Ingest now stamps source_hash — sha256 of the ingested body, frontmatter
excluded — onto the source page, and compares it before doing any work. An
unchanged source returns Skipped with no LLM call at all.
This is cost and signal, not correctness: #103 already made a re-ingest
byte-identical, so a repeated run was harmless but not free — a full
extraction over every chunk to produce a result that merges to nothing.
Building this first would have put idempotency in the guard rather than in
the write, which is the wrong dependency direction.
Body-only hashing on purpose. A re-crawl that stamps a new fetch date has
not changed the source, and treating that as drift would re-extract the
whole corpus every time a crawler ran. A missing or unreadable hash always
means "extract": a missed skip costs one extraction, a wrong skip loses an
update silently, and silence is the failure mode this repo keeps paying
for.
The skip is reported (Result.Skipped plus a warning naming the hash), not
silent — a run that does nothing must say so, or "the pipeline is fine" and
"the pipeline stopped working" look identical (#107).
Storing the hash required settling who owns which frontmatter field. #103
made the on-disk block win wholesale, which protects human-set metadata
from a regenerating writer but froze fields the generator legitimately
owns. wiki.Merge now refreshes an explicit generatorOwned allowlist —
last_updated and source_hash — and keeps everything else on disk. An
allowlist rather than a carve-out, so a field nobody has thought about
stays human-owned by default. That also retires the last_updated
limitation #103 shipped with.
Refs #105, #103, #107, brain#21.
Compile-on-ingest, first half. buildAndWrite did an unconditional
os.WriteFile, so re-ingesting a source replaced its page wholesale and
discarded everything accumulated since — including human edits.
hyperguild#43 recorded the symptom as "re-ingest overwrites wholesale";
the framing that ingest "appends" understates it.
Now the write reads what is on disk and merges the fresh extraction into
it, asymmetrically in the existing page's favour: on-disk frontmatter and
on-disk sections win, extraction-only sections are added, bullet lists
union. An extraction can add to a note but never silently rewrite what a
human put there, which is what makes it safe on every ingest rather than
behind a review gate.
Two supporting fixes in wiki.Merge, both required for this to be safe to
run repeatedly:
- append sections (Open Questions, Updates, Evolving Notes) concatenated
wholesale, which is correct exactly once. Re-ingesting an unchanged
source would grow them every run until the page was unreadable. Now only
genuinely new lines are appended. Line-level rather than block-level,
because the common case is a re-ingest carrying one new line alongside
several it already has, and a block-level check would duplicate the old
ones every time.
- rebuildContent kept whatever blank lines a section was parsed with and
added its own, so every merge pass grew the page by a blank line —
invisible in a diff viewer, fatal to byte-stability. Section bodies are
now normalised. Re-ingesting unchanged content is byte-identical, so
brain-sync does not commit noise that hides real edits.
The drift guard that would otherwise catch repeated ingests (hashing the
source body, B3) does not exist yet, so idempotency holds here rather than
upstream.
Known limitation, deliberate: on-disk frontmatter wins, so last_updated
keeps its first-ingest date on a revised page. The alternative is this
function editing frontmatter it does not own, and no lint reads that field.
Refs hyperguild#43.
A forge search for "brain-mcp" returned nothing for this repo: the description
mentioned neither the brain nor brain-mcp, and the README never used the string
or the hostname. Both appeared only in the generated CLAUDE.md/AGENTS.md. Since
#91 part 2 decided the code stays in ingestion, discoverability is answered by
naming.
Adds a "Where brain-mcp lives" section: the ingress, the package, a table
mapping what-you-are-looking-for to where-it-is (including that the brain
content is a separate repo), and why it is not standalone, with a pointer to
the ADR.
Also repoints the README's three forge links from the decommissioned
gitea.d-ma.be alias to git.d-ma.be. Dated files under docs/superpowers are
left alone — they record what was true when written.
Repo description and topics were set through the forge API, and NPM's
default-site was changed from congratulations to 404 so a retired hostname
reads as absent rather than as a moved repo.
Closes#94.
Co-authored-by: Mathias <mthbqv@gmail.com>
The routing decision is about reasoning capacity, not cost or provider.
Fast model (koala/qwen35-9b-fast) handles high-pass-rate calls; thinking
model (iguana/gemma4-26b) handles low-pass-rate calls. Removes the
implicit Anthropic dependency from the routing pod — both models go
through LiteLLM.
Renames: HYPERGUILD_LOCAL_MODEL → HYPERGUILD_FAST_MODEL,
HYPERGUILD_CLAUDE_MODEL → HYPERGUILD_THINKING_MODEL,
Router.LocalModel → FastModel, Router.ClaudeModel → ThinkingModel,
log decision "claude_fallback" → "thinking_fallback".
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add routing pod to README architecture diagram and env vars table.
Add routing MCP endpoint to .context/PROJECT.md. Regenerate derived
context adapters via task context:sync.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Enables exposing the supervisor MCP via Tailscale Funnel for claude.ai
custom-connector tests. Auth is opt-in: empty SUPERVISOR_MCP_TOKEN
preserves the existing unauthenticated behavior for tailnet-internal
callers and local dev.
When the token is set, every request must carry
"Authorization: Bearer <token>" or it is rejected with HTTP 401 and a
JSON-RPC -32001 error. Comparison uses crypto/subtle.ConstantTimeCompare;
the token value and the supplied header are never logged.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- README architecture diagram now shows two MCP servers (supervisor +
brain) with the brain hosted by ingestion directly.
- Connect-a-project example includes both servers.
- .context/PROJECT.md replaces the boilerplate "Knowledge base access"
block with the actual hyperguild MCP endpoints.
- Adapters regenerated via task context:sync.
Captures the transitional state where two MCPs coexist; the supervisor
MCP will shrink as skill workers move to SKILL.md.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Claude Code now supports MCP servers over HTTP natively (type: "http"
in .mcp.json). The stdio↔HTTP bridge binary was a workaround for the
older stdio-only constraint and is no longer needed — the supervisor
NodePort on koala (30320) is reachable over Tailscale from any client
machine.
Removed:
- cmd/bridge/ (Go source, ~60 lines)
- bin/supervisor-bridge artifact
- Taskfile bridge:build target and the build aggregate's reference
- README "Build the bridge binary" instruction
Updated:
- .mcp.json switched to {type:"http", url:"http://koala:30320/mcp"}
- README architecture diagram and "Connect a project" section
Behavioural prerequisite for this change shipped in 7f7524c
(notifications fix). Verified end-to-end: tier tool call returns
{tier:2, label:"lan-only"} via direct HTTP, no shim.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
mathias
mathias