mirrors / micro--go-micro

提交

4,311 提交 394 分支 441 Git 标签
codex/architect-3239
提交图

4311 次代码提交

此分支
此分支
所有分支
作者 SHA1 备注 提交日期
Codex 044c8ddead Update architect priorities
Harness (E2E) / Harnesses (mock LLM) (push) Has been cancelled
Harness (E2E) / Provider harnesses (live LLM conformance) (push) Has been cancelled
Lint / golangci-lint (push) Has been cancelled
Run Tests / Unit Tests (push) Has been cancelled
Run Tests / Etcd Integration Tests (push) Has been cancelled
 2026-06-28 10:13:10 +00:00
Asim Aslam 6da799d64f Classify AI retry failures (#3238) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 10:42:37 +01:00
Asim Aslam 220b370641 Update architect priorities (#3236) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 10:08:20 +01:00
Asim Aslam ac2163ef49 docs: align public TLS and A2A status (#3231) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 09:20:26 +01:00
Asim Aslam 9d6814f5ae docs: refresh roadmap after A2A task support (#3229) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 08:55:36 +01:00
Asim Aslam 929cd1ab1d Add A2A task continuation and push callbacks (#3226) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 07:09:03 +01:00
Asim Aslam fe651b4d01 Update architect priorities after x402 (#3224) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 06:35:10 +01:00
Asim Aslam 05ee980bf5 Harden x402 spend caps (#3222) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 04:54:15 +01:00
Asim Aslam e1d19c4cb5 Update architect priorities after memory and HITL (#3220) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 04:08:37 +01:00
Asim Aslam 61f873174c Add durable approval pause for agents (#3218) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 03:37:50 +01:00
Asim Aslam 71581e9a61 Add agent memory compaction controls (#3216) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 02:39:06 +01:00
Asim Aslam 892b4f185d Update architect priority queue after lifecycle hooks (#3213) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 01:30:09 +01:00
Asim Aslam 30f53e42a7 Expose model retry attempt metadata (#3207) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 00:56:21 +01:00
Asim Aslam 016eb82a32 Update architect priorities after streaming (#3205) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 00:29:03 +01:00
Asim Aslam a576f65b08 Improve A2A streaming task lifecycle (#3203) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 23:57:24 +01:00
Asim Aslam 07f0d30aea Update architect priority queue after observability (#3201) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 23:26:33 +01:00
Asim Aslam 3db9617f43 Add agent trace provider helper (#3198) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 23:02:09 +01:00
Asim Aslam c19e4829ba Update architect priority queue (#3196) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 22:28:28 +01:00
Asim Aslam f37ed42bf3 Add registry service readiness check (#3194) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 21:56:22 +01:00
Asim Aslam 114cd7e19e Update architect priorities after conformance (#3192) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 21:30:21 +01:00
Asim Aslam 28fc2ea340 Add agent provider conformance matrix (#3190) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 21:08:04 +01:00
Asim Aslam 38f5c13e65 Update architect priority queue (#3188) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 20:37:32 +01:00
Asim Aslam 27f5e2be52 Add OpenAI streaming path (#3185) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 20:01:45 +01:00
Asim Aslam 1fa7584be8 Update architect priority queue (#3183) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 19:34:11 +01:00
Asim Aslam e8c632456a Add checkpointed agent run resume (#3180) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 19:00:18 +01:00
Asim Aslam 9a410cbe8b Update architect priority queue (#3176) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 17:46:45 +01:00
Asim Aslam 620374ef22 Add zero-to-hero harness test contract (#3174) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 17:08:04 +01:00
Asim Aslam 31556b310e loop: continuous architect + lead the North Star with the mission/canon (#3172) 
* ci: run the architect continuously as the founder lens

Make the architect a continuous overseer (hourly at :59, just before the :29
increment) instead of an every-few-days check-in. Each run it tracks live state
(what merged, what's in flight), keeps the roadmap priorities live, and judges
cohesion across harness/framework/dev-UX plus missing pieces and realignment —
re-ranking internal/docs/PRIORITIES.md to match reality. It only opens a PR when
the ranking actually changes (otherwise it just posts an assessment and closes
its issue), to avoid churn.

* thesis: lead the North Star with the mission, grounded in the canon

Instill the years of context the loop was missing: the vision lives in the
corpus (blog, README, website), not a single doc. Lead THESIS.md with an
explicit Mission — "what problem we solve" (make building an agent as easy as
building a service, on one runtime, because an agent is a distributed system),
distilled from the corpus — and name the blog/README/website as the canon the
North Star is a distillation of and must stay faithful to. Wire the architect to
judge every priority against the mission and re-derive alignment from the canon,
flagging drift in either direction (work vs mission, or thesis vs the blog).

---------

Co-authored-by: Claude <noreply@anthropic.com>
 2026-06-27 16:58:24 +01:00
Asim Aslam 0e67971c53 ci: couple architect and increment loop through a ranked priority queue (#3171) 
The architect now prioritizes the roadmap + an internal scan into a single
ranked, issue-linked queue in internal/docs/PRIORITIES.md (re-ranked each run),
and the hourly increment loop works the top open item from that queue instead
of independently guessing each hour — falling back to its own judgment only
when the queue is empty. So work is roadmap-driven by default and the human can
redirect by reordering the file or its issues.

- New internal/docs/PRIORITIES.md (seeded from the roadmap + open issues).
- architecture-review.yml: architect owns/re-ranks PRIORITIES.md and keeps each
  top item backed by a scoped issue.
- continuous-improvement.yml: pick the top open queue item; close both the
  priority issue and the run tracker.
- CONTINUOUS_IMPROVEMENT.md: document the architect → queue → increment pipeline.

Co-authored-by: Claude <noreply@anthropic.com>
 2026-06-27 16:18:03 +01:00
Asim Aslam 2af5e6ae8f Record A2A agent replies in task history (#3170) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 16:09:30 +01:00
Asim Aslam 656c4ea1e7 flow: tag single-step run info as flow (#3168) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 15:16:38 +01:00
Asim Aslam 4a09b4469a Add flow execution timeout option (#3164) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 14:04:58 +01:00
Alexander Serheyev 25d66f737d fix: retract phantom modules for cmd paths (#3154) 
* fix: retract phantom modules for cmd and cmd/micro

* fix: remove temporary go.mod files to restore build
 2026-06-27 13:19:53 +01:00
Asim Aslam 45d68c932e Track parent run IDs for durable flows (#3162) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 13:07:18 +01:00
Asim Aslam c5c08e24d8 test: cover micro new no-mcp contract (#3160) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 12:17:19 +01:00
Asim Aslam 8a0f4a7636 Add flow step context to run info (#3158) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 11:22:23 +01:00
Asim Aslam bcf2c92931 Add A2A completed-task streaming (#3156) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 10:29:01 +01:00
Asim Aslam 57ca94a88b docs: align public x402 flag examples (#3153) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 09:08:38 +01:00
Asim Aslam ba231efe71 Update README.md 2026-06-27 07:08:08 +01:00
Asim Aslam f755eadd47 Propagate flow checkpoint failures (#3150) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 06:55:56 +01:00
Asim Aslam 467c937873 Improve flow run history validation (#3148) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 04:55:49 +01:00
Asim Aslam 3f45771840 Publish provider conformance summaries (#3146) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 03:29:12 +01:00
Asim Aslam c9e045961d Add flow run stage filtering (#3144) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 02:28:39 +01:00
Asim Aslam 590aacb518 docs: keep AI provider capability matrix verified (#3142) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 00:58:39 +01:00
Asim Aslam 87eb5ce665 Add filters for flow run history (#3140) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 00:00:58 +01:00
Asim Aslam ed904aa6ad Propagate flow run lineage to agent chats (#3138) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-26 23:04:18 +01:00
Asim Aslam 59d028b8e1 test ai retry policy semantics (#3136) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-26 22:16:59 +01:00
Asim Aslam 19818ad638 Expose streaming in provider capabilities (#3134) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-26 21:18:38 +01:00
Asim Aslam 993ce668b2 Add provider capability markdown export (#3132) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-26 20:20:08 +01:00
Asim Aslam 1d412fa6f5 Trigger test workflow on PR updates (#3130) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-26 19:14:39 +01:00