Commit graph

588 commits

Author SHA1 Message Date
toki
f14d3a201e Add archive logs and pycache files 2026-07-14 09:21:39 +09:00
toki
d58d61810a Remove cloud-G07 plan and code review files 2026-07-14 09:21:04 +09:00
toki
217930f9b0 feat: update claude client gateway configuration
- Simplify model display names (remove verbose descriptions)
- Add use-model.sh for quick profile switching (dev-corp/ornith/fable/sonnet/opus)
- Change default gateway port from 18443 to 18444
- Remove deprecated ANTHROPIC_CUSTOM_MODEL_OPTION env vars
- Support system/developer role messages in OpenAI conversion
- Remove gateway-models.json cache (no longer needed)
- Add environment variables for gateway port and PATH in launchd plist
2026-07-14 07:23:28 +09:00
5cd7aea826 fix(openai): provider native thinking을 보존한다
OpenAI-compatible passthrough에서 caller가 보낸 provider-native thinking field가 catalog 기본 thinking budget으로 덮이지 않아야 한다. provider가 거부한 extension field도 Edge가 선판단하지 않고 provider status/body로 relay되는지 테스트 근거를 남긴다.
2026-07-14 07:21:37 +09:00
f430a07a3d update roadmap phase and milestone for openai-compatible provider passthrough 2026-07-14 06:50:36 +09:00
132af4f479 chore: archive logs for openai-compatible-provider-passthrough-contract-sync task 2026-07-14 06:42:39 +09:00
33f8f5e57f feat(edge): OpenAI compatible provider pass-through & test coverage 2026-07-14 06:39:53 +09:00
leedongmyun
9cff91f8bf docs(benchmark): Ornith think 응답 비교표를 추가한다 2026-07-14 06:14:00 +09:00
59c2997d47 refactor(openai): call metadata 기반 response_mode 라우터 선택을 제거한다
provider 라우트는 raw tunnel 패스스루, 그 외 라우트는 정규화된
RunEvent 경로로 응답을 결정한다. caller metadata는 임의 컨텍스트이며
응답 경로/shape를 선택하지 않는다 (SDD S01).

- chat_handler.go: response_mode parse/switch 로직 제거, 라우트 기반 분기로 단순화
- responses_handler.go: tunnelResponsesPassthroughSideband 함수 및 response_mode switch 제거
- stream.go: 관련 response_mode 라벨 사용 정리
- server_test.go: response_mode 관련 테스트 케이스 제거 및 정리
- usage_metrics_test.go: 사용되지 않는 테스트 대목 제거
- docs/openai-usage-grafana.md: response_mode 라벨 설명을 passthrough/normalized로 수정
2026-07-13 21:05:04 +09:00
leedongmyun
9f5d15d91c chore: sync OpenAI compatible API contract, routing policy, and dev-corp test updates 2026-07-13 19:18:07 +09:00
toki
10ede9381b chore(dev-corp): Control Plane compose 배포 상태를 반영한다
dev-corp Control Plane/observability compose 배포 결과를 inventory와 smoke 기준에 남기고, native Edge metrics용 Prometheus 설정을 분리한다. 원격 Docker 빌드의 TLS 제약을 피할 수 있도록 Control Plane runtime image 경로도 추가한다.
2026-07-13 15:35:10 +09:00
5b468059ef docs(dev-corp): handoff 문서를 추가한다 2026-07-13 15:17:00 +09:00
toki
05a1026aa4 Merge remote-tracking branch 'origin/main' 2026-07-13 15:12:34 +09:00
toki
83c26c4ac3 chore: update test rules, docs, and client configuration 2026-07-13 15:12:24 +09:00
89bd18ffa5 feat: add compose configuration for dev and dev-corp test environments 2026-07-13 14:08:43 +09:00
bb367055aa Merge remote-tracking branch 'origin/main' 2026-07-13 12:14:56 +09:00
5368926822 feat(observability): compose 관측 구성을 추가한다 2026-07-13 12:14:34 +09:00
toki
89b6aaf9d6 update test rules and docs 2026-07-13 11:45:56 +09:00
toki
469d2f32b4 Update dev-corp inventory configuration 2026-07-13 07:10:18 +09:00
ae4819046e Merge branch 'main' of https://git.toki-labs.com/toki/iop 2026-07-13 06:25:59 +09:00
01ba1b5796 chore: mark model group dispatch milestones as complete 2026-07-13 06:25:42 +09:00
leedongmyun
5a3a63fac2 docs(dev-corp): Spark Ornith direct 인벤토리를 기록한다 2026-07-13 06:13:47 +09:00
b7fedd04dc feat(edge): model group dispatch code polish and test coverage 2026-07-13 05:54:54 +09:00
8473a5450e feat: custom field preservation and sideband observation
- Add custom field preservation implementation
- Add sideband observation support
- Update OpenAI-compatible API contract
- Update roadmap and task files
2026-07-12 21:15:18 +09:00
ceefb85055 chore: archive task files and update tests
- Move plan/code_review to archive
- Update test files (edge, node, server, model_queue)
2026-07-12 20:50:29 +09:00
3cfe3181c4 feat(edge): model group mixed provider dispatch implementation + archive completed tasks
- Implement mixed provider dispatch with selection-first and path classifier strategies
- Add model queue service for provider load balancing
- Add OpenAI chat handler and stream updates for mixed provider support
- Add comprehensive tests for dispatch and queue logic
- Add inventory for Ornith vLLM mixed provider config
- Archive completed agent tasks (G06, G07)
2026-07-12 15:42:16 +09:00
398c9247db docs(dev): Ornith vLLM 설정 인벤토리를 보강한다 2026-07-12 15:41:08 +09:00
9578744c35 docs(dev): Ornith FP8 vLLM 인벤토리를 기록한다 2026-07-12 15:10:59 +09:00
leedongmyun
70c99c17a8 docs(roadmap): 출력 검증 후속 마일스톤을 추가한다
OpenAI-compatible 출력 검증 범위를 syntax gate, runtime integrity filter, LLM judge 정책 스케치로 나눠 후속 작업을 추적하기 위해 추가한다.
2026-07-12 12:36:23 +09:00
aeec784c7b feat: 라우팅 정책 모델 오케스트레이션 진행 및 provider config 반영
- seulgivibe OpenAI-compatible provider 완료 후 archive로 이동
- 모델 그룹 혼합 제공자 디스패치 milestone 진행
- agent-spec: OpenAI-compatible surface, provider pool config refresh 갱신
- Go: mapper.go/config.go provider config 매핑 개선
- agent-task: 새 subtask plan/code-review 문서 추가
2026-07-11 14:27:24 +09:00
a2523513f5 Merge branch 'main' of https://git.toki-labs.com/toki/iop 2026-07-11 12:44:46 +09:00
1659fc568e feat: routing-policy-model-orchestration - responses passthrough & model group mixed provider dispatch 2026-07-11 12:44:32 +09:00
12a26d4b4c feat: routing-policy-model-orchestration - responses passthrough & model group mixed provider dispatch 2026-07-11 12:42:16 +09:00
leedongmyun
192cf8e417 Sync uncommitted changes to new branch 2026-07-11 12:29:03 +09:00
b38f978652 feat: update edge config runtime refresh, openai compatible provider, and mapper 2026-07-11 09:48:54 +09:00
c836f1e562 feat: update edge config, usage docs, tests, and roadmap 2026-07-11 04:47:11 +09:00
8150d4697e docs(agent-roadmap): usage-token-log-ops-mvp 마일스톤 및 SDD를 아카이브하고 관련 spec 갱신한다
usage-token-log-ops-mvp 마일스톤 완료에 따라
roadmap 파일들을 archive로 이동하고, PHASE.md와
agent-spec 문서를 현재 구현 상태로 동기화한다
2026-07-10 20:09:33 +09:00
64328d2639 chore: grafana rollup docs - archive completed task files and add usage guide 2026-07-10 19:02:17 +09:00
6a54d62837 Merge remote-tracking branch 'origin/main' 2026-07-10 17:54:54 +09:00
0bfcb0f189 feat: usage metrics - identity metering, usage token logging, and runtime proto 2026-07-10 17:54:23 +09:00
toki
c58fbac0d5 feat(agent-client): Claude 및 Pi 에이전트 클라이언트를 위한 설치 스크립트와 README를 추가한다 2026-07-10 15:35:26 +09:00
toki
ddcc4f42f8 docs: update dev-corp openai compatible call guide and pi settings guide 2026-07-10 08:55:24 +09:00
toki
14c88c32aa docs(docs): dev-corp OpenAI-compatible 호출 시 반복 출력 loop 방지를 위한 파라미터 가이드를 추가한다 2026-07-10 07:51:10 +09:00
toki
6ab66277b8 docs: update dev-corp profile with sampling parameter extension 2026-07-10 07:40:02 +09:00
toki
526bfb31a7 chore: remove IOP_ROADMAP_STATUS.md 2026-07-10 07:19:14 +09:00
65b48c96a2 Merge remote-tracking branch 'origin/main' 2026-07-09 22:13:00 +09:00
d2b03618ab feat: operational observability - usage token log ops MVP 2026-07-09 22:12:21 +09:00
leedongmyun
ef236878ff docs: update dev-corp openai-compatible call and pi settings guide 2026-07-09 21:02:50 +09:00
leedongmyun
a709db0251 docs(contract): dev-corp gemma4:26b 파라미터 범위 및 가이드 문서 추가 2026-07-09 20:48:05 +09:00
leedongmyun
6d2de5bd1c docs: update dev-corp runtime deploy skill, edge smoke and inventory 2026-07-09 18:18:29 +09:00