Round-5 review found a sixth bypass, same mechanism as round 4's CRLF gap,
one layer earlier: a leading UTF-8 BOM (EF BB BF) defeats
strings.HasPrefix(doc, "---\n") before CRLF normalization even applies.
Judged live-plausible rather than exotic — Notepad's default "UTF-8" save
and PowerShell's pre-v6 Out-File/Set-Content both emit a BOM — so fixed
inline at the same cost as the CRLF fix rather than deferred wholesale to
hyperguild#138.
Strip the BOM before the CRLF normalization in frontmatterBlock, so every
caller (fence-presence detection and frontmatterScalars) agrees regardless
of encoding.
Drawing the line here: further encoding variants in this family (NEL line
separators, UTF-16 BOM, lone-CR classic-Mac endings) are judged not
live-plausible in a git-tracked UTF-8 markdown corpus and are tracked
wholesale under hyperguild#138's parser consolidation rather than chased as
individual rounds on this PR.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Round-4 review found a fifth bypass, and this one needs no adversarial
old_str/new_str crafting at all: frontmatterBlock's fence detection matches
the literal byte sequence "---\n". A note whose fence lines use CRLF
("---\r\n") fails strings.HasPrefix(doc, "---\n") on the precondition read
purely from line-ending encoding — hadFence is false, so the round-3/round-4
checks can never fire, frontmatterScalars falls back to an empty map, and
claim.ValidateEnvelope({}) is nil by design. An invalid claim_provenance
value lands with zero error.
Zero CRLF-fenced notes exist in the live corpus today, but nothing in the
code prevented one, and this class of encoding-dependent false negative
could resurface in any of the other fence-based checks. Normalize once
inside frontmatterBlock so every caller (fence-presence detection and
frontmatterScalars) agrees regardless of line ending.
The broader structural concern — three independent, subtly inconsistent
fence-parsing implementations across internal/mcp, internal/api, and
internal/frontmatter, of which this CRLF gap is a direct symptom — is out
of scope for this PR and filed separately as hyperguild#138.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Round-3 review found a fourth bypass: checkClaimEnvelope always validates
frontmatterScalars(after), but an edit whose new_str drops the closing
"---" degrades `after` to "unfenced" in the same call. frontmatterBlock(after)
then returns ok=false, frontmatterScalars returns an empty map, and
claim.ValidateEnvelope({}) is nil by design (absent fields are valid) — so
an invalid enum value lands on disk with zero error, and the note is left
permanently unfenced.
A note that had a valid fence before the edit must still have one after, or
the edit is rejected outright — closes this off structurally rather than
special-casing the fence-removal shape. Also guards oldStr == "" as a no-op
(strings.Replace treats "" as matching position 0, which would otherwise
look like an edit that inserts text before the fence): that degenerate case
belongs to notes.Edit's own "old_str is empty" refusal (#115), not to the
envelope check — TestBrainEdit_EmptyOldStrErrorNamesRawArgumentBytes caught
the regression when this guard was still missing.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Round-2 review found a third bypass: checkClaimEnvelope required old_str to
be fully contained within the extracted frontmatter block (which excludes
both "---" fence lines). An old_str disambiguated across the closing fence
into the body — a natural choice, since notes.Edit requires old_str to be
unique — failed that containment test, so the gate skipped validation
entirely while notes.Edit applied the replace verbatim, reaching the same
invalid-enum outcome as the two bypasses already closed.
Remove the containment gate structurally instead of patching another edge:
checkClaimEnvelope now always computes the post-edit doc and validates its
resulting frontmatter, regardless of old_str's textual relationship to the
fence. A body-only edit leaves the frontmatter unchanged (still valid, since
the note started valid), so this is a no-op for the common case and
fail-closed for every case that touches the envelope, however old_str is
phrased.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Review of PR #136 found the gate trivially bypassable: touchesClaimEnvelope
only fired when old_str/new_str contained the claim-envelope FIELD NAME as a
substring, but a natural value-only diff (old_str: "asserted", new_str:
"guessed" against a claim_provenance line) never mentions the field name and
walked straight past it — notes.Edit wrote the invalid enum value to disk
with zero error.
Redesign the gate to be position-based instead of name-based: checkClaimEnvelope
now checks whether old_str is physically contained within the note's
frontmatter block (via the new frontmatterBlock helper), previews the exact
strings.Replace the real edit would perform, and validates the resulting
envelope before the edit is allowed to run. frontmatterScalars now builds on
the shared frontmatterBlock helper.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
hyperguild#123, the audit follow-up from #111: writeHallNote and
UpdateNote both validate the claim envelope (half_life/applies/
claim_provenance) before writing; brain_edit didn't -- a byte-level
string replace has no frontmatter awareness at all, so a caller could
rewrite an existing envelope line (e.g. flip claim_provenance from
asserted to guessed, or set half_life to a value outside the enum)
straight past the validator. This was the one live, model-facing gap
#123 identified; the ingestion pipeline write paths audited alongside it
turned out not to touch these fields at all, so this closes the issue.
Fixed by previewing what old_str->new_str would produce -- the exact
strings.Replace(before, old_str, new_str, 1) formula notes.Edit itself
uses internally -- and validating the envelope on that preview before
the real edit is allowed to run. Fail-closed: an invalid result blocks
the edit entirely, matching create/supersede's existing posture. Scoped
to notes only (scope == notes.ScopeNotes) since governance files have no
claim-envelope concept, and gated on a cheap substring check so an
ordinary body edit that never mentions an envelope field name pays
nothing extra.
The preview doesn't replicate notes.Edit's uniqueness/CRLF/conflict-
marker checks -- if old_str is absent or ambiguous, the preview may not
match what Edit ultimately does, but Edit independently and correctly
rejects those cases at write time regardless, so nothing about write
safety rides on this preview's accuracy, only the envelope check itself.
frontmatterScalars is a third, minimal implementation of the same
indented-line-safe scalar extraction as the sibling packages
(hyperguild#126/#128) -- deliberately not shared/exported across
packages (each package's frontmatter handling has slightly different
needs and none currently import each other), but built the same way
from the start this time rather than needing a follow-up fix.
Flip-tested: disabling the pre-check gate lets the invalid-envelope test
fail (the edit silently succeeds); restoring it passes. Full module
suite green.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Adds brain_reject (RejectNote + MCP tool) and fixes the watcher to skip raw/rejected/, preventing declined notes from being silently re-ingested and republished.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Co-authored-by: Mathias <mthbqv@gmail.com>
Removes brain_write legacy domain/type/knowledge-path params (ADR-0012) and migrates the previously-missed cmd/hyperguild CLI caller (hyperguild brain write) from <type> <slug> to <wing> <hall> <slug>, fixing a 100%% regression the first review round caught. Adds TestWrite_CLIPayloadRoundTrips exercising the real Handler.Write over HTTP to pin the wire contract.
Closes#79.
Co-authored-by: Mathias <mthbqv@gmail.com>
Textual-diff conflict detection only (semantic contradiction detection via brain-gardener Judge deferred, confirmed by Mathias, comment 12594). Includes canonicalBlock whitespace-run normalization fix for the disagreement comparison.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Co-authored-by: Mathias <mthbqv@gmail.com>
fix(wiki): give the preamble its own field instead of overloading heading=="" (#103)
Round 3 review: verified structurally that the preamble is no longer in the sections slice or the idx map, so it cannot collide with a degenerate `## ` heading. Flip-tested by reverting to the heading=="" model and confirming TestMerge_DegenerateEmptyHeadingDoesNotCollideWithPreamble goes red. Adversarial pass (multiple degenerate headings, frontmatter-only page, unicode around the ## boundary, 3x self-merge idempotency with preamble+degenerate) all held. CI green on 09aeaa9 (run 7820).
Co-authored-by: Mathias <mthbqv@gmail.com>
AutoTunnel matched note titles case-insensitively, so a one-word title linked
every entry that happened to use that word. Measured on the live corpus: 185
entries carry an auto-written See-also link to wiki/telos/decisions/wrong.md
(title "WRONG") and 136 to .../status.md — the two most-linked nodes in the
whole graph, and both of them artifacts of the English language rather than
references. telos's projects/problems/strategies/goals/beliefs entries account
for another ~60 between them.
That pollution is not cosmetic: inbound-link count is what the duplicate
Fixer picks survivors by, what orphan detection reads, and what brain_graph
shows.
One-word titles now need the title's own casing in the prose ("WRONG", "BERT",
"NLP" — an entity name in a sentence still links). Multi-word titles keep the
case-insensitive match: "risk tier middleware" is a real mention however it is
capitalised, and a three-word collision is not an accident.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The BrainStore is not the only door. POST /write — the HTTP path CLAUDE.md
hands to curl and scripts — calls api.WriteNote directly, so the strip
shipped one commit ago covered brain_write and capture while leaving the raw
door ungated. A gate one door wide is not a gate.
The BrainStore keeps its own call so it can still report Ref.Unlinked to the
MCP caller; running the strip twice is a no-op on content the primitive has
already cleaned.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Every brain write accepted [[targets]] that resolve to nothing — skill
names, repo names, agent-local memory-file slugs — and each one became a
permanent [high] broken-link finding. The brain-audit digest grew 19 -> 63
high findings between 2026-08-26 and 2026-09-16; 53 of the 63 were exactly
this, and none are fixable by brain-gardener's BrokenLinkFixer, which only
repoints edit-distance-1 renames. There is no target to repoint to.
StripUnresolvedLinks resolves each link against knowledge/ + wiki/ using
brain-gardener's own resolver semantics (bare slug or wing/hall/slug path
form, code spans excluded) and unwraps the misses to plain text, reporting
them as Ref.Unlinked / the MCP `unlinked` field.
Unwrap rather than reject: a refused write on claudewatcher's unattended
ingest path is a lost learning, and the author's words are worth keeping
even when the link is not. An empty corpus is a no-op, so a misconfigured
brainDir cannot strip every link in a note.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
CLAUDE_INGEST_SKIP_PROJECTS takes filepath.Match globs tested against
the project directory NAME, and a matching directory is skipped during
the directory WALK — so its files are never opened and their content
never enters the process. That is a stronger property than filtering
after reading, and the difference is observable: without SkipDir,
WalkDir lists the directory's entries, and an unreadable one aborts the
entire walk, silently stopping ingestion for every other project.
Globs rather than exact names because a project directory is derived
from the session's working directory, so a git worktree yields an
ephemeral name no exact-match list could keep up with.
An unparseable pattern refuses to run. filepath.Match returns an error
ALONGSIDE a false match, so a bad pattern checked per-file would ingest
the directory while the log complained — the failure nobody notices.
Validated once, up front, in both entry points.
This complements the client-name scrubber rather than replacing it. The
scrubber drops individual turns whose content matches a client
identity; this excludes whole workspaces whose content is confidential
in ways no pattern reliably recognises. Learnings from excluded
sessions are captured deliberately through the session-close ritual
instead.
Recorded caveat: the project directory reflects the session's working
directory, NOT the repositories it touches. A session run from ~/dev
that reads an excluded repo is not excluded by this. The scrubber
remains the control for content; this is a control for workspaces.
A mutation test earned the strongest assertion here: the original tests
could not distinguish SkipDir from filtering after the walk, because
neither opens files. The unreadable-directory test can.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Canonical lives at infra ci-templates/golangci.yml, distributed by the
infra#309 pattern: byte-identical copies, checksum drift gate in infra. Do
not edit this file here -- edit the canonical and run `task ci:sync`.
Verified locally before pushing, not pushed-and-hoped: golangci-lint v2.11.4
against a Go 1.26.1 toolchain (matching CI) reports 0 issues here.
Also applies gofumpt, which this config enables and the golangci-lint v2
default set does not check at all. That gap is why the drift was invisible:
earlier passes ran gofmt, which is weaker. Mechanical, deterministic,
build+vet verified.
Estate-wide consolidation pass. golangci-lint v2 default set enables NO
formatter, so gofmt drift accumulated silently across the estate -- 8 repos
were carrying it, this one included. Same hole that let two files rot in
dma-cli until they were found by hand (dma-cli#12).
Mechanical and deterministic: `gofmt -w`, nothing hand-edited. Verified
before commit -- gofmt -l now reports 0, go build and go vet both pass.
Clears this repo to adopt the canonical .golangci.yml (infra
ci-templates/golangci.yml, infra#309 pattern) in a later wave.
llm.Router was primary-then-fallback (berget -> iguana ollama). Both
have failed together at least once in production (berget 5xx outage +
a cold fallback model exceeding the shared timeout budget), leaving
brain_answer/brain_classify fully down.
Router gains an optional Tertiary *Client, tried only if both Primary
and Fallback fail. Nil-safe — existing 2-tier deployments (no
BRAIN_LLM_TERTIARY_URL) behave exactly as before.
main.go wires it from BRAIN_LLM_TERTIARY_URL/MODEL + GEMINI_API_KEY,
pointed at Google's OpenAI-compatible Gemini endpoint
(generativelanguage.googleapis.com/v1beta/openai/) — llm.Client already
speaks OpenAI-shaped chat-completions, so no new client type needed.
Tests: TestRouter_FallsBackToTertiaryWhenPrimaryAndFallbackFail,
TestRouter_TertiaryNotCalledWhenFallbackSucceeds, TestRouter_AllThreeFail,
TestRouter_NilTertiary (2-tier backward-compat). Full suite green
(both modules, -race), golangci-lint clean.
Deployment env vars (infra repo, separate commit — GitOps, TBD there
too): BRAIN_LLM_TERTIARY_URL, BRAIN_LLM_TERTIARY_MODEL, GEMINI_API_KEY
secretRef.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
First half of brain#21: half_life (volatile|seasonal|durable), applies
(local|homelab|universal), claim_provenance (asserted|inferred).
writeHallNote already passed unknown frontmatter keys through verbatim, so
preservation was free — a test now pins it so a refactor of the merge loop
cannot silently drop the fields. What was missing is validation, and it
fails closed: a value outside the enum is rejected (a lint skips what it
cannot parse, so the note would read as classified while nothing acts on
it); an envelope field without claim_provenance is rejected (a value a
model inferred must never be indistinguishable from one a human asserted,
or a single classifier pass launders guesses into apparent judgement
across the corpus); provenance alone is rejected too.
Validation runs before MkdirAll, so a rejected write leaves nothing behind.
The field is `applies`, not `scope`: scope: has been in use since brain#5
for glossary terms (homelab-core, project:<repo>), a disjoint value space
on the same key. The shipped schema keeps the name.
Notes with none of these fields are byte-identical to before. Bulk
backfill stays out of scope.
Schema documented in brain/CLAUDE.md via brain_edit_root, which produced
the hyperguild#97 audit record for the rewrite.
Refs brain#21, brain#19 (superseded), brain#5, hyperguild#97.
Co-authored-by: Mathias <mthbqv@gmail.com>
brain_edit_root was gated but unobserved: on success it emitted a slog.Warn
and nothing else. That proves a rewrite was allowed, not that one happened —
and brain-sync commits it within 15 minutes authored `brain-sync`, so git
history cannot tell a CLAUDE.md rewrite apart from routine note traffic.
A successful brain_edit_root now emits an ntfy notification and an AuditEntry
through the same sink a capture already uses. notes.Result gains
PrevContentHash so both ends of the change are identifiable.
Path and hashes only in the notification body. Reserved at Internal, not
Confidential, because Confidential makes DegradingSink refuse to record while
loki is down rather than buffer. Observation is best-effort and never fails
the call; a failure to observe logs at ERROR.
Ordinary brain_edit on knowledge//wiki/ is deliberately not audited — git
history already carries the same before/after bytes with a diff.
Closes#97.
Co-authored-by: Mathias <mthbqv@gmail.com>
brain_read returns a note verbatim; brain_edit is str_replace with an
exactly-once match, operating on the tree brain-sync commits from.
An adversarial design review before implementation changed three things:
1. Governance files are not in the model-facing tool. Brain content is
ingested from the outside world and reaches a model's context, and that
model would hold the editor — one poisoned page could rewrite the
CLAUDE.md a .dispatch-allow agent later loads as instructions. And
brain-sync merges with --strategy-option=ours, so the live tree beats a
human's corrective push on the conflicting lines. CLAUDE.md now goes
through brain_edit_root: de-surfaced from tools/list and gated on the
local static principal. The scopes are disjoint — the privileged door
has the smaller reach.
2. Reads needed the same allowlist, and brain_get already lacked it: it
returned verbatim session transcripts under archive/ by path. A test
proved the exposure live before the fix.
3. Canonicalise before allowlisting — knowledge/../.git/hooks/post-commit
would otherwise reach a hook that brain-sync executes in a pod holding
the Gitea push credentials.
Plus overlapping match counting, UTF-8 validation both ways, refusal while
git is mid-operation, flock with the read inside the lock, atomic
same-dir rename, and reindex only when frontmatter is touched.
Refs brain#4.
Co-authored-by: Mathias <mthbqv@gmail.com>
The tickets array was never broken. Every ticket in the reported batch
targeted a client repo, and the I1 gate refuses a confidential capture
through a us-nexus origin at any length — reproduced live: length 1 and
20 both fine for an internal repo, length 1 refused for a client one.
What made it look like an array bug is that the refusal named neither the
offending target nor that a policy had said no, so with 20 tickets in
flight "the array is broken" was a reasonable conclusion. The refusal now
names the targets carrying the effective classification, and tells a
caller who declared confidential themselves exactly that.
Regression tests at length 1 and 20 pin the path that was already
correct; a third pins per-item partial success.
Closes#91 part 1.
Co-authored-by: Mathias <mthbqv@gmail.com>
Four call sites did `s[:limit] + "…"`. Both halves are byte operations:
len() counts bytes and a slice cuts bytes. On Swedish text — å ä ö are
two bytes, an em dash three — the cut lands mid-character and leaves an
orphaned lead byte, producing invalid UTF-8.
It failed loudly in exactly one place: wiki/index.md is written raw to
disk, where every strict decoder then rejects the whole file. The other
three (brain_context excerpts x2, brain_query excerpts) feed MCP
responses, where encoding/json silently substitutes U+FFFD — so those had
been quietly eating the last character of truncated excerpts, with no
error anywhere and nothing to notice.
textutil.Truncate counts runes and appends the marker only when content
was actually dropped; an ellipsis on complete text is a lie about the
content. The test is a property, not an example: it walks the limit
across every offset of a multi-byte string and asserts utf8.Valid at each
one, so a future off-by-one cannot pass by picking a lucky boundary.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BeAp5LTscnz2W7Ubt4eJ6m
brain_pending existed the whole time four real items sat unreviewed from
2026-04-23 to 2026-07-15. The tool was never the gap — nothing ever
prompted anyone to call it. The system should be what remembers the queue
exists.
Option 2 from the issue: ride along with brain_context, which sessions
already call, so noticing an aging note costs nobody a decision to go
looking. No scheduled job, no ntfy wiring, nothing new to keep running.
Threshold-gated at 14 days, and silent below it — a notice on every
context call is one people learn to skip, which reproduces the original
failure with extra steps. It reports the whole queue once it speaks: the
threshold decides whether to talk, not what to count.
It never promotes, rejects or reorders. Age is a reason to ask a human,
not a verdict; an old note may be exactly right to promote once someone
looks. A test asserts the queue is untouched and that the payload carries
a hint rather than an action.
An unreadable raw/ dir degrades to silence — brain_context is a hot path
and must not fail because the review queue is broken.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BeAp5LTscnz2W7Ubt4eJ6m
brain_index is auto-called after every write, and its own description
said so. A verb surfaced to callers that callers should never call is
cognitive load with no decision behind it — ADR-0012 rule 4.
Removed from tools/list only. The dispatch case stays, so maintenance
can still rebuild a Map of Content by hand: de-surfacing hides the verb,
not the operation. A test pins both halves, since removing the descriptor
and removing the capability look identical from the tool list.
Nothing called it directly — grepped the skills, specs and docs.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BeAp5LTscnz2W7Ubt4eJ6m
On a cluster restart this pod can beat dex to serving, gets a 502 from
ingress, and exits — after connecting postgres, backfilling 794 graph
nodes and ingesting three session batches, all of which the restart
redoes. Nothing was misconfigured; it started first.
The validator now retries with bounded exponential backoff (8 attempts,
1s doubling to 30s) and is built immediately after ctx, before the
watcher and the backfill. That second part is the other half of the
issue: a genuine config error now fails in seconds rather than after all
that work.
Bounded on purpose. Retrying forever would convert a wrong issuer URL
into a process that looks alive and never serves, which is harder to
diagnose than a crash loop.
startupretry.Do is generic and tested directly: transient-then-success,
budget exhaustion surfacing the last error via errors.Is, prompt return
on context cancellation, growing-and-capped delays, and a zero-value
policy still making one attempt rather than silently succeeding.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BeAp5LTscnz2W7Ubt4eJ6m
`title: "Foo" — bar` opens with a quote and is not quoted; the previous
prefix check read it as already-quoted and left two notes broken. Probing
the value as the right-hand side of a mapping answers the real question —
does this load as written — and leaves anything that already parses alone,
whatever it parses into.
Repairs the last two quotable files in mathias/brain. Only wiki/index.md
remains unparseable, for an unrelated reason: a truncated UTF-8 sequence.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BeAp5LTscnz2W7Ubt4eJ6m
Hand-authored and promoted notes skip pipeline.BuildPages, so nothing
quotes their scalars. A title carrying an unescaped ": " yields a block
yaml.Unmarshal rejects, and every consumer that reads frontmatter drops
the note silently — 18 files repo-wide today, up from the 8 in #90.
frontmatter.Lint reports it; frontmatter.Fix quotes only what quoting can
rescue and refuses to return a document that still fails to parse, so an
unfixable file comes back byte-identical rather than half-repaired. Scan
walks a tree and reports an unreadable file as a finding instead of
aborting, so one poisoned note cannot hide the rest.
Sequence items are deliberately left alone: "- foo: bar" is valid YAML
that silently becomes a map, which is a type corruption rather than a
parse failure, and repairing it would rewrite notes that currently load.
task lint:frontmatter # report
task lint:frontmatter FIX=1 # repair in place
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BeAp5LTscnz2W7Ubt4eJ6m
ai-sessions#13: capture's `summary` field wrote a frontmatter shape
(title/harness/fidelity/captured_at/repos_touched) that ai-sessions'
own extract/audit pipeline can't parse -- silently invisible to that
repo's own audit tooling, and bypassing its redaction + Stage2
completeness gates by construction. Only 5 files ever landed this way
over 3 weeks; the summary capability's whole value (speed) fights
ai-sessions' whole value (redacted, audited, complete), so kill it
rather than build a second parse branch.
capture now persists insights -> brain and action items -> Gitea
tickets only. Removes Summary/SummaryResult/SummaryWriter and all
wiring (service, REST body, MCP tool schema); close-session updated to
stop assembling a summary payload. specs/capture-*.md kept as historical
record with a superseded note -- the feature shipped and is documented,
just no longer current behaviour.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WPdSHbp9Utb2hPFm9wDG59
Root cause was neither of the two mechanisms the issue named
(CanonicalizeLinks over-canonicalizing, or a schema/prompt bias) —
CanonicalizeLinks correctly resolved [[Mission]] because
wiki/concepts/mission.md genuinely exists; the extraction prompt has
no "mission" bias either. The real bug: watcher.processDir walks
brain/raw/ and feeds every .md/.txt/.pdf file to pipeline.Run as
source material to extract, with no exclusion for
tunnel-candidates-*.md — AutoTunnel's own fuzzy-match human-review
queue (logFuzzyCandidates writes it into that same raw/ directory).
The watcher's next poll re-ingested the raw candidate log itself, and
the LLM naturally surfaced "mission" as a wikilink because the log
literally lists `(term: "mission")` entries in its content — a
generic-word title match DetectTunnels correctly flagged as fuzzy
(not auto-tunneled) but which still leaked downstream once treated as
real source material.
api.ListPending already excludes tunnel-candidates-* when listing
raw/ for promotion; processDir gets the same exclusion.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Roq1ajWKR5f1hG5Df9wC6A
plainLinkRE matches any [[...]] without a pipe, including path-prefixed
forms like [[wing:homelab/failures/foo]] or [[wiki/agentsquad/decisions/bar]]
that the LLM extraction step occasionally emits. Title-lookup against
titleToSlug always fails for these (they're paths, not titles), so they
were silently left broken.
Before falling to the unknown-wikilink warning, strip a known wing:/wiki/
root prefix and emit the clean wing/hall/slug path directly — matching
the brain-graph path-style link convention.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Roq1ajWKR5f1hG5Df9wC6A
opts.Content can already carry its own "---\n...\n---" block (e.g. from
an upstream extraction/promotion step). writeHallNote used to prepend a
second block unconditionally, making a standard frontmatter parser blind
to everything the first block declared (title, tags, ...).
splitFrontmatter now pulls the existing block's fields out first;
wing/hall/created_at are always fresh-injected, and type/domain/
source_type prefer the note's own existing value over the opts
fallback. Remaining existing fields are carried through verbatim into
the single merged block.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Roq1ajWKR5f1hG5Df9wC6A
pipeline.Run parses source/author/published from the raw content's own
frontmatter and applies them deterministically to source-type RawPages
after LLM extraction — never relies on the LLM to copy them through.
buildFrontmatter now emits all three (source pages only) when present.
Backfill of the 46 already-affected wiki/sources/*.md notes is a
separate concern per the issue, not done here.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Roq1ajWKR5f1hG5Df9wC6A
Found via a real live-cluster end-to-end test (POST /ingest-path with a real
.docx against the deployed ingestion + docmark): 'decode docmark response:
invalid character e looking for beginning of value'. docmark's Streamable-HTTP
transport frames every response as SSE (event: message\r\ndata: {...}\r\n\r\n,
Content-Type: text/event-stream) -- stateless_http=True removes the need for
an initialize handshake/session ID, it does NOT change the wire framing to
bare JSON. My original client + its own test mock both assumed bare JSON,
so the unit tests passed while the real call failed.
sseDataPayload() extracts the data: line before JSON-unmarshaling; falls back
to the raw body if no SSE framing is present (forward-compatible). Test mock
(docmark_test.go) now emits the SAME framing the live server actually sends,
confirmed by directly probing docmark's live response before writing the fix.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Wires the sovereign docmark MCP server (git.d-ma.be/mathias/docmark) as the
converter for formats ingestion previously couldn't handle at all -- DOCX,
XLSX, PPTX, PNG/JPG. A single self-contained tools/call POST (docmark runs
stateless_http, no session handshake needed) does the conversion.
- internal/extract/docmark.go: extractViaDocmark(path) -- reads DOCMARK_URL +
DOCMARK_BEARER_TOKEN from env, base64-encodes the file, calls docmark's
convert_to_markdown tool, surfaces tool/HTTP errors with context.
- internal/extract/extract.go: routes .docx/.xlsx/.pptx/.png/.jpg/.jpeg to it.
- internal/api/handler.go: isSupportedExtension() replaces the static
supportedExtensions map -- the new extensions are gated on DOCMARK_URL being
set, checked per-request. When DOCMARK_URL is unset (e.g. this repo's
current deployed state), behavior is byte-for-byte unchanged from today:
same 400/silent-skip as before. Zero risk until the env var is actually
wired in infra.
TDD throughout: docmark.go tested via httptest mock (success, not-configured,
tool-error, HTTP-error, all 6 new extensions route correctly); handler-level
test proves the DOCMARK_URL gate (docx 400 when unset, 200 when a working
mock is configured). Full task check green (fmt/vet/govulncheck/all tests).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
errcheck flagged two unchecked fmt.Fprintf return values in
internal/webhook/webhook.go, failing CI (run 310/311) for the whole
'trigger brain-sync on Gitea push' feature -- so no new ingestion image was
ever built, and the deployed image predates this feature entirely even
though infra's manifest (secret, RBAC, env wiring) was already live.
Both writes are best-effort informational text after WriteHeader has already
committed the status code -- a failed write here only happens on client
disconnect and nothing depends on it succeeding, so explicitly discard
(_, _ =) rather than log-and-continue noise.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds POST /webhooks/brain-sync: verifies Gitea's HMAC-SHA256 signature,
checks the push is to mathias/brain main, then creates a one-off Job from
the existing brain-sync CronJob's template (same script the 15-min poll
already runs, just triggered on-demand). Off by default -- opt in via
GITEA_WEBHOOK_SECRET, since it needs Job-create RBAC in the "brain"
namespace a fresh deploy won't have.
10 new tests (internal/webhook), including a fake-clientset reactor to
simulate server-side GenerateName expansion, which the plain fake tracker
doesn't do on its own.
Needs (follow-up, infra repo): RBAC granting ingestion's ServiceAccount
get on cronjobs/brain-sync + create on jobs in the brain namespace, the
GITEA_WEBHOOK_SECRET env, and the actual Gitea webhook registration.
claudeSink wrote every raw transcript into brain/wiki/claude-sessions/facts/
(BM25-indexed), duplicating what ai-sessions' curated summaries already
cover and out-ranking them in search (177,818 vs 45,335 BM25 weight on the
same query, per ai-sessions#10 investigation). Raw dumps now land in
brain/archive/claude-sessions/<host>/ — kept for deep lookups, never
indexed, never deleted.
Refs: ai-sessions#10
writeRequest and WriteNoteOptions have matching fields again now that
both carry SourceType, so the explicit field-by-field literal added
in ee1204d is flagged as a redundant conversion. Back to the plain
type conversion. Caught by task check (golangci-lint), not run
locally before the previous push -- plain go test passed, task check
(which adds -race and golangci-lint) didn't.
The unsourced-check fix (source_type: internal) only covered
claudewatcher's writes. 41 residual findings on the audit's next run
were manually-authored hall=facts entries written via brain_write/
capture -- also first-party observations, just a different write path,
with no way to mark them internal short of hand-editing every entry.
writeHallNote now defaults source_type to internal whenever hall ==
"facts" and the caller didn't set it explicitly. An explicit
source_type: external (now threaded through the /write HTTP endpoint)
opts a genuinely citation-needing entry back out.
brain-gardener#5: the audit's unsourced check was flagging 59 raw
claudewatcher session dumps as high-severity hallucination risk,
because it can't distinguish a first-party observation (a session
transcript) from an external claim needing citation.
Adds WriteNoteOptions.SourceType, emitted as source_type: <value> in
the wing/hall frontmatter route. claudeSink (the claudewatcher sink)
now always sets source_type: internal on the notes it writes.
Unblocks CD: the build's go mod download failed because mcp-chassis was
imported via the old gitea.d-ma.be module path, which the renamed server no
longer serves a matching go-import meta tag for. Point at the renamed module
git.d-ma.be/mathias/mcp-chassis v0.2.0 (mcp-chassis 69d389d) + go mod tidy.
Fresh download now resolves; ingestion builds + tests green.
This restores the normal CI path so the routing pass-rate fix (da9bdc4,
#73) builds and deploys through gitea Actions. Refs #74, #73, #35.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Wires the curation primitives into the MCP surface (all three sites:
tools() descriptors, handleCall dispatch, package doc) and registers the
GET /pending + POST /promote REST routes. brain_promote additionally
re-indexes the promoted note into the graph (best-effort), matching the
other write paths. brain_pending is the human-review-queue complement to
the agent-facing brain_write.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Closes the human curation loop: list brain/raw/ notes awaiting review
(oldest-first, with excerpt) and promote one into brain/wiki/<wing>/<hall>/.
PromoteNote rewrites frontmatter (sets wing/hall/promoted_at, preserves
created_at + custom fields via the existing frontmatter editor), rebuilds
the wing _index, and runs auto-tunnel. Atomic from the caller's view:
hall/wing/slug/collision validation happens before any fs change, and the
source is deleted only after the destination write succeeds (write-then-
delete, never move) — a collision or write failure leaves raw/ intact.
Default slug = filename minus the YYYY-MM-DD- prefix.
Also exposes GET /pending + POST /promote for shell scripts (bad
hall/collision/missing-source → 400, not 500).
Scope note: operates on raw/ (the retrospective-skill review queue) per
this issue's spec. The knowledge/ legacy pile is #22's bulk-migration
concern, not this ongoing queue.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A live token-scope probe against mathias/ai-sessions revealed gitea's
contents API uses POST to create and PUT (sha required) to update — the
first impl always PUT'd, so creating a new summary 422'd "[SHA]: Required".
The httptest mock had the same wrong assumption. Pick the method by
whether the file exists (GET sha). Token confirmed contents:write
(push:true) by the probe.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The deployed CaptureService was constructed with a nil SummaryWriter, so
a capture carrying a summary block returned the partial-failure
"no summary writer configured" (surfaced in the 2026-06-23 claude.ai
dogfood). The Gitea client already reaches mathias/* over BRAIN_GITEA_TOKEN
and now implements SummaryWriter, so inject it (type-asserted from the
tracker) — no new credential, no manifest change. Session summaries now
write to mathias/ai-sessions at summaries/<harness>/<YYYY-MM>/...
Reuses the existing token deliberately; assumes it carries contents:write
scope on ai-sessions (it already does issue writes for the tracker). If
the token is issue-scoped only, the live write 422s — a token-scope widen,
not a code fix.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds Client.WriteFile (Gitea contents API) so the Gitea client also
implements capture.SummaryWriter. Upserts: a GET resolves the current
blob sha so an existing file is updated (the richer-fidelity-supersedes
rule for re-captured sessions) rather than 422'd. Owner stays the fixed
const; token only in the Authorization header (no leak — regression
tested). Refactors the HTTP path into a shared request() helper so the
contents flow can branch on 404 without it being an error.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
mathiasandClaude Sonnet 5