文件历史

提交图

425 次代码提交

作者 SHA1 备注 提交日期
Asim Aslam cf9c015cf8 ci: add docs wayfinding guard (#4303)
Co-authored-by: Codex <codex@openai.com>
2026-07-08 02:12:09 +01:00
Asim Aslam 243d7904e8 Fix plan-delegate notify recovery (#4299)
Co-authored-by: Codex <codex@openai.com>
2026-07-08 01:00:03 +01:00
Asim Aslam 7697b2587c Wire universe harness services to shared broker (#4289)
Co-authored-by: Codex <codex@openai.com>
2026-07-07 23:08:10 +01:00
Asim Aslam 5c5186a230 Add agent debugging quickcheck docs (#4285)
Co-authored-by: Codex <codex@openai.com>
2026-07-07 22:17:15 +01:00
Asim Aslam 2c562c8827 Add scaffold check to zero-to-hero harness (#4279)
Co-authored-by: Codex <codex@openai.com>
2026-07-07 21:24:27 +01:00
Asim Aslam 6a25bbfc05 docs: link website first-agent examples map (#4266)
Co-authored-by: Codex <codex@openai.com>
2026-07-07 19:24:22 +01:00
Asim Aslam e96898d362 test: verify installed on-ramp wayfinding (#4207)
Co-authored-by: Codex <codex@openai.com>
2026-07-07 02:20:46 +01:00
Asim Aslam f6951d2bb0 Enforce idempotent delegate notifications (#4200)
Co-authored-by: Codex <codex@openai.com>
2026-07-07 01:03:54 +01:00
Asim Aslam 0c4ea84ee3 harness: dedupe delegated notify paraphrases (#4185)
Co-authored-by: Codex <codex@openai.com>
2026-07-06 22:17:10 +01:00
Asim Aslam 7c036459cf docs: add micro loop quickstart wayfinding (#4179)
Co-authored-by: Codex <codex@openai.com>
2026-07-06 21:23:10 +01:00
Asim Aslam 941d43bdf5 harness: dedupe delegated owner notifications (#4173)
Co-authored-by: Codex <codex@openai.com>
2026-07-06 20:16:40 +01:00
Asim Aslam d92d63943c Add no-secret agent debugging smoke (#4153)
Co-authored-by: Codex <codex@openai.com>
2026-07-06 15:08:34 +01:00
Asim Aslam 3ec50d1a7d Add first-agent tutorial smoke harness (#4140)
Co-authored-by: Codex <codex@openai.com>
2026-07-06 11:06:12 +01:00
Asim Aslam 498aac59f4 Stabilize duplicate plan-delegate notify replays (#4133)
Co-authored-by: Codex <codex@openai.com>
2026-07-06 09:12:58 +01:00
Asim Aslam ec27ce2e25 Fix first-agent quickstart numbering (#4125)
Co-authored-by: Codex <codex@openai.com>
2026-07-06 07:18:03 +01:00
Asim Aslam 45cf24162b Add first-agent examples CLI wayfinding (#4124)
Co-authored-by: Codex <codex@openai.com>
2026-07-06 07:17:16 +01:00
Asim Aslam 9dfb35d85a Guard provider conformance workflow scheduling (#4120)
Co-authored-by: Codex <codex@openai.com>
2026-07-06 04:59:35 +01:00
Asim Aslam 96eea598fc docs: align first-agent inspect command (#4113)
Co-authored-by: Codex <codex@openai.com>
2026-07-06 03:30:28 +01:00
Asim Aslam 6f2fefc1e1 Make plan-delegate notify replay idempotent (#4108)
Co-authored-by: Codex <codex@openai.com>
2026-07-06 02:22:20 +01:00
Asim Aslam eb16370f03 Add zero-to-hero CLI entrypoint (#4102)
Co-authored-by: Codex <codex@openai.com>
2026-07-06 01:02:09 +01:00
Asim Aslam 2963ac3fa6 docs: align architecture with agent lifecycle (#4095)
goreleaser / goreleaser (push) Has been cancelled
Co-authored-by: Codex <codex@openai.com>
2026-07-05 23:59:15 +01:00
Asim Aslam 36fd5b7bcd Promote first-agent doctor recovery (#4090)
Co-authored-by: Codex <codex@openai.com>
2026-07-05 22:59:00 +01:00
Asim Aslam e95d565502 docs: add install troubleshooting on-ramp (#4084)
Co-authored-by: Codex <codex@openai.com>
2026-07-05 21:59:12 +01:00
Asim Aslam f8619d89b6 docs: align website quickstart on-ramp (#4080)
Co-authored-by: Codex <codex@openai.com>
2026-07-05 21:06:30 +01:00
Asim Aslam d0dce12797 test docs wayfinding link targets (#4069)
Co-authored-by: Codex <codex@openai.com>
2026-07-05 19:01:31 +01:00
Asim Aslam 24a64aadb0 test examples lifecycle map (#4062)
Co-authored-by: Codex <codex@openai.com>
2026-07-05 18:01:38 +01:00
Asim Aslam 304d14331c docs: lead getting started with no-secret path (#4057)
Co-authored-by: Codex <codex@openai.com>
2026-07-05 17:09:01 +01:00
Asim Aslam 4a6ab4016d docs: add agent demo to first-agent on-ramp (#4044)
Co-authored-by: Codex <codex@openai.com>
2026-07-05 14:04:27 +01:00
Asim Aslam 153f178db6 docs: refresh coherence changelog (#4021)
Co-authored-by: Codex <codex@openai.com>
2026-07-05 09:10:28 +01:00
Asim Aslam 3f5547e781 ai: add anthropic streaming (#4009)
Co-authored-by: Codex <codex@openai.com>
2026-07-05 04:57:58 +01:00
Asim Aslam af4d81cba3 harness: require notify inside plan delegate flow (#3986)
goreleaser / goreleaser (push) Has been cancelled
Co-authored-by: Codex <codex@openai.com>
2026-07-05 00:00:26 +01:00
Asim Aslam f7c2ff0a74 docs: surface first-agent example path (#3975)
Co-authored-by: Codex <codex@openai.com>
2026-07-04 22:22:42 +01:00
Asim Aslam 54a80bc930 harness: verify first-agent on-ramp (#3967)
Co-authored-by: Codex <codex@openai.com>
2026-07-04 21:05:30 +01:00
Asim Aslam 45624a25e0 Stabilize plan-delegate notify wait (#3926)
Co-authored-by: Codex <codex@openai.com>
2026-07-04 13:06:43 +01:00
Asim Aslam ebc315505b examples: add smallest first agent (#3920)
Co-authored-by: Codex <codex@openai.com>
2026-07-04 12:13:08 +01:00
Asim Aslam 47ff1bc6f5 Add AP2 mandate foundation for A2A (#3899)
Co-authored-by: Codex <codex@openai.com>
2026-07-04 09:35:01 +01:00
Asim Aslam 6c6ce0e2a7 docs: update coherence changelog (#3897)
Co-authored-by: Codex <codex@openai.com>
2026-07-04 09:14:57 +01:00
Asim Aslam ab0bf29c79 feat(loop): add a security role that vets for vulnerabilities (#3818)
Adds an opt-in `security` role to `micro loop` and wires it into go-micro's own
loop. On a schedule it dispatches the agent to audit the codebase for real,
exploitable vulnerabilities and file them.

Security gets a deliberately more conservative policy than the other roles,
encoded in .github/loop/prompts/security.md:
- NEVER auto-merges a security change (fixes stay human-reviewed).
- NEVER publishes exploit detail / PoC in a public issue — novel exploitable
  findings get a concise `security` + `needs-human` issue (class, location,
  impact) routed to private disclosure; only known/public dep CVEs get a
  bump PR (no auto-merge).
- Weekly by default (`--security-cron`, 0 6 * * 1); tunable.

The go-micro prompt targets its real attack surface: MCP/A2A gateways, x402
payments, JWT/wrapper auth, provider BaseURL SSRF + key leakage, the agent
tool loop (prompt injection / guardrail bypass), TLS defaults, the loop's own
PAT, and dependency CVEs via govulncheck.

Note: an agent review is not a gate. The deterministic companion — govulncheck
as a required CI check — is a recommended follow-up so known-vulnerable deps
can't merge at all.


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

Co-authored-by: Claude <noreply@anthropic.com>
2026-07-04 07:03:08 +01:00
Asim Aslam 96e822d656 Add no-secret debug transcript checkpoint (#3889)
Co-authored-by: Codex <codex@openai.com>
2026-07-04 06:57:18 +01:00
Asim Aslam 7963342999 docs: test first-agent wayfinding (#3884)
Co-authored-by: Codex <codex@openai.com>
2026-07-04 04:55:59 +01:00
Asim Aslam 5b27c5b239 Fix plan-delegate notify completion race (#3877)
Co-authored-by: Codex <codex@openai.com>
2026-07-04 03:29:05 +01:00
Asim Aslam bc732bb513 docs: surface durable agent example (#3861)
goreleaser / goreleaser (push) Has been cancelled
Co-authored-by: Codex <codex@openai.com>
2026-07-04 00:02:40 +01:00
Asim Aslam 3cafff8789 Make agent preflight failures actionable (#3851)
Co-authored-by: Codex <codex@openai.com>
2026-07-03 22:00:02 +01:00
Asim Aslam 55070f1597 Harden A2A fallback stream validation (#3839)
Co-authored-by: Codex <codex@openai.com>
2026-07-03 20:03:40 +01:00
Asim Aslam 5c38a23fe4 Classify plan-delegate timeout side effects (#3834)
Co-authored-by: Codex <codex@openai.com>
2026-07-03 19:07:08 +01:00
Asim Aslam bd7625f947 Tighten delegated notify harness prompt (#3816)
Co-authored-by: Codex <codex@openai.com>
2026-07-03 16:25:49 +01:00
Asim Aslam 331e3f32bd Fix universe concierge notify handoff (#3811)
Co-authored-by: Codex <codex@openai.com>
2026-07-03 15:31:48 +01:00
Asim Aslam b8c03dafa2 Stabilize plan-delegate notify recovery (#3799)
Co-authored-by: Codex <codex@openai.com>
2026-07-03 13:30:58 +01:00
Asim Aslam e92978f3eb Add minimax to provider conformance (#3794)
Co-authored-by: Codex <codex@openai.com>
2026-07-03 12:30:56 +01:00
Asim Aslam a356ab36a8 ai/minimax: complete provider surface (matrix, conformance, changelog) (#3784)
* ai/minimax: complete provider surface (matrix, conformance, changelog)

Follow-up after merging the MiniMax provider (#3769), mirroring the Ollama
completeness pass (#3637):

- Add the `minimax` row to the AI provider capability matrix and blank-import
  ai/minimax in provider_capabilities_test.go so the matrix stays enforced
  against the registry.
- Add minimax to the stream-conformance allowlist (+ import) so its streaming
  is actually exercised against the OpenAI-compatible SSE contract, not just
  registered. It passes via the shared ai/internal/openaiapi path.
- Record the provider in CHANGELOG [Unreleased].

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL

* ai: update capabilities_test provider assertions for minimax

Adding the minimax blank-import to the shared ai_test binary (for stream
conformance) also registers it for TestRegisteredProviders / TestCapabilityRows
/ TestCapabilityMatrix in capabilities_test.go, which pin the exact provider
set. Update those assertions to include minimax. (Fixes the Unit Tests failure
my scoped `-run TestStreamProviders` check missed — go compiles all _test.go in
a package into one binary.)

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL

---------

Co-authored-by: Claude <noreply@anthropic.com>
2026-07-03 11:10:29 +01:00