure.
- **DO** act in good faith to avoid privacy violations, data destruction, or service disruption.
We are committed to working with security researchers and will not take legal action against individuals who discover and report vulnerabilities responsibly.
## Security Best Practices for Users
- Always use the latest version of ProxyPilot.
- Review and understand the proxy configurations before deployment.
- Use secure connections (HTTPS) where applicable.
- Regularly review access logs for suspicious activity.
Thank you for helping keep ProxyPilot and its users safe.
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.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")
# Per-entry proxy-url also supports "direct" or "none" to bypass both the global proxy-url and environment proxies explicitly.
proxy-url:""
# When true, unprefixed model requests only use credentials without a prefix (except when prefix == model name).
force-model-prefix:false
# When true, forward filtered upstream response headers to downstream clients.
# Default is false (disabled).
passthrough-headers:false
# Number of times to retry a request. Retries will occur if the HTTP response code is 403, 408, 500, 502, 503, or 504.
request-retry:3
# Maximum number of different credentials to try for one failed request.
# Set to 0 to keep legacy behavior (try all available credentials).
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
# when the client omits them, while OS/arch remain runtime-derived. When
# stabilize-device-profile is enabled, OS/arch stay pinned to the baseline values below,
# while user-agent/package-version/runtime-version seed a software fingerprint that can
# still upgrade to newer official Claude client versions.
This is a static, copy-paste demo showing how the middleware rewrites requests.
## Responses API (Codex CLI style)
Input:
```json
{
"model":"gpt-5-codex",
"instructions":"Follow the user's request.",
"input":[
{"role":"user","content":[{"type":"input_text","text":"Build a todo app"}]}
]
}
```
Injected (INITIALIZER mode):
```json
{
"model":"gpt-5-codex",
"instructions":"Follow the user's request.\n\n<harness_mode>INITIALIZER</harness_mode>\nYou are the **Initializer Agent** in a Long-Running Agent Harness.\nYour ONLY goal is to set up the project environment for future Coding Agents.\n\n**CRITICAL INSTRUCTIONS**:\n1. **Analyze the User's Request**: Understand what feature or app needs to be built.\n2. **Create 'feature_list.json'**:\n - Write a JSON file listing ALL features/requirements as separate items.\n - Mark them all as \"passes\": false.\n - Format:\n Request: \"Build a todo app\"\n File Content:\n [\n { \"category\": \"core\", \"description\": \"User can add a todo\", \"steps\": [\"Open app\", \"Enter text\", \"Press enter\", \"See new item\"], \"passes\": false },\n { \"category\": \"core\", \"description\": \"User can delete a todo\", \"steps\": [\"Open app\", \"Click delete\", \"Item removed\"], \"passes\": false }\n ]\n3. **Create 'claude-progress.txt'**:\n - Create this file with a header \"## Progress Log\".\n - Add an initial entry: \"- [Initializer] Environment setup started.\"\n4. **Create 'init.sh' (Optional)**:\n - If a dev server is needed, create a script to start it (e.g., 'npm run dev').\n5. **Initial Commit**:\n - Initialize git if not present.\n - Commit these foundational files.\n\n**DO NOT** start implementing features yourself. Your job is ONLY to scaffold the harness.",
"input":[
{"role":"user","content":[{"type":"input_text","text":"Build a todo app"}]}
]
}
```
## Chat Completions (Claude / OAI chat)
Input:
```json
{
"model":"claude-sonnet-4-5-thinking",
"messages":[
{"role":"system","content":"You are a helpful assistant."},
{"role":"user","content":"Set up the repo"}
]
}
```
Injected (INITIALIZER mode):
```json
{
"model":"claude-sonnet-4-5-thinking",
"messages":[
{
"role":"system",
"content":"You are a helpful assistant.\n\n<harness_mode>INITIALIZER</harness_mode>\nYou are the **Initializer Agent** in a Long-Running Agent Harness.\nYour ONLY goal is to set up the project environment for future Coding Agents.\n\n**CRITICAL INSTRUCTIONS**:\n... (same initializer prompt) ..."
},
{"role":"user","content":"Set up the repo"}
]
}
```
## CODING mode trigger
If `feature_list.json` or `claude-progress.txt` exists under `harness-root-dir`,
the middleware switches to CODING mode and injects the Coding prompt instead.
- 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:
When all credentials are blocked for a model, CLIProxyAPI now reports more informative HTTP statuses:
- Quota/rate cooldown: `429` with `code: model_cooldown` and `Retry-After`
- Temporarily blocked credentials (non-quota): `503` with `code: auth_unavailable`, `Retry-After`, and a JSON error body including blocked counts and recent upstream HTTP statuses (when known)
**proxypilot** is the unified command-line interface for the ProxyPilot local AI proxy. It provides both **server** functionality (running the proxy server) and **switch** functionality (toggling AI agents between proxy mode and native mode).
## Installation
### Via bun (recommended)
```bash
bun install -g proxypilot
```
### Via npm
```bash
npm install -g proxypilot
```
### Via Go
```bash
go install github.com/Finesssee/ProxyPilot/cmd/server@latest
```
### Manual Download
Download pre-built binaries from [GitHub Releases](https://github.com/Finesssee/ProxyPilot/releases).
Available binaries:
-`proxypilot-darwin-amd64` - macOS Intel
-`proxypilot-darwin-arm64` - macOS Apple Silicon
-`proxypilot-linux-amd64` - Linux x64
-`proxypilot-linux-arm64` - Linux ARM64
-`proxypilot-windows-amd64.exe` - Windows x64
## Server Mode
Run ProxyPilot as a local proxy server:
```bash
proxypilot # Start server on default port (8317)
proxypilot -config /path/to/config # Use custom config file
```
### Server Features
- Routes AI requests through configured providers
- Automatic model aliasing and translation
- OAuth login helpers for various providers
- Agent configuration management
### Login Commands
```bash
proxypilot --login # Login to Google Account (Gemini)
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 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.
### Login Options
```bash
--no-browser # Don't open browser automatically for OAuth
--incognito # Use incognito/private mode (useful for multiple accounts)
--no-incognito # Force disable incognito mode
```
### Import Commands
```bash
proxypilot --vertex-import <file> # Import Vertex service account key JSON
proxypilot --kiro-import # Import Kiro token from Kiro IDE
```
## Agent Configuration
ProxyPilot can automatically configure AI CLI tools to use the proxy.
### Detect Installed Agents
```bash
proxypilot --detect-agents
```
Example output:
```
Detecting installed CLI agents...
Claude Code: [+] Installed
Binary: /usr/local/bin/claude
Config: ~/.claude/settings.json
Codex CLI: [+] Installed
Binary: /usr/local/bin/codex
Config: ~/.codex
Gemini CLI: [-] Not found
```
### Setup Commands
```bash
proxypilot --setup-all # Configure all detected agents
Switch AI agents between proxy mode (through ProxyPilot) and native mode (direct API access). Think of it like `nvm` for Node versions, but for AI agent configurations.
### Usage
```bash
proxypilot --switch <agent> # Show status of specific agent
- Sends `stream: true` but typically uses `Accept: application/json`
- CLIProxyAPI uses a non-stream upstream call and **synthesizes SSE** for reliability.
- Notes:
- Droid attempts to JSON-parse each SSE `data:` line, so `data: [DONE]` must **not** be emitted for this client.
- Routing transparency:
- For localhost requests, the same headers as Codex apply for underlying routing.
- The `/v0/management/routing/preview?model=...` endpoint is the easiest way to debug which provider a `model` will map to before sending a turn from Droid/Factory.
- If body has `"stream": true` and `Accept` includes `text/event-stream`, ProxyPilot streams SSE.
- If `Accept: application/json`**without**`text/event-stream`, ProxyPilot automatically downgrades to non-streaming and returns JSON, even when `stream: true`.
- Notes:
- Responses from localhost include routing headers as above.
- For debugging, you can issue a test request and inspect:
-`X-ProxyPilot-Requested-Model` vs `X-ProxyPilot-Resolved-Model` to see alias/`auto`/thinking normalisation.
-`X-ProxyPilot-Provider-Candidates` and `X-ProxyPilot-Resolved-Provider` to see which upstream(s) and which provider actually ran.
- Returns JSON describing how a given model name will be normalised and which provider candidates will be used.
-`POST /v0/management/routing/preview`
- Accepts a full request JSON body (OpenAI/OpenAIResponses-compatible), extracts the `model` field, and returns the same routing preview for that model.
-`/v0/management/routing/recent`
- Returns a small in-memory list of the last few routed requests (timestamp, path, requested/resolved model, provider + candidates).
- Both endpoints require a management key and are intended for localhost use.
### `gemini-3-*` provider preference
- Primary: `antigravity`
- Fallback: `gemini-cli` (only used if antigravity is unavailable/cooling)
- Rotation: disabled between these two providers to keep the primary stable.
CLIProxyAPI can be used as a local OpenAI-compatible endpoint for Cursor.
## 1) Start CLIProxyAPI
Run the server and note the listening address (default: `http://localhost:8318`).
## 2) Configure Cursor
In Cursor settings:
- **API base URL**: `http://localhost:8318` (recommended)
- Alternatively: `http://localhost:8318/v1` (CLIProxyAPI also provides non-`/v1` aliases for this case)
- **API key**: use one of the keys from `config.yaml` under `api-keys`
- Example: `your-cli-proxy-api-key`
## 3) Model selection
Cursor will query `GET /v1/models` (or `/models` when base URL ends with `/v1`).
Pick any model exposed by your configured providers.
## Notes
-`POST /v1/embeddings` is implemented and returns deterministic synthetic embeddings to keep IDE features working even when an embeddings backend is not configured.
Hindsight is an **agent memory system** (retain/recall/reflect) that can run locally and expose an **MCP server**. It can help reduce “context rot” and repeated “prompt too long” failures by moving long-term memory out of the chat history and into a separate store the agent can query.
CLIProxyAPI is a **proxy + translator**. It is not the “agent brain”, so the best integration is to run Hindsight as a **sidecar** and let your CLI agent call it via MCP tools.
Repo: https://github.com/vectorize-io/hindsight
## Recommended architecture
- Keep CLIProxyAPI focused on: auth, routing, translation, compatibility fixes, and request trimming.
- Run Hindsight separately (Docker or `pip install hindsight-api`).
- Add Hindsight as an MCP server to your agentic client (Droid/Factory CLI, Claude Code, etc.).
- Teach the agent (via your system prompt) to:
-`retain` stable preferences and project facts
-`recall` before large context dumps
-`reflect` after successes/failures to improve consistency
## Run Hindsight locally
### Docker (easy)
```bash
# Provide an LLM key/model for Hindsight’s internal reasoning (separate from CLIProxyAPI)
exportHINDSIGHT_API_LLM_PROVIDER=openai
exportHINDSIGHT_API_LLM_API_KEY=sk-...
exportHINDSIGHT_API_LLM_MODEL=gpt-4o-mini
docker run --rm -it -p 8888:8888 -p 9999:9999 \
-e HINDSIGHT_API_LLM_PROVIDER \
-e HINDSIGHT_API_LLM_API_KEY \
-e HINDSIGHT_API_LLM_MODEL \
-v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
ghcr.io/vectorize-io/hindsight:latest
```
- REST API: `http://localhost:8888`
- MCP server: `http://localhost:8888/mcp`
- UI: `http://localhost:9999`
### Python (no Docker)
```bash
pip install hindsight-api -U
exportHINDSIGHT_API_LLM_PROVIDER=openai
exportHINDSIGHT_API_LLM_API_KEY=sk-...
hindsight-api
```
## Connect your agent via MCP
Hindsight exposes MCP two ways:
- **HTTP MCP**: `http://localhost:8888/mcp`
- **stdio MCP**: `hindsight-local-mcp`
How you register an MCP server depends on the client. Many clients use a `.mcp.json` file. Typical patterns:
### Option A: stdio MCP (most portable)
```json
{
"mcpServers":{
"hindsight":{
"command":"hindsight-local-mcp",
"args":[],
"env":{
"HINDSIGHT_API_LLM_PROVIDER":"openai",
"HINDSIGHT_API_LLM_API_KEY":"sk-..."
}
}
}
}
```
### Option B: HTTP MCP
If your client supports HTTP MCP servers, point it at:
-`http://localhost:8888/mcp`
## Operational notes / gotchas
- **Privacy**: Hindsight stores memory content (and may call its own LLM). Treat it like a database of user data.
- **Tool-call correctness**: If you see tool sequencing errors in Claude/Vertex, check `docs/tool-calling-and-cli-compat.md`.
- **Keep it optional**: Don’t enable or inject memory tools by default from CLIProxyAPI; different clients have different tool behaviors, and tool injection can increase prompt size.
## Next step (if you want deeper integration)
If you want CLIProxyAPI to “own” the Hindsight lifecycle, we can spec a thin optional module:
-`config.yaml`:
-`hindsight.enabled`
-`hindsight.base_url`
-`hindsight.auth_header` (optional)
- A small “memory helper” doc + scripts to start/stop the Hindsight sidecar alongside CLIProxyAPI.
5. Fallback hash of `Authorization + User-Agent` (hashed; raw values are not stored)
## Retrieval / injection
- Dropped items are appended as JSONL events (`dropped_chat` / `dropped_responses`)
- Retrieval is a lightweight keyword scorer over the last ~2MB of stored events
- Up to 8 snippets (~6k chars) are injected by appending to the **last user message** (best-effort).
## Anchored summaries (heuristic)
When history is trimmed, ProxyPilot writes a lightweight anchor summary based on **heuristic extraction**
(latest user intent + file/command hits). It does not use an LLM to summarize old turns.
Key behaviors:
- No LLM-based summarization of old turns. The anchored summary is generated by heuristic extraction (latest user intent + file/command hits) from dropped messages, not a model-produced summary.
- No explicit “~140k sweet spot” threshold or scheduled compression cycle. The memory flow only kicks in when a request exceeds budget and must be trimmed.
- No explicit cache-aware anchoring beyond append-only scaffold (we preserve append-only, but we don’t do Droid’s full anchored compression pipeline).
To preserve stable prompt prefixes for long sessions, CLIProxyAPI injects session state as an **append-only scaffold** by default (it appends a new system message/input entry instead of mutating prior content).
Packed block format:
-`<proxypilot_state>`
-`<pinned>` from `pinned.md`
-`<anchor>` from `summary.md`
-`<todo>` from `todo.md`
-`<spec>` when Spec Mode is enabled
## Text normalization
Some clients (notably PowerShell `ConvertTo-Json`) can store TODO/pinned state with escaped sequences like `\\n` / `\\u2019`.
CLIProxyAPI normalizes common escape sequences when reading/writing `todo.md`, `pinned.md`, and `summary.md` so the injected state stays readable.
## AGENTS.md pinning
If `harness-root-dir` is set (or provided to the middleware), CLIProxyAPI will read `AGENTS.md` from that directory and merge it into pinned context.
## Spec Mode (optional)
Spec Mode can be enabled to require a spec/plan before any code changes:
- Header: `X-CLIProxyAPI-Spec-Mode: true`
- Env: `CLIPROXY_SPEC_MODE=1`
When enabled and not yet approved, the scaffold injects a spec prompt that asks the agent to produce a reviewable specification and wait for approval.
## Semantic memory (local embeddings)
ProxyPilot can optionally embed and retrieve semantic memory using a local Ollama embed model.
This runs fully local and is **always-on** when enabled.
Embedding of dropped history is queued in the background to keep request latency low.
Environment variables:
-`CLIPROXY_SEMANTIC_ENABLED` (default: enabled)
-`CLIPROXY_SEMANTIC_MODEL` (default: `embeddinggemma`; also supports `nomic-embed-text`)
For advanced context compression using LLM-generated structured summaries and token-aware proactive trimming, see [Context Compression](context-compression.md).
## Agentic Harness
For structured incremental development workflows (INITIALIZER/CODING modes, feature tracking, progress logging), see [Agentic Harness](agentic-harness.md).
ProxyPilot is a local AI proxy with CLI + system tray interface for agentic tools (Droid/Factory, Codex CLI, Warp).
This repo started as a fork of CLIProxyAPI, but is now branded as ProxyPilot. For compatibility, some internal names and headers still use `CLIProxyAPI` (e.g. `X-CLIProxyAPI-*`).
## What’s included
- ProxyPilot tray app (Windows) to start/stop/restart the proxy engine, open the web dashboard in browser, open logs, and toggle autostart.
- Prompt-budget middleware to reduce “prompt too long” failures in strict CLIs.
- Long-session memory with pinned state + persistent TODO (local disk).
- Optional auth debugging and cooldown reset endpoints for local troubleshooting.
-`Auto-start proxy` (starts the proxy engine when ProxyPilot launches)
On Windows this uses a per-user Run entry (no admin required).
## Local management (Dashboard / tray)
When the proxy is started by the ProxyPilot tray app, it sets a per-user `MANAGEMENT_PASSWORD` for the engine process so `/v0/management/*` endpoints are enabled for local use.
The password is stored in the ProxyPilot UI state file:
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.
## Logs / diagnostics
Useful paths:
-`logs/proxypilot-engine.out.log`
-`logs/proxypilot-engine.err.log`
-`logs/v1-responses-*.log` / `logs/v1-chat-completions-*.log` (request logs, if enabled)
*`SetProviders` replaces the provider slice using a defensive copy.
*`Providers` retrieves a snapshot that can be iterated safely from other goroutines.
*`BuildProviders` translates `config.Config` access declarations into runnable providers. When the config omits explicit providers but defines inline API keys, the helper auto-installs the built-in `config-api-key` provider.
If the manager itself is `nil` or no providers are configured, the call returns `nil, nil`, allowing callers to treat access control as disabled.
## Authenticating Requests
```go
result,err:=manager.Authenticate(ctx,req)
result,authErr:=manager.Authenticate(ctx,req)
switch{
caseerr==nil:
caseauthErr==nil:
// Authentication succeeded; result describes the provider and principal.
// Supplied credentials were present but rejected.
default:
// Transport-level failure was returned by a provider.
// Internal/transport failure was returned by a provider.
}
```
`Manager.Authenticate` walks the configured providers in order. It returns on the first success, skips providers that surface `ErrNotHandled`, and tracks whether any provider reported `ErrNoCredentials`or`ErrInvalidCredential` for downstream error reporting.
If the manager itself is `nil` or no providers are registered, the call returns `nil, nil`, allowing callers to treat access control as disabled without branching on errors.
`Manager.Authenticate` walks the configured providers in order. It returns on the first success, skips providers that return `AuthErrorCodeNotHandled`, and aggregates `AuthErrorCodeNoCredentials`/`AuthErrorCodeInvalidCredential` for a final result.
Each `Result` includes the provider identifier, the resolved principal, and optional metadata (for example, which header carried the credential).
## Configuration Layout
## Built-in `config-api-key` Provider
The manager expects access providers under the `auth.providers` key inside `config.yaml`:
The proxy includes one built-in access provider:
-`config-api-key`: Validates API keys declared under top-level `api-keys`.
- Metadata: `Result.Metadata["source"]` is set to the matched source label.
In the CLI server and `sdk/cliproxy`, this provider is registered automatically based on the loaded configuration.
```yaml
auth:
providers:
- name:inline-api
type:config-api-key
api-keys:
- sk-test-123
- sk-prod-456
api-keys:
- sk-test-123
- sk-prod-456
```
Fields map directly to `config.AccessProvider`: `name` labels the provider, `type` selects the registered factory, `sdk` can name an external module, `api-keys` seeds inline credentials, and `config` passes provider-specific options.
## Loading Providers from External Go Modules
### Loading providers from external SDK modules
To consume a provider shipped in another Go module, point the `sdk` field at the module path and import it for its registration side effect:
To consume a provider shipped in another Go module, import it for its registration side effect:
```go
import(
@@ -89,19 +80,11 @@ import (
)
```
The blank identifier import ensures `init` runs so `sdkaccess.RegisterProvider` executes before `BuildProviders`is called.
## Built-in Providers
The SDK ships with one provider out of the box:
-`config-api-key`: Validates API keys declared inline or under top-level `api-keys`. It accepts the key from `Authorization: Bearer`, `X-Goog-Api-Key`, `X-Api-Key`, or the `?key=` query string and reports `ErrInvalidCredential` when no match is found.
Additional providers can be delivered by third-party packages. When a provider package is imported, it registers itself with `sdkaccess.RegisterProvider`.
The blank identifier import ensures `init` runs so `sdkaccess.RegisterProvider` executes before you call `RegisteredProviders()`(or before `cliproxy.NewBuilder().Build()`).
### Metadata and auditing
`Result.Metadata` carries provider-specific context. The built-in `config-api-key` provider, for example, stores the credential source (`authorization`, `x-goog-api-key`, `x-api-key`, or`query-key`). Populate this map in custom providers to enrich logs and downstream auditing.
`Result.Metadata` carries provider-specific context. The built-in `config-api-key` provider, for example, stores the credential source (`authorization`, `x-goog-api-key`, `x-api-key`, `query-key`,`query-auth-token`). Populate this map in custom providers to enrich logs and downstream auditing.
A provider must implement `Identifier()` and `Authenticate()`. To expose it to configuration, call `RegisterProvider` inside `init`. Provider factories receive the specific `AccessProvider` block plus the full root configuration for contextual needs.
A provider must implement `Identifier()` and `Authenticate()`. To make it available to the access manager, call `RegisterProvider` inside `init` with an initialized provider instance.
## Error Semantics
-`ErrNoCredentials`: no credentials were present or recognized by any provider.
-`ErrInvalidCredential`: at least one provider processed the credentials but rejected them.
-`ErrNotHandled`: instructs the manager to fall through to the next provider without affecting aggregate error reporting.
-`NewNoCredentialsError()` (`AuthErrorCodeNoCredentials`): no credentials were present or recognized. (HTTP 401)
-`NewInvalidCredentialError()` (`AuthErrorCodeInvalidCredential`): credentials were present but rejected. (HTTP 401)
-`NewNotHandledError()` (`AuthErrorCodeNotHandled`): fall through to the next provider.
Return custom errors to surface transport failures; they propagate immediately to the caller instead of being masked.
Errors propagate immediately to the caller unless they are classified as `not_handled` / `no_credentials` / `invalid_credential` and can be aggregated by the manager.
## Integration with cliproxy Service
`sdk/cliproxy` wires `@sdk/access` automatically when you build a CLI service via `cliproxy.NewBuilder`. Supplying a preconfigured manager allows you to extend or override the default providers:
`sdk/cliproxy` wires `@sdk/access` automatically when you build a CLI service via `cliproxy.NewBuilder`. Supplying a manager lets you reuse the same instance in your host process:
```go
coreCfg,_:=config.LoadConfig("config.yaml")
providers,_:=sdkaccess.BuildProviders(coreCfg)
manager:=sdkaccess.NewManager()
manager.SetProviders(providers)
accessManager:=sdkaccess.NewManager()
svc,_:=cliproxy.NewBuilder().
WithConfig(coreCfg).
WithAccessManager(manager).
WithConfigPath("config.yaml").
WithRequestAccessManager(accessManager).
Build()
```
The service reuses the manager for every inbound request, ensuring consistent authentication across embedded deployments and the canonical CLI binary.
Register any custom providers (typically via blank imports) before calling `Build()` so they are present in the global registry snapshot.
### Hot reloading providers
### Hot reloading
When configuration changes, rebuild providers and swap them into the manager:
When configuration changes, refresh any config-backed providers and then reset the manager's provider chain:
This mirrors the behaviour in `cliproxy.Service.refreshAccessProviders` and `api.Server.applyAccessConfig`, enabling runtime updates without restarting the process.
This mirrors the behaviour in `internal/access.ApplyAccessProviders`, enabling runtime updates without restarting the process.
Merged upstream CLIProxyAPI releases `v6.8.40` through `v6.8.46` into ProxyPilot on branch `sync-upstream-v6.8.40-to-v6.8.46` and prepared the next dev release tag `v0.3.0-dev-0.40`.
## Upstream Releases Included
-`v6.8.40` - adaptive thinking updates across Claude, Codex, OpenAI, and Antigravity flows
-`v6.8.44` - watcher timer fix and initial GPT-5.4 registry entry
-`v6.8.45` - GPT-5.4 description cleanup and conditional `service_tier` handling
-`v6.8.46` - Gemini 3.1 Flash Lite Preview registry support and Codex websocket `response.create` cleanup
## Conflict Resolution Notes
- Kept ProxyPilot branding in `README.md` during the `v6.8.41` merge.
- Preserved deletion of `README_CN.md` when upstream tried to reintroduce it.
- Accepted upstream behavior in translator, watcher, executor, and registry paths unless the fork already had a stronger ProxyPilot-specific customization.
## Verification
- Clean `origin/main` baseline still fails `go test ./sdk/cliproxy/auth` in `TestFileStore_Delete_RemovesFile`; treated as a pre-existing failure.
- Targeted subsystem checks passed after each upstream merge for thinking, translators, watcher, registry, executor, and OpenAI websocket paths.
- Final full-suite verification should still record the pre-existing `sdk/cliproxy/auth` failure explicitly if it remains on the final release commit.
Merged upstream CLIProxyAPI releases `v6.8.47` through `v6.8.49` into ProxyPilot on branch `sync-upstream-v6.8.47-to-v6.8.49`, fixed fork-specific release lookup drift, and prepared the next dev release tag `v0.3.0-dev-0.41`.
- Kept ProxyPilot branding and structure in `README.md` during the `v6.8.49` merge.
- Preserved deletion of `README_CN.md` when upstream tried to reintroduce it.
- Accepted upstream behavior in watcher, registry, auth scheduler, translator, and executor paths unless the fork already had a stronger ProxyPilot-specific customization.
## Fork-Specific Follow-Ups
- Updated `UPSTREAM_VERSION` to `v6.8.49`.
- Updated `features.json` upstream marker to `CLIProxyAPI v6.8.49`.
- Fixed `.github/workflows/check-upstream.yml` so it compares the tracked `UPSTREAM_VERSION` tag against the latest upstream release tag instead of comparing upstream HEAD to itself.
- Switched fork-facing release lookups in `internal/api/handlers/management/config_basic.go` and `internal/proxypilotupdate/github.go` to `Finesssee/ProxyPilot` releases.
Merged upstream CLIProxyAPI releases `v6.8.50` and `v6.8.51` directly into ProxyPilot `main`, resolved fork-specific conflicts in startup and Docker publishing paths, prepared the next dev release tag `v0.3.0-dev-0.42`, then switched release publishing to a local/manual flow and uploaded the release assets outside GitHub Actions.
## Upstream Releases Included
-`v6.8.50` - preserve string-form system prompts, cap websocket body log growth, and extend scheduler / executor coverage
-`v6.8.51` - refresh model catalog from network on startup, register Codex models by plan tier, and refresh release / workflow paths
## Conflict Resolution Notes
- Kept ProxyPilot Docker publishing identity in `.github/workflows/docker-image.yml` and added the upstream models catalog refresh step before image builds.
- Kept ProxyPilot's management-password startup flow in `cmd/server/main.go` and added `registry.StartModelsUpdater(...)` before service startup.
- Accepted the upstream move from generated static registry data to embedded `internal/registry/models/models.json`, including deletion of `internal/registry/model_definitions_static_data.go`.
## Fork-Specific Follow-Ups
- Updated `internal/cmd/list_models.go` to use the new Codex plan-tier model getters instead of the removed `registry.GetOpenAIModels`.
- Fixed `sdk/auth/filestore.go` delete-path resolution so nested relative auth IDs delete under the configured base dir, absolute paths still work for the management API, and traversal outside the base dir is rejected.
- Updated `UPSTREAM_VERSION` to `v6.8.51`.
- Updated `features.json` upstream marker to `CLIProxyAPI v6.8.51`.
- Changed `.github/workflows/proxypilot-release.yml` and `.github/workflows/docker-image.yml` from tag-triggered runs to manual dispatch so releases can be built locally and uploaded manually instead of consuming GitHub Actions minutes.
- Built the `v0.3.0-dev-0.42` release assets locally from the tag snapshot and uploaded:
-`go test ./sdk/cliproxy/auth -run 'TestFileStore_Delete_(RemovesFile|NotFound|AbsolutePath|RejectsTraversalOutsideBaseDir)' -v` - PASS
-`go test ./sdk/cliproxy/auth` - PASS
-`go test ./sdk/cliproxy/...` - PASS
-`go test ./...` - PASS
## Release Notes
- Next dev tag: `v0.3.0-dev-0.42`
- Latest upstream target at merge time: `CLIProxyAPI v6.8.51`
## Maintenance Review
- Completed parallel findings-first review of `internal/auth/*`, `internal/translator/*`, and `internal/api/handlers/*` on 2026-03-12 12:01:40 +07.
- Auth review findings:
-`internal/auth/kiro/token_repository.go` only queues `auth_method` values `idc` and `builder-id` for background refresh even though `internal/auth/kiro/oauth.go` persists social logins as `auth_method: "social"` and the refresher has a default OAuth refresh path for non-SSO methods. Result: Google/GitHub Kiro tokens are skipped by auto-refresh.
-`internal/auth/kiro/token_repository.go` walks nested token files but rewrites refreshed tokens back to `filepath.Join(baseDir, token.ID)` after truncating IDs to `filepath.Base(path)`. Result: nested Kiro token files would be rewritten into the auth root instead of their original directory.
- Translator review findings:
-`internal/translator/kiro/openai` can emit streamed tool-call argument deltas with the wrong OpenAI tool index.
-`internal/translator/kiro/openai` does not actually enforce `tool_choice`; it still forwards tools when callers request `none` or pin a specific function.
-`internal/translator/openai/openai/responses` downgrades `developer` messages to `user`.
-`internal/translator/gemini/openai/chat-completions` reads/mapping finish reasons incorrectly for some response shapes.
-`internal/translator/gemini/openai/responses` can send `functionResponse.name = "unknown"` on follow-up tool-output requests.
- API handler review findings:
-`internal/api/handlers/management/memory.go` uses raw `session` query values to build filesystem paths for delete/export/import instead of the memory store's sanitized session path helper, allowing traversal outside the memory store root.
-`internal/api/handlers/management/generic_import.go` derives auth filenames from the first characters of imported API keys, exposing secret prefixes in filenames and management responses.
-`internal/api/handlers/management/auth_files.go` writes uploaded auth files to disk before validation and leaves invalid files behind on registration failure.
-`internal/api/handlers/management/config_basic.go` returns a zero-value config from `GetConfig` because it serializes `new(*h.cfg)` instead of the current config.
-`internal/api/handlers/management/auth_priority.go` and `internal/api/handlers/management/auth_files.go` update priority in places the runtime selector does not read, so management-set auth priority does not affect routing and does not persist reliably for file-backed auths.
- Config mutation helpers in `internal/api/handlers/management/handler.go` mutate `h.cfg` before persistence succeeds, so failed writes can leave runtime config diverged from disk until restart.
- Review validation:
-`go test ./internal/auth/... ./internal/translator/... ./internal/api/handlers/...` - PASS
## Maintenance Fixes
- Hardened management memory delete/export/import so session names are validated before resolving filesystem paths, blocking traversal attempts outside the memory store root.
- Changed bulk API-key import filenames to opaque `provider-import-...` names so credential prefixes are no longer exposed in filenames or management responses.
- Changed auth upload handling to validate uploaded JSON before committing it to disk and to roll back failed registrations instead of leaving broken auth files behind.
- Fixed `GetConfig` to return the live in-memory config and changed the simple config mutation helpers to persist cloned config state instead of mutating runtime config before the file write succeeds.
- Fixed file-backed auth persistence so `priority`, `prefix`, and `proxy_url` survive saves, reloads, and management edits, and so runtime selection prefers `Auth.Priority` with a legacy attribute fallback.
- Changed token writers across codex, claude, gemini, kimi, qwen, iflow, copilot, and vertex to use atomic `0600` JSON writes.
- Fixed Kiro background refresh so blank refresh responses do not erase the existing refresh token, nested token paths refresh in place, and social auth token files participate in the refresh scan.
- Fixed Kiro OAuth callback servers so shutdown waits on a dedicated completion signal instead of racing the login flow for the only callback result.
- Fixed Kiro/OpenAI tool streaming to keep a stable mapping from content-block indexes to OpenAI tool ordinals.
- Fixed Kiro/OpenAI request translation so `tool_choice=none|required|function` is enforced instead of treated as a prompt-only hint.
- Fixed OpenAI Responses to Chat Completions conversion to preserve `developer` role messages.
- Fixed Gemini/OpenAI finish-reason mapping so OpenAI receives valid enums while the original Gemini reason is preserved in `native_finish_reason`.
- Added a bounded Gemini function-call name cache so `previous_response_id` follow-up tool outputs resolve the original function name and fail closed when they cannot.
## Maintenance Fix Verification
-`go test ./internal/auth/... ./sdk/auth ./sdk/cliproxy/auth ./internal/translator/... ./internal/api/handlers/...` - PASS
-`go test ./internal/api/handlers/management` - PASS
Merged upstream CLIProxyAPI release `v6.8.55` into ProxyPilot `main`, carrying forward the fork's workflow and branding decisions while absorbing upstream changes from `v6.8.52` through `v6.8.55`.
Built the release assets locally and published `v0.3.0-dev-0.43` on GitHub as the latest ProxyPilot release.
## Upstream Releases Included
- `v6.8.52` - Codex websocket header defaults and related compatibility updates
- `v6.8.53` - Antigravity model refresh and proxy helper improvements
- `v6.8.54` - auth file metadata exposure and management API test coverage
- `v6.8.55` - auth list priority/note support, Gemini responses tool-output fixes, and proxy utility additions
## Conflict Resolution Notes
- Kept the fork versions of `.github/workflows/docker-image.yml`, `.github/workflows/release.yaml`, `.github/workflows/pr-test-build.yml`, and `.goreleaser.yml` so this sync does not alter CI or release automation.
- Kept ProxyPilot README branding and deleted the upstream `README_CN.md` revival because this fork intentionally does not ship that file.
- Merged `internal/api/handlers/management/auth_files.go` semantically so ProxyPilot keeps its `Auth.Priority` persistence while also adding upstream `note` support and priority/note exposure in the auth-file API.
- Kept the stricter Gemini Responses JSON validation in `internal/translator/gemini/openai/responses/gemini_openai-responses_request.go` so partial JSON strings are not embedded as structured results.
## Repo State Updates
- Updated `UPSTREAM_VERSION` to `v6.8.55`.
- Updated `features.json` upstream marker to `CLIProxyAPI v6.8.55`.
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.
- Updated `features.json` upstream marker to `CLIProxyAPI v6.9.12`.
- Prepared the repo for the next local/manual release: `v0.3.0-dev-0.49`.
## 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-0.49`
- `gh release list -R Finesssee/ProxyPilot --limit 5`
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.