Queue the Next-phase agent streaming item and the a2a multi-skill gap that
block a real consumer from retiring its bespoke planner / A2A handler. The
architecture-review pass re-ranks from here.
* 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>
* ci: self-merge Codex PRs via native auto-merge; retire the sweep
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.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
* docs: document the durable loop mechanics (stub→gh, branch, auto-merge)
Capture the hard-won wiring of the autonomous loop so it isn't re-derived:
fresh issue per increment, user-PAT dispatch (Codex ignores the bot), Codex
opening the PR via gh (make_pr is a no-op stub), unique codex/ branch + label,
and native auto-merge gated by branch protection with 0 approvals. Adds a
"do-not-break" list (don't re-add approvals, don't reuse one tracker issue,
don't use make_pr, don't re-implement during the summary→PR lag).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
* website: rename section to "Features"; trim subtitle
Rename the feature-grid heading from "The Runtime Around the Agent" to
"Features", and drop "once they leave the demo." from the subtitle.
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>
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.
Co-authored-by: Claude <noreply@anthropic.com>
Add internal/docs/THESIS.md — the vision the autonomous loop steers by: a
holistic agent harness AND service framework encapsulating the lifecycle of
services -> agents -> workflows (workloads come after agents; the value is in
composing it into systems that do real work, on schedules and in loops).
Wire it in as the alignment criterion: the continuous-improvement charter and
the Codex dispatch prompt now require every increment to advance the North Star,
so improvements compound toward the thesis instead of drifting locally.
Co-authored-by: Claude <noreply@anthropic.com>
Define the autonomous improvement loop (internal/docs/CONTINUOUS_IMPROVEMENT.md):
full autonomy with correctness (build/test/lint) as the only gate, work sourced
from roadmap + issues + an improvement radar + dogfooding, Claude Code driving
and Codex executing scoped tasks, with brand/positioning and breaking API kept
with the human.
Add a durable scheduled GitHub Action (.github/workflows/continuous-improvement.yml)
as the session-independent backbone — a safe no-op until an ANTHROPIC_API_KEY
secret is added.
Co-authored-by: Claude <noreply@anthropic.com>
Replace the drifted, contradictory roadmap set (two public roadmaps, the
AI-native-era business-model doc, stale status snapshots) with one
canonical roadmap focused on agentic development and developer experience.
- internal/website/docs/roadmap.md — the single source of truth: where we
are (v6), the principles (build into what people run; CLI-first; the
0->1 and 0->hero getting-started contract; interaction; battle-tested),
and prioritized work (cross-provider conformance + resilience now;
durable agent loop, streaming, observability next).
- ROADMAP.md — concise, points to the canonical.
- roadmap-2026 + the internal ROADMAP_2026/STATUS docs — collapsed to
pointers (keeps blog/CLAUDE links alive, removes drift).
- CLAUDE.md — references the single roadmap + CHANGELOG for status.
Co-authored-by: Claude <noreply@anthropic.com>
* test(harness): read agent plan from the scoped store
The store-scoping change moved an agent's plan from the default table
key agent/{name}/plan to its own table (database "agent", table {name},
key "plan"). The plan-delegate harness tests still read the old key and
failed with 'not found'; read through store.Scope(mem, "agent", name)
like the agent does.
* docs: orient agents-first across README, landing, and docs overview
Lead with agents (then services and flows), surface MCP + A2A as the
interop story, and frame agents as services. Landing hero and feature
grid reordered agents-first with an A2A gateway card.
* v6: module path go-micro.dev/v6, TLS secure by default, NewService
Cut v6. Three breaking changes, bundled so the major bump is paid once:
- Module path go-micro.dev/v5 -> go-micro.dev/v6 across all imports + go.mod.
- TLS verification on by default (was off). MICRO_TLS_SECURE removed;
MICRO_TLS_INSECURE=true opts out for self-signed/dev.
- micro.NewService(name, opts...) is the canonical service constructor,
symmetric with NewAgent/NewFlow; micro.New kept as a deprecated alias;
the old name-less NewService(opts...) removed. Generators emit NewService.
Also ports the JWT auth token provider in-module (go-micro.dev/v6/auth/jwt/token
on golang-jwt/jwt/v5), dropping the v5-pinned github.com/micro/plugins/v5/auth/jwt
and the deprecated dgrijalva/jwt-go.
Docs/README/landing updated to v6 and @latest; v5->v6 migration guide added;
CHANGELOG cut as [6.0.0]. Blog posts left at their historical versions.
---------
Co-authored-by: Claude <noreply@anthropic.com>
* feat(a2a): Agent2Agent protocol gateway
Add gateway/a2a — exposes registered agents over the open A2A protocol so
agents on other frameworks can discover and call them. Agent Cards are
generated from registry metadata (the same way the MCP gateway derives
tools from service endpoints); incoming A2A tasks translate to the
agent's existing Agent.Chat RPC, so there's no per-agent code.
v1 is the synchronous JSON-RPC binding: message/send returns a completed
Task, tasks/get retrieves it, and Agent Cards are served for discovery;
streaming and push notifications are advertised as unsupported. Run with
'micro a2a serve' (cmd/micro/a2a). Tests cover card generation,
message/send, tasks/get, listing, and unknown-method errors.
* docs: A2A guide, README contents + A2A section, universe A2A check
- Add a Contents table of contents at the top of the README and an A2A
subsection under Building Agents.
- Add the Agent2Agent (A2A) guide and register it in the docs nav.
- Exercise the A2A gateway in the universe harness: the concierge agent
is reached over A2A (message/send -> Agent.Chat -> completed task).
* feat(a2a): outbound client — call external A2A agents
Add a2a.Client (Send/Card) so a Go Micro agent or flow can call an agent
on any framework by URL — the outbound counterpart to the gateway. Wired
in two places: flow.A2A(url) as a workflow step (the cross-framework
Dispatch), and agent delegate to an http(s) URL routes over A2A. The
universe harness now drives the gateway through the client, exercising
both directions. Tests cover client send/card and the round trip.
* docs: A2A both-directions — guide, README, changelog, blog #26
---------
Co-authored-by: Claude <noreply@anthropic.com>
* docs: design note for flow steps + Checkpoint durable execution
* docs: fold in durable-execution decisions (State struct, single Step, run retention, retry)
* docs: rename State.Payload to State.Data
* feat(flow): ordered steps + Checkpoint durable execution
A flow can now be an ordered list of steps (a task with stages) instead
of a single LLM turn. State carries typed Data plus a Stage marker; each
step is checkpointed before and after via a pluggable Checkpoint
(store-backed by default), so a run survives a crash and resumes where it
stopped without re-running completed steps. Flow-level Retry with a
per-step override; runs retained for audit unless DeleteOnSuccess.
Step actions: Call (RPC), LLM (augmented turn), Dispatch (to an agent),
or any StepFunc. Single-step and agent-dispatch flows are unchanged.
* feat(flow): top-level re-exports + durable flow example
Expose the step/checkpoint API from the micro package (FlowSteps,
FlowStep, FlowState, FlowRetry, FlowWithCheckpoint, FlowCall/LLM/Dispatch,
Checkpoint, StoreCheckpoint) and add a runnable, key-free example
demonstrating crash + resume.
* docs: document durable flow steps (guide, README, CLI help)
* docs: blog post + changelog for durable workflows
* fix(flow): scope checkpoint keys by flow name (flow/{name}/runs/{id})
Run keys were flow/runs/{id} — a single global keyspace shared by every
flow on the default store. Namespace them by flow name so each flow's
state is kept apart. StoreCheckpoint now takes a scope argument (the flow
passes its name by default).
* feat(store): Scope handle; scope agent and flow state by name
Add store.Scope(s, database, table) — a store handle that confines every
operation to a database/table without mutating the shared store, so
co-located components don't clobber each other's table (the failure mode
of the global Init(Table(...)) approach).
Use it to keep each agent's memory and plan in its own table
(agent/{name}) and each flow's runs in its own (flow/{name}), instead of
one global table partitioned only by key prefix. Services already scope
by service name.
* feat: consistent state model — service store scoping, flow registry, list/history CLI
- service: scope store via store.Scope (database service / table name),
retiring the Init(store.Table(name)) global-mutation hack; bridge the
default store so handlers using store.DefaultStore stay isolated.
- flow: register in the registry as type=flow while running (with trigger
and step count), deregister on Stop. Live discovery, like agents.
- cli: micro flow list (registry), micro flow runs <name> (durable store),
micro agent history <name> (durable store). list = running, runs/history
= durable, mirroring the service model.
* test: mini-universe end-to-end harness + scheduled GitHub Action
internal/harness/universe boots a small but real go-micro world — four
services, a durable checkout flow that crashes at payment and resumes,
and a guardrailed agent with a tool wrapper reached over RPC — drives the
scenario, asserts the end state (10 checks), and shuts down. Everything
is real except the LLM (mocked), so it's deterministic and needs no key;
-provider anthropic runs it live. Exits non-zero on failure, so it's an
end-to-end test, not just a demo.
Adds .github/workflows/universe.yml (push/PR/daily/dispatch) running the
universe + existing harnesses on the mock provider, plus an opt-in job
that runs live when ANTHROPIC_API_KEY is set. 'make harness' runs them
locally.
* ci: run the live universe job against AtlasCloud (ATLASCLOUD_API_KEY)
* ci: run the live universe job only on schedule or manual dispatch
The deterministic mock job still runs on push/PR/daily; the live
(AtlasCloud) job runs daily and on manual workflow_dispatch only, so
changes don't burn API credits on every PR but can still be checked
against a real model on demand.
---------
Co-authored-by: Claude <noreply@anthropic.com>
Restructure ai.ToolHandler to the structured, ctx-carrying shape that
mirrors a go-micro RPC handler:
func(ctx context.Context, call ai.ToolCall) ai.ToolResult
This reuses the existing ToolCall (with its correlation ID) and
ToolResult types instead of the flat (name, input)->(any, string)
signature, and adds ToolCall.Scan for typed argument access.
Add ai.ToolWrapper and the agent option WrapTool / micro.AgentWrapTool —
the tool-side analogue of client.CallWrapper and server.HandlerWrapper.
Reframe the built-in guardrails (MaxSteps, LoopLimit, ApproveTool) as
composed wrappers around a base handler; developer wrappers compose
outermost, so they observe every call and result, including refusals.
Update all provider call sites, the MCP server and chat handlers, the
integration harnesses, and docs to the new signature.
Co-authored-by: Claude <noreply@anthropic.com>
Add LoopLimit: refuse a tool call repeated with identical arguments in
one Ask, with a self-heal message so the model changes approach. Catches
the no-progress loop that MaxSteps (count) and the gateway circuit
breaker (failures) miss. Enforced at the same tool-handler choke point as
MaxSteps/ApproveTool; on by default (lenient 3); AgentLoopLimit(0) to
disable. Tests cover repeats, distinct calls, disabled, and default-on.
Docs: new Agent Guardrails guide (MaxSteps/LoopLimit/ApproveTool, the
ApproveTool integration seam for external policy engines, and the
gateway's RateLimit/CircuitBreaker), nav + README + AGENT_DESIGN updates,
and blog/23 'Agent Guardrails'.
Co-authored-by: Claude <noreply@anthropic.com>
Codex