15 Commits

Author SHA1 Message Date
CJACK
c099a6f7bf feat: add unified response history session management across Claude, Gemini, and OpenAI API backends
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-03 17:24:38 +08:00
CJACK
1286b02247 refactor: remove legacy compatibility configuration and UI components 2026-05-03 04:14:19 +08:00
CJACK
dc5bffdf89 refactor: centralize assistant turn semantics and stream accumulation into new assistantturn and completionruntime packages 2026-05-02 23:28:43 +08:00
d407ccb773 perf(streaming): optimize TTFT and reduce buffering latency
Core changes:
- stream.go: New accumulation buffer architecture with scanner goroutine
  + select loop, MinChars=16, MaxWait=10ms, first-flush-immediate
- dedupe.go: Add TrimContinuationOverlapFromBuilder to avoid string copies
- claude/stream_runtime_core.go: Integrate toolstream for incremental text
- claude/stream_runtime_finalize.go: toolstream flush support
- stream_emitter.js: Reduce DeltaCoalescer thresholds (160->16 chars, 80->20ms)
- empty_retry: Add thinking-aware empty output detection
- Fix reasoning_content leak and finish_reason=null in edge cases
- Fix tail content truncation when max_tokens exceeded

Tests: sync test expectations with upstream for thinking content
2026-05-02 20:28:30 +08:00
CJACK
0bca6e2cee feat: implement context cancellation handling for chat and response stream runtimes to ensure clean termination without retries 2026-05-01 23:20:46 +08:00
706e68de23 fix: increase stream timeout constants for large-context models; guard against context-cancelled double-recording
- Increase StreamIdleTimeout from 90s to 300s and MaxKeepaliveCount from 10 to 40
  to prevent premature stream termination with DeepSeek V4 Pro (~50K token contexts)
- Add r.Context().Err() check after ConsumeSSE in empty_retry_runtime (chat + responses)
  to prevent historySession.error() from overwriting historySession.stopped()
  when the request context is cancelled

References:
- MaxKeepaliveCount=10 creates a 50s no-content timeout that kills the stream
  before DeepSeek V4 Pro can produce its first token with large contexts
- Hermes Agent reports 'No response from provider for 180s' because the
  underlying SSE connection was already terminated by ds2api at 50s
- Context cancellation path: OnContextDone -> stopped(), then finalize()
  with empty output -> retry -> error() overwrites stopped()
2026-05-01 21:11:36 +08:00
CJACK.
7c3ff6ee7e Merge pull request #374 from shern-point/feat/full-context-file-token-accounting
Feat/full context file token accounting
2026-04-30 02:12:55 +08:00
CJACK.
63e62fd1b0 Merge pull request #372 from shern-point/feat/accurate-context-token-length
Feat/accurate context token length
2026-04-30 02:11:32 +08:00
shern-point
6a778e0d35 feat: include inline-uploaded file tokens in context token accounting
Track byte sizes of inline-uploaded files during PreprocessInlineFileInputs and convert them to conservative token estimates (bytes/3). RefFileTokens is threaded through StandardRequest into all OpenAI chat/responses usage builders so returned prompt_tokens/input_tokens reflect the full upstream context cost including attached files.
2026-04-30 01:42:51 +08:00
shern-point
415a2359ad feat: route OpenAI responses usage through preserved prompt text
Use the stored full-context prompt text for responses accounting so neutral placeholder prompts do not underreport returned input token counts.
2026-04-30 00:45:31 +08:00
CJACK.
33f6fef015 Fix tool-call fallback on sanitized empty text and remove history wrapper tags 2026-04-29 23:04:45 +08:00
MiY
241334c658 Fix stream compatibility and vision model exposure 2026-04-29 20:23:13 +08:00
shern-point
b9c8e90d98 refactor: thread tool schemas through responses tool outputs
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-28 13:46:06 +08:00
CJACK
b82bc1311a fix: use parent_message_id and fresh PoW headers for empty-output retry and continue
Previously retry/continue requests reused the initial PoW header and
lacked parent_message_id, causing them to land as disconnected root
messages in the DeepSeek session instead of proper follow-up turns.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-04-27 21:31:51 +08:00
CJACK
0378d8c0a9 feat: add empty-output retry and Vercel auto-continue support
- Auto-retry Chat/Responses streams once when upstream output is empty but not content-filtered, reusing session/token/PoW and appending a regeneration suffix to the prompt
- Wire DeepSeek continue API into Vercel streams for multi-round thinking output exhaustion
- Defer empty-output errors in stream finalizers to enable synthetic retry; only surface failure when the retry budget is exhausted
- Track content_filter stops to avoid retry on filtered outputs
- Add comprehensive tests for stream/non-stream retry, Responses retry, and content_filter no-retry
- Update prompt-compatibility.md documentation

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-04-27 18:00:52 +08:00