* ai/minimax: complete provider surface (matrix, conformance, changelog)
Follow-up after merging the MiniMax provider (#3769), mirroring the Ollama
completeness pass (#3637):
- Add the `minimax` row to the AI provider capability matrix and blank-import
ai/minimax in provider_capabilities_test.go so the matrix stays enforced
against the registry.
- Add minimax to the stream-conformance allowlist (+ import) so its streaming
is actually exercised against the OpenAI-compatible SSE contract, not just
registered. It passes via the shared ai/internal/openaiapi path.
- Record the provider in CHANGELOG [Unreleased].
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
* ai: update capabilities_test provider assertions for minimax
Adding the minimax blank-import to the shared ai_test binary (for stream
conformance) also registers it for TestRegisteredProviders / TestCapabilityRows
/ TestCapabilityMatrix in capabilities_test.go, which pin the exact provider
set. Update those assertions to include minimax. (Fixes the Unit Tests failure
my scoped `-run TestStreamProviders` check missed — go compiles all _test.go in
a package into one binary.)
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>
Follow-up cleanup after merging the Ollama provider (#3636):
- Add the `ollama` row to the AI provider capability matrix in the provider
guide, and blank-import `ai/ollama` in provider_capabilities_test.go so the
matrix stays enforced against the registry (the provider registers a stream
but wasn't imported in that test, so its row went unchecked).
- README: bump "7 LLM providers" → 8 and list Ollama (local + cloud); add its
default model (`llama3.2`) to the model table.
- Fix a fictional model name shipped in the example and package doc:
`gemma4:31b-cloud` → `gpt-oss:120b`. gemma4 doesn't exist, and the `-cloud`
suffix is for cloud models proxied through a local Ollama, not the direct
ollama.com/v1 endpoint the example uses.
- Record the provider and the new agent.BaseURL/micro.AgentBaseURL option in
the CHANGELOG [Unreleased] section.
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
Co-authored-by: Claude <noreply@anthropic.com>
Add a dedicated Ollama AI provider (ai/ollama/) that auto-detects
local vs cloud mode based on the base URL:
- Local Ollama: native /api/chat endpoint with NDJSON streaming
- Ollama Cloud: OpenAI-compatible /v1/chat/completions with SSE streaming
Both modes support tool calls with a multi-round execution loop.
Add agent.BaseURL option so agents can point at non-default LLM
endpoints (e.g. local Ollama, proxies). Wire it through micro.AgentBaseURL
at the top level.
Include a complete example (examples/agent-ollama/) demonstrating a
knowledge-base service with auto-discovered tools, a custom time tool,
streaming, and env-var configuration for local vs cloud.
Closes#3632
* atlascloud: env-selectable chat model; run conformance on a stronger model
The daily provider-conformance harness fails 4/5 harnesses on Atlas Cloud —
its default chat model answers agent/tool-use conformance prompts
conversationally instead of performing the task. Atlas is currently the only
provider with a key configured, so the whole live run is red.
Make the Atlas Cloud provider honor an ATLASCLOUD_MODEL env override (falling
back to the existing default), and set it in the harness workflow to a
stronger tool-use model (Qwen3, overridable via an Actions variable). No
change to the default for normal use.
* atlascloud: use minimaxai/minimax-m3 for conformance model
---------
Co-authored-by: Claude <noreply@anthropic.com>
Streaming is implemented now (v6.3.3); the old test expected
ErrStreamingUnsupported and failed. Replace it with a real SSE streaming
test (httptest) that also asserts stream_options.include_usage and the
final usage chunk.
* ai/atlascloud: surface token usage on streams
Request stream_options.include_usage and return the final usage chunk
as a Response with Usage set, so streaming callers can record usage.
* ai/openai: surface token usage on streams
Request stream_options.include_usage and return the final usage chunk
as a Response with Usage set, so streaming callers can record usage.
* Initial plan
* fix: remove extra blank line in ai/anthropic/anthropic.go (gofmt)
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
* ai: add WithMaxTokens option
Let callers cap response length; providers send max_tokens when set
(anthropic keeps its 8192 default otherwise).
* ai: add WithMaxTokens option
Let callers cap response length; providers send max_tokens when set
(anthropic keeps its 8192 default otherwise).
* ai: add WithMaxTokens option
Let callers cap response length; providers send max_tokens when set
(anthropic keeps its 8192 default otherwise).
* ai: add WithMaxTokens option
Let callers cap response length; providers send max_tokens when set
(anthropic keeps its 8192 default otherwise).
* ai/atlascloud: thread Request.Messages into the request
Fold conversation history (req.Messages) between the system prompt and
the final user prompt so multi-turn context reaches the model.
Refs #3292
* ai/openai: thread Request.Messages into the request
Fold conversation history (req.Messages) between the system prompt and
the final user prompt so multi-turn context reaches the model.
Refs #3292
* ai/anthropic: thread Request.Messages into the request
Fold conversation history (req.Messages) between the system prompt and
the final user prompt so multi-turn context reaches the model.
Refs #3292
Follow-up to #3017. A Generate runs the whole tool-execution turn, so
auto-retrying it re-runs already-executed (possibly side-effecting) tool
calls. Default ModelMaxAttempts 3 -> 1: retries are now opt-in via
ModelRetry. The timeout stays as a safety net.
Also harden ai.GenerateWithRetry: always back off between retries
(exponential, capped at 30s, default 200ms if unset) so an opt-in retry
can't busy-loop the provider even with Backoff=0.
Verified: go build, go test -race ./agent/... ./ai/, golangci-lint.
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>
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>
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>
* 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>
* refactor(ai): rename ToolSet to Tools, simplify wiring with WithTools
Move tool discovery/execution fully into the ai package as ai.Tools
(formerly ai.ToolSet), and simplify the usage model:
- NewTools(reg, ai.ToolClient(c)) takes the execution client as an
option instead of threading it through Handler(c) per call
- New ai.WithTools(tools) option wires the tool handler into a model
in one call, replacing ai.WithToolHandler(set.Handler(c))
- ai.DiscoverTools(reg) for one-shot discovery
Before:
set := ai.NewToolSet(reg)
list, _ := set.Discover()
m := ai.New(p, ai.WithToolHandler(set.Handler(client)))
After:
tools := ai.NewTools(reg, ai.ToolClient(client))
list, _ := tools.Discover()
m := ai.New(p, ai.WithTools(tools))
Update ai/flow, micro chat, README, ai integration doc, Atlas Cloud
guide, and blog posts 3/8/9/10.
* feat(cli): add per-interface commands (registry, broker, store, config)
Map go-micro's core interfaces onto the CLI so the framework's
building blocks are inspectable and manipulable from the terminal:
micro registry list/get/watch service discovery
micro broker publish/subscribe pub/sub messaging
micro store read/write/delete/list persistence
micro config get/dump dynamic config (from env)
Structured pluggably in cmd/micro/resource: each interface is one
file exposing a Command() func, all wired through a commandFuncs
slice in resource.go. Adding a new resource command is a single
file plus one slice entry. Shared printJSON/fail helpers keep
output and errors consistent across commands.
Each command's verbs mirror the interface methods. Output is JSON
for structured data, raw for single values. Update README and
getting-started with an "inspecting the framework" section.
* docs: update CLI README with all new commands
Add documentation for commands that were missing from the CLI README:
- micro new --template (crud, pubsub, api)
- micro api (standalone HTTP gateway)
- micro registry list/get/watch
- micro broker publish/subscribe
- micro store read/write/delete/list
- micro config get/dump
- micro chat (interactive LLM agent)
- micro flow run/exec (event-driven orchestration)
- micro mcp serve/list/test
Organized into sections: API Gateway, Inspecting the Framework
(registry, broker, store, config), and AI & Agents (chat, flow, mcp).
* refactor(ai): move History from caller to Request field
History is now pure state (no Generate method). Instead, pass it
via Request.History and call ai.Generate(ctx, model, req):
Before:
hist := ai.NewHistory("system prompt", 50)
resp, _ := hist.Generate(ctx, model, prompt, tools)
After:
hist := ai.NewHistory(50)
resp, _ := ai.Generate(ctx, model, &ai.Request{
Prompt: prompt,
SystemPrompt: "system prompt",
Tools: tools,
History: hist,
})
The model is always the thing you call. History is context you
pass in. ai.Generate() handles the bookkeeping: prepends
accumulated messages before the call, records the exchange after.
NewHistory no longer takes a system prompt (it belongs on the
Request, where it always did).
Update micro chat, ai/flow, and all blog posts/docs.
* refactor(ai): make History a plain message accumulator
History no longer has Generate or touches the model. It's just
Add/Messages/Reset/Len with truncation — a helper for building
Request.Messages across turns.
Before:
hist := ai.NewHistory(50)
resp, _ := ai.Generate(ctx, m, &ai.Request{History: hist, ...})
After:
hist := ai.NewHistory(50)
hist.Add("user", prompt)
resp, _ := m.Generate(ctx, &ai.Request{Messages: hist.Messages(), ...})
hist.Add("assistant", resp.Reply)
Remove History field from Request. Remove package-level
ai.Generate(ctx, model, req) wrapper — users call m.Generate()
directly, which is the interface method. History is a convenience
for accumulating messages, not a participant in generation.
Update micro chat, ai/flow, blog posts 9 and 10.
---------
Co-authored-by: Claude <noreply@anthropic.com>
Move tool discovery/execution fully into the ai package as ai.Tools
(formerly ai.ToolSet), and simplify the usage model:
- NewTools(reg, ai.ToolClient(c)) takes the execution client as an
option instead of threading it through Handler(c) per call
- New ai.WithTools(tools) option wires the tool handler into a model
in one call, replacing ai.WithToolHandler(set.Handler(c))
- ai.DiscoverTools(reg) for one-shot discovery
Before:
set := ai.NewToolSet(reg)
list, _ := set.Discover()
m := ai.New(p, ai.WithToolHandler(set.Handler(client)))
After:
tools := ai.NewTools(reg, ai.ToolClient(client))
list, _ := tools.Discover()
m := ai.New(p, ai.WithTools(tools))
Update ai/flow, micro chat, README, ai integration doc, Atlas Cloud
guide, and blog posts 3/8/9/10.
Co-authored-by: Claude <noreply@anthropic.com>
* feat: update Go Micro logo to interconnected nodes design
Replace the text-on-blue-square logo with a modern icon: three
teal nodes connected in a triangle, representing distributed
systems. Generated via Atlas Cloud. Clean at all sizes — works
as GitHub avatar, favicon, and nav bar icon.
* feat: new logo, AI integration architecture doc, and landing page CTA
Update logo to triangle-nodes icon + "Go Micro" text wordmark.
Save icon-only variant for favicon/avatar use.
Add docs/ai-integration.md — a single page that explains how the
AI stack fits together: services → registry → MCP gateway →
ai/tools → ai.Model → micro chat. Layer-by-layer with code
examples, provider table, and "what you don't need" section.
Add AI Integration to docs sidebar navigation (after Getting
Started). Update the landing page AI section with a direct CTA
button linking to the new doc.
* fix: restore original logo and add border-radius to all renders
Revert logo to original. Add border-radius: 8px to the logo img
in the landing page nav, docs layout nav, and blog layout nav
so the square logo renders with rounded corners everywhere.
Remove unused icon.png.
* feat(ai): add ai/flow package and micro flow CLI
Add ai/flow — event-driven LLM orchestration for go-micro. A Flow
subscribes to a broker topic, discovers services as tools, and
feeds each event into an LLM that decides which RPCs to call.
Key types:
- flow.New(name, opts...) creates a flow with trigger topic,
prompt template, provider config
- flow.Register(registry, broker, client) wires it into a service
- flow.Execute(ctx, data) runs the flow once (for testing/CLI)
- flow.Results() returns execution history
Add micro flow CLI with two subcommands:
- micro flow run: subscribe to a topic and react to events
- micro flow exec: one-shot execution with inline data
Both output JSON results with flow name, prompt, tool calls,
reply, answer, duration, and errors.
Example:
micro flow run --trigger events.user.created \
--prompt "New user: {{.Data}}. Send welcome email." \
--provider anthropic
micro flow exec --prompt "List all users" --provider anthropic
* docs: update flows blog post with ai/flow package and CLI examples
Add "Update: We Built It" section to blog/9 showing the ai/flow
package API, CLI usage for both event-driven and one-shot modes,
and what it does/doesn't do. Links the conceptual discussion to
the shipped implementation.
---------
Co-authored-by: Claude <noreply@anthropic.com>
* feat(website): redesign docs and blog layouts, add blog header images
Redesign both layouts to match the new landing page:
- Consistent nav bar with logo, Docs, Blog, GitHub, Reference, Home
- Consistent footer with copyright and links
- CSS custom properties for theming
- Updated typography, spacing, and code block styling
- Active sidebar link highlighting in docs
- Dark mode support preserved
Generate 4 blog header images via Atlas Cloud:
- blog-deploy.png for post 1 (micro deploy)
- blog-mcp.png for posts 2, 3, 7 (MCP-related)
- blog-agents-demo.png for post 4 (agents demo)
- blog-dx.png for post 5 (DX cleanup)
- Reuse data-model.png for post 6 (model package)
All 7 existing blog posts now have header images.
* fix(website): prevent horizontal scroll on mobile landing page
Add overflow-x: hidden on html and body. Set max-width: 100% and
height: auto on all section and two-col images. Add overflow:
hidden to .two-col grid. Constrain hero pre with max-width and
overflow-x. Reduce font sizes and padding at mobile breakpoint.
* feat(website): add images to remaining core doc pages
Generate 5 more images via Atlas Cloud for docs:
- registry.png: service discovery diagram
- broker.png: pub/sub message broker pattern
- transport.png: multi-transport layers (HTTP, gRPC, NATS)
- config.png: dynamic configuration from multiple sources
- observability.png: monitoring dashboard with metrics/traces
Add images to registry.md, broker.md, transport.md, config.md,
observability.md, and architecture.md. All 11 main doc pages
now have header images.
* feat: add sponsor logos to landing page, README images, and flows blog post
Add Anthropic and Atlas Cloud sponsor logos to the landing page
with links to their respective blog posts. Logos display at 0.7
opacity with hover effect.
Add architecture and MCP agent images to the GitHub README for
the Overview and MCP sections.
Write blog post 9: "From Chat to Flows" — explores the concept
of LLM-powered service orchestration. Compares micro chat's
interactive model with persistent event-driven flows, shows how
the existing building blocks (ai/tools, History, broker) could
compose into a flow engine, discusses tradeoffs vs traditional
orchestration (Step Functions, Temporal), and includes a working
15-line code example. Explicitly positions it as a concept for
community feedback, not an announcement.
* feat(website): add animated hero video to landing page
Generate a 6-second hero video via Atlas Cloud's image-to-video
API (gemini-omni-flash). Shows the microservices network diagram
animating with data flowing between nodes.
Replace the static hero image with an autoplay muted looping
video element. Falls back to the static image via poster
attribute and img fallback for browsers without video support.
* feat(ai): add VideoModel interface with Atlas Cloud provider
Add ai.VideoModel interface for video generation alongside Model
and ImageModel. Supports text-to-video and image-to-video via
VideoRequest with prompt, reference images, duration, aspect
ratio, and resolution fields.
Implement GenerateVideo for Atlas Cloud using their async API:
POST /api/v1/model/generateVideo → poll /api/v1/model/prediction.
Default model is gemini-omni-flash image-to-video. Polls every
5 seconds until completion or context cancellation.
Register Atlas Cloud as a video provider via ai.RegisterVideo.
Add 3 tests: registration, no-key error, compile-time interface
check. Update ai/README.md with VideoModel docs.
The ai package now covers all three modalities:
- Model (text) — 7 providers
- ImageModel (image) — 2 providers (Atlas Cloud, OpenAI)
- VideoModel (video) — 1 provider (Atlas Cloud)
---------
Co-authored-by: Claude <noreply@anthropic.com>
* feat(cli): add CRUD, pub/sub, and API gateway templates for micro new
Add --template flag to 'micro new' with three preset templates:
- crud: CRUD service with Create/Read/Update/Delete/List, in-memory
store with sync.RWMutex, UUID generation, pagination, and doc
comments with @example tags for MCP tool discovery.
- pubsub: Event-driven service with Publish/Stats RPCs and a
Subscribe method that hooks into the broker. Includes event
types with ID, type, source, data, and timestamp.
- api: API gateway service with Health and Endpoint RPCs, an
internal HTTP route table, and a response recorder for
proxying requests through RPC.
All templates include MCP-ready doc comments and work with
--no-mcp. The default template (no flag) is unchanged.
Usage:
micro new myservice --template crud
micro new myservice --template pubsub
micro new myservice --template api
* fix(ai): update Atlas Cloud provider to use actual API formats
Fix the Atlas Cloud image generation to use their real async API:
POST /api/v1/model/generateImage → poll /api/v1/model/prediction/{id}
instead of the OpenAI-compatible endpoint which doesn't exist.
Add Quality and OutputFormat fields to ai.ImageRequest for
provider-specific image parameters.
Update default text model from llama-3.3-70b (doesn't exist) to
deepseek-ai/DeepSeek-V3-0324 (their flagship model). Update
default image model to openai/gpt-image-2/text-to-image.
* feat(website): add AI-generated images to landing page, docs, and blog
Generate 5 images via Atlas Cloud's image API (gpt-image-2) to
elevate the website experience:
- hero.png: microservices network graph for landing page
- architecture.png: registry + broker architecture diagram
- mcp-agent.png: AI agent calling services via MCP
- developer-experience.png: terminal showing micro run/chat
- blog-atlas.png: Atlas Cloud unified API illustration
Add visual sections to the landing page with architecture,
MCP integration, and developer experience showcases. Add
images to docs index, MCP docs, and Atlas Cloud blog post.
All images resized to 1200px wide and optimized for web.
Generated using Atlas Cloud sponsor credits.
* feat(website): redesign landing page and add images to docs
Redesign the landing page from a centered card layout to a
full-width modern site with:
- Top navigation bar
- Hero section with gradient background and CTA buttons
- Full-width image showcase sections
- Two-column layout for architecture, MCP, and DX sections
- Feature grid with 6 capabilities
- Footer with links
- Responsive breakpoints for mobile
Generate 3 more images via Atlas Cloud for docs:
- getting-started.png for the getting started guide
- deployment.png for the deployment guide
- data-model.png for the data model docs
Add images to getting-started.md, model.md, and deployment.md.
---------
Co-authored-by: Claude <noreply@anthropic.com>
* feat(ai): add ImageModel interface with Atlas Cloud and OpenAI support
Add ai.ImageModel interface for text-to-image generation alongside
the existing ai.Model for text. Uses the same options pattern
(WithAPIKey, WithBaseURL) and the same provider registration
system (RegisterImage/NewImage).
Implement GenerateImage for Atlas Cloud and OpenAI providers via
the OpenAI-compatible /v1/images/generations endpoint. Default
image model is gpt-image-1. Responses return images as URL,
base64, or both depending on the provider.
Update Atlas Cloud blog post and integration guide with image
generation examples. Update ai/README.md with ImageModel docs.
* fix(website): widen docs content by reducing layout max-width to 1100px
Remove the 800px max-width on .content (which left empty space on
the right) and reduce the overall .layout and footer from 1400px
to 1100px. With the 230px sidebar this gives ~830px of content
width — readable and fills the page properly on desktop.
* feat(ai): add History for multi-turn conversation state
Add ai.History — a lightweight message accumulator that tracks
user prompts, assistant replies, and tool call/result pairs
across turns. FIFO truncation when message count exceeds the
configured limit. System prompt is passed through on every
Generate call.
Wire History into micro chat so conversations are multi-turn by
default (limit 50 messages). Add 'reset' command to clear
history mid-session.
5 unit tests covering accumulation, truncation, reset, snapshot
isolation, and tool call recording.
---------
Co-authored-by: Claude <noreply@anthropic.com>
Asim Aslam