Commit Graph

214 Commits

Author SHA1 Message Date
Mathias Bergqvist
751f410ca6 test(routing): pin tool-schema parity with supervisor
Captures the four routed skills' (review, debug, retrospective, trainer)
tool definitions as a JSON snapshot and asserts the routing pod's registry
advertises byte-equal schemas. A deliberate schema change fails this test,
requiring an intentional snapshot update in lockstep with consumers.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-04 22:59:06 +02:00
Mathias Bergqvist
3a99d5e20e refactor(routing): surface logger errors via slog.Warn
Replace silent `_ = r.Logger.LogDecision(...)` discards with an
if-err check that emits slog.Warn on failure. A brain outage now
produces a visible warn line instead of swallowing the telemetry
error entirely.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-04 22:55:35 +02:00
Mathias Bergqvist
9a258ca32a feat(routing): router dispatch wrapper
Composes Fetcher + Policy + Logger + CompleteFunc into a single Run method.
Falls open to Claude on local-model errors; defaults to local when brain is
unreachable. Skill packages will receive Router.Run as their CompleteFunc.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-04 22:51:01 +02:00
Mathias Bergqvist
2a5a74f7c0 feat(routing): decision logger via brain MCP session_log
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-04 15:52:09 +02:00
Mathias Bergqvist
d40a5ac890 test(routing): cover TTL expiry in fetcher
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-04 15:50:01 +02:00
Mathias Bergqvist
b77820534a feat(routing): pass-rate fetcher with TTL cache
HTTP client that calls GET /pass-rate?skill=X&window=Y on the brain pod.
Caches *float64 results (including nil) per-skill for the configured TTL
(default 60s). On non-200 or network error returns (nil, err) so the
upstream router can fall through to default-to-local.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-04 15:46:11 +02:00
Mathias Bergqvist
db64ecb1d9 feat(routing): canonical request hash
SHA-256 of (system, user) joined with 0x00 separator, truncated to
uint64. Drives deterministic sample-band routing: identical prompt pair
→ same hash → same local-vs-Claude decision on every call.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-04 15:41:42 +02:00
Mathias Bergqvist
ea29e5ebb8 feat(routing): decision policy
Pure-function Policy{Floor,Ceil} with Decide(*float64, uint64) Decision.
Rules in priority order: nil → local; ≥floor → local; <ceil → claude;
sample band → low bit of requestHash.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-04 15:36:59 +02:00
Mathias Bergqvist
ccf080db59 refactor(routing): clarify Floor/Ceil semantics + extend test coverage
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-04 15:34:22 +02:00
Mathias Bergqvist
69c038478b feat(routing): RoutingConfig + LoadRouting
Typed config struct and env parser for the routing pod. Kept separate
from the supervisor Config to avoid forcing routing fields onto the
supervisor and vice versa. Uses the existing envOr helper from config.go.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-04 15:25:31 +02:00
Mathias Bergqvist
b6bcc93048 docs(plan6): implementation plan for Mode 2 routing pod
All checks were successful
CI / Lint / Test / Vet (push) Successful in 10s
CI / Mirror to GitHub (push) Successful in 3s
14 TDD-shaped tasks across two worktrees: hyperguild for code
(internal/routing package, cmd/routing binary, Dockerfile, CD
workflow, mode template, smoke test, docs) and infra for the
k3s manifests (deployment, service, nodeport, SOPS-encrypted
secret). Plan 7 amendment baked in: internal/skills/{review,
debug,retrospective,trainer} survive Plan 6 — Plan 7 only
deletes tdd, spec, and the supervisor binary.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-04 14:53:03 +02:00
Mathias Bergqvist
51e01233a4 docs(plan6): spec for Mode 2 routing pod
All checks were successful
CI / Lint / Test / Vet (push) Successful in 10s
CI / Mirror to GitHub (push) Successful in 3s
Drafted via superpowers:feature-spec. Plan 6 of 7 in the skill
migration. Surface frozen at 4 cost-routable skills (code_review,
debug, retrospective, trainer); LiteLLM proxies model choice; pass-
rate drives the route decision with default-to-local plus an env
kill switch for the empty-data window. Plan 7 amendment baked in:
internal/skills/{review,debug,retrospective,trainer} survive Plan 6.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-04 14:29:26 +02:00
Mathias Bergqvist
f49850d23b chore(mcp): require bearer token for supervisor MCP
All checks were successful
CI / Lint / Test / Vet (push) Successful in 10s
CI / Mirror to GitHub (push) Successful in 4s
The pod now enforces SUPERVISOR_MCP_TOKEN; this matches the .mcp.json
header so a Claude Code session in this repo authenticates correctly.
Token comes from the operator's shell env, not the repo.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-04 13:57:14 +02:00
Mathias Bergqvist
928f23ab1b feat(mcp): optional bearer-token auth via SUPERVISOR_MCP_TOKEN
All checks were successful
CI / Lint / Test / Vet (push) Successful in 10s
CI / Mirror to GitHub (push) Successful in 3s
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>
2026-05-04 07:31:29 +02:00
Mathias Bergqvist
1b9c4905a5 docs(plans): patch Plan 5 — test helper sessions/ subdir + sessionlog docstring step
All checks were successful
CI / Lint / Test / Vet (push) Successful in 9s
CI / Mirror to GitHub (push) Successful in 4s
Two corrections applied during Plan 5 execution:

  - Task 2 test helper writeSession now joins a sessions/ subdir so it
    matches the handler's <brainDir>/sessions/*.jsonl scan path.
    (The original heredoc would have produced 0 records in tests.)

  - Task 6 grew a Step 1.5 to update the session_log MCP tool's
    final_status description, picking up a spec requirement that
    didn't translate into a task in the original plan.
2026-05-03 22:59:21 +02:00
Mathias Bergqvist
400025715a feat: pass-rate /pass-rate endpoint and CLI — Plan 5 of hyperguild migration
All checks were successful
CI / Lint / Test / Vet (push) Successful in 9s
CI / Mirror to GitHub (push) Successful in 3s
Adds the read side of pass-rate logging that consumes the SKILL.md
instrumentation landed in the local-dev companion merge:

  - GET /pass-rate?skill=X&window=Y on the brain pod (ingestion module)
    walks brain/sessions/*.jsonl, normalizes legacy {ok,error,skipped}
    to canonical {pass,fail,skip}, returns aggregate counts plus
    pass_rate (null when pass+fail == 0).

  - hyperguild brain pass-rate <skill> [--window 7d] [--json] CLI
    subcommand (third nested verb under brain).

  - session_log MCP tool docstring updated to lead with the new
    pass|fail|skip vocabulary; legacy values still accepted by both
    the tool's loose validator and the aggregator's normalization.

This is the brain HTTP REST API's first GET endpoint — pure reads
follow REST semantics; legacy POST routes (query, write, ingest, etc.)
all take JSON bodies. Future read endpoints SHOULD use GET.

Plan 6 routing pod is the consumer; one week of usage data between
this merge and Plan 6 deploy will mean Plan 6 lands on real numbers.

Plan: docs/superpowers/plans/2026-05-03-pass-rate-logging.md
Spec: docs/superpowers/specs/2026-05-03-pass-rate-logging-design.md
2026-05-03 22:58:24 +02:00
Mathias Bergqvist
986e3e1d12 docs(hyperguild): document brain pass-rate subcommand and /pass-rate endpoint
Adds pass-rate to the CLI README's subcommand block. Updates CLAUDE.md
to note the new /pass-rate endpoint alongside the existing brain
HTTP REST API surface. Updates the session_log MCP tool's
final_status description to reflect the new pass|fail|skip vocabulary
introduced by Plan 5's SKILL.md instrumentation; the aggregator
still accepts legacy ok|error|skipped values for backwards compat.
2026-05-03 22:55:35 +02:00
Mathias Bergqvist
593d1a4c6d feat(hyperguild): brain pass-rate subcommand
Adds 'hyperguild brain pass-rate <skill> [--window 7d] [--json]'
calling the new /pass-rate endpoint. Human output:
  tdd: 47 / 50 = 94% (window: 7d)
or 'no data (window: 7d)' when pass_rate is null.

PassRateResult mirrors the response envelope; PassRate is *float64
so null is preserved across decode.
2026-05-03 22:44:04 +02:00
Mathias Bergqvist
417bf224eb feat(brain): register GET /pass-rate route
Adds the route entry alongside the existing POST routes. Note: this
is the brain HTTP REST API's first GET endpoint — it follows REST
semantics for pure reads, while the legacy POST routes (query, write,
ingest, etc.) all take JSON bodies. Future read endpoints SHOULD use
GET; future write endpoints continue with POST.
2026-05-03 22:40:31 +02:00
Mathias Bergqvist
37dbd22eff feat(brain): /pass-rate aggregator and handler
Adds a new HTTP GET handler at the ingestion pod that walks
brain/sessions/*.jsonl, filters by skill name and timestamp window
(default 7d, accepts Nh and Nd), normalizes legacy status vocabulary
(ok->pass, error->fail, skipped->skip), and returns aggregated counts
plus pass_rate.

Pass rate is null when pass+fail == 0, distinguishing 'no data' from
'always passes'. Plan 6 routing pod will check for null before
making decisions.

Route registration in cmd/server/main.go lands in a follow-up commit.
2026-05-03 22:37:41 +02:00
Mathias Bergqvist
cbf5cab5e7 docs(plans): pass-rate logging implementation plan — Plan 5
All checks were successful
CI / Lint / Test / Vet (push) Successful in 10s
CI / Mirror to GitHub (push) Successful in 4s
Seven-task plan spanning two worktrees: Phase 1 (local-dev) for
SKILL.md instrumentation (pilot tdd, then rollout to 6 binary-outcome
skills), Phase 2 (hyperguild) for the /pass-rate endpoint + CLI
subcommand. Uses GET for the pure-read endpoint (REST semantics)
despite the brain API's POST-everywhere precedent for legacy
endpoints.

Pilot-then-rollout structure: tdd SKILL.md lands first; the
endpoint TDD task naturally exercises the new logging contract
as the dogfood validation step before the other 6 skills get
instrumented.
2026-05-03 22:29:56 +02:00
Mathias Bergqvist
af52f501fe docs(specs): pass-rate logging design — Plan 5 of hyperguild migration
Skill instrumentation pattern, brain /pass-rate HTTP endpoint, and
optional hyperguild CLI subcommand for shell access. Pilot with tdd
SKILL.md, then roll out to 6 binary-outcome skills (code-review,
debug, feature-spec, session-retrospective, trainer, spec-driven-dev).

Decisions: SKILL.md as source of truth for the logging contract;
on-demand aggregation from JSONL (no materialized counters until
proven necessary); pass|fail|skip vocabulary forward, with
ok|error|skipped accepted by the read-side aggregator for backwards
compat.

Seven success criteria, ten out-of-scope items, six risks.
2026-05-03 22:23:28 +02:00
Mathias Bergqvist
b3b1fde825 feat: hyperguild CLI — Plan 4 of hyperguild migration
All checks were successful
CI / Lint / Test / Vet (push) Successful in 15s
CI / Mirror to GitHub (push) Successful in 3s
A small Go binary at cmd/hyperguild/ providing four subcommands:

  - tier              probe Anthropic + LiteLLM, print operating tier
  - brain query       BM25 search the brain via HTTP REST
  - brain write       write a knowledge entry from stdin
  - mode <name>       bootstrap .mcp.json (cloud|client-local|sovereign)

Reuses internal/tier verbatim. Brain access uses the HTTP REST API
at ${BRAIN_URL:-http://koala:30330} with POST /query and POST /write.
Mode templates include a Plan 6 routing-pod placeholder (client-local)
and a Crush-fallback note (sovereign).

Stdlib only — flag, net/http, encoding/json. 32 unit tests via
httptest.Server fakes; smoke-tested end-to-end against the live brain.

Replaces the supervisor's tier MCP. Plans 5 (pass-rate logging) and 6
(routing pod) build on the brain client and tier subcommand.

Plan: docs/superpowers/plans/2026-05-03-hyperguild-cli.md
Spec: docs/superpowers/specs/2026-05-03-hyperguild-cli-design.md
2026-05-03 22:06:48 +02:00
Mathias Bergqvist
ab4cfaaeb7 fix(hyperguild): remove redundant subcommand prefixes from error messages
dispatch() already prefixes errors with 'hyperguild <subcmd>: ', so
handlers re-prefixing with their own name produced stuttered output
like 'hyperguild brain: brain query: topic required'. Strip the
redundant prefixes from the seven affected errors.New / fmt.Errorf
calls in brain.go and mode.go.

Also fix the LITELLM_BASE_URL usage text — it's optional (empty
falls through to airplane tier), not required, matching the
README.
2026-05-03 22:06:33 +02:00
Mathias Bergqvist
eb844edb29 docs(specs): correct brain Query method (POST not GET)
The brain HTTP REST /query endpoint accepts POST with JSON body
{query, limit}, not GET with URL query string. Surfaced empirically
during Plan 4 Task 7 smoke testing. Spec text now matches the
implementation.
2026-05-03 22:00:05 +02:00
Mathias Bergqvist
317ec20392 fix(hyperguild): brain Query uses POST /query with JSON body
The brain HTTP REST /query endpoint accepts POST with JSON
{query, limit}, not GET with URL query string. Surfaced by
Task 7 smoke testing — GET returned 405 Method Not Allowed.

The response shape ({results:[...]}) is unchanged; only the
request side flips to POST + JSON body. brainClient.Write was
already using POST + JSON body and is unaffected.

Tests updated to assert POST + JSON body on the Query path.
2026-05-03 21:59:17 +02:00
Mathias Bergqvist
eab8775f5f feat(hyperguild): README + Taskfile integration
Adds cmd/hyperguild/README.md (subcommands, env vars, install path)
and three Taskfile targets:

  task hyperguild:dev     — go run from source
  task hyperguild:build   — build into ./bin/hyperguild
  task hyperguild:install — go install into $GOBIN

Concludes Plan 4 of the hyperguild migration. The binary replaces
the supervisor's tier MCP and surfaces brain HTTP REST access plus
mode bootstrap to shell pipelines and ad-hoc agent prompts.
2026-05-03 21:56:20 +02:00
Mathias Bergqvist
a0d0914a85 feat(hyperguild): mode subcommand
'hyperguild mode <cloud|client-local|sovereign>' writes a per-mode
.mcp.json template:

  - cloud:        brain MCP only
  - client-local: brain + routing placeholder with _routing_pending
                  pointer to Plan 6
  - sovereign:    brain only + top-level _mode_note explaining Crush
                  is primary; .mcp.json is Claude Code fallback

Default output is ./.mcp.json; --out overrides; --force overwrites.
Brain URL sourced from BRAIN_URL (default http://koala:30330) so the
template stays in lockstep with the user's brain host.

All three subcommands now wired; notYet/errNotImplemented removed
from main.go.
2026-05-03 21:50:05 +02:00
Mathias Bergqvist
8f9642df69 feat(hyperguild): brain write subcommand
Reads markdown from stdin, POSTs to the brain's /write endpoint with
type + slug, prints the resulting path. Pairs with 'brain query' for
shell-friendly read/write access to the brain HTTP REST API.

Tests cover success, missing args, backend error propagation, and
empty stdin (which produces an empty content payload — the brain
server's responsibility to validate).
2026-05-03 21:42:36 +02:00
Mathias Bergqvist
cd5f3c0175 feat(hyperguild): brain query subcommand
Adds 'hyperguild brain query <topic>' against the brain HTTP REST
/query endpoint. Default human output prints path + score + title;
--json passes through the response envelope. --limit overrides the
default 5-result cap.

runBrainWrite remains a stub for Task 5.
2026-05-03 21:37:39 +02:00
Mathias Bergqvist
ed4966927c feat(hyperguild): brain HTTP REST client
Adds brainClient with Query and Write methods against the brain's
HTTP REST endpoints (/query, /write). Constructor reads BRAIN_URL env
var, defaulting to http://koala:30330 — the Tailscale-exposed
NodePort that serves both MCP and REST.

Tests cover success, transport error, and non-200 cases via
httptest fakes; URL override is verified via t.Setenv.
2026-05-03 21:32:48 +02:00
Mathias Bergqvist
3c4e8e8bb8 feat(hyperguild): tier subcommand
Adds the tier subcommand to the hyperguild CLI. Reuses
internal/tier.Detect verbatim, sources probe URLs from
ANTHROPIC_PROBE_URL (default https://api.anthropic.com) and
LITELLM_BASE_URL (no default — empty triggers airplane).

Human-readable output by default; --json emits the same Info struct
as the supervisor's tier MCP returns. Tests cover all three tier
states via httptest fakes.
2026-05-03 21:27:33 +02:00
Mathias Bergqvist
5c88eff46f feat(hyperguild): subcommand router skeleton
Lays down the cmd/hyperguild/ entry point. Defines the subcommand
contract (ctx, args, stdin, stdout, stderr) error, the dispatch()
function that's testable without os.Exit, and stubs for tier / brain /
mode that return errNotImplemented. Subsequent commits replace each
stub.

Part of Plan 4 (hyperguild CLI) of the hyperguild migration.
2026-05-03 21:21:08 +02:00
Mathias Bergqvist
646a86f2c3 docs(specs): fix brain URL port (3300 → 30330)
Pod-internal port is 3300; Tailscale-exposed NodePort is 30330.
External clients including the planned hyperguild CLI hit 30330.
2026-05-03 21:01:51 +02:00
Mathias Bergqvist
adf0504116 docs(specs): hyperguild CLI design — Plan 4 of hyperguild migration
Implementation-level spec for the hyperguild CLI: a stdlib Go binary
at cmd/hyperguild/ with subcommands tier, brain query/write, and mode
(cloud|client-local|sovereign). Replaces the supervisor's tier MCP and
provides shell-friendly access to the brain HTTP REST API.

Six measurable success criteria, seven out-of-scope items, six risks.
Decisions logged: stdlib flag + inline router (no cobra), reuse
internal/tier verbatim, BRAIN_URL env override, mode subcommand writes
.mcp.json with per-mode template plus placeholder for the Plan 6
routing pod.
2026-05-03 20:59:45 +02:00
Mathias Bergqvist
d44427e71f docs: document brain MCP endpoint at koala:30330
All checks were successful
CI / Lint / Test / Vet (push) Successful in 9s
CI / Mirror to GitHub (push) Successful in 3s
- 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>
2026-05-02 23:03:45 +02:00
Mathias Bergqvist
2635cdcaa7 chore: add brain MCP server alongside supervisor
The brain MCP at koala:30330 hosts the brain_* and session_log tools
formerly on supervisor. Supervisor stays connected during the
transition; its skill workers and the brain duplication will be
removed in a later plan.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-02 23:02:28 +02:00
Mathias Bergqvist
e922471229 fix(context-sync): short-circuit when root AGENT.md is unreachable
All checks were successful
CI / Lint / Test / Vet (push) Successful in 9s
CI / Mirror to GitHub (push) Successful in 3s
In CI's clean checkout the tree-walk for ~/dev/.context/AGENT.md
finds nothing, leaving ROOT_CONTEXT empty. The script previously
proceeded to regenerate AGENTS.md, .cursorrules,
.aider.conventions.md, and .context/system-prompt.txt as
project-only — but the committed versions are root+project, so
the drift gate added in cc401d9 fails CI on every push.

When no root context is reachable, only regenerate CLAUDE.md
(which is project-only by design — Claude Code walks up the tree
itself to find the root). The root-bearing adapters are left
untouched, eliminating the false-positive drift.

Local runs (with root context reachable) are unchanged.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-02 22:55:43 +02:00
Mathias Bergqvist
87ff1f907c fix(ingestion): silence errcheck on resp.Body.Close in integration test
Some checks failed
CI / Lint / Test / Vet (push) Failing after 3s
CI / Mirror to GitHub (push) Has been skipped
CI's golangci-lint flagged the un-checked deferred Close. Match the
existing project pattern (defer func() { _ = ... }()).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-02 14:55:29 +02:00
Mathias Bergqvist
9cc179dec6 feat: brain MCP migration — extract brain_* + session_log into ingestion pod
Some checks failed
CI / Lint / Test / Vet (push) Failing after 2s
CI / Mirror to GitHub (push) Has been skipped
Slice 1 of the larger SKILL.md + routing-MCP architecture migration.
Adds an MCP HTTP handler to the ingestion service at POST /mcp,
exposing 5 tools (brain_query, brain_write, brain_ingest_raw,
brain_ingest, session_log). Plan and 9 implementation commits
preserved on the feat/brain-mcp-migration branch.

NodePort 30330 wired in infra repo separately (commit 008548e).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-02 14:05:08 +02:00
Mathias Bergqvist
370d30e376 feat(ingestion): mount MCP handler at POST /mcp
The ingestion server now exposes both REST and MCP on the same port
(3300). MCP shares brainDir, pipeline config, and LLM client with the
REST handlers — single source of process state.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-01 19:41:05 +02:00
Mathias Bergqvist
bd0c1d75fd feat(ingestion): implement session_log MCP tool
Appends a JSON line to brainDir/sessions/<session_id>.jsonl using the
session package copied in Task 2. Required for upcoming pass-rate
logging.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-01 13:04:40 +02:00
Mathias Bergqvist
8c87460bff feat(ingestion): implement brain_ingest MCP tool
Wraps pipeline.Run with the existing LLM client. Mirrors the HTTP
/ingest and /ingest-path semantics — accepts either path or
content+source, validates mutual exclusion, surfaces an explicit error
when the LLM client is not configured (test-mode).

ctx is threaded through to pipeline.Run for cancellation.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-01 13:02:02 +02:00
Mathias Bergqvist
809d435480 feat(ingestion): implement brain_ingest_raw MCP tool
Wraps pipeline.RunRaw directly. Same dry-run semantics as the HTTP
/ingest-raw endpoint. Test exercises a single concept page; asserts
returned path and that no file is written under dry_run.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-01 10:28:05 +02:00
Mathias Bergqvist
e4a94df4fc feat(ingestion): extract WriteNote helper and add brain_write MCP tool
api.WriteNote captures the file-write logic that was previously inline
in Handler.Write. The existing HTTP endpoint now delegates to it; the
new MCP brain_write tool reuses the same function. Path-traversal
guard is strengthened to explicitly reject filenames containing path
separators or "..", so the rejection is surfaced before filepath.Base
strips the suspicious component (the previous defense-in-depth prefix
check became unreachable for these inputs after Base normalisation).
HTTP error code for caller-input errors shifts from 500 to 400, which
is semantically correct and not exercised by any existing test.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-01 10:25:38 +02:00
Mathias Bergqvist
7dcb5610fe feat(ingestion): implement brain_query MCP tool
Wraps the existing search.Query function. Same BM25 over
brain/knowledge/ and brain/wiki/ that the HTTP /query endpoint serves.
Plan note: handleCall switch replaces the single-line stub from Task 1
— no unknownToolError type to remove since Task 1 inlined the error.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-01 09:56:40 +02:00
Mathias Bergqvist
63c8d114e8 feat(ingestion): add session package for JSONL log persistence
Copy of internal/session from the supervisor module — the ingestion
service needs it for the upcoming session_log MCP tool. The supervisor
copy will be removed in the supervisor-retirement plan; until then
the two packages are intentionally identical and pinned (no edits).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-01 09:54:24 +02:00
Mathias Bergqvist
54f7d373bd feat(ingestion): add MCP server skeleton with tools/list
Adds an MCP HTTP handler under ingestion/internal/mcp. Implements
initialize, tools/list, and the JSON-RPC notification skip from prior
work. Tool dispatch is stubbed (returns unknown-tool error) and will be
filled in by subsequent tasks.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-01 09:43:23 +02:00
Mathias Bergqvist
a412eee427 docs: add brain MCP migration plan
13 TDD-disciplined tasks moving brain_* and session_log out of the
supervisor pod and into the ingestion pod's MCP handler. Slice 1 of
the larger SKILL.md + routing-MCP architecture migration.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-01 09:27:28 +02:00
Mathias Bergqvist
3d6f33881b chore: remove sources: from context:sync to disable Task source-cache
Some checks failed
CI / Lint / Test / Vet (push) Failing after 1s
CI / Mirror to GitHub (push) Has been skipped
Task's sources: declaration cached the regeneration on the assumption
that adapter outputs depend only on .context/AGENT.md (or PROJECT.md +
.skills/). The cache occasionally skipped legitimate runs after manual
edits to root or template content not detectable from those source paths.
context-sync.sh is idempotent and cheap; running it on every invocation
is the right default. The freshness gate (git status --porcelain) is
unaffected — it always checked the actual git tree state.
2026-04-30 23:14:20 +02:00