Commit Graph
1873 Commits
Author SHA1 Message Date
Luis Pater 24cf7fa6a2 Merge pull request #156 from taetaetae/fix/kiro-api-region
fix(kiro): Do not use OIDC region for API endpoint
2026-01-31 01:13:47 +08:00
Luis Pater bf66bcad86 Merge pull request #155 from PancakeZik/feature/use-q-endpoint
feat(kiro): switch to Amazon Q endpoint as primary
2026-01-31 01:13:15 +08:00
taetaetae fafef32b9e fix(kiro): Do not use OIDC region for API endpoint
Kiro API endpoints only exist in us-east-1, but OIDC region can vary
by Enterprise user location (e.g., ap-northeast-2 for Korean users).

Previously, when ProfileARN was not available, the code fell back to
using OIDC region for API calls, causing DNS resolution failures:

  lookup codewhisperer.ap-northeast-2.amazonaws.com: no such host

This fix removes the OIDC region fallback for API endpoints.
The region priority is now:
1. api_region (explicit override)
2. ProfileARN region
3. us-east-1 (default)

Fixes: Issue #253 (200-400x slower response times due to DNS failures)
2026-01-31 00:05:53 +09:00
Joao 1e764de0a8 feat(kiro): switch to Amazon Q endpoint as primary
Switch from CodeWhisperer endpoint to Amazon Q endpoint for all auth types:

- Use q.{region}.amazonaws.com/generateAssistantResponse as primary endpoint
- Works universally across all AWS regions (CodeWhisperer only exists in us-east-1)
- Use application/json Content-Type instead of application/x-amz-json-1.0
- Remove X-Amz-Target header for Q endpoint (not required)
- Add x-amzn-kiro-agent-mode: vibe header
- Add x-amzn-codewhisperer-optout: true header
- Keep CodeWhisperer endpoint as fallback for compatibility

This change aligns with Amazon's consolidation of services under the Q branding
and provides better multi-region support for Enterprise/IDC users.
2026-01-30 13:50:19 +00:00
Luis Pater b3b8d71dfc Merge pull request #154 from router-for-me/plus
v6.7.32
v6.7.32-0
2026-01-30 21:34:38 +08:00
Luis Pater ca29c42805 Merge branch 'main' into plus 2026-01-30 21:34:30 +08:00
Luis Pater fcefa2c820 Merge pull request #152 from taetaetae/feat/kiro-dynamic-region-support
feat(kiro): Add dynamic region support for API endpoints
2026-01-30 21:30:04 +08:00
Luis Pater 6b6d030ed3 feat(auth): add custom HTTP client with utls for Claude API authentication
Introduce a custom HTTP client utilizing utls with Firefox TLS fingerprinting to bypass Cloudflare fingerprinting on Anthropic domains. Includes support for proxy configuration and enhanced connection management for HTTP/2.
v6.7.32
2026-01-30 21:29:41 +08:00
Luis Pater fd5b669c87 Merge pull request #150 from PancakeZik/fix/write-tool-truncation-handling
fix: handle Write tool truncation when content exceeds API limits
2026-01-30 21:15:31 +08:00
Luis Pater 30d832c9b1 Merge pull request #144 from woopencri/main
fix: handle zero output_tokens for kiro non-streaming requests
2026-01-30 21:06:20 +08:00
Luis Pater 2448691136 Merge pull request #143 from CheesesNguyen/fix/kiro-refresh-token
fix: refresh token for kiro enterprise account
2026-01-30 21:05:00 +08:00
taetaetae e7cd7b5243 fix: Support separate OIDC and API regions via ProfileARN extraction
Address @Xm798's feedback: OIDC region may differ from API region in some
Enterprise setups (e.g., OIDC in us-east-2, API in us-east-1).

Region priority (highest to lowest):
1. api_region - explicit override for API endpoint region
2. ProfileARN - extract region from arn:aws:service:REGION:account:resource
3. region - OIDC/Identity region (fallback)
4. us-east-1 - default

Changes:
- Add extractRegionFromProfileARN() to parse region from ARN
- Update getKiroEndpointConfigs() with 4-level region priority
- Add regionSource logging for debugging
2026-01-30 21:52:02 +09:00
Luis Pater 33f89a2609 Merge pull request #140 from janckerchen/fix/github-copilot-logging
fix: support github-copilot provider in AccountInfo logging
2026-01-30 20:51:50 +08:00
Luis Pater 403a731e22 Merge pull request #139 from janckerchen/fix/github-copilot-vision-header
fix: add Copilot-Vision-Request header for vision content
2026-01-30 20:51:18 +08:00
Luis Pater 3631fab7e2 Merge pull request #153 from router-for-me/plus
v6.7.31
v6.7.31-0
2026-01-30 20:46:42 +08:00
Luis Pater b3d292a5f9 Merge branch 'main' into plus 2026-01-30 20:45:33 +08:00
taetaetae 9293c685e0 fix: Correct Amazon Q endpoint URL path
Revert the Amazon Q endpoint path to root '/' instead of '/generateAssistantResponse'.

The '/generateAssistantResponse' path is only for CodeWhisperer endpoint with
'GenerateAssistantResponse' target. Amazon Q endpoint uses 'SendMessage' target
which requires the root path.

Thanks to @gemini-code-assist for catching this copy-paste error.
2026-01-30 16:30:03 +09:00
taetaetae 38094a2339 feat(kiro): Add dynamic region support for API endpoints
## Problem
- Kiro API endpoints were hardcoded to us-east-1 region
- Enterprise users in other regions (e.g., ap-northeast-2) experienced
  significant latency (200-400x slower) due to cross-region API calls
- This is the API endpoint counterpart to quotio PR #241 which fixed
  token refresh endpoints

## Solution
- Add buildKiroEndpointConfigs(region) function for dynamic endpoint generation
- Extract region from auth.Metadata["region"] field
- Fallback to us-east-1 for backward compatibility
- Use case-insensitive authMethod comparison (consistent with quotio PR #252)

## Changes
- Add kiroDefaultRegion constant
- Convert hardcoded endpoint URLs to dynamic fmt.Sprintf with region
- Update getKiroEndpointConfigs to extract and use region from auth
- Fix isIDCAuth to use case-insensitive comparison

## Testing
- Backward compatible: defaults to us-east-1 when no region specified
- Enterprise users can now use their local region endpoints

Related:
- quotio PR #241: Dynamic region for token refresh (merged)
- quotio PR #252: authMethod case-insensitive fix
- quotio Issue #253: Performance issue report
2026-01-30 16:25:32 +09:00
Luis Pater d7d54fa2cc feat(ci): add cleanup step for temporary Docker tags in workflow v6.7.31 2026-01-30 09:15:00 +08:00
Luis Pater 31649325f0 feat(ci): add multi-arch Docker builds and manifest creation to workflow v6.7.30 2026-01-30 07:26:36 +08:00
Luis Pater a709e5a12d fix(config): ensure empty mapping persists for oauth-model-alias deletions #1305 v6.7.29 2026-01-30 04:17:56 +08:00
Luis Pater f0ac77197b Merge pull request #1300 from sususu98/feat/log-api-response-timestamp
fix(logging): add API response timestamp and fix request timestamp timing
2026-01-30 03:27:17 +08:00
Luis Pater da0bbf2a3f Merge pull request #1298 from sususu98/fix/restore-usageMetadata-in-gemini-translator
fix(translator): restore usageMetadata in Gemini responses from Antigravity
2026-01-30 02:59:41 +08:00
sususu98 295f34d7f0 fix(logging): capture streaming TTFB on first chunk and make timestamps required
- Add firstChunkTimestamp field to ResponseWriterWrapper for sync capture
- Capture TTFB in Write() and WriteString() before async channel send
- Add SetFirstChunkTimestamp() to StreamingLogWriter interface
- Make requestTimestamp/apiResponseTimestamp required in LogRequest()
- Remove timestamp capture from WriteAPIResponse() (now via setter)
- Fix Gemini handler to set API_RESPONSE_TIMESTAMP before writing response

This ensures accurate TTFB measurement for all streaming API formats
(OpenAI, Gemini, Claude) by capturing timestamp synchronously when
the first response chunk arrives, not when the stream finalizes.
2026-01-29 22:32:24 +08:00
sususu98 c41ce77eea fix(logging): add API response timestamp and fix request timestamp timing
Previously:
- REQUEST INFO timestamp was captured at log write time (not request arrival)
- API RESPONSE had NO timestamp at all

This fix:
- Captures REQUEST INFO timestamp when request first arrives
- Adds API RESPONSE timestamp when upstream response arrives

Changes:
- Add Timestamp field to RequestInfo, set at middleware initialization
- Set API_RESPONSE_TIMESTAMP in appendAPIResponse() and gemini handler
- Pass timestamps through logging chain to writeNonStreamingLog()
- Add timestamp output to API RESPONSE section

This enables accurate measurement of backend response latency in error logs.
2026-01-29 22:22:18 +08:00
Joao 876b86ff91 fix: handle json.Marshal error for truncated write bash input 2026-01-29 13:07:20 +00:00
Joao acdfa1c87f fix: handle Write tool truncation when content exceeds API limits
When the Kiro/AWS CodeWhisperer API receives a Write tool request with content
that exceeds transmission limits, it truncates the tool input. This can result in:
- Empty input buffer (no input transmitted at all)
- Missing 'content' field in the parsed JSON
- Incomplete JSON that fails to parse

This fix detects these truncation scenarios and converts them to Bash tool calls
that echo an error message. This allows Claude Code to execute the Bash command,
see the error output, and the agent can then retry with smaller chunks.

Changes:
- kiro_claude_tools.go: Detect three truncation scenarios in ProcessToolUseEvent:
  1. Empty input buffer (no input transmitted)
  2. JSON parse failure with file_path but no content field
  3. Successfully parsed JSON missing content field
  When detected, emit a special '__truncated_write__' marker tool use

- kiro_executor.go: Handle '__truncated_write__' markers in streamToChannel:
  1. Extract file_path from the marker for context
  2. Create a Bash tool_use that echoes an error message
  3. Include retry guidance (700-line chunks recommended)
  4. Set hasToolUses=true to ensure stop_reason='tool_use' for agent continuation

This ensures the agent continues and can retry with smaller file chunks instead
of failing silently or showing errors to the user.
2026-01-29 12:22:55 +00:00
Luis Pater 4eb1e6093f feat(handlers): add test to verify no retries after partial stream response
Introduce `TestExecuteStreamWithAuthManager_DoesNotRetryAfterFirstByte` to validate that stream executions do not retry after receiving partial responses. Implement `payloadThenErrorStreamExecutor` for test coverage of this behavior.
v6.7.28
2026-01-29 17:30:48 +08:00
Luis Pater 189a066807 Merge pull request #1296 from router-for-me/log
fix(api): update amp module only on config changes
2026-01-29 17:27:52 +08:00
hkfires d0bada7a43 fix(config): prune oauth-model-alias when preserving config 2026-01-29 14:06:52 +08:00
sususu98 9dc0e6d08b fix(translator): restore usageMetadata in Gemini responses from Antigravity
When using Gemini API format with Antigravity backend, the executor
renames usageMetadata to cpaUsageMetadata in non-terminal chunks.
The Gemini translator was returning this internal field name directly
to clients instead of the standard usageMetadata field.

Add restoreUsageMetadata() to rename cpaUsageMetadata back to
usageMetadata before returning responses to clients.
2026-01-29 11:16:00 +08:00
hkfires 8510fc313e fix(api): update amp module only on config changes 2026-01-29 09:28:49 +08:00
woopencri f2b0ce13d9 fix: handle zero output_tokens for kiro non-streaming requests 2026-01-28 16:27:34 +08:00
CheesesNguyen b8652b7387 feat: normalize authentication method to lowercase for case-insensitive matching during token refresh and introduce new CLIProxyAPIPlus component. 2026-01-28 14:54:58 +07:00
CheesesNguyen b18b2ebe9f fix: Implement graceful token refresh degradation and enhance IDC SSO support with device registration loading for Kiro. 2026-01-28 14:47:04 +07:00
Luis Pater 9e5b1d24e8 Merge pull request #1276 from router-for-me/thinking
feat(thinking): enable thinking toggle for qwen3 and deepseek models
v6.7.27
2026-01-28 11:16:54 +08:00
Luis Pater a7dae6ad52 Merge remote-tracking branch 'origin/dev' into dev 2026-01-28 10:59:00 +08:00
Luis Pater e93e05ae25 refactor: consolidate channel send logic with context-safe handlers
Optimize channel operations by introducing reusable context-aware send functions (`send` and `sendErr`) across `wsrelay`, `handlers`, and `cliproxy`. Ensure graceful handling of canceled contexts during stream operations.
2026-01-28 10:58:35 +08:00
hkfires c8c27325dc feat(thinking): enable thinking toggle for qwen3 and deepseek models
Fix #1245
2026-01-28 09:54:05 +08:00
hkfires c3b6f3918c chore(git): stop ignoring .idea and data directories 2026-01-28 09:52:44 +08:00
Luis Pater bbb55a8ab4 Merge pull request #1170 from BianBianY/main
feat: optimization enable/disable auth files
2026-01-28 09:34:35 +08:00
cybitandClaude 58290760a9 fix: support github-copilot provider in AccountInfo logging
Changed the provider matching logic in AccountInfo() method to use
prefix matching instead of exact matching. This allows both 'github'
(Kiro OAuth) and 'github-copilot' providers to be correctly identified
as OAuth providers, enabling proper debug logging output.

Before: Use OAuth logs were missing for github-copilot requests
After: Logs show "Use OAuth provider=github-copilot auth_file=..."

Co-Authored-By: Claude (claude-sonnet-4.5) <noreply@anthropic.com>
2026-01-27 21:56:00 +08:00
Luis Pater 8f522eed43 Merge pull request #138 from router-for-me/plus
v6.7.26
v6.7.26-0
2026-01-27 20:40:12 +08:00
Luis Pater 3dc001a9d2 Merge branch 'main' into plus 2026-01-27 20:39:59 +08:00
Luis Pater ee54ee8825 Merge pull request #137 from geen02/fix/idc-auth-method-case-sensitivity
fix: case-insensitive auth_method comparison for IDC tokens
2026-01-27 20:38:03 +08:00
Luis Pater 2395b7a180 Merge pull request #135 from gogoing1024/main
支持多个idc登录凭证保存
2026-01-27 20:36:56 +08:00
Luis Pater 7583193c2a Merge pull request #1257 from router-for-me/model
feat(api): add management model definitions endpoint
v6.7.26
2026-01-27 20:32:04 +08:00
hkfires 7cc3bd4ba0 chore(deps): mark golang.org/x/text as indirect 2026-01-27 19:19:52 +08:00
hkfires 88a0f095e8 chore(registry): disable gemini 2.5 flash image preview model 2026-01-27 18:33:13 +08:00
hkfires c65f64dce0 chore(registry): comment out rev19-uic3-1p model config 2026-01-27 18:33:13 +08:00