New#2
Open
Ironboxplus wants to merge 1409 commits into
Open
Conversation
Ironboxplus
force-pushed
the
new
branch
6 times, most recently
from
dae9fcf to
c55780c
Compare
Ironboxplus
force-pushed
the
new
branch
3 times, most recently
from
1c05e6a to
08e2429
Compare
Ironboxplus
force-pushed
the
new
branch
4 times, most recently
from
82e53c6 to
982b813
Compare
Ironboxplus
force-pushed
the
new
branch
2 times, most recently
from
f53e4cc to
ab55e95
Compare
Ironboxplus
force-pushed
the
new
branch
4 times, most recently
from
2293a13 to
06dff20
Compare
Ironboxplus
force-pushed
the
new
branch
2 times, most recently
from
ed8b239 to
4888395
Compare
Ironboxplus
force-pushed
the
new
branch
2 times, most recently
from
9582f7c to
6b7618e
Compare
Ironboxplus
force-pushed
the
new
branch
2 times, most recently
from
309a7d4 to
ba191cd
Compare
Ironboxplus
force-pushed
the
new
branch
2 times, most recently
from
822d96c to
9ec6f63
Compare
The input item ID dedupe added in router-for-me#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.
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.
…versions - 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: router-for-me#3447
…e is available - 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: router-for-me#3471
…N schema processing - 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: router-for-me#3512
…port - 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: router-for-me#3600
…ence - 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: router-for-me#3903
…to Gemini requests - 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: router-for-me#3721
- 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: router-for-me#3750
… with large inputs - 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: router-for-me#3751
- 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: router-for-me#3764
- 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: router-for-me#3792
…l handling - 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: router-for-me#3833
… request handling - 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: router-for-me#3863
…set functionality - 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: router-for-me#3866
…Gemini requests - 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: router-for-me#3874
…request and response translations - 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: router-for-me#3878
- 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: router-for-me#3901
- 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: router-for-me#3920
…eplay-fc-order-upstream-dev fix(antigravity): HOME Gemini replay and functionCall ordering before functionResponse
…ent 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.
…ority calculation logic - Added `applyCodexClientNonTemplatePriorities` to assign higher priorities to non-template Codex client models dynamically. - Implemented `maxCodexClientTemplatePriority` to set base priority for non-template models relative to template models. - Updated unit tests to validate priority calculation for custom models.
- 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.
…lugin calls - 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.
… configuration - Implemented `unregisterOpenAICompatExecutor` to remove OpenAI-compatible executors dynamically. - Updated `ensureExecutorsForAuth` to unregister incompatible executors while handling plugin candidates. - Adjusted runtime configuration logic to ensure proper synchronization during updates with `syncPluginModelRuntime`.
… for compatibility grouping - 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: router-for-me#3940 router-for-me#3941
Merge upstream/main into new. Major upstream changes pulled in: - Removed gemini-cli provider and amp integration (feat!: remove amp) - New pluginstore subsystem, videos handlers, websockets executors - translator refactors (Gemini video URLs, tool/call ID handling, cache token detail) - management log cursors, config-snapshot-based reload Conflict resolution (kept both optimizations; preferred upstream's canonical/refactored code on conflict): - internal/registry/model_definitions.go: kept both new consts/builtins (local claudeBuiltinFableModelInfo + upstream codexBuiltinImage15ModelInfo, normalizeAntigravityCapabilityModelID); aligned Fable 5 builtin metadata to upstream's canonical models.json values (created/description). - internal/registry/models/models.json: took upstream's canonical Fable 5 metadata. - internal/registry/model_updater.go: dropped GeminiCLI field from mergeModelCatalog (upstream removed the gemini-cli provider / staticModelsJSON.GeminiCLI). - internal/runtime/executor/helps/usage_helpers_test.go: kept local Claude cache-token tests (fork optimization preserved); repointed orphaned ParseGeminiCLI* tests to the surviving ParseGeminiUsage/ParseGeminiStreamUsage after upstream's refactor; dropped the traffic-only-guard test (upstream removed hasGeminiFamilyUsageTokenFields). Added TDD coverage: - internal/registry/model_definitions_fable_test.go: guarantees Fable 5 builtin presence via WithClaudeBuiltins and enforces builtin/models.json metadata consistency (red->green verified). Verification: go build OK, go vet unchanged (pre-existing warnings only), go test ./... — the only failures (Codex image-edit, XAI reasoning-effort, Gemini reasoning-signature) are confirmed pre-existing on clean upstream/main.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
12 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.