Commit Graph

23 Commits

Author SHA1 Message Date
Cyrus
030bf5e6c7 feat(kiro): add IDC auth and endpoint improvements, redesign fingerprint system
- Add IAM Identity Center (IDC) authentication with CLI flags (--kiro-idc-login, --kiro-idc-start-url, --kiro-idc-region) and login flow
- Add ProfileArn auto-fetching in Execute/ExecuteStream for imported IDC accounts
- Simplify endpoint preference with map-based alias lookup and getAuthValue helper
- Redesign fingerprint as global singleton with external config and per-account deterministic generation
- Add StartURL and FingerprintConfig fields to Kiro config
- Add AgentContinuationID/AgentTaskType support in Kiro translators
- Add comprehensive tests for executor, fingerprint, SSO OIDC, and AWS helpers
- Add CLI login documentation to README
2026-02-27 00:58:03 +08:00
Darley
6e634fe3f9 fix: filter out orphaned tool results from history and current context 2026-02-23 14:33:59 +08:00
DragonBaiMo
7c9c89dace fix(kiro): keep thinking enabled across request formats 2026-02-20 20:34:40 +08:00
taetaetae
14f044ce4f refactor: extract default assistant content to shared constants
Apply code review feedback from gemini-code-assist:
- Move fallback strings to kirocommon package as exported constants
- Update kiro_claude_request.go to use shared constants
- Update kiro_openai_request.go to use shared constants
- Improves maintainability and avoids duplication
2026-02-05 23:36:57 +09:00
taetaetae
49ef22ab78 refactor: simplify inputMap initialization logic
Apply code review feedback from gemini-code-assist:
- Initialize inputMap upfront instead of using nested if blocks
- Combine Exists() and IsObject() checks into single condition
- Remove redundant nil check
2026-02-05 07:12:42 +09:00
taetaetae
ae4638712e fix(kiro): handle tool_use in content array for compaction requests
Problem:
- PR #162 fixed empty string content but missed array content with tool_use
- OpenCode's compaction requests send assistant messages with content as array
- When content array contains only tool_use (no text), content becomes empty
- This causes 'Improperly formed request' errors from Kiro API

Example of problematic message format:
{
  "role": "assistant",
  "content": [
    {"type": "tool_use", "id": "...", "name": "todowrite", "input": {...}}
  ]
}

Solution:
- Extract tool_use from content array (Anthropic/OpenCode format)
- This is in addition to existing tool_calls handling (OpenAI format)
- The empty content fallback from PR #162 will then work correctly

Fixes compaction failures that persisted after PR #162 merge.
2026-02-05 07:08:14 +09:00
taetaetae
1f7c58f7ce refactor: use constants for default assistant messages
Apply code review feedback from gemini-code-assist:
- Define default messages as local constants to improve maintainability
- Avoid magic strings in the empty content handling logic
2026-02-03 07:10:38 +09:00
taetaetae
b45ede0b71 fix(kiro): handle empty content in messages to prevent Bad Request errors
Problem:
- OpenCode's /compaction command and auto-compaction (at 80%+ context)
  sends requests that can result in empty assistant message content
- Kiro API strictly requires non-empty content for all messages
- This causes 'Bad Request: Improperly formed request' errors
- After compaction failure, the malformed message stays in history,
  breaking all subsequent requests in the session

Solution:
- Add fallback content for empty assistant messages in
  buildAssistantMessageFromOpenAI()
- Add history truncation (max 50 messages) to prevent oversized requests
- This ensures all messages have valid content before sending to Kiro API

Fixes issues with:
- /compaction command returning Bad Request
- Auto-compaction breaking sessions
- Conversations becoming unresponsive after compaction failure
2026-02-01 15:47:18 +09:00
Darley
7c7c5fd967 Fix Kiro tool schema defaults 2026-01-26 08:27:53 +08:00
TinyCoder
c169b32570 refactor(kiro): Remove unused variables in OpenAI translator
Remove dead code that was never used:
- toolCallIDToName map: built but never read from
- seenToolCallIDs: declared but never populated, only suppressed with _
2025-12-24 15:10:35 +07:00
TinyCoder
36a512fdf2 fix(kiro): Handle tool results correctly in OpenAI format translation
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.
2025-12-24 15:10:35 +07:00
Ravens2121
d687ee2777 feat(kiro): implement official reasoningContentEvent and improve metadat 2025-12-18 04:38:22 +08:00
Ravens2121
f3d1cc8dc1 chore: change debug logs from INFO to DEBUG level 2025-12-16 05:32:03 +08:00
Ravens2121
0a3a95521c feat: enhance thinking mode support for Kiro translator
Changes:
2025-12-16 05:01:40 +08:00
Ravens2121
c3ed3b40ea feat(kiro): Add token usage cross-validation and simplify thinking mode handling 2025-12-14 16:40:33 +08:00
Ravens2121
9c04c18c04 feat(kiro): enhance request translation and fix streaming issues
English:
- Fix <thinking> tag parsing: only parse at response start, avoid misinterpreting discussion text
- Add token counting support using tiktoken for local estimation
- Support top_p parameter in inference config
- Handle max_tokens=-1 as maximum (32000 tokens)
- Add tool_choice and response_format parameter handling via system prompt hints
- Support multiple thinking mode detection formats (Claude API, OpenAI reasoning_effort, AMP/Cursor)
- Shorten MCP tool names exceeding 64 characters
- Fix duplicate [DONE] marker in OpenAI SSE streaming
- Enhance token usage statistics with multiple event format support
- Add code fence markers to constants

中文:
- 修复 <thinking> 标签解析:仅在响应开头解析,避免误解析讨论文本中的标签
- 使用 tiktoken 实现本地 token 计数功能
- 支持 top_p 推理配置参数
- 处理 max_tokens=-1 转换为最大值(32000 tokens)
- 通过系统提示词注入实现 tool_choice 和 response_format 参数支持
- 支持多种思考模式检测格式(Claude API、OpenAI reasoning_effort、AMP/Cursor)
- 截断超过64字符的 MCP 工具名称
- 修复 OpenAI SSE 流中重复的 [DONE] 标记
- 增强 token 使用量统计,支持多种事件格式
- 添加代码围栏标记常量
2025-12-14 11:57:16 +08:00
Ravens2121
01cf221167 feat(kiro): 代码优化重构 + OpenAI翻译器实现 2025-12-14 06:58:50 +08:00
Ravens2121
84920cb670 feat(kiro): add multi-endpoint fallback & thinking mode support 2025-12-12 13:43:36 +08:00
Ravens2121
cd4e84a360 feat(kiro): enhance request format, stream handling, and usage tracking
## English Description

### Request Format Fixes
- Fix conversationState field order (chatTriggerType must be first)
- Add conditional profileArn inclusion based on auth method
- builder-id auth (AWS SSO) doesn't require profileArn
- social auth (Google OAuth) requires profileArn

### Stream Processing Enhancements
- Add headersLen boundary validation to prevent slice out of bounds
- Handle incomplete tool use at EOF by flushing pending data
- Separate message_delta and message_stop events for proper streaming
- Add error logging for JSON unmarshal failures

### JSON Repair Improvements
- Add escapeNewlinesInStrings() to handle control characters in JSON strings
- Remove incorrect unquotedKeyPattern that broke valid JSON content
- Fix handling of streaming fragments with embedded newlines/tabs

### Debug Info Filtering (Optional)
- Add filterHeliosDebugInfo() to remove [HELIOS_CHK] blocks
- Pattern matches internal state tracking from Kiro/Amazon Q
- Currently disabled pending further testing

### Usage Tracking
- Add usage information extraction in message_delta response
- Include prompt_tokens, completion_tokens, total_tokens in OpenAI format

---

## 中文描述

### 请求格式修复
- 修复 conversationState 字段顺序(chatTriggerType 必须在第一位)
- 根据认证方式条件性包含 profileArn
- builder-id 认证(AWS SSO)不需要 profileArn
- social 认证(Google OAuth)需要 profileArn

### 流处理增强
- 添加 headersLen 边界验证,防止切片越界
- 在 EOF 时处理未完成的工具调用,刷新待处理数据
- 分离 message_delta 和 message_stop 事件以实现正确的流式传输
- 添加 JSON 反序列化失败的错误日志

### JSON 修复改进
- 添加 escapeNewlinesInStrings() 处理 JSON 字符串中的控制字符
- 移除错误的 unquotedKeyPattern,该模式会破坏有效的 JSON 内容
- 修复包含嵌入换行符/制表符的流式片段处理

### 调试信息过滤(可选)
- 添加 filterHeliosDebugInfo() 移除 [HELIOS_CHK] 块
- 模式匹配来自 Kiro/Amazon Q 的内部状态跟踪信息
- 目前已禁用,等待进一步测试

### 使用量跟踪
- 在 message_delta 响应中添加 usage 信息提取
- 以 OpenAI 格式包含 prompt_tokens、completion_tokens、total_tokens
2025-12-11 05:37:22 +08:00
Ravens
8d5f89ccfd fix(kiro): fix translator format mismatch for OpenAI protocol
Amp-Thread-ID: https://ampcode.com/threads/T-019b092b-f2de-72a1-b428-72511c0de628
Co-authored-by: Amp <amp@ampcode.com>
2025-12-11 01:15:00 +08:00
Your Name
2bf9e08b31 style(kiro): convert Chinese comments to English in base64 image handling 2025-12-07 21:51:24 +08:00
Your Name
5d716dc796 fix(kiro): 修复 base64 图片格式转换问题 2025-12-07 21:34:44 +08:00
Mansi
02d8a1cfec feat(kiro): add AWS Builder ID authentication support
- 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
2025-12-05 22:46:24 +03:00