Match the real-model conformance cadence to the dev/loop velocity so live
regressions and provider drift surface within the hour instead of up to 24h.
The mock harness already runs on every push/PR; this only changes the live
(credentialed) schedule.
Co-authored-by: Claude <noreply@anthropic.com>
* atlascloud: env-selectable chat model; run conformance on a stronger model
The daily provider-conformance harness fails 4/5 harnesses on Atlas Cloud —
its default chat model answers agent/tool-use conformance prompts
conversationally instead of performing the task. Atlas is currently the only
provider with a key configured, so the whole live run is red.
Make the Atlas Cloud provider honor an ATLASCLOUD_MODEL env override (falling
back to the existing default), and set it in the harness workflow to a
stronger tool-use model (Qwen3, overridable via an Actions variable). No
change to the default for normal use.
* atlascloud: use minimaxai/minimax-m3 for conformance model
---------
Co-authored-by: Claude <noreply@anthropic.com>
* 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>
Add the verification loop as a ranked priority — the one missing layer from
the four-loop framing (agent / verification / event-driven / hill-climbing):
flow.Verify + flow.LLMGrader to grade a step's output against a rubric and
retry with feedback. The architect will re-rank on its next pass.
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>
Codex