brain_write with a custom filename omitted the .md extension, causing
search to skip the file (search.go filters on HasSuffix .md).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Small models (phi4-mini) produce correct markdown analysis but then
append the old {status/phase/skill} JSON schema out of training habit.
stripResultJSON() detects and removes these trailing fences so Claude
Code receives clean prose regardless of model behaviour.
Non-schema json blocks (config examples etc) are preserved.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Local models (phi4-mini, qwen3-coder-30b) ignore soft instructions
and revert to JSON from their training. Move the prohibition to the
very top with bold caps before any other content.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Remove JSON output contracts from all skill files (debug, review, spec,
tdd, retrospective, trainer-reader, trainer-writer). Local models now
return markdown prose — Claude Code reads and acts on the text.
Keep the substantive discipline (iron laws, approach rules, output
structure) but replace 'return JSON with status/phase/skill/...' with
clear markdown format instructions.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Remove JSON output contract, verification rules, escalation, and scope
limits that applied to the old Claude subprocess workers. Local models
are now consultants returning markdown prose, not JSON executors.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Ingestion server is a pure-Go HTTP binary — alpine runtime, no node.js.
CD now builds both supervisor and ingestion images on every push,
updates both deployment.yaml files in the infra repo.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Replace ollama/ prefix with iguana/ and koala/ prefixes to match
actual model IDs exposed by LiteLLM on this cluster.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Drop the three-layer Claude subprocess orchestration (local model →
Claude verifier → cloud escalation). Skills now call LiteLLM directly
and return plain text to Claude Code, which decides what to do with it.
- Delete executor, orchestrator, verifier, result, attempts packages
- Simplify LiteLLMExecutor: Run(Request)→Result becomes Complete(model,sys,user)→(string,int64,error)
- Replace ExecutorFn with CompleteFunc in all 6 skill configs
- Rewrite all skill handlers to call Complete and return {"text","model","duration_ms"}
- Simplify config/models: remove Verifier/LlamaSwapURL, add ModelFor
- Bump version to v0.5.0
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
gitea.d-ma.be:30022 is refused externally — the NodePort is only
reachable on koala locally. Use HostName 127.0.0.1 in SSH config
so git@gitea.d-ma.be connects to localhost:30022 instead.
Unindented heredoc content inside a YAML literal block breaks parsing.
Gitea silently drops workflows with YAML errors, causing the CD job
to never trigger.
gitea.d-ma.be port 22 is rejected (NPM only proxies HTTP/HTTPS).
The runner runs on koala where the Gitea SSH NodePort 30022 is
reachable locally. Use SSH config override instead of ssh-keyscan.
