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>
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>
Rework `micro loop` so the workflows are the mechanism and each dispatch role's
instruction is an editable .github/loop/prompts/<role>.md file (the policy).
That split lets any repo — including go-micro itself — customize behavior by
editing prompt files instead of forking the CLI, which is the prerequisite for
go-micro consuming its own tool without losing its richer prompts.
- Add two opt-in roles: `coherence` (README/docs/CHANGELOG alignment) and
`release` (cut the next patch tag on new commits; bakes in the
persist-credentials:false fix so the PAT push isn't clobbered by the
checkout token — the 403 we hit on the live release action).
- `--roles` selects which roles to scaffold (default planner,builder,triage;
`all` for everything); `--tag-prefix`, `--release-cron`, `--coherence-cron`
added. Templates keep the << >> delimiters so GHA ${{ }} passes through;
prompts leave __ISSUE__/__RUNURL__ as runtime tokens the workflow substitutes.
- `micro loop verify` now checks each present role workflow has its prompt.
- README updated with the five roles and a copy-pasteable flag example
(folds in the readability fix from the now-closed #3651).
Verified: build, `go test ./cmd/micro/loop/...`, vet, golangci-lint (0 issues),
gofmt; and an end-to-end `micro loop init --roles all` whose generated
workflows all parse as valid YAML and pass `micro loop verify`.
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
Co-authored-by: Claude <noreply@anthropic.com>
`micro loop init` writes an autonomous improvement loop into any repository —
the same planner/builder/triage loop that maintains go-micro, generalized:
- planner (loop-planner.yml): keeps a ranked queue in .github/loop/PRIORITIES.md
- builder (loop-builder.yml): builds the top open item as a single-concern PR,
auto-merged on green CI
- triage (loop-triage.yml): turns CI failures into scoped fix issues
plus .github/loop/NORTH_STAR.md (direction) and PRIORITIES.md (queue).
The agent adapter is mention-based, not hardcoded to Codex: `--agent @codex`
(or any @mention agent that responds on an issue and can run gh), `--token-secret`,
`--branch`, `--ci-workflow`, and cron flags are the whole config-vs-core boundary.
Templates use << >> delimiters so GitHub Actions' own ${{ }} expressions pass
through untouched. `micro loop verify` checks the wiring and flags the two things
the CLI can't: the token secret and branch protection (the green-CI gate).
Built inside go-micro with the config/core split already drawn, so the workflows
can later be extracted to a standalone reusable-workflows repo without a rewrite.
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
Co-authored-by: Claude <noreply@anthropic.com>
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>
Follow-up to #3006:
- provider-conformance: build each harness to a temp binary and run that
instead of 'go run'. 'go run' launches the harness as a child it doesn't
kill on context cancellation, so a timed-out harness (which starts local
services) could be orphaned and outlive the run. Running the built binary
makes the per-run timeout actually terminate the work.
- contract test: skip under -short, and use 'go build ./...' instead of
'go test ./...' (the contract is that the generated service builds). This
keeps the default unit-test suite from shelling out to the toolchain and
the network on every run.
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
Co-authored-by: Claude <noreply@anthropic.com>
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>
* docs: compare Go Micro with Google ADK in the comparison guide
Adds a 'vs Agent Frameworks (Google ADK)' section: ADK builds an agent,
Go Micro builds the distributed system the agent lives in (agents are
services in the mesh). Covers the category difference, a feature table,
when to choose each, and MCP/A2A interoperability.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
* docs: replace ADK comparison slogan with concrete explanation
State plainly what each tool provides (ADK builds an agent process; Go Micro
builds the surrounding service mesh) instead of marketing phrasing.
* lint: apply golangci-lint autofixes; exclude ST1003 and demo errcheck
Mechanical, behaviour-preserving fixes applied by 'golangci-lint run --fix':
gofmt, misspell (US spelling), usestdlibvars (http.Method*/Status*), unconvert,
and the auto-fixable staticcheck simplifications (QF*, S1017/S1019/S1023/S1039).
Config: exclude ST1003 (remaining offenders are exported API renames, e.g.
web.Id, which would break compatibility) and skip errcheck for examples/ and
internal/harness/ (demo code where fire-and-forget is intentional).
Build and test compilation verified.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
* lint: WIP cleanup checkpoint (errcheck config + partial fixes)
Checkpoint of an in-progress golangci-lint cleanup (background pass). Builds
cleanly; lint is not yet zero. Follow-up commit will complete the cleanup and
switch CI to a blocking full-tree lint.
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>
* examples: support desk agent + blog walkthrough
A real-world, runnable example (examples/support): customers/tickets/notify
services become the agent's tools, a flow turns a ticket.created event into
the agent's work, and an approval gate guards the one action that touches a
customer. Runs with no API key (mock model) or against a live provider.
Adds blog/28 'Building a Support Agent in Go' and indexes both.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
* fix(new): protoless services by default; fix @latest install (#2985)
micro new now scaffolds a reflection-based service by default — plain Go
types registered via service.Handle, no .proto, no Makefile proto target.
The generated project builds and runs with 'go run .' and zero external
tooling. Protocol Buffers move behind --proto (the crud/pubsub/api
templates imply it). When the proto workflow is used and protoc /
protoc-gen-go / protoc-gen-micro are missing, print exact install
instructions instead of failing with a cryptic plugin error.
Also fixes the 'go install go-micro.dev/v6/cmd/micro@latest' version
constraint conflict: the vanity go-import meta still advertised /v5, so Go
fell back to the bare module and resolved an ancient v1.x tag. Advertise
/v6 (keeping /v5 for existing users) and add a version-pin fallback note to
the install docs.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
* fix(new,install): pin generated go.mod to current go-micro; lead install with prebuilt binary (#2985)
- micro new now requires the exact go-micro version the CLI was built from
(via build info), falling back to 'latest' for dev builds. An explicit
require is also more robust than a bare import: 'go mod tidy' reliably
resolves it, where a requireless go.mod could fail vanity discovery.
- Make the precompiled binary (curl install.sh) the recommended install in
the docs; demote 'go install' to a from-source option with the version-pin
fallback note.
- Sync the stale internal/scripts/install.sh to the working website script
(it expected an old micro-OS-ARCH asset name; releases ship
micro_OS_ARCH.tar.gz).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
* website: add corrected nginx vanity-import config (#2985)
The live go-micro.dev handler echoed the full request path into the
go-import prefix ($host$1), so go install go-micro.dev/v6/cmd/micro@latest
got prefix go-micro.dev/v6/cmd/micro — a package, not the module root — and
Go fell back to the ancient v1.x tags (version constraints conflict).
Add a dedicated /vN location that emits the module root (go-micro.dev/vN)
for any sub-path, and make the catch-all advertise the current module roots
instead of echoing arbitrary paths.
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>
* 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>
* feat(agent): tool-execution wrappers via WrapTool
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.
* examples: add agent-wrap-tool showing AgentWrapTool
A runnable example of tool-execution middleware: an observe wrapper that
times calls and records per-tool metrics (correlated by call ID), and a
retry wrapper that recovers a flaky service call before the model sees
it. Demonstrates outermost-first composition and the wrapper/guardrail
interaction (retries are seen by loop detection).
* docs: note AgentWrapTool in README capabilities and CHANGELOG
* fix(generate): pin scaffolded go.mod to one version constant
The two generators pinned different, stale go-micro versions (v5.24.0
for services, v5.25.0 for agents). Centralize on a single
goMicroVersion constant (v5.29.0) so generated services and agents stay
in sync with the framework and there's one place to bump on release.
---------
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>
Follow-up to the merged x402 integration (#2964). Drop the commerce-y
'price' vocabulary for the protocol's own 'amount', and add per-tool
pricing as an operator concern (the way scopes/rate-limits are set at the
gateway).
- x402.Config: Price -> Amount (default), plus Amounts map for per-tool
overrides; AmountFor(tool) resolves per-tool -> default. Add a Require
primitive (per-request enforcement) and LoadConfig for an operator
config file.
- MCP gateway: enforce payment per-tool inside /mcp/call (where scopes
are enforced) using AmountFor, instead of a flat path-based middleware.
- CLI: --x402-price -> --x402-amount; add --x402-config (per-tool file)
to micro mcp serve and micro-mcp-gateway.
- docs: new Payments (x402) guide + nav + README section; blog/22
updated to Amount/Amounts and the config-file model.
Co-authored-by: Claude <noreply@anthropic.com>
Integrate the x402 payment protocol (HTTP 402) so a tool can require a
stablecoin payment and an agent can settle it — the next step after
autonomous agents (blog 21): agents that act, and pay.
- wrapper/x402: HTTP middleware enforcing the 402 challenge/verify flow,
with a pluggable Facilitator interface. Go Micro carries no chain or
crypto code — verification/settlement is delegated to a facilitator
(Coinbase CDP, Alchemy, self-hosted), so Base and Solana are just
different facilitators behind one interface. HTTPFacilitator default;
tests cover challenge / accept / reject via a mock facilitator.
- MCP gateway: optional Options.Payment gates /mcp/call (listing tools
and health stay free); off unless configured.
- micro mcp serve and micro-mcp-gateway: opt-in --x402-pay-to/-price/
-network/-facilitator flags (env vars on the standalone binary).
- blog/22 'Integrating x402: Payments for Agents'; README feature row.
Pricing is flat per call for now; richer models and an agent-side spend
cap (next to MaxSteps/ApproveTool) are follow-ups.
Co-authored-by: Claude <noreply@anthropic.com>
* feat: add plan and delegate as built-in agent tools
Give agents two self-capabilities, expressed as plain tools wired into
the existing tool handler — no harness or graph, consistent with
"services are the only abstraction":
- plan: record/update an ordered plan, persisted to store-backed memory
and surfaced in the system prompt on later turns (externalized
planning).
- delegate: hand a self-contained subtask to another agent.
Delegate-first — if the target names a registered agent it is called
via RPC; otherwise a focused ephemeral sub-agent is created with
agent.New + Ask in a fresh, isolated context (loads/persists no
history, no built-in tools, so it cannot re-delegate).
Both are added automatically to any non-ephemeral agent, so existing
micro.NewAgent services and micro chat routing get them for free.
Tests are hermetic (memory store + memory registry).
* feat: add agent-plan-delegate example and document plan/delegate
- examples/agent-plan-delegate: coordinator that plans multi-step work,
creates tasks with its own tools, and delegates notification to a
separate registered comms agent over RPC.
- integration tests driving the full Ask loop through a fake provider:
plan tool exposure + persistence, ephemeral delegation with isolated
context, delegate-first RPC routing to a registered agent.
- docs: README (Building Agents + features + examples), AGENT_DESIGN
(Built-in Capabilities), agent-patterns guide (Pattern 9), CLAUDE.md.
* docs: blog post and guide for plan & delegate
- blog/17: "Plan & Delegate: Deep Agents in Go" — what the feature is,
how plan and delegate work, and a runnable getting-started path.
- guides/plan-delegate: reference guide with the smallest-agent snippet,
plan/delegate semantics, and the multi-agent example; linked in nav.
- example: auto-detect provider/key from common env vars (ANTHROPIC_API_KEY,
OPENAI_API_KEY, ...) so 'export KEY && go run main.go' just works.
- onboarding: getting-started paths now include go mod init / go get and a
clone-and-run path, so a reader can actually run it from a cold start.
* refactor: reframe plan/delegate blog and clean up sub-agent construction
- blog/17 retitled "Agents That Plan and Delegate" and reframed around
intent (plan = state intent, delegate = direct it), positioned as the
next beat after blog 15/16 and tied to the existing store + agent RPC
rather than re-announcing them. "Deep agents" now a single in-passing
nod, matching how blog 14 references LangChain.
- agent: add unexported newEphemeral constructor for sub-agents instead
of type-asserting the public Agent interface to set an internal field;
matches the options-only construction idiom used elsewhere.
* feat: expose plan & delegate in the micro chat fallback
Add agent.Builtins(opts...) — returns the built-in tools plus a handler,
so the plan/delegate capabilities can be wired into a tool loop that
isn't a running Agent. micro chat's direct-service fallback now reuses
it (single source of truth, no duplicated handler logic), so planning
and delegation are available there too, not just for registered agents.
Adds a test for the accessor; notes CLI availability in the guide.
---------
Co-authored-by: Claude <noreply@anthropic.com>
Run Tests / Etcd Integration Tests (push) Has been cancelled
goreleaser / goreleaser (push) Has been cancelled
* perf: compress hero image — 1.4MB to 80KB
Resized from 1536px to 1200px, converted to JPEG at quality 80.
80KB loads instantly vs 1.4MB stalling on slower connections.
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
* docs: micro run drops into interactive console
One command does everything — generate, start, and chat. No
separate micro chat step. The landing page shows micro run
dropping straight into the > prompt.
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
* feat: interactive console in micro run, -d for detached mode
micro run now drops into an interactive chat console after services
start. The console discovers services, exposes them as tools, and
lets you talk to them through an LLM — same as micro chat but
built into the run experience.
- Detects MICRO_AI_PROVIDER and MICRO_AI_API_KEY from environment
- Falls back to provider-specific env vars (ANTHROPIC_API_KEY, etc.)
- If no API key, prints hint and blocks on Ctrl-C (no console)
- -d / --detach flag skips the console (background mode)
- Ctrl-C always shuts everything down
Removed adopters section from README.
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
---------
Co-authored-by: Claude <noreply@anthropic.com>
* docs: remove code references from landing page feature grid
Landing page describes concepts, not APIs. Removed micro.NewAgent()
and micro.NewFlow() code references. Features described in plain
language — what they do, not how to code them.
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
* fix: update micro flow CLI to import from go-micro.dev/v5/flow
The flow package moved to top-level but the CLI still imported
from the old ai/flow path. Fixed to use go-micro.dev/v5/flow.
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
---------
Co-authored-by: Claude <noreply@anthropic.com>
* docs: Agent interface design sketch
Proposes Agent as a top-level abstraction alongside Service in the
micro package. Agent manages services — scoped tools, system prompt,
conversation memory, registry-discoverable.
Design only, no implementation.
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
* feat: Agent as a first-class abstraction
Introduce micro.NewAgent() alongside micro.New() — Agent is to
intelligence what Service is to capability.
Agent interface:
- Chat(ctx, message) (*Response, error) — core interaction method
- Run() — registers in registry, subscribes to broker, blocks
- Stop() — graceful shutdown
- Scoped tools — only sees endpoints of its assigned services
- Persistent memory — conversation history stored in store
- Agent-to-agent — communication via broker topics
Top-level API:
agent := micro.NewAgent("task-mgr",
micro.AgentServices("task"),
micro.AgentPrompt("You manage tasks."),
micro.AgentProvider("anthropic"),
)
agent.Run()
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
* feat: wire agents into chat router, add micro agent CLI, expose Flow
Three top-level abstractions:
micro.New("task") — Service (capability)
micro.NewAgent("task-mgr") — Agent (intelligence)
micro.NewFlow("onboard-user") — Flow (event-driven orchestration)
micro chat as router:
- Discovers agents from registry on startup
- Single agent: routes directly
- Multiple agents: LLM classifies intent, dispatches to right agent
via route_to_agent tool
- No agents: falls back to current direct-service behaviour
- Banner shows discovered agents
micro agent CLI:
- micro agent list — shows registered agents and their services
- micro agent describe <name> — shows agent details from registry
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
* feat: move flow to top level, update docs for three abstractions
Package structure now consistent:
service/ — Service (capability)
agent/ — Agent (intelligence)
flow/ — Flow (event-driven orchestration)
ai/flow/ kept as backward-compatible re-export.
Updated across all surfaces:
- CLAUDE.md: added agent/ and flow/ to project structure
- README: added "Building Agents" section with NewAgent() examples,
updated features table (Agents, Flows, Chat router), CLI table
(agent list, agent describe), docs links
- Website: features grid shows Services, Agents, Flows as the three
pillars alongside generation, MCP, and pluggable architecture
- micro.go: Flow imported from top-level flow/ package
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
* docs: rewrite getting-started, fix ai-integration import paths
Getting started now covers all three abstractions:
- Service (write handlers, micro run, templates)
- Agent (micro.NewAgent, scoped tools, memory, CLI)
- Flow (event-driven LLM orchestration)
Leads with prompt-based generation, then manual service creation.
ai-integration.md: fixed flow import path from go-micro.dev/v5/ai/flow
to go-micro.dev/v5/flow, updated stack diagram to show agent/flow/chat.
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
* blog: Introducing micro.NewAgent()
Post 16 — announces Agent as a first-class abstraction. Shows the
API (NewAgent, AgentServices, AgentPrompt, AgentProvider), scoped
tools, persistent memory, multi-service agents, multi-agent systems,
and the three-abstraction comparison table (Service/Agent/Flow).
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
* feat: fix agent registration, blog post 16
Agent registration:
- Add node with address so mDNS can discover agents
- Store type and services in node metadata (mDNS requirement)
- Connect broker before subscribing, non-fatal if broker unavailable
- Print registration confirmation on Run()
Agent/chat discovery:
- Check both service-level and node-level metadata for type=agent
(mDNS stores metadata on nodes, not services)
Blog post 16: "Introducing micro.NewAgent()" — announces the Agent
abstraction with code examples, comparison table, multi-agent patterns.
Tested end-to-end: micro run → micro agent list discovers the agent →
micro chat routes to it → agent calls service endpoints.
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
* feat: agents are proper services with RPC Chat endpoint
Refactored agent to use server.Server instead of fake registry entries.
An agent now:
- Creates a real RPC server with server.Name(agentName)
- Registers an Agent.Chat handler callable via standard RPC
- Sets server metadata type=agent, services=x,y for discovery
- No more fake addresses or broker hacks
micro chat calls agents via RPC (client.Call) instead of creating
local agent instances. The registry stays clean — agents are real
services with real endpoints.
Removed broker dependency from agent options. Agent-to-agent
communication is just RPC like everything else.
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
* feat: agent uses proto-defined RPC interface
Added agent/proto/agent.proto with Agent service definition:
rpc Chat(ChatRequest) returns (ChatResponse)
Agent now implements the generated AgentHandler interface and
registers via pb.RegisterAgentHandler. The Chat endpoint is a
standard proto-based RPC callable by any go-micro client.
Renamed the programmatic API from Chat() to Ask() to avoid
collision with the proto handler method name.
micro chat calls agents via standard RPC with JSON-encoded
request/response — no special types needed on the caller side.
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
* feat: generate agent alongside services, update all docs
micro run --prompt now generates an agent binary that manages all
the generated services. The agent reads MICRO_AI_PROVIDER and
MICRO_AI_API_KEY from the environment. micro run propagates these
when started with --prompt.
Run banner shows services and agents separately.
Updated README, getting-started guide, and landing page to show
the complete flow: generate → services + agent start → micro chat
routes to agent → agent orchestrates services.
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
---------
Co-authored-by: Claude <noreply@anthropic.com>
* feat: add micro new --prompt and micro run --prompt
Add AI-powered service generation: describe a system in natural
language and get real go-micro services with proto definitions,
handlers, doc comments, and MCP support.
micro new --prompt "a contact book with notes and tags" \
--provider anthropic
Generates:
contacts/ — CRUD service with name, email, phone fields
notes/ — notes linked to contacts
tags/ — tagging system
Each service gets:
proto/{name}.proto — domain model + CRUD endpoints
handler/{name}.go — in-memory store, @example tags for MCP
main.go — MCP-enabled, proper imports
go.mod + Makefile — compiles with go mod tidy + make proto
micro run --prompt does the same then starts all services.
The LLM designs the architecture (service names, fields, endpoints,
descriptions) and returns structured JSON. Code generation uses
the existing template patterns — the output is standard go-micro
code that compiles, runs, and is immediately callable via MCP
and micro chat. No AI dependency at runtime.
* feat: LLM generates real business logic with compile-fix loop
Rebuild the generate package so the LLM writes actual handler
code with business logic, not just CRUD scaffolding.
The flow is now:
1. LLM designs architecture (service names, fields, endpoints)
→ returns structured JSON
2. Proto, main.go, go.mod, Makefile generated deterministically
from the design (guaranteed to be correct)
3. go mod tidy + make proto compiles the protos
4. LLM generates handler code with REAL business logic
→ given the proto, endpoint descriptions, and go-micro patterns
5. go build — does it compile?
6. If no: feed errors back to LLM, get fixed code (up to 3 attempts)
7. If yes: service is ready
The handler prompt instructs the LLM to:
- Use sync.RWMutex for thread-safe in-memory state
- Include validation, edge cases, meaningful errors
- Write doc comments with @example tags for MCP
- Implement actual domain logic, not just map operations
Proto generation still uses deterministic templates (CRUD +
custom endpoints from the design spec) to guarantee correctness.
The compile-fix loop catches LLM mistakes automatically.
Both micro new --prompt and micro run --prompt use this flow.
* fix: handle edge cases in prompt-based generation
- Fix PATH for protoc-gen-micro in child processes
- Handle existing directories: skip structural files (main.go,
go.mod, Makefile) if dir exists, always regenerate proto,
only write placeholder handler if none exists
- Allow re-running micro new --prompt on same directory to
iterate on business logic without clobbering user edits
Tested end-to-end: "a simple todo list with tasks and categories"
generates 2 services (task-service, category-service) with real
business logic (validation, toggle complete, etc.), compiles
after 1 fix iteration, and runs with 6 MCP tools discovered.
* feat: auto-detect modified handlers on regeneration
Instead of requiring a --keep-handlers flag, the generate package now
tracks a SHA-256 hash of each generated handler in a .micro metadata
file. On re-run, if the user has edited the handler since generation,
it's left untouched. Unmodified handlers are regenerated normally.
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
* feat: add tests, fix go.mod, gitignore, proto tracking, spinner
- Add 12 tests covering helpers, proto generation, hash tracking
- Fix go.mod: write minimal module file, let go mod tidy resolve deps
- Add .gitignore to prompt-generated services
- Protect user-edited proto files (same hash tracking as handlers)
- Add spinner during LLM calls so it doesn't look hung
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
* feat: signal handling, existing service discovery, help text
- Ctrl+C during generation now cancels LLM calls immediately via
signal-aware context; re-run picks up where it left off
- Design() scans for existing services in the working directory and
includes their proto definitions in the prompt, so the LLM extends
the system rather than redesigning from scratch
- Updated --prompt help text with usage examples on both new and run
- Listed all supported providers in flag descriptions
- Added discoverExisting test
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
* feat: show endpoints in run --prompt output, add micro chat hint
Print endpoint names and descriptions when designing services so users
see what was built. Add a micro chat hint to the run banner so users
know how to interact with their services after startup.
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
* fix: generated go.mod uses go 1.24 with explicit go-micro require
go 1.22 with no explicit require caused Go to resolve sub-packages
(gateway/mcp, client, server) as separate modules, hitting stale v1.18
tags. Pin to go 1.24 + require go-micro.dev/v5 v5.24.0 so go mod tidy
resolves all sub-packages from the root module correctly.
Tested end-to-end: 4 services generated and compiled successfully.
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
* fix: skip handler regeneration when proto unchanged
Compare proto hash before and after structure generation. If the proto
didn't change and the handler wasn't edited by the user, skip go mod
tidy, make proto, LLM handler generation, and compile-fix entirely.
Prints "(unchanged)" instead.
Reduces re-run of 4-service project from ~2 minutes to ~10 seconds.
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
* feat: confirm design before generating code
Show the service design (names, endpoints) and prompt "Generate? [Y/n]"
before spending LLM time on handler generation. Applies to both
micro new --prompt and micro run --prompt. Default is yes (enter).
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
* fix: use port :0 for MCP in generated multi-service projects
Each generated service had mcp.WithMCP(":3001") hardcoded, causing
port conflicts when running multiple services. Use :0 to auto-assign
a free port. micro run's central gateway handles unified MCP access.
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
* feat: truncation detection, tool result display in chat
- Detect truncated LLM responses (unbalanced braces, doesn't end
with '}') and retry with a conciseness hint before falling through
to compile-fix
- Show tool call results in micro chat output (← for success, ✗ for
errors) so users can see what the LLM did
- Add Result/Error fields to ToolCall, populated by Anthropic provider
after tool execution
- Add isTruncated tests
Tested end-to-end with Anthropic: services generate, compile, start,
register, respond to RPC calls, and micro chat discovers and calls
tools correctly.
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
* fix: Anthropic tool loop, service naming, chat tool results
Anthropic provider:
- Fix tool execution loop to properly iterate (was re-processing all
tool calls instead of only new ones each round)
- Clean assistant content blocks before sending back (strip 'id' from
text blocks that Anthropic rejects on input)
- Include tools in follow-up requests so model can make additional calls
- Loop up to 10 rounds until model responds with text only
Service naming:
- Strip '-service' suffix from micro.New() name so services register
as 'task', 'category' instead of 'taskservice', 'categoryservice'
Chat:
- Show tool results (← for success) and errors (✗) in chat output
Tested end-to-end: create task → list tasks works as multi-step
orchestration through micro chat with Anthropic Claude.
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
* feat: blog post 13 — from prompt to production
Covers the full micro run --prompt flow: design, generate, compile-fix,
run, and chat orchestration. Positions agent-as-orchestrator as the
answer to service coordination.
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
* fix: timeouts, max_tokens, TTY detection, smaller services
- Add 60s timeout on design, 90s on handler generation, 60s on
compile-fix LLM calls so hung providers don't block forever
- Bump Anthropic max_tokens from 4096 to 8192 to reduce truncation
- Add TTY detection: spinner prints static message in non-TTY (CI/pipes)
instead of ANSI escape codes
- Tighten prompts: max 200 lines per handler, 2-4 services, 5-8 fields,
explicit "services don't call each other" rule
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
* feat: chat suggests creating services when capabilities are missing
Update system prompt with the list of available services. When the user
asks for something no existing service can handle, the agent explains
what's available and suggests the exact micro new --prompt command to
create the missing service.
This is the natural evolution path: start with a few services, talk to
them via chat, and when the domain grows, the agent tells you what to
add. Each service stays small and focused.
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
* feat: chat generates and starts services inline, drop -service suffix
Chat agent now has a micro_generate_service tool. When the user asks
for a capability that doesn't exist, the agent generates the service,
compiles it, starts it as a background process, waits for registration,
re-discovers tools, and uses the new endpoints immediately — all within
the conversation.
Service naming: design prompt now instructs LLM to return names without
'-service' suffix (e.g. 'task' not 'task-service'). buildMain keeps
TrimSuffix as safety net for backward compatibility.
Spawned processes are cleaned up when chat exits.
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
* docs: rewrite blog post 13 with inline service generation
Updated to reflect the full UX: services generate and start within
the chat conversation. Added the shipping example showing the agent
creating a service mid-conversation. Removed -service suffix from
all examples. Tightened the narrative around agent-as-orchestrator.
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
* feat: persistent storage, README quickstart, auto-detect new services
Storage: generated handlers now use go-micro's store package instead
of in-memory maps. Data persists across restarts. The handler prompt
includes store API examples so the LLM generates correct store usage.
README: added "Generate From a Prompt" section with micro run --prompt
and micro chat examples, linking to blog post 13.
Watcher: micro run now scans for new service directories every 5s. When
micro chat generates a service, micro run detects the new directory,
builds it, starts it, and adds it to the watcher — fully automatic.
Added AddDir/Dirs methods to the watcher.
Blog: updated post 13 with persistent storage example and watcher note.
https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd
---------
Co-authored-by: Claude <noreply@anthropic.com>
* feat: expose framework primitives via API gateway and MCP
Add registry, store, and broker as both HTTP routes and MCP tools
so AI agents and HTTP clients can inspect and operate the framework.
API gateway (/micro/* namespace):
GET /micro/registry List registered services
GET /micro/registry/{name} Describe a service
GET /micro/store List store keys
GET /micro/store/{key} Read a record
POST /micro/store/{key} Write a record
POST /micro/broker/{topic} Publish a message
MCP gateway (micro_* tool prefix):
micro_registry_list List services
micro_registry_get Describe a service
micro_store_list List keys
micro_store_read Read a record
micro_store_write Write a record
micro_broker_publish Publish a message
Framework tools use a Handler field on the MCP Tool struct for
direct dispatch (no RPC). Service tools continue to use RPC.
Rate limiters and circuit breakers are applied to framework
tools the same as service tools.
* fix: make framework internals opt-in on API and MCP gateways
Framework primitives (registry, broker, store) are now only
exposed when explicitly enabled:
API gateway: micro api --internal
MCP gateway: Options{Internal: true}
Off by default — user services are always exposed, framework
internals require the flag. Banner output only shows framework
routes when enabled.
* fix: always expose framework internals, gate by auth in production
Revert the --internal flag approach. Framework primitives (registry,
broker, store) are now always exposed:
- micro api: /micro/* routes always available (dev tool)
- MCP gateway: micro_* tools always registered. When Auth is
configured (production), they require micro:admin scope.
Without Auth (dev), they're open — same as all other tools.
This follows the existing pattern: micro run/api = dev (open),
micro server = production (auth + scopes). Framework internals
follow the same security model as user services.
Remove the Internal option from MCP Options. Remove --internal
flag from micro api.
Note: scope persistence depends on the store backend. The default
in-memory store does not survive restarts. Use MICRO_STORE=file
for persistent scopes in production.
* fix: correct DefaultStore comment — it's file-backed, not memory
* fix(server): don't recreate deleted admin user on restart
When the default admin account is deleted via the dashboard, set
a marker key (auth/.admin-deleted) in the store. On startup, skip
admin creation if the marker exists. This prevents the default
admin/micro credentials from reappearing after restart when the
user has intentionally removed them.
* fix: improve agent playground first-run UX and fix doc 404s
Agent playground:
- Add setup hint in empty state explaining how to get started
(click Settings, enter API key, type a prompt)
- Hide hint automatically when API key is already configured
- Add all 7 providers to dropdown (was only OpenAI + Anthropic)
- Include CLI fallback suggestion (micro chat)
Docs:
- Fix .md links to .html across all doc pages — Jekyll serves
.html files, not .md. Fixes 404s including the micro run guide.
---------
Co-authored-by: Claude <noreply@anthropic.com>
Asim Aslam