CLIProxyAPI

fix: apply thinkingLevel from model suffix metadata for Gemini 3

The previous commit added thinkingLevel support but didn't apply it
when the reasoning effort came from model name suffix (e.g., model(minimal)).

This was because ResolveThinkingConfigFromMetadata returns nil for
level-based models, bypassing the metadata application.

Changes:
- Add ApplyGemini3ThinkingLevelFromMetadata for standard Gemini API
- Add ApplyGemini3ThinkingLevelFromMetadataCLI for CLI API format
- Update gemini_cli_executor to apply Gemini 3 thinkingLevel from metadata
- Update antigravity_executor to apply Gemini 3 thinkingLevel from metadata
- Update aistudio_executor to apply Gemini 3 thinkingLevel from metadata
- Add comprehensive test coverage for Gemini 3 thinkingLevel functions

Ben Vargas · 2025-12-17 16:08:38 -07:00

598f0af19b

feat: use thinkingLevel for Gemini 3 models per Google documentation

Per Google's official documentation, Gemini 3 models should use
thinkingLevel (string) instead of thinkingBudget (number) for
optimal performance.

From Google's Gemini Thinking docs:
> Use the thinkingLevel parameter with Gemini 3 models. While
> thinkingBudget is accepted for backwards compatibility, using
> it with Gemini 3 Pro may result in suboptimal performance.

Changes:
- Add model family detection functions (IsGemini3Model, IsGemini25Model,
  IsGemini3ProModel, IsGemini3FlashModel)
- Add ApplyGeminiThinkingLevel and ApplyGeminiCLIThinkingLevel functions
  for applying thinkingLevel config
- Add ValidateGemini3ThinkingLevel for model-specific level validation
- Add ThinkingBudgetToGemini3Level for backward compatibility conversion
- Update NormalizeGeminiThinkingBudget to convert budget to level for
  Gemini 3 models
- Update ApplyDefaultThinkingIfNeeded to not set a default level for
  Gemini 3 (lets API use its dynamic default "high")
- Update ConvertThinkingLevelToBudget to preserve thinkingLevel for
  Gemini 3 models
- Add Levels field to all Gemini 3 model definitions:
  - Gemini 3 Pro: ["low", "high"]
  - Gemini 3 Flash: ["minimal", "low", "medium", "high"]

Backward compatibility:
- Gemini 2.5 models continue to use thinkingBudget as before
- If thinkingBudget is provided for Gemini 3, it's converted to the
  appropriate thinkingLevel
- Existing configurations continue to work

Ben Vargas · 2025-12-17 15:28:20 -07:00

a33f5d31fc

refactor(thinking): export thinking helpers

Expose thinking/effort normalization helpers from the executor package
so conversion tests use production code and stay aligned with runtime
validation behavior.

hkfires · 2025-12-15 09:16:15 +08:00

367a05bdf6

Fixed: #534

fix(aistudio): correct JSON string boundary detection for backslash sequences

hkfires · 2025-12-15 09:00:14 +08:00

27a5ad8ec2

refactor(executor): clarify executor comments and oauth names

hkfires · 2025-12-11 21:56:44 +08:00

27c9c5c4da

refactor(executor): clarify providers and streams

Add package and constructor documentation for AI Studio, Antigravity,
Gemini CLI, Gemini API, and Vertex executors to describe their roles and
inputs.

Introduce a shared stream scanner buffer constant in the Gemini API
executor and reuse it in Gemini CLI and Vertex streaming code so stream
handling uses a consistent configuration.

Update Refresh implementations for AI Studio, Gemini CLI, Gemini API
(API key), and Vertex executors to short‑circuit and simply return the
incoming auth object, while keeping Antigravity token renewal as the
only executor that performs OAuth refresh.

Remove OAuth2-based token refresh logic and related dependencies from
the Gemini API executor, since it now operates strictly with API key
credentials.

hkfires · 2025-12-11 21:56:43 +08:00

fc9f6c974a

fix(executor): centralize default thinking config

hkfires · 2025-12-09 21:05:06 +08:00

9b202b6c1c

feat(executor): normalize thinking budget across all Gemini executors

hkfires · 2025-12-09 21:05:06 +08:00

5ec9b5e5a9

feat(aistudio): normalize thinking budget in request translation

hkfires · 2025-12-09 08:27:44 +08:00

96b55acff8

refactor(executor): dedupe thinking metadata helpers across Gemini executors

Extract applyThinkingMetadata and applyThinkingMetadataCLI helpers to
payload_helpers.go and use them across all four Gemini-based executors:
- gemini_executor.go (Execute, ExecuteStream, CountTokens)
- gemini_cli_executor.go (Execute, ExecuteStream, CountTokens)
- aistudio_executor.go (translateRequest)
- antigravity_executor.go (Execute, ExecuteStream)

This eliminates code duplication introduced in the -reasoning suffix PR
and centralizes the thinking config application logic.

Net reduction: 28 lines of code.

auroraflux · 2025-11-30 15:20:15 -08:00

1c6f4be8ae

fix(aistudio): strip Gemini generation config overrides

Remove generationConfig.maxOutputTokens, generationConfig.responseMimeType and generationConfig.responseJsonSchema from the Gemini payload in translateRequest so we no longer send unsupported or conflicting response configuration fields. This lets the backend or caller control response formatting and output limits and helps prevent potential API errors caused by these keys.

hkfires · 2025-11-23 19:44:03 +08:00

62bfd62871

Fixed: #302

**feat(executor): enhance WebSocket error handling and metadata logging**

- Added handling for stream closure before start with appropriate error recording.
- Improved metadata logging for non-OK HTTP status codes in WebSocket responses.
- Consolidated event processing logic with `processEvent` for better error handling and payload management.
- Refactored stream initialization to include the first event handling for smoother execution flow.

Luis Pater · 2025-11-22 11:18:13 +08:00

d291eb9489

feat(executor): share SSE usage filtering across streams

hkfires · 2025-11-21 16:51:05 +08:00

4ba5b43d82

Fixed: #291

**feat(executor): add thinking level to budget conversion utility**

- Introduced `ConvertThinkingLevelToBudget` to map thinking level ("high"/"low") to corresponding budget values.
- Applied the utility in `aistudio_executor.go` before stripping unsupported configs.
- Updated dependencies to include `tidwall/gjson` for JSON parsing.

Luis Pater · 2025-11-21 00:48:12 +08:00

cbcfeb92cc

**feat(runtime): add payload configuration support for executors**

Introduce `PayloadConfig` in the configuration to define default and override rules for modifying payload parameters. Implement `applyPayloadConfig` and `applyPayloadConfigWithRoot` to apply these rules across various executors, ensuring consistent parameter handling for different models and protocols. Update all relevant executors to utilize this functionality.

Luis Pater · 2025-11-13 23:27:40 +08:00

fcd98f4f9b

fix(executor): remove safetySettings from payload in token counting request

Luis Pater · 2025-11-03 17:31:43 +08:00

64774a5786

fix(executor): only apply thinking config to supported models

hkfires · 2025-10-29 19:19:17 +08:00

7dd93a4a25

fix(executor): pass authID to relay instead of provider

hkfires · 2025-10-28 19:28:26 +08:00

663b9b35ab

feat(registry): unify Gemini models and add AI Studio set

hkfires · 2025-10-28 19:00:25 +08:00

5dced4c0a6

fix(aistudio): ensure colon-spaced JSON in responses

hkfires · 2025-10-26 20:21:45 +08:00

7f266aa19e

refactor(wsrelay): rename RoundTrip to NonStream

hkfires · 2025-10-26 20:01:46 +08:00

f3f31274e8

fix(aistudio): remove generationConfig and tools when action is countTokens

hkfires · 2025-10-26 16:28:20 +08:00

7459c2c81a

fix(aistudio): strip usage metadata from non-final stream chunks

hkfires · 2025-10-26 07:46:04 +08:00

ea6065f1b1

feat(aistudio): track Gemini usage and improve stream errors

hkfires · 2025-10-26 07:46:04 +08:00

c32e013605

feat: add websocket routing and executor unregister API

- Introduce Server.AttachWebsocketRoute(path, handler) to mount websocket
  upgrade handlers on the Gin engine.
- Track registered WS paths via wsRoutes with wsRouteMu to prevent
  duplicate registrations; initialize in NewServer and import sync.
- Add Manager.UnregisterExecutor(provider) for clean executor lifecycle
  management.
- Add github.com/gorilla/websocket v1.5.3 dependency and update go.sum.

Motivation: enable services to expose WS endpoints through the core server
and allow removing auth executors dynamically while avoiding duplicate
route setup. No breaking changes.

hkfires · 2025-10-26 07:46:03 +08:00

3839d93ba0

25 Commits