* blog+docs: drop the word "bet" from the tRPC-Agent-Go comparison
Reword "two bets" / "opposite bet" / "the bet is" to approaches / premise /
principle across blog/32 and the comparison guide.
* blog: expand /blog/32 into a field guide on agent frameworks
Roughly double the length with deeper context: the first wave (LangChain &
co.), the two layers of a harness (intra-agent vs operational), loop
engineering and the move to scheduled/looping/work-performing agents, a
survey of where the frameworks are going (LangGraph, CrewAI, AutoGen, ADK,
tRPC-Agent-Go), then Go Micro's "an agent is a service" position, the honest
tRPC-Agent-Go contrast, and MCP/A2A interop. Drops the word "bet" throughout.
---------
Co-authored-by: Claude <noreply@anthropic.com>
Add a fair, honest positioning piece on the architectural fork with
tRPC-Agent-Go (an agent SDK alongside your services / graph DSL) vs Go Micro
(one runtime where an agent is a service, every endpoint a tool, durable
flows not a graph DSL). New blog post /blog/32 + a parallel section in the
existing comparison guide; honest about where tRPC-Agent-Go is ahead
(eval, self-evolution, RAG) and that they interoperate over MCP/A2A.
Co-authored-by: Claude <noreply@anthropic.com>
* loop: establish the continuous-improvement charter + scheduled backbone
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.
* docs: mark harness Resilience as shipped
Resilience (per-call timeout + context propagation + opt-in retry/backoff)
landed in #3017/#3021; update the agent-harness status table from
'In progress' to 'Shipped'.
---------
Co-authored-by: Claude <noreply@anthropic.com>
- Add the canonical concept doc 'The Agent Harness' (docs/guides/agent-harness.md)
+ nav entry: what the harness is, each piece mapped to a feature, honest
about shipped vs in-progress.
- Add blog post /blog/30 'Go Micro is an Agent Harness' (the public articulation;
precise about what ships today vs the Now/Next roadmap).
- Align the ROADMAP.md opening line to the agent-harness framing.
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
Co-authored-by: Claude <noreply@anthropic.com>
Adds the agentic 'loop' to flows: flow.Loop(body, opts...) is a StepFunc
that runs a body step repeatedly, carrying State across passes, until a
stop condition fires or a hard iteration cap is reached.
- Stop modes: flow.Until (code-defined predicate) and flow.UntilLLM (the
model judges the goal met after each pass — the supervised 'Ralph'
loop). Either firing stops the loop.
- flow.LoopMax is the guardrail: the body never runs more than n times, so
the loop always terminates and can't run up an unbounded bill. Hitting
the cap returns the latest state rather than erroring.
- flow.OnIteration reports per-pass progress.
- Composes as a normal flow step (checkpointed by the step engine).
- Exposed at the top level as micro.FlowLoop / FlowUntil / FlowUntilLLM /
FlowLoopMax / FlowOnIteration, symmetric with the other Flow* helpers.
Includes tests, an offline runnable example (examples/flow-loop), an
'Agent Loops' guide, and a CHANGELOG entry.
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.
---------
Co-authored-by: Claude <noreply@anthropic.com>
Plain 'go install go-micro.dev/v6/cmd/micro@latest' fails on the public
module proxy with a version-constraints conflict: the proxy has cached the
sub-paths go-micro.dev/v6/cmd and .../cmd/micro as standalone v0/v1 modules
(from old github.com/micro/go-micro tags, surfaced during an earlier vanity
meta bug), so @latest resolves to v1.18.0 with a mismatched module path.
A version-prefix query (@v6) sidesteps it: those cached sub-path modules
have no v6.x.x versions, so Go falls back to the go-micro.dev/v6 root
module and builds correctly. Verified against proxy.golang.org.
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
Co-authored-by: Claude <noreply@anthropic.com>
Closes the remaining ask in #2980 without adding a parallel callback API.
ToolResult.Refused tags a guardrail block with a reason (ai.RefusedLoop /
RefusedMaxSteps / RefusedApproval) so a wrapper can switch on it instead of
parsing the message. ai.RunInfo (RunID, ParentID, Agent) rides on the
context passed to the tool handler, giving wrappers run correlation and
delegation lineage. Before/after/retry/failure were already covered by
AgentWrapTool; this adds the metadata. Docs + tests included.
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>
Refactor the A2A handler into a reusable dispatcher + Invoke seam and
expose NewAgentHandler(card, invoke) + Card(). An agent now serves its
own A2A endpoint with AgentA2A(addr) / WithA2A — handling tasks
in-process (no RPC hop, no separate gateway). The gateway and embedded
agent share the same handler; the only difference is RPC vs in-process
invocation. Docs, README, and changelog cover both deployment modes.
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>
* feat(mcp): advertise x402 payment requirements in the tool catalog
/mcp/tools now includes each priced tool's payment requirements (amount,
network, asset, payTo) when payments are enabled, so an agent can see the
cost before calling and choose by price — a shoppable catalog, the
foundation for a tool marketplace. Free tools carry no payment block; the
shared Tool struct is copied when pricing so it isn't mutated. Tests cover
priced/free tools and payments-disabled. Documented in the payments guide.
* feat(x402): consumer client with a spend budget (pay-and-retry)
Add x402.Client, the consumer counterpart to Middleware: it settles 402
challenges automatically via a pluggable Payer, up to a spend Budget. A
call that would exceed the budget is refused before any payment is made,
and spend accumulates across calls — the spend cap that keeps an
autonomous, paying caller in bounds. Tests cover pay-within-budget,
refuse-over-budget, budget accumulation, and free endpoints, end to end
against the server Middleware with a mock facilitator and payer. Guide
documents the consumer side; agent-level AgentMaxSpend is the next step.
* chore: gofmt gateway/mcp/benchmark_test.go (trailing newline)
---------
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>
A go-micro service can keep running while it has silently lost its
connection to the registry (etcd, Consul, …) — the process looks healthy
but other services can no longer discover it, and Kubernetes sees the
pod as fine. health.RegistryCheck(reg) probes connectivity via
ListServices and, registered as a critical check, makes /health/ready
report not-ready so a readiness probe can pull the pod from rotation.
- Works with any registry implementation (no interface change).
- Honors the check timeout: an unreachable/hung registry is reported
down rather than blocking the probe.
- Tests cover healthy, down, timeout, nil, and the not-ready integration.
- Documented in the health guide with the Kubernetes readiness example.
Co-authored-by: Claude <noreply@anthropic.com>
* docs: group README features by section (AI / Framework / DX)
The features table repeated 'AI' down the Category column. Split into
three grouped tables — AI, Framework, Developer experience & deployment —
dropping the repetitive column. Adds a Guardrails row (MaxSteps,
ApproveTool).
* test: flow-to-agent end-to-end in the harness
Proves 'Flow triggers, Agent reasons': a workflow with FlowAgent hands an
event to the registered conductor agent over RPC, which plans, creates
tasks, and delegates to comms — the whole chain over real RPC with only
the LLM mocked. Deterministic (shared in-memory registry, no sleeps),
passes under -race.
* blog: 'The Evolution of Microservices' (#19)
A technical history of distributed-systems eras — the monolith's
coordination cost, the distributed-systems tax, containers and
declarative orchestration, the service mesh, and the modular-monolith
correction — establishing the durable unit (named, typed, discoverable,
independently deployable) that every runtime wave required. Then the
technical argument for agents: an LLM tool call needs exactly a service
interface, so the caller shifts from deterministic code to a reasoner
that composes typed capabilities from intent, with the honest caveats
(non-determinism, cost, guardrails). Not a product pitch.
* docs: bump install version to v5.27.0
---------
Co-authored-by: Claude <noreply@anthropic.com>
* docs: group README features by section (AI / Framework / DX)
The features table repeated 'AI' down the Category column. Split into
three grouped tables — AI, Framework, Developer experience & deployment —
dropping the repetitive column. Adds a Guardrails row (MaxSteps,
ApproveTool).
* test: flow-to-agent end-to-end in the harness
Proves 'Flow triggers, Agent reasons': a workflow with FlowAgent hands an
event to the registered conductor agent over RPC, which plans, creates
tasks, and delegates to comms — the whole chain over real RPC with only
the LLM mocked. Deterministic (shared in-memory registry, no sleeps),
passes under -race.
* blog: 'The Evolution of Microservices' (#19)
A technical history of distributed-systems eras — the monolith's
coordination cost, the distributed-systems tax, containers and
declarative orchestration, the service mesh, and the modular-monolith
correction — establishing the durable unit (named, typed, discoverable,
independently deployable) that every runtime wave required. Then the
technical argument for agents: an LLM tool call needs exactly a service
interface, so the caller shifts from deterministic code to a reasoner
that composes typed capabilities from intent, with the honest caveats
(non-determinism, cost, guardrails). Not a product pitch.
---------
Co-authored-by: Claude <noreply@anthropic.com>
* blog: 'Not Everything Should Be an Agent' (#18) on workflows
The workflow counterpart to the plan/delegate post: when the path is
known, use a deterministic Flow, not an autonomous agent. Frames flow vs
agent as two modes of the same building blocks, covers flow-triggers-
agent dispatch and the agent guardrails, and gives the simplest-first
guidance (single call -> workflow -> agent). Continues the arc from
blog 14/16/17; references Building Effective Agents in passing.
* docs: fix new-user onboarding friction
- README: lead Quick Start with a no-key 30-second path (micro new ->
micro run -> curl), then the AI --prompt path with an explicit
'export ANTHROPIC_API_KEY' so the headline command no longer fails
silently for users without a key.
- Unify all install versions to v5.26.0 (README + docs were split across
v5.16.0 / v5.25.0).
- Refresh the docs landing overview from the old 'microservices
framework' framing to 'services and agents', matching the README.
- getting-started: add Prerequisites (Go 1.21+, and that a provider key
is only needed for AI features).
- README features: Flows -> Workflows wording.
---------
Co-authored-by: Claude <noreply@anthropic.com>
* docs: map go-micro onto Anthropic's workflows-vs-agents taxonomy
- new guide 'Agents and Workflows': adopts Anthropic's Building Effective
Agents vocabulary — workflow (predefined path) = flow, agent (dynamic
self-direction) = agent — maps the augmented-LLM building block and the
five workflow patterns onto go-micro, and shows routing (chat router)
and orchestrator-workers (conductor + plan/delegate) are already native.
- flow package doc reframed as a workflow (predefined path) per the same
taxonomy, with guidance on flow vs agent.
- nav + README link the new guide.
* feat: agent guardrails — step limit and tool approval hook
Anthropic's Building Effective Agents stresses stopping conditions and
human-in-the-loop checkpoints for autonomous agents. Add both as plain
options enforced at the tool-handler choke point — no provider changes,
no new abstraction:
- MaxSteps(n): bound tool executions per Ask; beyond the limit, actions
are refused and the model is told to stop and summarize.
- ApproveTool(fn): gate each action before it runs; returning false
blocks it and surfaces the reason to the model. The internal plan tool
is never gated.
Exposed at the micro package (AgentMaxSteps, AgentApproveTool, ApproveFunc).
Tests cover the limit, blocking, and that plan is not gated. Guardrails
section of the agents-and-workflows guide updated from 'active work' to
documented options.
* feat: flow can dispatch to an agent (flow triggers, agent reasons)
Unify the engine without collapsing the workflow/agent distinction. A
Flow with Agent set hands each event's rendered prompt to a named
registered agent over RPC (Agent.Chat) instead of running its own LLM
step — so the workflow stays the deterministic trigger and the agent is
the reasoning engine, with its plan, delegate, memory, and guardrails.
A plain flow is unchanged (single augmented-LLM step).
- flow.Agent(name) / micro.FlowAgent(name); flow stores the client and
skips model setup when dispatching.
- test: dispatch routes to comms.Agent.Chat with the rendered prompt and
records the reply.
- guide: 'Flow triggers, Agent reasons' section.
---------
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>
Codex