d8fa80e7bc
chore: clean up review files and update log_safety_test
2026-07-06 15:45:56 +09:00
0e93b615f6
update roadmap phases and milestones
2026-07-06 15:41:31 +09:00
8835a8fbd3
doc(G04): fill implementation section of CODE_REVIEW
2026-07-06 15:41:11 +09:00
2b3793149c
fix(edge/openai): remove preview fields from production logs
...
Remove all *_preview zap.String/Any fields from OpenAI-compatible log
calls (chat_handler, responses_handler, stream) so that prompt, content,
reasoning, source, and delta values are never written in plain to
operational logs.
Replace preview fields with non-content metadata:
- prompt_len, content_len, reasoning_len, delta_len, source_len
- message_count, content_len, finish_reason, tool_call_count
Also remove the now-unused previewString helper from types.go.
Add log_safety_test.go with regression tests that:
- verify no *_preview fields exist on any log line
- verify operational metadata fields are retained for observability
- verify logOpenAICompatStreamOutput does not emit delta_preview
2026-07-06 15:21:50 +09:00
18b2880738
Add review_followup_alignment task
2026-07-06 10:46:46 +09:00
86b10a6c54
sync: agent-ops from agentic-framework v1.1.163
2026-07-06 10:24:22 +09:00
toki
ca5eb4685c
fix(edge): provider-pool thinking과 queue 정책을 정리한다
...
vLLM-MLX provider-pool에서 strict output이 thinking을 끄지 않도록 하고, queue_timeout_ms=0을 IOP queue timeout 없음으로 해석해야 한다. long reasoning/long-context 요청은 IOP queue timeout이 아니라 caller cancellation과 backend timeout 정책으로 제어한다.
2026-07-06 10:16:43 +09:00
cb426fe9f5
sync: agent-ops from agentic-framework v1.1.162
2026-07-06 10:06:12 +09:00
698f03c0ea
refactor: clean up long-context admission smoke test files and input estimator
2026-07-06 09:33:08 +09:00
e1dcbc105c
chore: long-context admission smoke test files reorganized and updated
2026-07-06 08:00:36 +09:00
2d08d240d4
update task, test, and config files
2026-07-05 20:53:43 +09:00
5b95208f4c
feat: edge runtime model queue and status dispatch updates
...
- Update control-plane edge wire and edge-node runtime wire contracts
- Refactor model queue service with admission control
- Update chat handler and responses handler for edge
- Modify run dispatch and status provider logic
- Add/modify runtime proto definitions
- Move G07 status logs to archive
2026-07-05 20:01:27 +09:00
35eb21959f
feat: queue skip support in model queue
2026-07-05 19:50:11 +09:00
b2754b871f
feat: long context admission support - refactor edge server, add input estimator
2026-07-05 19:26:06 +09:00
2c9faad1f3
feat: long context admission support - refactor edge server, add input estimator
2026-07-05 18:18:58 +09:00
26e2301116
feat: long context admission support for model group
2026-07-05 15:44:54 +09:00
568b57ff20
Update roadmap: phase PHASE.md and archive openai-compatible-tool-call-boundary-hardening milestone
2026-07-05 05:50:42 +09:00
d233efdb9c
Add all modified and untracked files
2026-07-05 05:23:09 +09:00
205c369a04
Include missing untracked files
2026-07-05 05:20:11 +09:00
9b64a26f18
Update roadmap and openai server implementation
2026-07-05 05:19:02 +09:00
dccfbff9ff
feat(roadmap): 업데이트 OpenAI-compatible Tool Call Boundary Hardening 마일스톤 상태를 검토중으로 변경
2026-07-04 19:50:39 +09:00
53e09201a0
update: sync contract, test documents and cleanup task
2026-07-04 19:17:25 +09:00
59e55d409e
feat: openai-compatible tool call boundary hardening & knowledge tool optimization
2026-07-04 18:21:27 +09:00
0ca170013d
feat: openai-compatible tool call boundary hardening changes
2026-07-04 17:31:03 +09:00
fcd6068501
chore: update openai-compatible tool call boundary hardening milestone
2026-07-04 17:11:33 +09:00
7261b919d5
feat: operational observability provider management milestones and phase updates
2026-07-04 16:58:09 +09:00
b55d1a2e85
fix: document and verify provider priority leveling
2026-07-04 15:05:36 +09:00
9b4c6ac644
feat: edge server-side streaming refactoring and contract/docs update
2026-07-04 13:46:39 +09:00
82ad78754e
refactor: simplify response language retry logic in iop-rule-loader
2026-07-04 11:07:29 +09:00
25b171c295
refactor: simplify response language retry logic in iop-rule-loader
2026-07-04 10:49:54 +09:00
fa3eb5f939
chore: update iop-rule-loader
2026-07-04 10:44:34 +09:00
4cd214f53c
feat: add .pi/ config for iop-rule-loader
2026-07-04 10:17:40 +09:00
de44a80cb7
Merge branch 'main' of https://git.toki-labs.com/toki/iop
2026-07-04 10:04:55 +09:00
001365a05f
Update phase status and add new milestone for openai-compatible tool call boundary hardening
2026-07-04 10:04:25 +09:00
77ab36cbd1
feat: edge config refresh and OpenAI handlers update
...
- Add config refresh classification and test coverage
- Update OpenAI chat/responses/stream handlers with config refresh support
- Add comprehensive server tests for config refresh
- Update local dev guide with config refresh information
- Extend config package with ConfigRefresh field
2026-07-04 09:33:00 +09:00
toki
367e7f3dc4
feat(openai): 모델 생성 정책을 적용한다
...
provider pool 모델 catalog의 출력 토큰 기본값과 thinking budget을 OpenAI-compatible 요청에 반영하고, Ornith dev-runtime 기준과 관련 계약 문서를 함께 맞춘다.
2026-07-04 09:20:56 +09:00
cb64df5b39
feat(openai-compat): update think-control implementation and clean up old task docs
...
- Update openai-compatible-api.md contract
- Refactor openai_compat.go adapter
- Update openai_compat_test.go
- Update edge-local-dev-guide.md
- Archive old task files and remove obsolete PLAN/CODE_REVIEW docs
2026-07-04 05:53:48 +09:00
eea8dd0ae9
feat: add think-control API fields and dev smoke tests
...
- Add think, reasoning_effort, thinking_token_budget, include_reasoning to openai-compatible-api.md
- Document provider-specific think-control policies (vLLM, Lemonade)
- Add conflict and strict output policies
- Update edge-local-dev-guide.md with think-control smoke examples
2026-07-03 20:48:11 +09:00
45e864188c
docs(archive): m-openai-compatible-think-control 아카이브 로그를 추가한다
2026-07-03 15:09:00 +09:00
37bab752d0
feat(openai): think 컨트롤 필드 전달과 include_reasoning 옵션을 지원한다
...
node 어댑터에서 think, reasoning_effort, thinking_token_budget 필드를
vllm, lemonade 등 제공자별로 변환하여 전달하도록 변경한다.
vllm은 chat_template_kwargs로, lemonade는 직접 필드로 전달한다.
에드지는 include_reasoning=false일 때 reasoning_content를
스트림과 비스트림 응답에서 모두 삭제하도록 변경한다.
관련 테스트를 추가한다.
2026-07-03 15:05:39 +09:00
3e1248d584
chore: update knowledge-tool-optimization-extension phase, SDD, and openai changes
2026-07-03 14:29:51 +09:00
8838e0aced
fix(openai): reasoning alias를 처리한다
2026-07-03 12:57:19 +09:00
9ecf7f9fef
feat: add OpenAI compat stream trace logging
...
- Add stream trace logging to edge server streamChatCompletion
- Add stream trace logging to node adapter openai_compat provider
- Enable trace via IOP_OPENAI_COMPAT_TRACE_STREAM env var or iop_trace_stream metadata
- Track content, reasoning, tool_calls chunks with think tag detection
2026-07-03 11:54:26 +09:00
c724158c04
update roadmap: mark tool-call-runtime-validation-retry as completed and archive
2026-07-03 08:27:11 +09:00
ac0271cf29
roadmap: knowledge-tool-optimization-extension update PHASE and retry milestone
2026-07-03 08:05:12 +09:00
0eb78377ee
sync: to agentic-framework v1.1.161
2026-07-03 05:32:24 +09:00
2fb34ea868
Merge branch 'main' of https://git.toki-labs.com/toki/iop
2026-07-03 05:09:29 +09:00
c3b40cbe1c
feat(edge): tool validation contract and chat completion retry
2026-07-03 05:08:02 +09:00
toki
d6dd3da59d
docs(dev-corp): Control Plane 검증 기준을 갱신한다
...
native Control Plane이 활성화된 provider-pool 상태와 capacity smoke 결과를 dev-corp 테스트 규칙과 인벤토리에 반영한다.
2026-07-02 16:07:26 +09:00
c48f531cba
chore: add reasoning_delta_log_preservation task archive
2026-07-02 14:10:36 +09:00
