mirrors / micro--go-micro

文件历史

4,453 提交 394 分支 441 Git 标签
codex/increment-3578
提交图

80 次代码提交

作者 SHA1 备注 提交日期
Asim Aslam 0811234f3e agent: execute text tool call fallbacks (#3554) 
Co-authored-by: Codex <codex@openai.com>
 2026-07-01 15:27:14 +01:00
Asim Aslam c110774dc7 Add opt-in retries for agent tool calls (#3535) 
Co-authored-by: Codex <codex@openai.com>
 2026-07-01 10:57:33 +01:00
Asim Aslam 04e8759d41 test agent checkpoint resume after restart (#3529) 
Co-authored-by: Codex <codex@openai.com>
 2026-07-01 09:06:46 +01:00
Asim Aslam b58eed1698 Add retrieval-backed agent memory (#3518) 
Co-authored-by: Codex <codex@openai.com>
 2026-07-01 04:59:16 +01:00
Asim Aslam 49bac7e4a8 trace scheduled flow dispatch metadata (#3510) 
Co-authored-by: Codex <codex@openai.com>
 2026-07-01 02:42:31 +01:00
Asim Aslam d259383645 Harden agent terminal failure statuses (#3499) 
Co-authored-by: Codex <codex@openai.com>
 2026-07-01 00:03:21 +01:00
Asim Aslam 3081dab246 Add agent memory summarizer hook (#3479) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-30 20:18:23 +01:00
Asim Aslam f5bf5f7987 Wire A2A streaming through agent StreamAsk (#3471) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-30 19:18:23 +01:00
Asim Aslam 3ec12b7c72 Trace agent checkpoint resume events (#3468) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-30 18:22:00 +01:00
Asim Aslam 010e0fe57c Classify agent run failure summaries (#3430) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-30 10:55:14 +01:00
Asim Aslam 8847668c83 Improve agent telemetry error classification (#3418) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-30 07:06:38 +01:00
Asim Aslam 2dbf70d0ed Guard terminal agent checkpoints on resume (#3406) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-30 02:34:43 +01:00
Asim Aslam 7b8139ca3c Harden agent tool execution timeouts (#3395) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-29 23:55:43 +01:00
Asim Aslam b25a9171c5 ci: fold agent checks into provider conformance (#3389) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-29 23:08:09 +01:00
Asim Aslam 4cc1ebb315 Document canceled human-input resumes (#3371) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-29 19:24:26 +01:00
Asim Aslam 585dd789a4 Redact agent run inputs from traces (#3366) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-29 18:31:20 +01:00
Asim Aslam 971bfdb954 agent: reuse tools instance in setupWithToolHandler (fix StreamAsk tool resolution) (#3365)
goreleaser / goreleaser (push) Has been cancelled
 2026-06-29 18:24:21 +01:00
Asim Aslam b83b8d164f Add stream resume for agent checkpoints (#3352) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-29 13:19:17 +01:00
Asim Aslam f1504507a3 agent: add tool-aware stream ask (#3347) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-29 11:13:52 +01:00
Asim Aslam 317bb300ae agent: harden compacted memory resume (#3339) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-29 09:25:59 +01:00
Asim Aslam 159963ab39 agent: trace model attempt metadata (#3333) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-29 07:16:19 +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 66438697b3 Improve compacting memory recall ranking (#3276) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-28 19:03:39 +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 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 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 3db9617f43 Add agent trace provider helper (#3198) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 23:02:09 +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 27f5e2be52 Add OpenAI streaming path (#3185) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-27 20:01:45 +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 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 130022e544 Record full agent timelines without tracing (#3118) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-26 13:27:08 +01:00
Asim Aslam 0d3f3f2be5 Record agent run timelines without tracing (#3116) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-26 12:35:03 +01:00
Asim Aslam ae91863343 Add trace filter for agent runs (#3114) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-26 10:50:49 +01:00
Asim Aslam ddde9472fc Expose agent chat run identifiers (#3108) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-26 08:53:33 +01:00
Asim Aslam d8f711431f agent: stop canceled tool execution (#3096) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-26 00:07:26 +01:00
Asim Aslam 5d22cd4a5b Correlate agent trace spans (#3094) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-25 23:09:39 +01:00
Asim Aslam 18ae00dad0 Harden agent harness contracts (#3080) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-25 17:36:36 +01:00
Asim Aslam 03791759ef Add filtered agent run summaries (#3070) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-25 12:35:39 +01:00
Asim Aslam 5e3cef7cd9 Add agent run summary status and duration (#3068) 
Co-authored-by: Codex <codex@openai.com>
 2026-06-25 10:50:49 +01:00
Asim Aslam 4c7e6e96eb agent: correlate run timelines with traces (#3057) 2026-06-25 07:20:11 +01:00
Asim Aslam 53193fbbe7 agent: mark successful run timelines complete (#3054) 2026-06-25 06:50:51 +01:00
Asim Aslam d369cf290c Improve agent run index summaries (#3049) 2026-06-25 01:31:08 +01:00
Asim Aslam 7a0ca65b68 Expose agent run IDs on responses (#3044) 2026-06-24 23:10:45 +01:00
Asim Aslam ff6af5d46b Make agent run timelines deterministic (#3038) 2026-06-24 20:42:38 +01:00
Asim Aslam 5e9accfd45 Add agent OpenTelemetry run observability (#3027) 2026-06-24 14:57:25 +01:00
Asim Aslam a8ea60120e agent: make model retries opt-in and harden retry backoff (#3021) 
Follow-up to #3017. A Generate runs the whole tool-execution turn, so
auto-retrying it re-runs already-executed (possibly side-effecting) tool
calls. Default ModelMaxAttempts 3 -> 1: retries are now opt-in via
ModelRetry. The timeout stays as a safety net.

Also harden ai.GenerateWithRetry: always back off between retries
(exponential, capped at 30s, default 200ms if unset) so an opt-in retry
can't busy-loop the provider even with Backoff=0.

Verified: go build, go test -race ./agent/... ./ai/, golangci-lint.

Co-authored-by: Claude <noreply@anthropic.com>
 2026-06-24 12:42:15 +01:00
Asim Aslam ab2c092693 Add agent model retry and timeout resilience (#3017) 2026-06-24 12:30:58 +01:00
Asim Aslam 3e885308a0 lint: clear the golangci-lint backlog and enforce a blocking lint in CI (#2995) 
Fixes #2988. Brings 'golangci-lint run ./...' to zero issues (was ~373):

- errcheck: explicitly ignore fire-and-forget calls with '_ =' (and a small
  errcheck.exclude-functions list for response writes — json Encoder.Encode,
  http ResponseWriter.Write, fmt.Fprint*); genuine cases handled.
- unused: remove dead code (unexported decls and dead test helpers) and the
  imports they orphaned.
- staticcheck: ST1005 error strings, ST1016 receiver names, S1000/S1017/S1019/
  S1023 simplifications, SA4004/SA4006/SA4010 dead code, SA1021 net.IP.Equal,
  SA6002 (store *[]byte in sync.Pool).
- govet: fix a context leak (lostcancel) in internal/util/mdns and move
  t.Fatal/Fatalf out of goroutines (testinggoroutine) in tests.
- ineffassign, unconvert: mechanical fixes.

CI: the Lint workflow now runs a blocking full-tree 'golangci-lint run' on
pushes and PRs (dropped only-new-issues now that the tree is clean).

Verified: go build, go vet, test compilation, and unit tests for the
behaviourally-touched packages all pass.


Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL

Co-authored-by: Claude <noreply@anthropic.com>
 2026-06-22 18:51:30 +01:00