mirrors / micro--go-micro

提交

4,348 提交 394 分支 441 Git 标签
codex/increment-3326
提交图

4348 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 c5fb19aa60 Add OpenAI-compatible streaming providers
Lint / golangci-lint (push) Has been cancelled
Run Tests / Unit Tests (push) Has been cancelled
Harness (E2E) / Harnesses (mock LLM) (push) Has been cancelled
Harness (E2E) / Provider harnesses (live LLM conformance) (push) Has been cancelled
Run Tests / Etcd Integration Tests (push) Has been cancelled
 2026-06-29 04:01:11 +00:00
Asim Aslam 5ee3a5224f ai/atlascloud: replace stale Stream_NotImplemented test (#3324)
goreleaser / goreleaser (push) Has been cancelled
Streaming is implemented now (v6.3.3); the old test expected
ErrStreamingUnsupported and failed. Replace it with a real SSE streaming
test (httptest) that also asserts stream_options.include_usage and the
final usage chunk.
v6.3.5 		2026-06-29 03:36:39 +01:00
Asim Aslam c9f1ac921f Update architect priorities after agent resume (#3322)
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
Co-authored-by: Codex <codex@openai.com>
 2026-06-29 02:49:27 +01:00
Asim Aslam c395010565 Expose durable agent resume APIs (#3319) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-29 02:36:07 +01:00
Asim Aslam dca263f301 Update architect priorities after CLI inspection (#3317) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-29 01:27:51 +01:00
Asim Aslam 3540bf5a50 Add CLI inspect command for run history (#3313) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-29 00:57:40 +01:00
Asim Aslam 0d86fd5bcd Update architect priorities after failure hardening (#3311) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-29 00:33:17 +01:00
Asim Aslam 205d6a55a3 Respect provider retry-after backoff hints (#3309) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 23:57:17 +01:00
Asim Aslam 7588a427cc Update architect priorities (#3307) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 23:28:55 +01:00
Asim Aslam 7b9937068d ai: surface token usage on streaming responses (#3304)
goreleaser / goreleaser (push) Has been cancelled
* ai/atlascloud: surface token usage on streams

Request stream_options.include_usage and return the final usage chunk
as a Response with Usage set, so streaming callers can record usage.

* ai/openai: surface token usage on streams

Request stream_options.include_usage and return the final usage chunk
as a Response with Usage set, so streaming callers can record usage.
v6.3.4 		2026-06-28 23:13:25 +01:00
Asim Aslam f8d8cb39a7 Document provider conformance scheduling (#3303) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 22:55:49 +01:00
Asim Aslam 87a0c0c93b ai/atlascloud: implement streaming (#3301)
goreleaser / goreleaser (push) Has been cancelled
Atlas exposes an OpenAI-compatible SSE chat endpoint; emit content
deltas as they arrive instead of returning ErrStreamingUnsupported.
v6.3.3 		2026-06-28 22:42:03 +01:00
Copilot f31a7acf0b fix: gofmt formatting in ai/anthropic/anthropic.go (#3299) 
* Initial plan

* fix: remove extra blank line in ai/anthropic/anthropic.go (gofmt)

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
 2026-06-28 22:38:32 +01:00
Asim Aslam 4279a5eed3 ai: add WithMaxTokens option (#3300)
goreleaser / goreleaser (push) Has been cancelled
* ai: add WithMaxTokens option

Let callers cap response length; providers send max_tokens when set
(anthropic keeps its 8192 default otherwise).

* ai: add WithMaxTokens option

Let callers cap response length; providers send max_tokens when set
(anthropic keeps its 8192 default otherwise).

* ai: add WithMaxTokens option

Let callers cap response length; providers send max_tokens when set
(anthropic keeps its 8192 default otherwise).

* ai: add WithMaxTokens option

Let callers cap response length; providers send max_tokens when set
(anthropic keeps its 8192 default otherwise).
v6.3.2 		2026-06-28 22:37:50 +01:00
Asim Aslam c39a846d3b Update architecture priorities (#3298) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 22:31:33 +01:00
Asim Aslam b707c7e305 ai: thread Request.Messages into provider requests (#3293)
goreleaser / goreleaser (push) Has been cancelled
* ai/atlascloud: thread Request.Messages into the request

Fold conversation history (req.Messages) between the system prompt and
the final user prompt so multi-turn context reaches the model.

Refs #3292

* ai/openai: thread Request.Messages into the request

Fold conversation history (req.Messages) between the system prompt and
the final user prompt so multi-turn context reaches the model.

Refs #3292

* ai/anthropic: thread Request.Messages into the request

Fold conversation history (req.Messages) between the system prompt and
the final user prompt so multi-turn context reaches the model.

Refs #3292
v6.3.1 		2026-06-28 22:19:59 +01:00
Asim Aslam 5bfc37708d Add support example smoke test (#3291) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 21:58:56 +01:00
Asim Aslam 4d852c5e36 Update architect priorities after deploy contract (#3289) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 21:32:15 +01:00
Asim Aslam f7a3e8461e test deploy inner-loop contract (#3287) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 21:07:20 +01:00
Asim Aslam 87eb540a04 Update architect priorities for DX gaps (#3285) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 20:35:29 +01:00
Asim Aslam 48e05385c7 Add agent human input pause resume (#3281) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 20:04:25 +01:00
Asim Aslam cb10149f54 Update architect priorities after memory work (#3279) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 19:24:54 +01:00
Asim Aslam 66438697b3 Improve compacting memory recall ranking (#3276) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 19:03:39 +01:00
Asim Aslam 6e1c11ca74 Update architect priorities after A2A handoffs (#3274) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 18:33:59 +01:00
Asim Aslam 44c08a6bd2 Add A2A resubscribe and input-required handoffs (#3271) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 17:59:49 +01:00
Asim Aslam 9c01202599 Update architect priorities after OTel spans (#3269) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 17:32:36 +01:00
Asim Aslam b4cfe51115 Emit agent run events on OTel spans (#3267) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 17:04:26 +01:00
Asim Aslam 2221834707 Update architect priorities after streaming conformance (#3265) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 16:33:06 +01:00
Asim Aslam 5813f53117 test ai streaming conformance (#3263) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 16:17:23 +01:00
Asim Aslam 72e6161b02 Update architect priorities after agent checkpointing (#3261) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 15:41:44 +01:00
Asim Aslam 1789819c39 Add agent tool checkpoint replay protection (#3259) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 15:22:11 +01:00
Asim Aslam 8676dcacf2 Update architect priority queue after 0-to-hero (#3257) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 14:38:08 +01:00
Asim Aslam 22b3b9ca22 Add zero-to-hero CI reference scenario (#3252) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 14:09:17 +01:00
Asim Aslam 4ca8948ba4 Update architect priorities after 0-to-1 verification (#3250) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 13:34:18 +01:00
Asim Aslam 28cbf0be7e test: verify scaffolded service run and call contract (#3248) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 13:14:22 +01:00
Asim Aslam e8e6cb1210 Update architect priorities after conformance (#3246) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 12:40:00 +01:00
Asim Aslam 2a06a043bd ci: run live agent provider conformance (#3244) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 12:23:04 +01:00
Asim Aslam 6eef58f815 Update architect priorities (#3242) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 11:13:36 +01:00
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