Backstop for the gate: previously loop-triage only fired on Harness (E2E)
failures, so a red lint or test on master (e.g. the misspell that slipped past
because golangci-lint isn't a required check) produced no fix issue. Now triage
watches all the gate workflows.
- micro loop: `--ci-workflow` accepts a comma-separated list of workflow names,
rendered into the triage workflow_run trigger as a YAML array; the issue names
the actual failed workflow via github.event.workflow_run.name. (generic CLI)
- go-micro: regenerate loop-triage.yml to watch "Harness (E2E)", "Lint",
"Run Tests"; generalize the triage prompt beyond the harness (a lint/test
failure on master is a real regression to fix, not a flake to ignore).
- Docs: update CONTINUOUS_IMPROVEMENT.md triage description.
Note: this is defense-in-depth. The primary fix is making golangci-lint a
required status check so red lint can't merge in the first place — that stays
with the human (branch protection).
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
Co-authored-by: Claude <noreply@anthropic.com>
* feat(loop): go-micro now runs on `micro loop` (dogfood its own tool)
Replace go-micro's five hand-written loop workflows with ones generated by
`micro loop init --roles all`, making "go-micro builds itself with micro loop"
literally true rather than aspirational.
- Generate loop-planner/builder/triage/coherence/release.yml via the CLI with
go-micro's cadence and wiring (planner :59, builder :29, coherence 07:00,
release 23:00; CI gate "Harness (E2E)"; token CODEX_TRIGGER_TOKEN; base master;
tag prefix v). The old loop-architect.yml and loop-devrel.yml become
loop-planner.yml and loop-coherence.yml.
- Move the queue to .github/loop/PRIORITIES.md and add .github/loop/NORTH_STAR.md
(a concise steer pointing to internal/docs/THESIS.md), adopting the loop's
convention.
- Preserve go-micro's rich instructions as editable policy in
.github/loop/prompts/{planner,builder,triage,coherence}.md — the architect
founder-lens + adoption steer, the increment builder, harness-failure triage,
and the DevRel changelog/blog pass — faithfully ported from the old inline
prompts. Behavior is preserved; only the mechanism is now generated.
- CLI refinement the migration surfaced: prompts (and NORTH_STAR/PRIORITIES) are
now write-once — `micro loop init --force` refreshes workflow MECHANICS but
never clobbers customized POLICY. Added renderKeep + a test.
- Update internal/docs/CONTINUOUS_IMPROVEMENT.md (renamed workflows, moved queue,
the prompt-file model, and a note that these files are generated by micro loop).
Verified: build, go test ./cmd/micro/loop/..., golangci-lint (0 issues), gofmt;
`micro loop verify` passes; all generated workflows are valid YAML; re-running
init --force is idempotent and preserves policy.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
* loop: strip prompt editorial comments before posting to the agent
Verification of the migration surfaced that a dispatch workflow posted the
prompt file's leading <!-- editorial --> header to the agent, and __ISSUE__
inside it got substituted too (e.g. "Keep 4242 literal"). Harmless (invisible
in rendered markdown) but unclean and mildly confusing. The dispatch and triage
body construction now strips <!-- --> blocks with `sed '/<!--/,/-->/d'` before
substituting runtime tokens. Regenerated go-micro's workflows; added a test.
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>
* docs: complete Ollama provider surface (capability matrix, README, example fixes)
Follow-up cleanup after merging the Ollama provider (#3636):
- Add the `ollama` row to the AI provider capability matrix in the provider
guide, and blank-import `ai/ollama` in provider_capabilities_test.go so the
matrix stays enforced against the registry (the provider registers a stream
but wasn't imported in that test, so its row went unchecked).
- README: bump "7 LLM providers" → 8 and list Ollama (local + cloud); add its
default model (`llama3.2`) to the model table.
- Fix a fictional model name shipped in the example and package doc:
`gemma4:31b-cloud` → `gpt-oss:120b`. gemma4 doesn't exist, and the `-cloud`
suffix is for cloud models proxied through a local Ollama, not the direct
ollama.com/v1 endpoint the example uses.
- Record the provider and the new agent.BaseURL/micro.AgentBaseURL option in
the CHANGELOG [Unreleased] section.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
* loop-release: don't let checkout's persisted GITHUB_TOKEN clobber the PAT push
The daily release job computed the next tag correctly but the tag push 403'd:
"Permission to micro/go-micro.git denied to github-actions[bot]" (run
28554612450). Cause: actions/checkout persists the default GITHUB_TOKEN as an
http.extraheader Authorization credential for github.com, which git sends on
ALL requests to that host — including our manual
`git push https://x-access-token:${PAT}@github.com/...`. The persisted header
overrides the URL-embedded PAT, so the push authenticates as
github-actions[bot], which can't push tags (the job only grants
contents: read).
Set persist-credentials: false so no extraheader is written and the PAT in the
push URL is the only credential used.
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>
The DevRel pass now keeps the changelog living instead of letting it drift:
each daily run reconciles a Keep-a-Changelog `[Unreleased]` section against the
PRs that actually merged (user-facing entries only; internal loop/CI churn
skipped) and rolls it into a dated version heading whenever loop-release cuts a
new v6.MINOR.PATCH tag. When enough user-facing work has accumulated (roughly a
week's worth, not a near-empty post every day) it also drafts a "what's new"
changelog blog post narrating what shipped.
Autonomy boundary preserved: CHANGELOG.md upkeep is a safe factual change and
rides the auto-merged DevRel PR; the changelog blog post is opened as its own
PR but left for the human to review/merge, since blog voice stays with the human.
Also fix the CHANGELOG preamble: it claimed calendar versions (YYYY.MM) while
tags are semver (v6.MINOR.PATCH). Correct it, add an `[Unreleased]` section
seeded from real recent work, and note the historical 2026.0x headings.
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
Co-authored-by: Claude <noreply@anthropic.com>
There was no working, prominent Discord link. Update the stale invite code
(WeMU5AGxD → G8Gk5j3uXr) everywhere it appeared (README, docs, blog, landing,
SECURITY, issue templates, contrib), and add the link prominently: the site
nav and footer includes (so it shows on every landing/docs/blog page), a
Discord badge + a Community line in the README, and a "Join Discord" button on
the landing.
Co-authored-by: Claude <noreply@anthropic.com>
The framework's depth is strong but the on-ramp is the adoption gap, and the
architect queue had filled entirely with internal hardening. Steer the
architect to weight the developer on-ramp/DX (first-agent tutorial,
discoverable examples, docs wayfinding, install friction, debugging) at least
as highly as internal work — a developer succeeding on their first agent
matters more than another conformance/observability increment. Adoption issues
filed: #3561-#3565.
Also add loop-release.yml: a daily patch release that tags v6.MINOR.PATCH+1
when master has new commits (pushed with the PAT so goreleaser fires), so the
installable framework tracks the loop's daily improvements instead of lapsing.
Minor/major bumps stay with the human.
Co-authored-by: Claude <noreply@anthropic.com>
Rename the autonomous-loop workflows so the Actions list maps to the
long-running-agent harness pattern (planner → generator → evaluator):
architecture-review.yml -> loop-architect.yml "Loop: Architect (Planner)"
continuous-improvement.yml -> loop-builder.yml "Loop: Builder (Generator)"
devrel-review.yml -> loop-devrel.yml "Loop: DevRel"
harness-triage.yml -> loop-triage.yml "Loop: Triage (Evaluator feedback)"
harness.yml stays the shared Evaluator/CI gate (triage still matches it by the
"Harness (E2E)" name). Document the pipeline + role mapping in
CONTINUOUS_IMPROVEMENT.md, and point to it from CONTRIBUTING so the development
process is discoverable. No behavior change — schedules, gates, and required
checks are unaffected.
Co-authored-by: Claude <noreply@anthropic.com>
Close the loop's feedback path: when the live provider-conformance harness
fails, harness-triage.yml dispatches Codex to triage the failing run — read
logs, root-cause, dedupe against open issues, and file scoped codex/enhancement
issues that the hourly increment loop then fixes and the next harness run
verifies. Transient flakes are ignored; breaking/architectural fixes are
escalated as needs-human rather than auto-built. No human in the middle short
of a genuine judgment call. Documented in CONTINUOUS_IMPROVEMENT.md.
Co-authored-by: Claude <noreply@anthropic.com>
Match the real-model conformance cadence to the dev/loop velocity so live
regressions and provider drift surface within the hour instead of up to 24h.
The mock harness already runs on every push/PR; this only changes the live
(credentialed) schedule.
Co-authored-by: Claude <noreply@anthropic.com>
* atlascloud: env-selectable chat model; run conformance on a stronger model
The daily provider-conformance harness fails 4/5 harnesses on Atlas Cloud —
its default chat model answers agent/tool-use conformance prompts
conversationally instead of performing the task. Atlas is currently the only
provider with a key configured, so the whole live run is red.
Make the Atlas Cloud provider honor an ATLASCLOUD_MODEL env override (falling
back to the existing default), and set it in the harness workflow to a
stronger tool-use model (Qwen3, overridable via an Actions variable). No
change to the default for normal use.
* atlascloud: use minimaxai/minimax-m3 for conformance model
---------
Co-authored-by: Claude <noreply@anthropic.com>
* 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>
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>
The hourly loop ships increments but nothing watches the whole. Add two
periodic high-altitude passes, same dispatch mechanism (fresh issue → @codex):
- devrel-review.yml (daily): audits README, website, docs, blog for coherence
with the North Star, README crispness, and blog-worthy material. Safe
alignment/crispness fixes auto-merge; brand/positioning copy and blog drafts
are surfaced in a report for the human, never auto-merged.
- architecture-review.yml (every ~3 days): reviews the framework/harness against
the thesis and files scoped follow-up issues that feed the increment loop. It
does not make breaking/architectural changes itself.
Documented both in CONTINUOUS_IMPROVEMENT.md (Overseer passes).
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
Co-authored-by: Claude <noreply@anthropic.com>
With branch protection + "Allow auto-merge" now enabled on master, Codex
enables GitHub auto-merge on its own PR (gh pr merge --squash --auto) right
after opening it, so the PR lands the moment the required CI checks pass —
no polling sweep, and the green-CI gate is enforced by GitHub instead of by
gh pr checks in a cron. Removes auto-merge-codex.yml and updates the dispatch
and AGENTS.md accordingly.
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
Co-authored-by: Claude <noreply@anthropic.com>
Codex was pushing to a generic branch (e.g. "work"), which the auto-merge
sweep ignores (it only matches codex/* branches with the codex label) and
which collides across runs. The dispatch and AGENTS.md now instruct Codex to
create a unique codex/increment-<issue> branch and pass --label codex to
gh pr create, so every increment is isolated and actually swept.
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
Co-authored-by: Claude <noreply@anthropic.com>
Codex's make_pr tool in the Cloud sandbox is a no-op stub — it records the
PR title/body and returns them "for downstream consumption" (the manual
"Create PR" click), but never pushes a branch or calls the GitHub API. That
is why "make_pr called, nothing happened": the tool literally cannot open a
PR. With the gh CLI now installed in the Codex setup and origin pointed at
the repo, the dispatch tells Codex to push and open the PR itself
(git push + gh pr create) instead of relying on make_pr.
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
Co-authored-by: Claude <noreply@anthropic.com>
Codex derives its PR branch name from the triggering issue's context, so
re-commenting on a single tracker issue (#3024) every hour collapsed every
increment onto one branch name. The first increment opened a PR; the rest
collided on the occupied branch and silently failed to open one — which is
why repeated runs produced "make_pr called, nothing happened."
Open a unique issue per run and dispatch Codex there, so each increment gets
its own branch and a clean PR. The dispatch asks Codex to "Closes #<issue>"
so each tracking issue auto-closes when its PR merges. The explicit
branch-name request (which Codex ignored in favor of the issue-derived name)
is dropped.
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
Co-authored-by: Claude <noreply@anthropic.com>
* fix: harden flow step execution against nil Run and cancellation
A step with no Run function panicked the run; it now returns a clear
configuration error. The retry loop also kept retrying after the run's
context was canceled or its deadline passed — it now stops immediately
and surfaces the context error, preserving cancellation/deadline
semantics for durable workflow runs. Adds regression coverage for both.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
* ci: give each Codex dispatch a unique branch to avoid collisions
Codex derives its PR branch name from the dispatch text. The hourly loop
posted an identical generic prompt every run, so every increment resolved
to the same branch name — the previous increment's branch (until auto-
merged and deleted) blocked the next PR from opening. Include the run
number in the prompt and explicitly request a fresh
codex/improvement-<run_number> branch, so each increment is isolated.
auto-merge-codex.yml still matches (codex/* prefix) and deletes on merge.
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>
* thesis: position Go Micro as complementary to LangChain, not competing
Add a 'Where we fit' section: 'harness' has two layers — the intra-agent
harness (single-model runtime: prompts, tools, context, sandbox, the Ralph
loop) that LangChain/LangGraph/deepagents/Claude Code own and we do NOT
compete with, and the operational harness (the distributed substrate agents
operate inside: services-as-tools, discovery, durable runs, observability,
interop, the services->agents->workflows lifecycle) which is our focus. They
stack and interoperate via MCP/A2A; we make those agents better neighbours,
not obsolete.
* ci: gate Codex dispatch on CODEX_TRIGGER_TOKEN secret
Codex ignores @codex comments authored by the github-actions bot, so the
hourly dispatch was producing no PRs while still posting to the tracker
issue. Gate the comment step on the presence of CODEX_TRIGGER_TOKEN: the
workflow now no-ops until a PAT for a Codex-followed account is set, then
activates automatically with no further change.
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>
Codex