CLIProxyAPI

fix: require dot in gemini25Pattern regex for precise matching

Ben Vargas · 2025-12-17 16:09:50 -07:00

88798816f2

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

test(gemini): add test cases and improve compatibility for complex schema cases in CleanJSONSchemaForGemini function

Luis Pater · 2025-12-17 17:38:53 +08:00

47885e3710

feature: Improves schema flattening and tool use handling

Updates schema flattening logic to handle multiple non-null types, providing a more descriptive "Accepts" hint.

Removes redundant tracking of the current tool name in `Params` as it's no longer needed for streaming limits, simplifying the structure.

이대희 · 2025-12-17 17:30:23 +09:00

aea337cfe2

Update internal/util/translator.go

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

이대희 · 2025-12-17 17:15:11 +09:00

27734a23b1

feature: Improves Gemini JSON schema compatibility

Enhances compatibility with the Gemini API by implementing a schema cleaning process.

This includes:
- Centralizing schema cleaning logic for Gemini in a dedicated utility function.
- Converting unsupported schema keywords to hints within the description field.
- Flattening complex schema structures like `anyOf`, `oneOf`, and type arrays to simplify the schema.
- Handling streaming responses with empty tool names, which can occur in subsequent chunks after the initial tool use.

이대희 · 2025-12-17 17:10:53 +09:00

1b8e538a77

fix(thinking): align budget effort mapping across translators

Unify thinking budget-to-effort conversion in a shared helper, handle disabled/default thinking cases in translators, adjust zero-budget mapping, and drop the old OpenAI-specific helper with updated tests.

hkfires · 2025-12-16 18:34:43 +08:00

28a428ae2f

fix(thinking): normalize effort mapping

Route OpenAI reasoning effort through ThinkingEffortToBudget for Claude
translators, preserve "minimal" when translating OpenAI Responses, and
treat blank/unknown efforts as no-ops for Gemini thinking configs.

Also map budget -1 to "auto" and expand cross-protocol thinking tests.

hkfires · 2025-12-15 09:16:15 +08:00

d20b71deb9

fix(thinking): centralize reasoning_effort mapping

Move OpenAI `reasoning_effort` -> Gemini `thinkingConfig` budget logic into
shared helpers used by Gemini, Gemini CLI, and antigravity translators.

Normalize Claude thinking handling by preferring positive budgets, applying
budget token normalization, and gating by model support.

Always convert Gemini `thinkingBudget` back to OpenAI `reasoning_effort` to
support allowCompat models, and update tests for normalization behavior.

hkfires · 2025-12-15 09:16:14 +08:00

716aa71f6e

Merge branch 'dev' into think

Luis Pater · 2025-12-12 22:16:44 +08:00

f3f0f1717d

fix(executor): improve model compatibility handling for OpenAI-compatibility

Enhances payload handling by introducing OpenAI-compatibility checks and refining how reasoning metadata is resolved, ensuring broader model support.

Luis Pater · 2025-12-12 21:57:25 +08:00

9f511f0024

fix(thinking): map budgets to effort levels

Ensure thinking settings translate correctly across providers:
- Only apply reasoning_effort to level-based models and derive it from numeric
  budget suffixes when present
- Strip effort string fields for budget-based models and skip Claude/Gemini
  budget resolution for level-based or unsupported models
- Default Gemini include_thoughts when a nonzero budget override is set
- Add cross-protocol conversion and budget range tests

hkfires · 2025-12-12 21:33:20 +08:00

374faa2640

refactor(thinking): use parentheses for metadata suffix

hkfires · 2025-12-11 18:39:07 +08:00

e79f65fd8e

refactor(thinking): use bracket tags for thinking meta

Align thinking suffix handling on a single bracket-style marker.

NormalizeThinkingModel strips a terminal `[value]` segment from
model identifiers and turns it into either a thinking budget (for
numeric values) or a reasoning effort hint (for strings). Emission
of `ThinkingIncludeThoughtsMetadataKey` is removed.

Executor helpers and the example config are updated so their
comments reference the new `[value]` suffix format instead of the
legacy dash variants.

BREAKING CHANGE: dash-based thinking suffixes (`-thinking`,
`-thinking-N`, `-reasoning`, `-nothinking`) are no longer parsed
for thinking metadata; only `[value]` annotations are recognized.

hkfires · 2025-12-11 18:17:28 +08:00

facfe7c518

fix(runtime): unify claude thinking config resolution

hkfires · 2025-12-11 17:20:44 +08:00

6285459c08

fix(util): do not strip thinking suffix on registered models

NormalizeThinkingModel now checks ModelSupportsThinking before removing
"-thinking" or "-thinking-<ver>", avoiding accidental parsing of model
names where the suffix is part of the official id (e.g., kimi-k2-thinking,
qwen3-235b-a22b-thinking-2507).

The registry adds ThinkingSupport metadata for several models and
propagates it via ModelInfo (e.g., kimi-k2-thinking, deepseek-r1,
qwen3-235b-a22b-thinking-2507, minimax-m2), enabling accurate detection
of thinking-capable models and correcting base model inference.

hkfires · 2025-12-11 15:52:14 +08:00

007572b58e

fix(runtime): unify reasoning effort metadata overrides

hkfires · 2025-12-11 14:35:05 +08:00

3a81ab22fd

fix(runtime): validate reasoning effort levels

hkfires · 2025-12-11 12:36:54 +08:00

519da2e042

fix(util): align reasoning effort handling with registry

hkfires · 2025-12-11 12:20:12 +08:00

169f4295d0

fix(util): centralize reasoning effort normalization

hkfires · 2025-12-11 12:14:51 +08:00

d06d0eab2f

feat(runtime): add thinking config normalization

hkfires · 2025-12-11 11:51:33 +08:00

3ffd120ae9

feat(util): implement dynamic thinking suffix normalization and refactor budget resolution logic

- Added support for parsing and normalizing dynamic thinking model suffixes.
- Centralized budget resolution across executors and payload helpers.
- Retired legacy Gemini-specific thinking handlers in favor of unified logic.
- Updated executors to use metadata-based thinking configuration.
- Added `ResolveOriginalModel` utility for resolving normalized upstream models using request metadata.
- Updated executors (Gemini, Codex, iFlow, OpenAI, Qwen) to incorporate upstream model resolution and substitute model values in payloads and request URLs.
- Ensured fallbacks handle cases with missing or malformed metadata to derive models robustly.
- Refactored upstream model resolution to dynamically incorporate metadata for selecting and normalizing models.
- Improved handling of thinking configurations and model overrides in executors.
- Removed hardcoded thinking model entries and migrated logic to metadata-based resolution.
- Updated payload mutations to always include the resolved model.

Luis Pater · 2025-12-11 03:10:50 +08:00

423ce97665

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(util): add DeleteKey function and update antigravity executor for Claude model compatibility**

Luis Pater · 2025-12-05 01:55:45 +08:00

d6352dd4d4

**feat(util): add -reasoning suffix support for Gemini models**

Adds support for the `-reasoning` model name suffix which enables
thinking/reasoning mode with dynamic budget. This allows clients to
request reasoning-enabled inference using model names like
`gemini-2.5-flash-reasoning` without explicit configuration.

The suffix is normalized to the base model (e.g., gemini-2.5-flash)
with thinkingBudget=-1 (dynamic) and include_thoughts=true.

Follows the existing pattern established by -nothinking and
-thinking-N suffixes.

auroraflux · 2025-11-30 01:18:57 -08:00

32d3809f8c

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

Add AMP fallback proxy and shared Gemini normalization

- add fallback handler that forwards Amp provider requests to ampcode.com when the provider isn’t configured locally
- wrap AMP provider routes with the fallback so requests always have a handler
- share Gemini thinking model normalization helper between core handlers and AMP fallback

Ben Vargas · 2025-11-19 18:23:17 -07:00

8193392bfe

feat: add auto model resolution and model creation timestamp tracking

- Add 'created' field to model registry for tracking model creation time
- Implement GetFirstAvailableModel() to find the first available model by newest creation timestamp
- Add ResolveAutoModel() utility function to resolve "auto" model name to actual available model
- Update request handler to resolve "auto" model before processing requests
- Ensures automatic model selection when "auto" is specified as model name

This enables dynamic model selection based on availability and creation time, improving the user experience when no specific model is requested.

TUGOhost · 2025-11-11 20:30:09 +08:00

92f4278039

feat(config): support HTTP headers across providers

hkfires · 2025-11-08 20:52:05 +08:00

cfb9cb8951

feat(gemini): add Gemini API key endpoints

hkfires · 2025-10-31 11:09:28 +08:00

7c1c4ee60b

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

hkfires · 2025-10-29 19:19:17 +08:00

7dd93a4a25

feat(claude): map Anthropic 'thinking' to Gemini thinkingBudget

hkfires · 2025-10-29 19:19:17 +08:00

41577bce07

feat(ws): add WebSocket auth

hkfires · 2025-10-26 07:46:04 +08:00

359b8de44e

feat: prefer util.WritablePath() for logs and local storage

hkfires · 2025-10-19 10:19:55 +08:00

d16599fa1d

feat(logging): centralize sensitive header masking

hkfires · 2025-10-18 17:16:00 +08:00

9f45806106

Fixed: #129 #123 #102 #97

feat: add all protocols request and response translation for Gemini and Gemini CLI compatibility

Luis Pater · 2025-10-17 02:11:29 +08:00

4477c729a4

Feature: #103

feat(gemini): add Gemini thinking configuration support and metadata normalization

- Introduced logic to parse and apply `thinkingBudget` and `include_thoughts` configurations from metadata.
- Enhanced request handling to include normalized Gemini model metadata, preserving the original model identifier.
- Updated Gemini and Gemini-CLI executors to apply thinking configuration based on metadata overrides.
- Refactored handlers to support metadata extraction and cloning during request preparation.

Luis Pater · 2025-10-16 11:31:18 +08:00

ade279d1f2

feat(registry, executor, util): add support for gemini-2.5-flash-image-preview and improve aspect ratio handling

- Introduced `gemini-2.5-flash-image-preview` model to the registry with updated definitions.
- Enhanced Gemini CLI and API executors to handle image aspect ratio adjustments for the new model.
- Added utility function to create base64 white image placeholders based on aspect ratio configurations.

Luis Pater · 2025-10-10 01:49:58 +08:00

20787cd107

refactor(proxy): improve SOCKS5 proxy authentication handling

- Added nil check for proxy user credentials to prevent potential nil pointer dereference.
- Enhanced authentication logic for SOCKS5 proxies in `proxy_helpers.go` and `proxy.go`.

Luis Pater · 2025-09-30 11:23:39 +08:00

832268cae7

refactor(util): Centralize auth directory path resolution

Introduces a new utility function, `util.ResolveAuthDir`, to handle the normalization and resolution of the authentication directory path.

Previously, the logic for expanding the tilde (~) to the user's home directory was implemented inline in `main.go`. This refactoring extracts that logic into a reusable function within the `util` package.

The new `ResolveAuthDir` function is now used consistently across the application:
- During initial server startup in `main.go`.
- When counting authentication files in `util.CountAuthFiles`.
- When the configuration is reloaded by the watcher.

This change eliminates code duplication, improves consistency, and makes the path resolution logic more robust and maintainable.

hkfires · 2025-09-27 09:06:51 +08:00

6136a77eb3

refactor(config): migrate to SDKConfig and streamline proxy handling

- Replaced `config.Config` with `config.SDKConfig` across components for simpler configuration management.
- Updated proxy setup functions and handlers to align with `SDKConfig` improvements.
- Reorganized handler imports to match new SDK structure.

Luis Pater · 2025-09-27 04:50:23 +08:00

57c9ba49f4

feat(logging): introduce centralized logging with custom format and Gin integration

- Implemented a global logger with structured formatting for consistent log output.
- Added support for rotating log files using Lumberjack.
- Integrated new logging functionality with Gin HTTP server for unified log handling.
- Replaced direct `log.Info` calls with `fmt.Printf` in non-critical paths to simplify core functionality.

Luis Pater · 2025-09-26 00:54:52 +08:00

cf734f7e7b

rebuild branch

Luis Pater · 2025-09-25 10:32:48 +08:00

f5dc380b63

remove all

Luis Pater · 2025-09-25 10:31:02 +08:00

3f69254f43

chore(docs): add and refine package-level comments across modules

- Added detailed package-level comments to improve documentation coverage.
- Clarified parameter descriptions, return types, and functionality of exported methods across packages.
- Enhanced overall code readability and API documentation consistency.

Luis Pater · 2025-09-25 00:14:17 +08:00

0db0b03db9

Removed the cookie snapshot feature.

hkfires · 2025-09-24 22:12:29 +08:00

d4f5ec2492

refactor: standardize constant naming and improve file-based auth handling

- Renamed constants from uppercase to CamelCase for consistency.
- Replaced redundant file-based auth handling logic with the new `util.CountAuthFiles` helper.
- Fixed various error-handling inconsistencies and enhanced robustness in file operations.
- Streamlined auth client reload logic in server and watcher components.
- Applied minor code readability improvements across multiple packages.

Luis Pater · 2025-09-22 02:56:45 +08:00

d9ad65622a

v6 version first commit

Luis Pater · 2025-09-22 01:40:24 +08:00

4999fce7f4

66 Commits