Commit Graph

9 Commits

Author SHA1 Message Date
Quorinex
74a959260e chore: optimize model handling 2026-05-10 20:57:40 +08:00
Quorinex
a24529d783 chore: sync dev branch proxy and workflow updates 2026-05-10 18:57:40 +08:00
luka7620
a063efd494 v1.1 适配opus4.7调用 2026-05-10 12:53:00 +08:00
Quorinex
d71bf09dde chore: bump version to 1.0.3 and refactor model mapping 2026-02-23 21:46:42 +08:00
edxeth
6151888df5 fix: stabilize thinking streams, multimodal parsing, and token accounting (#20)
* fix: stabilize multimodal image compatibility across OpenCode flows

Advertise vision-capable metadata in /v1/models and make model matching deterministic so OpenCode does not downgrade image support or route 4.6 models incorrectly. Expand request translation to accept OpenCode/OpenAI attachment shapes, sanitize [Image N] placeholders safely, keep image-only follow-up turns non-empty, and improve token accounting so base64 image bytes no longer inflate prompt token usage and trigger premature compaction.

* fix: deduplicate thinking streams and trim injected prompt noise

* fix: align /v1/messages thinking blocks and message_start usage

* fix: reduce repetitive thinking across tool turns

Select a single reasoning stream source, prevent chunk replay, and preserve structured tool-loop context so the model keeps continuity instead of re-planning each turn.

* fix: unify token counting on existing API endpoints

Compute usage deterministically on /v1/messages and /v1/chat/completions even when upstream omits tokenUsage.

- remove roo-only token path and keep behavior on existing endpoints
- add proxy/token_estimator.go with shared Claude/OpenAI estimators (input/system/messages/tools + output/thinking/tool calls)
- wire stream/non-stream handlers to use estimator-derived input/output usage
- update /v1/messages/count_tokens to reuse the same estimator
- keep robust upstream usage parsing/normalization in proxy/kiro.go while dropping parser-level estimate fallback

Why: direct upstream tests show metering/context events frequently arrive without tokenUsage in this environment; this made usage zero or inconsistent. Local deterministic accounting keeps reported usage stable and explicit.
2026-02-23 20:33:53 +08:00
edxeth
f4049948f1 feat: add Claude Sonnet 4.6 and Opus 4.6 to model list and mapping (#18)
- Add claude-sonnet-4.6 (dot and dash variants) to modelMap in translator.go
- Add claude-sonnet-4.6 and claude-opus-4.6 (plus -thinking variants) to the
  static fallback model list in handler.go
- Realign existing opus-4.6 entries for consistency
2026-02-21 14:33:41 +08:00
Quorinex
306f49f9ac fix: add usage field to OpenAI streaming response final chunk (#10) 2026-02-10 09:42:31 +08:00
Quorinex
01e9d0577c feat: add thinking mode support with configurable output formats 2026-02-04 17:42:30 +08:00
Quorinex
c5e6d42163 feat: Kiro API Proxy - OpenAI/Anthropic compatible API service
- Multi-account pool with round-robin load balancing
- Auto token refresh for IAM IdC and Social auth
- Streaming support (SSE)
- Web admin panel with account management
- Docker support with GitHub Actions CI/CD
- Machine ID management per account
- Usage tracking (requests, tokens, credits)
2026-02-04 00:37:05 +08:00