99e2ea0f9f
docs(priorities): refresh architect queue
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
2026-06-30 15:50:44 +00:00
e1b3c587aa
Add configurable provider conformance dispatch ( #3459 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-30 16:31:49 +01:00
da2bbab80c
docs(priorities): refresh architect queue ( #3457 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-30 15:55:52 +01:00
5a59e1ece4
agent: verify durable resume example ( #3452 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-30 15:26:32 +01:00
aea03ba9e7
priorities: queue the flow verification/grader loop ( #3435 ) ( #3436 )
...
Add the verification loop as a ranked priority — the one missing layer from
the four-loop framing (agent / verification / event-driven / hill-climbing):
flow.Verify + flow.LLMGrader to grade a step's output against a rubric and
retry with feedback. The architect will re-rank on its next pass.
Co-authored-by: Claude <noreply@anthropic.com >
2026-06-30 15:17:18 +01:00
54bc05e48f
docs(priorities): advance agent durability queue ( #3450 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-30 14:40:14 +01:00
3ef0d98a16
flow: analyze run traces for optimization ( #3447 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-30 14:25:15 +01:00
5a6c8d8b30
docs(priorities): advance architect queue ( #3445 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-30 13:41:58 +01:00
1cd918c2b9
flow: add verification grader loop ( #3443 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-30 13:28:53 +01:00
e96d4a67bc
docs(priorities): refresh architect queue ( #3441 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-30 13:09:37 +01:00
8994fd03f6
Add A2A fallback provider conformance harness ( #3438 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-30 12:37:40 +01:00
0595130f16
run: surface MCP tools in the micro run banner by default ( #3434 )
...
The gateway already serves /mcp/tools on :8080 unconditionally (every
endpoint is an AI-callable tool), but the startup banner only printed an MCP
line when --mcp-address was set — so the live `micro run` experience hid the
harness's signature feature even though it was running, and didn't match the
README. Always advertise MCP Tools on the gateway address; keep the optional
standalone MCP-protocol server (--mcp-address) as a clearly separate line.
No behavior change — banner output only.
Co-authored-by: Claude <noreply@anthropic.com >
2026-06-30 11:21:26 +01:00
37eccc425e
docs(priorities): advance provider conformance queue ( #3433 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-30 11:14:39 +01:00
010e0fe57c
Classify agent run failure summaries ( #3430 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-30 10:55:14 +01:00
113f268268
docs: align DevRel public surface facts ( #3428 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-30 09:26:20 +01:00
c10697f08d
docs(priorities): advance resilience queue ( #3427 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-30 09:25:32 +01:00
f61f3dc04d
test: add AI stream provider conformance ( #3423 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-30 08:56:12 +01:00
d9e6c68938
docs(priorities): refresh architect queue ( #3421 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-30 07:40:48 +01:00
8847668c83
Improve agent telemetry error classification ( #3418 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-30 07:06:38 +01:00
e45bf3d114
docs(priorities): remove completed durable resume item ( #3416 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-30 05:50:51 +01:00
98d1f58cd6
Add durable agent resume example ( #3414 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-30 04:56:14 +01:00
51158ed2a7
docs(priorities): refresh architect queue ( #3412 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-30 04:04:11 +01:00
09bf82d4f6
fix a2a stream fallback ( #3410 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-30 03:26:42 +01:00
7d77f31ae2
docs(priorities): advance architect queue ( #3408 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-30 02:47:16 +01:00
2dbf70d0ed
Guard terminal agent checkpoints on resume ( #3406 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-30 02:34:43 +01:00
136c24ad5f
docs(priorities): advance architect queue ( #3404 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-30 01:28:16 +01:00
dc93addb10
ci: consolidate developer flow harness ( #3399 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-30 00:59:24 +01:00
09b4b8cc85
docs(priorities): drop shipped reliability item ( #3397 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-30 00:29:11 +01:00
7b8139ca3c
Harden agent tool execution timeouts ( #3395 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-29 23:55:43 +01:00
ea6f7f6976
docs(priorities): refresh architect queue ( #3393 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-29 23:32:10 +01:00
b25a9171c5
ci: fold agent checks into provider conformance ( #3389 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-29 23:08:09 +01:00
2fe4eb71d1
docs(priorities): refresh architect queue ( #3387 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-29 22:37:54 +01:00
c4e110c77f
Add deploy dry-run harness checkpoint ( #3384 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-29 22:14:28 +01:00
e4bb9d6bc7
docs(priorities): refresh architect queue ( #3382 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-29 21:43:53 +01:00
562deb0557
docs(examples): maintain zero-to-hero support path ( #3379 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-29 21:24:45 +01:00
551beb0858
docs(priorities): remove completed A2A skill item ( #3377 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-29 20:44:39 +01:00
d831ba2c45
Add typed A2A skill endpoints ( #3375 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-29 20:21:41 +01:00
a14633b9e8
docs(priorities): remove completed human-input item ( #3373 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-29 19:45:54 +01:00
4cc1ebb315
Document canceled human-input resumes ( #3371 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-29 19:24:26 +01:00
38ff084756
docs(priorities): refresh architect queue ( #3369 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-29 19:07:01 +01:00
585dd789a4
Redact agent run inputs from traces ( #3366 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-29 18:31:20 +01:00
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
57873cc5a5
docs(priorities): refresh architect queue ( #3363 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-29 18:04:52 +01:00
86bfced452
Wire getting-started harness into make ( #3360 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-29 16:58:29 +01:00
8863d27623
events: WithStore option for a durable, replayable stream ( #3357 )
...
goreleaser / goreleaser (push) Has been cancelled
* events: add WithStore option for a durable stream
* events: honor injected store in NewStream
2026-06-29 15:25:14 +01:00
efb4b3d191
docs(priorities): refresh architect queue ( #3355 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-29 14:27:42 +01:00
b83b8d164f
Add stream resume for agent checkpoints ( #3352 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-29 13:19:17 +01:00
11ff58fec7
docs(priorities): refresh architect queue ( #3350 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-29 12:41:44 +01:00
f1504507a3
agent: add tool-aware stream ask ( #3347 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-29 11:13:52 +01:00
a2a7ee17e0
docs(priorities): drop shipped memory item ( #3345 )
...
Co-authored-by: Codex <codex@openai.com >
2026-06-29 10:38:20 +01:00
Codex