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.
buildOrch now returns a closure instead of *Orchestrator. Each invocation
calls models.ChainFor(skill, req.Model) so a non-empty caller override
collapses to a single-entry chain (no escalation). The attempts slice is
also allocated fresh per call, preventing unbounded growth across requests.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Each skill now gets its own Orchestrator built from its ChainFor entry,
with LiteLLM for local tiers and Claude for cloud tiers. Removes the
defunct models.Resolve calls and single shared executor.Run pattern.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
