hyperguild#79's caller audit (done in a prior session) found the removal
was safe:
- The promote/pending flow (#38/#81, ingestion/internal/api/promote.go)
operates exclusively on brainDir/raw/ -> brainDir/wiki/<wing>/<hall>/. It
never touches brainDir/knowledge/, so removing the knowledge/ write path
does not break it.
- No live caller uses domain/type or the knowledge/ path: checked
hyperguild itself, mathias/skills, mathias/agentsquad, mathias/dispatch,
mathias/cad, mathias/cad-atlas.
- internal/skills/brain (a skill.go + handlers.go pair) defined a third,
even-more-legacy brain_write shape (type/domain/filename, no wing/hall)
for an old "supervisor" MCP server whose cmd/supervisor/main.go no
longer exists. Nothing outside its own test imported it; deleted
entirely as it encodes the exact legacy shape this issue removes.
Changes:
- ingestion/internal/mcp/handlers.go: brain_write's tool schema and
brainWriteArgs drop type/domain; wing+hall are now marked required in
the schema.
- ingestion/internal/api/handler.go: WriteNote has one behaviour — wing+
hall required, routing to wiki/<wing>/<hall>/. writeLegacyNote and the
knowledge/-path branch are deleted. Omitting wing or hall now returns
"wing and hall are required" (400 over HTTP, a tool error over MCP) —
the only sane failure mode left once there is no other valid
destination.
- ingestion/internal/capture/ports.go, internal/brainstore/store.go: drop
Type/Domain from capture.Note and its WriteNoteOptions construction.
pipeline/*.go's unrelated "domain" field (a different, legitimate
concept for brain_ingest_raw) is untouched.
- internal/skills/brain/: deleted (orphaned legacy tool schema, dead
since cmd/supervisor was removed).
Tests: added TestWriteNote_RequiresWingAndHall (api),
TestBrainWriteRequiresWingAndHall +
TestBrainWriteIgnoresLegacyTypeAndDomainParams (mcp) for the new single
behaviour; removed tests that only exercised the deleted legacy path
(TestWrite_IncludesFrontmatterWhenTypeProvided,
TestWriteNote_HallRouteExistingTypeWinsOverOptsType,
TestBrainWriteRejectsTraversal, TestBrainWriteAcceptsDoubleDotInName —
the latter two's filename-sanitisation behaviour is covered independently
by internal/brain/path_test.go's TestNotePath_SanitisesWingAndSlug /
TestSanitise, which is unaffected by this change).
Co-Authored-By: Claude Sonnet 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>
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
Splits the audit port into Reserve (before any write) + Record (after),
so "confidential + sink-down → refuse before any write" is literally true
even though the audit record — which lists what landed — can only be
written afterwards.
- AuditSink.Reserve(ctx, level) → AuditOutcome | error. The error path
refuses the capture before writing: confidential + central sink down,
or the all-tiers floor (nothing can record).
- AuditSink.Record(ctx, entry, outcome) persists per the reserved outcome.
- Service: I5 gate runs after the I1 gate and after the dry-run
short-circuit (dry-run never probes the sink). AuditBuffered surfaces on
the receipt. New ErrAuditUnavailable sentinel (→ HTTP 503).
The tier→behaviour decision lives in the sink impl (#54's DegradingSink),
not the service — the service just honours Reserve's verdict.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
#52's IssueTracker spec is CloseIssue(repo, number, comment). Refine the
#51 port signature to match and have the service pass the ticket body as
the closing comment (empty ⇒ close only). Keeps the close-with-comment
flow first-class rather than forcing two separate ticket items.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The Clean-Architecture core of the capture capability (#49b). Pure
orchestration over ports — no HTTP, no live Gitea, no audit I/O — fully
unit-tested against fakes before any adapter exists.
- Ports: BrainStore (#45 write/update/get), IssueTracker, SummaryWriter,
ClassificationPolicy (satisfied by #50's classification.Config),
AuditSink. Entities: Insight, Ticket, Summary, CaptureContext,
CaptureInput, CaptureReceipt.
- CaptureService.Capture: validate-before-write (fail-closed), resolve
effective classification (stricter of declared vs target-derived;
under-declaration logged as a security event), orchestrate insights
(write/supersede) → tickets → summary best-effort, emit a request-level
audit record of exactly what landed, return a partial-aware receipt.
- dry_run short-circuits after validation, writes nothing (not even audit).
Out of scope here, layered on later: the I1 origin sovereignty gate (#53,
needs the server-derived principal) and the classification-aware audit
degradation/refusal (#54). "Effective" is folded into the service as
classification.Stricter rather than a port method — the stricter-wins
rule is use-case policy.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
mathiasandClaude Sonnet 5