Commit Graph

1026 Commits

Author SHA1 Message Date
Luis Pater
ba6aa5fbbe Merge branch 'router-for-me:main' into main v6.6.7-0 2025-12-12 20:09:31 +08:00
Luis Pater
1c52a89535 Merge pull request #502 from router-for-me/iflow
fix(auth): prevent duplicate iflow BXAuth tokens
2025-12-12 20:03:37 +08:00
hkfires
e7cedbee6e fix(auth): prevent duplicate iflow BXAuth tokens 2025-12-12 19:57:19 +08:00
Luis Pater
75ce0919a0 Merge pull request #21 from router-for-me/plus
v6.6.6
v6.6.6-0
2025-12-12 18:42:09 +08:00
Luis Pater
7f4f6bc9ca Merge branch 'main' into plus 2025-12-12 18:41:39 +08:00
Luis Pater
b8194e717c Merge pull request #500 from router-for-me/think
fix(codex): raise default reasoning effort to medium
2025-12-12 18:35:26 +08:00
hkfires
d131435e25 fix(codex): raise default reasoning effort to medium 2025-12-12 18:18:48 +08:00
Luis Pater
6e43669498 Fixed: #440
feat(watcher): normalize auth file paths and implement debounce for remove events
2025-12-12 16:50:56 +08:00
Luis Pater
54d4fd7f84 remove PR_DOCUMENTATION.md v6.6.5-1 2025-12-12 16:10:15 +08:00
Luis Pater
8dc690a638 Merge pull request #20 from Ravens2121/master
feat(kiro): 支持思考模型 (Thinking Mode) 并通过多配额故障转移增强稳定性
2025-12-12 16:09:28 +08:00
Ravens2121
fdeb84db2b Merge branch 'router-for-me:main' into master 2025-12-12 13:44:07 +08:00
Ravens2121
84920cb670 feat(kiro): add multi-endpoint fallback & thinking mode support 2025-12-12 13:43:36 +08:00
Ravens2121
204bba9dea refactor(kiro): update Kiro executor to use CodeWhisperer endpoint and improve tool calling support 2025-12-12 09:27:30 +08:00
Luis Pater
35fdd7bc05 Merge branch 'router-for-me:main' into main v6.6.5-0 2025-12-12 08:54:36 +08:00
Luis Pater
fc054db51a Merge pull request #494 from ben-vargas/fix-gpt-reasoning-none
fix(models): add "none" reasoning effort level to gpt-5.2
2025-12-12 08:53:19 +08:00
Luis Pater
6e2306a5f2 refactor(handlers): improve request logging and payload handling 2025-12-12 08:52:52 +08:00
Ben Vargas
b09e2115d1 fix(models): add "none" reasoning effort level to gpt-5.2
Per OpenAI API documentation, gpt-5.2 supports reasoning_effort values
of "none", "low", "medium", "high", and "xhigh". The "none" level was
missing from the model definition.

Reference: https://platform.openai.com/docs/api-reference/chat/create#chat_create-reasoning_effort
2025-12-11 15:26:23 -07:00
Luis Pater
6a94afab6c Merge branch 'router-for-me:main' into main v6.6.4-0 2025-12-12 04:08:54 +08:00
Luis Pater
a68c97a40f Fixed: #492 2025-12-12 04:08:11 +08:00
Luis Pater
218dc17713 Merge branch 'router-for-me:main' into main v6.6.3-0 2025-12-12 03:03:36 +08:00
Luis Pater
cd2da152d4 feat(models): add GPT 5.2 model definition and prompts 2025-12-12 03:02:27 +08:00
Luis Pater
28469576bf Merge branch 'router-for-me:main' into main v6.6.2-0 2025-12-12 02:41:05 +08:00
Ravens2121
40e7f066e4 feat(kiro): enhance Kiro executor with retry, deduplication and event filtering 2025-12-12 01:59:06 +08:00
Luis Pater
ef0edbfe69 refactor(claude): replace strings.Builder with simpler output string concatenation v6.6.1-1 2025-12-11 22:34:06 +08:00
Luis Pater
bb6312b4fc Merge pull request #488 from router-for-me/gemini
Unify the Gemini executor style
2025-12-11 22:14:17 +08:00
hkfires
3c315551b0 refactor(executor): relocate gemini token counters 2025-12-11 21:56:44 +08:00
hkfires
27c9c5c4da refactor(executor): clarify executor comments and oauth names 2025-12-11 21:56:44 +08:00
hkfires
fc9f6c974a 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.
2025-12-11 21:56:43 +08:00
Luis Pater
242b4d5754 Merge pull request #19 from router-for-me/plus
v6.6.1
v6.6.1-0
2025-12-11 21:35:16 +08:00
Luis Pater
4ce7c61a17 Merge branch 'main' into plus 2025-12-11 21:33:49 +08:00
Luis Pater
a74ee3f319 Merge pull request #481 from sususu98/fix/increase-buffer-size
fix: increase buffer size for stream scanners to 50MB across multiple executors
2025-12-11 21:20:54 +08:00
Luis Pater
564bcbaa54 Merge pull request #487 from router-for-me/amp
fix(amp): set status on claude stream errors
2025-12-11 21:18:19 +08:00
hkfires
88bdd25f06 fix(amp): set status on claude stream errors 2025-12-11 20:12:06 +08:00
hkfires
e79f65fd8e refactor(thinking): use parentheses for metadata suffix 2025-12-11 18:39:07 +08:00
Luis Pater
2760989401 Merge pull request #485 from router-for-me/think
Think
2025-12-11 18:27:00 +08:00
hkfires
facfe7c518 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.
2025-12-11 18:17:28 +08:00
hkfires
6285459c08 fix(runtime): unify claude thinking config resolution 2025-12-11 17:20:44 +08:00
hkfires
21bbceca0c docs(runtime): document reasoning effort precedence 2025-12-11 16:35:36 +08:00
hkfires
f6300c72b7 fix(runtime): validate thinking config in iflow and qwen 2025-12-11 16:21:50 +08:00
hkfires
007572b58e 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.
2025-12-11 15:52:14 +08:00
hkfires
3a81ab22fd fix(runtime): unify reasoning effort metadata overrides 2025-12-11 14:35:05 +08:00
hkfires
519da2e042 fix(runtime): validate reasoning effort levels 2025-12-11 12:36:54 +08:00
hkfires
169f4295d0 fix(util): align reasoning effort handling with registry 2025-12-11 12:20:12 +08:00
hkfires
d06d0eab2f fix(util): centralize reasoning effort normalization 2025-12-11 12:14:51 +08:00
hkfires
3ffd120ae9 feat(runtime): add thinking config normalization 2025-12-11 11:51:33 +08:00
hkfires
a03d514095 feat(registry): add thinking metadata for models 2025-12-11 11:28:44 +08:00
Luis Pater
69fccf0015 Merge pull request #18 from Ravens2121/master
Kiro Executor Stability and API Compatibility Improvements
v6.6.0-1
2025-12-11 08:35:22 +08:00
Luis Pater
1da03bfe15 Merge pull request #479 from router-for-me/claude
fix(claude): prevent final events when no content streamed
2025-12-11 08:18:59 +08:00
Ravens2121
6133bac226 feat(kiro): enhance Kiro executor stability and compatibility
## 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
2025-12-11 08:13:33 +08:00
Ravens2121
f302be5ce6 Merge branch 'router-for-me:main' into master 2025-12-11 05:40:10 +08:00