CLAUDE.md has a specific meaning in the Claude Code ecosystem (agent
instructions). The wiki schema for the ingestion pipeline should live
in schema.md to avoid confusion.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Return error when both path and content are supplied simultaneously
- Improve tool description to clearly state the two valid call forms
- Add per-field descriptions so LLMs understand what each parameter requires
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds an optional path field to brain_ingest so Claude can ingest files
or directories directly by path without embedding content in the call.
Routing: path set → /ingest-path; content+source set → /ingest; neither → error.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Wires pipeline.Run into the HTTP layer so callers can ingest raw text
or files/directories without touching the filesystem directly. Rewrites
main.go to parse LLM and watcher env vars and build pipeline.Config.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Polls brain/raw/ on a configurable ticker, derives human-readable source
names from filenames, runs the pipeline, and moves files to
processed/YYYY-MM-DD/ on success or failed/ on error with a log.md entry.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds prompt.go (BuildPrompt + systemPrompt) and pipeline.go (Run, Config,
Result, mergeAll) that wire chunking, LLM calls, parse, merge, index rebuild,
and log append into a single ingestion pipeline. Includes integration tests
covering write, dry-run, and duplicate-path merge scenarios.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
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>
Implements escalation chains per skill with three-layer priority:
1. Caller override (model param) — no escalation
2. Per-skill chain from models.yaml
3. default_chain fallback
New APIs:
- Verifier() — fixed verifier for output validation
- LlamaSwapURL() — base URL for warm-state probing
- ChainFor(skill, override) — ordered model list for escalation
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Reader agent scans session logs for SFT/DPO candidates; writer receives
reader output and formats+writes training pairs to brain/training-data/.
Adds trainer-reader.md and trainer-writer.md discipline prompts.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds the spec skill that generates structured implementation specs from
requirements and writes them to a configurable output path in the project.
Follows the same pattern as review/debug skills with session history injection.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Implements the debug skill following the same pattern as review. The skill
accepts project_root + error (+ optional context/model/session_id), prepends
session history, and calls the executor to produce 3-5 ordered hypotheses —
diagnosis only, no fixes.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Implements the review skill following the same pattern as retrospective/tdd.
Validates project_root and files args, prepends session history when a
session_id is provided, and delegates to the executor with Read,Bash tools.
Iron-law discipline prompt enforces CRITICAL/WARNING/SUGGESTION output format.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds SessionsDir to tdd.Config, session_id to tool input schemas, and a
prependHistory method that reads the session JSONL log and prepends a
formatted history block to the task prompt before worker invocation.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- check job: lint + test + vet across both Go modules (root + ingestion)
- mirror job: pushes main + tags to github.com/mathiasb/hyperguild after check passes
- Taskfile: add VERSION/SHORT_SHA vars, fix build/lint/test/vet for multi-module,
add tag and push tasks — matches cobalt-dingo conventions
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
--json-schema combined with --output-format text produces empty stdout.
The structured result is in the "structured_output" field of the json
envelope. Updated executor to unwrap the envelope.
Also removes --bare flag which disables OAuth keychain reads, causing
silent auth failure when ANTHROPIC_API_KEY is not set.
Adds goreman Procfile + stdio bridge (cmd/bridge) for Claude Code MCP
integration. Task start/stop replaced with goreman + port-kill.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
All 8 MCP tools verified (tdd_red, tdd_green, tdd_refactor, brain_query,
brain_write, tier, session_log, retrospective). Ingestion write/query,
brain_query, tier, and session_log all return correct responses end-to-end.
Brain note written during smoke test committed to raw/ and wiki/concepts/.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add "retrospective" to validPhases so non-TDD skills pass Validate().
Return []Entry{} instead of nil in session.Read when no file exists,
so JSON serialisation produces [] rather than null.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds internal/skills/retrospective/ — an MCP skill that reads a session
log and dispatches a worker subprocess (via ExecutorFn) to identify
learnings and write them to the brain. Follows the same executor pattern
as the TDD skill.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds two new MCP skill packages:
- internal/skills/org: exposes the tier tool, calling an injected TierFn
for testability; returns current operating tier as structured JSON
- internal/skills/sessionlog: exposes the session_log tool, appending
structured JSONL entries to brain/sessions/{session_id}.jsonl; requires
session_id, wraps internal/session.Append
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The write handler was building a hand-rolled map that dropped the type
and domain fields from writeArgs. Pass the struct directly so all fields
reach the ingestion server. Strengthen the test to assert the request
body contains the type field.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds the brain skill that proxies HTTP calls to the ingestion server,
exposing brain_query (/query) and brain_write (/write) as MCP tools.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
mathiasandClaude Sonnet 4.6