docs: name brain-mcp and say where its code lives (#94 ) (#99 )

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>
feat(mcp): record and alert on a governance-file rewrite (#97 ) (#98 )
2026-08-22 06:10:06 +00:00 · 2026-08-22 06:09:53 +00:00 · 2026-08-18 18:14:05 +00:00 · 2026-08-18 18:13:48 +00:00 · 2026-08-18 06:05:18 +00:00 · 2026-08-18 07:13:15 +02:00
82 changed files with 3855 additions and 314 deletions
@@ -78,6 +78,14 @@ These rules apply to every task across every project, regardless of harness.
   - Surface the brain entries and issue numbers in the closing summary so the
     trail is auditable.

+## CAD sprint patterns
+
+Two CAD sprint archetypes (defs: brain `wiki/homelab/decisions/continuous-agentic-development-cad-concept-2026-06-16`):
+- **Inception Sprint** — birth a new repo. Oath-gated close; tag only once every clause holds. Brain: `.../inception-sprint-and-oath`.
+- **Sweep Sprint** — clear an existing backlog. Parallel read-only research per issue → sequential one-issue-per-commit execution. Brain: `.../sweep-sprint-and-oath`.
+
+Shared: decisions that are yours, not the agent's, surface as `DECISION NEEDED` (question/options/recommendation/blocks) — ask live if you're present, else comment and wait, never act past it. Live-breaking regressions get `git revert`, never forward-fixed; host-network work skips even read-only research (solo, synchronous, you present). Rule 6's closing ritual only fires once every Oath clause genuinely holds — blocked = descoped-and-tracked, never marked done.
+
 ## Default stack

 | Layer | Default | Fallback | Last resort |
@@ -88,7 +96,7 @@ These rules apply to every task across every project, regardless of harness.
 | Containers | Docker Compose (dev), k3s (prod) | — | — |
 | DB | PostgreSQL + sqlc | SQLite | — |
 | Search | pgvector (vector), BM25 | Qdrant (when >1M vectors or hybrid retrieval) | — |
-| Logging | slog (structured) | — | — |
+| Logging | slog (structured) | stdlib `logging` w/ structured `extra=` (or structlog) | — |
 | Testing | Table-driven, testify | — | — |
 | Agents (Go) | google.golang.org/adk + pkg/litellm adapter | — | — |

@@ -97,7 +105,12 @@ Exploratory: Rust, Zig — I'll tell you when I want these.
 ## Code conventions

 - **Go style**: golines, gofumpt, golangci-lint
- **Errors**: `fmt.Errorf("operation: %w", err)` — never naked, never log-and-return
+- **Python style** (fallback language): ruff (format+lint, one tool), mypy --strict (non-negotiable,
+  matches Go's static typing discipline), pytest + pytest-cov (table-driven via
+  `@pytest.mark.parametrize`), uv (venv+deps+lock, one tool), pydantic-settings (typed env-var config
+  — same principle as Go's typed structs), src-layout + `pyproject.toml` only (no `setup.py`)
+- **Errors**: `fmt.Errorf("operation: %w", err)` — never naked, never log-and-return.
+  Python: `raise X from e` (exception chaining, same principle) — never bare `except`, never silent `pass`
 - **Naming**: stdlib conventions, no stuttering
 - **Architecture**: prefer stdlib over frameworks, constructor injection, env-var config parsed into typed structs
 - **Git**: conventional commits (`feat:`, `fix:`, `chore:`), commit directly to main,
@@ -0,0 +1,2 @@
+# Presence of this file marks this repo as opt-in for headless dispatch.
+# See dispatch#3.
@@ -48,9 +48,23 @@ jobs:
          mkdir -p ~/.ssh
          echo "${{ secrets.INFRA_DEPLOY_KEY }}" > ~/.ssh/infra_deploy_key
          chmod 600 ~/.ssh/infra_deploy_key
-          printf 'Host git.d-ma.be\n  HostName 127.0.0.1\n  Port 30022\n  StrictHostKeyChecking no\n' >> ~/.ssh/config
-
-          GIT_SSH_COMMAND="ssh -i ~/.ssh/infra_deploy_key -o IdentitiesOnly=yes" \
+          # In-cluster DNS to gitea's SSH NodePort service, not 127.0.0.1:30022
+          # (that only worked when act_runner ran on koala's bare host network;
+          # from inside the containerized runner's own pod netns, loopback
+          # never reaches the host — "Connection refused", found 2026-07-27).
+          #
+          # Pass as -o overrides on the ssh invocation itself, NOT appended to
+          # ~/.ssh/config: $HOME (/data) is a PVC that persists across job
+          # runs on this runner (same "workspace not ephemeral" class as
+          # brain: act-runner-host-executor-tmp-persists), so an appended
+          # line here would pile up duplicate `Host git.d-ma.be` blocks
+          # across every run — ssh_config is first-match-wins, so a stale
+          # entry from an earlier failed run would silently shadow this
+          # fix forever (exactly what happened once already: this fix's
+          # own first attempt got appended AFTER an already-stale entry
+          # and lost). CLI -o options always win regardless of file state,
+          # so this step is safe to re-run any number of times.
+          GIT_SSH_COMMAND="ssh -i ~/.ssh/infra_deploy_key -o IdentitiesOnly=yes -o HostName=gitea-ssh-nodeport.gitea.svc.cluster.local -o Port=22 -o StrictHostKeyChecking=no" \
            git clone "${INFRA_REPO}" /tmp/infra-update

          cd /tmp/infra-update
@@ -0,0 +1,63 @@
+# gitleaks config for the hyperguild repo (infra#39 — leak prevention pass,
+# Phase 3 checklist item: "gitleaks pre-commit hook in infra AND hyperguild").
+#
+# Ported from mathias/infra's .gitleaks.toml (2026-08-04) — same homelab
+# token-shape rules, minus the SOPS/searxng allowlists infra needed (this
+# repo doesn't use SOPS).
+
+title = "hyperguild gitleaks config"
+
+[extend]
+useDefault = true
+
+# --- Homelab-specific rules -------------------------------------------------
+
+[[rules]]
+id = "homelab-static-bearer"
+description = "Homelab MCP/LLM static bearer or API key assigned a long literal value"
+regex = '''(?i)\b(DMABE_[A-Z0-9_]+|[A-Z0-9_]*MCP_TOKEN|ROUTING_MCP_TOKEN|INFRA_MCP_TOKEN|BRAIN_MCP_TOKEN|GITEA_MCP_TOKEN|LITELLM_MASTER_KEY|LITELLM_SALT_KEY|DMABE_LLMAPI_KEY|BRAIN_PG_DSN)\s*[:=]\s*['"]?([A-Za-z0-9/_+.\-]{16,})['"]?'''
+keywords = ["dmabe_", "mcp_token", "litellm_master_key", "litellm_salt_key", "llmapi_key", "brain_pg_dsn"]
+[[rules.allowlists]]
+description = "Env indirection is not a literal secret"
+regexes = [
+  '''os\.environ''',
+  '''valueFrom''',
+  '''secretKeyRef''',
+  '''\$\{?[A-Za-z_][A-Za-z0-9_]*\}?''',
+  '''REDACTED''',
+  '''<[A-Z_]+>''',
+]
+
+[[rules]]
+id = "homelab-authorization-bearer"
+description = "Hardcoded Authorization: Bearer header"
+regex = '''(?i)authorization['"]?\s*[:=]\s*['"]?bearer\s+([A-Za-z0-9/_+.\-=]{16,})'''
+keywords = ["authorization", "bearer"]
+[[rules.allowlists]]
+description = "Env indirection is not a literal secret"
+regexes = [
+  '''\$\{?[A-Za-z_][A-Za-z0-9_]*\}?''',
+  '''os\.environ''',
+  '''REDACTED''',
+  '''<[A-Z_]+>''',
+]
+
+# --- Global allowlist: claudewatcher's own scrubber test fixtures ------------
+# ingestion/internal/claudewatcher/{scrubber,watcher}_test.go deliberately
+# contain fake secret-shaped literals to test that the scrubber detects and
+# redacts them. Verified 2026-08-04: all 9 findings here are test fixtures
+# (github-pat, jwt, generic-api-key, homelab-authorization-bearer rules) plus
+# 1 doc finding that was gitleaks matching the literal placeholder word
+# "REDACTED" in a plan doc — not a real secret in either case.
+[[allowlists]]
+description = "claudewatcher scrubber test fixtures — deliberately fake secrets"
+paths = [
+  '''ingestion/internal/claudewatcher/scrubber_test\.go$''',
+  '''ingestion/internal/claudewatcher/watcher_test\.go$''',
+]
+
+[[allowlists]]
+description = "Literal placeholder word REDACTED matched as if it were a token (verified 2026-08-04: extracted Secret == 'REDACTED' exactly, gitleaks' curl-auth-header rule matched the placeholder text itself, not a real credential)"
+condition = "AND"
+paths = ['''docs/superpowers/plans/2026-04-22-phase4-attempt-wiring\.md$''']
+regexes = ['''REDACTED''']
@@ -73,6 +73,14 @@ These rules apply to every task across every project, regardless of harness.
   - Surface the brain entries and issue numbers in the closing summary so the
     trail is auditable.

+## CAD sprint patterns
+
+Two CAD sprint archetypes (defs: brain `wiki/homelab/decisions/continuous-agentic-development-cad-concept-2026-06-16`):
+- **Inception Sprint** — birth a new repo. Oath-gated close; tag only once every clause holds. Brain: `.../inception-sprint-and-oath`.
+- **Sweep Sprint** — clear an existing backlog. Parallel read-only research per issue → sequential one-issue-per-commit execution. Brain: `.../sweep-sprint-and-oath`.
+
+Shared: decisions that are yours, not the agent's, surface as `DECISION NEEDED` (question/options/recommendation/blocks) — ask live if you're present, else comment and wait, never act past it. Live-breaking regressions get `git revert`, never forward-fixed; host-network work skips even read-only research (solo, synchronous, you present). Rule 6's closing ritual only fires once every Oath clause genuinely holds — blocked = descoped-and-tracked, never marked done.
+
 ## Default stack

 | Layer | Default | Fallback | Last resort |
@@ -83,7 +91,7 @@ These rules apply to every task across every project, regardless of harness.
 | Containers | Docker Compose (dev), k3s (prod) | — | — |
 | DB | PostgreSQL + sqlc | SQLite | — |
 | Search | pgvector (vector), BM25 | Qdrant (when >1M vectors or hybrid retrieval) | — |
-| Logging | slog (structured) | — | — |
+| Logging | slog (structured) | stdlib `logging` w/ structured `extra=` (or structlog) | — |
 | Testing | Table-driven, testify | — | — |
 | Agents (Go) | google.golang.org/adk + pkg/litellm adapter | — | — |

@@ -92,7 +100,12 @@ Exploratory: Rust, Zig — I'll tell you when I want these.
 ## Code conventions

 - **Go style**: golines, gofumpt, golangci-lint
- **Errors**: `fmt.Errorf("operation: %w", err)` — never naked, never log-and-return
+- **Python style** (fallback language): ruff (format+lint, one tool), mypy --strict (non-negotiable,
+  matches Go's static typing discipline), pytest + pytest-cov (table-driven via
+  `@pytest.mark.parametrize`), uv (venv+deps+lock, one tool), pydantic-settings (typed env-var config
+  — same principle as Go's typed structs), src-layout + `pyproject.toml` only (no `setup.py`)
+- **Errors**: `fmt.Errorf("operation: %w", err)` — never naked, never log-and-return.
+  Python: `raise X from e` (exception chaining, same principle) — never bare `except`, never silent `pass`
 - **Naming**: stdlib conventions, no stuttering
 - **Architecture**: prefer stdlib over frameworks, constructor injection, env-var config parsed into typed structs
 - **Git**: conventional commits (`feat:`, `fix:`, `chore:`), commit directly to main,
@@ -5,6 +5,11 @@ Instead of letting Claude Code do whatever it wants, hyperguild enforces structu
 workflows (TDD red/green/refactor), logs every session, and accumulates learnings
 into a searchable brain.

+**This repo is also where `brain-mcp` lives** — the MCP server at
+`brain-mcp.d-ma.be` that `brain_query`, `brain_write`, `brain_read`, `brain_edit`
+and `capture` are served from. It is not a separate deployable; see
+[Where brain-mcp lives](#where-brain-mcp-lives).
+
 ## Hypothesis

 > We believe routing skill tasks through local models, backed by brain context,
@@ -20,7 +25,7 @@ usage, the fast-model routing path should be reconsidered.

 **hyperguild = Claude Code + MCP.** This is a supervisor for Claude Code sessions specifically.
 For multi-agent orchestration (OpenCode + LiteLLM, executor/reviewer pipelines), see
-[agentsquad](http://gitea.d-ma.be/mathias/agentsquad) — a separate harness for a different
+[agentsquad](https://git.d-ma.be/mathias/agentsquad) — a separate harness for a different
 orchestration model. Skills (mathias/skills) are shared between both.

 ## How it works
@@ -44,6 +49,33 @@ brain/
 └── knowledge/      — legacy flat notes (migration pending: hyperguild#22)
 ```

+## Where brain-mcp lives
+
+`brain-mcp` is served from **`ingestion/internal/mcp`** in this repo, at
+**`brain-mcp.d-ma.be`**. It is a component *inside* the `ingestion` service, not
+a standalone deployable — one pod in the `supervisor` namespace serves the MCP
+endpoint, the REST API, and the claudewatcher together.
+
+| You are looking for | It is here |
+|---|---|
+| The MCP tool surface (`brain_query`, `brain_write`, `brain_read`, `brain_edit`, `capture`, …) | `ingestion/internal/mcp` |
+| The HTTP/REST API (`/query`, `/write`, `/ingest`) | `ingestion/internal/api` |
+| Session ingestion from Claude Code transcripts | `ingestion/internal/claudewatcher` |
+| The brain *content* (notes, wings, halls) | [`mathias/brain`](https://git.d-ma.be/mathias/brain) — a separate repo |
+| Deployment manifests | `config/supervisor` |
+
+### Why it is not its own repo
+
+Asked and decided in [#91](https://git.d-ma.be/mathias/hyperguild/issues/91)
+(part 2). `internal/mcp` imports 17 of ingestion's other internal packages and
+has exactly one importer — it is the MCP facade over the service's own
+internals, so "move it out" resolves to renaming `ingestion`, publishing 17
+packages as a shared library, or maintaining a shim. The discoverability problem
+that prompted the question is answered by naming it here instead.
+
+Full reasoning, including the reversal trigger: brain
+`wiki/hyperguild/decisions/brain-mcp-stays-in-ingestion-fix-discoverability-by-name`.
+
 ## Phase 1 tools (available now)

 | Tool | What it does |
@@ -58,7 +90,7 @@ brain/
 | `tier` | Returns the current connectivity tier (1=cloud, 2=LAN, 3=offline) |

 > **Note:** `tdd_red/green/refactor` and `spec` were retired in Plan 7 (2026-05-12).
-> They are now SKILL.md files in [mathias/skills](http://gitea.d-ma.be/mathias/skills).
+> They are now SKILL.md files in [mathias/skills](https://git.d-ma.be/mathias/skills).

 ## Connect a project

@@ -147,7 +179,7 @@ The routing pod selects models per skill call based on historical pass rate:

 ## Open issues

-See [issues](http://gitea.d-ma.be/mathias/hyperguild/issues) — key open items:
+See [issues](https://git.d-ma.be/mathias/hyperguild/issues) — key open items:

 - **#25** — skills platform overhaul (audit first, then lazy loading + brain feedback loop)
 - **#24** — reduce context burn from skill listing
@@ -101,12 +101,48 @@ tasks:
      - task: lint
      - task: test
      - task: vet
+      - task: security:gitleaks
+
+  # ── Security ─────────────────────────────────────────────
+  security:gitleaks:
+    desc: Scan the working tree for secrets (gitleaks, fail-closed; skipped if gitleaks absent)
+    dir: '{{.ROOT_DIR}}'
+    cmds:
+      - |
+        GL="$(command -v gitleaks || true)"
+        [ -z "$GL" ] && [ -x "$(go env GOPATH 2>/dev/null)/bin/gitleaks" ] && GL="$(go env GOPATH)/bin/gitleaks"
+        if [ -z "$GL" ]; then
+          echo "⚠ gitleaks not installed — skipping secret scan (CI enforces it)."
+          echo "  Install: go install github.com/zricethezav/gitleaks/v8@latest"
+          exit 0
+        fi
+        "$GL" detect --no-git --redact --config .gitleaks.toml --source .
+
+  security:gitleaks:history:
+    desc: "One-time FULL-HISTORY secret audit (infra#39 rotation pass; not a per-push gate)"
+    dir: '{{.ROOT_DIR}}'
+    cmds:
+      - |
+        GL="$(command -v gitleaks || true)"
+        [ -z "$GL" ] && [ -x "$(go env GOPATH 2>/dev/null)/bin/gitleaks" ] && GL="$(go env GOPATH)/bin/gitleaks"
+        if [ -z "$GL" ]; then
+          echo "gitleaks not installed: go install github.com/zricethezav/gitleaks/v8@latest" >&2
+          exit 2
+        fi
+        echo "Scanning FULL git history (redacted). Known historical leaks are expected"
+        echo "until the infra#39 rotation pass completes — triage against the rotation list."
+        "$GL" detect --redact --config .gitleaks.toml

  lint:
    cmds:
      - golangci-lint run ./...
      - cd ingestion && golangci-lint run ./...

+  lint:frontmatter:
+    desc: Report brain notes whose YAML frontmatter does not parse (BRAIN=path, FIX=1 repairs in place)
+    cmds:
+      - cd ingestion && go run ./cmd/frontmatterlint {{if .FIX}}-fix{{end}} {{.BRAIN | default "../../brain"}}
+
  test:
    cmds:
      - go test -race -count=1 ./...
@@ -8,7 +8,7 @@ import (
 	"io"
 	"os"

-	"github.com/mathiasbq/supervisor/internal/tier"
+	"git.d-ma.be/mathias/hyperguild/internal/tier"
 )

 const defaultAnthropicProbe = "https://api.anthropic.com"
@@ -1,4 +1,4 @@
-module github.com/mathiasbq/supervisor
+module git.d-ma.be/mathias/hyperguild

 go 1.26.1

@@ -0,0 +1,53 @@
+// Command frontmatterlint reports markdown notes whose YAML frontmatter does
+// not parse, and optionally repairs the ones that only need quoting.
+//
+//	go run ./cmd/frontmatterlint ../../brain          # report
+//	go run ./cmd/frontmatterlint -fix ../../brain     # repair in place
+//
+// Exit codes: 0 clean (or everything repaired), 1 findings remain, 2 the scan
+// itself failed.
+package main
+
+import (
+	"flag"
+	"fmt"
+	"os"
+
+	"github.com/mathiasbq/hyperguild/ingestion/internal/frontmatter"
+)
+
+func main() {
+	fix := flag.Bool("fix", false, "repair files that quoting can rescue, in place")
+	flag.Parse()
+
+	root := "."
+	if flag.NArg() > 0 {
+		root = flag.Arg(0)
+	}
+
+	findings, err := frontmatter.Scan(root, *fix)
+	if err != nil {
+		fmt.Fprintln(os.Stderr, "frontmatterlint:", err)
+		os.Exit(2)
+	}
+
+	var unresolved int
+	for _, f := range findings {
+		if f.Repaired {
+			fmt.Printf("repaired  %s\n", f.Path)
+			continue
+		}
+		unresolved++
+		fmt.Printf("BROKEN    %s: %v\n", f.Path, f.Err)
+	}
+
+	if unresolved > 0 {
+		fmt.Fprintf(os.Stderr, "\n%d file(s) with unparseable frontmatter", unresolved)
+		if !*fix {
+			fmt.Fprint(os.Stderr, " — re-run with -fix")
+		}
+		fmt.Fprintln(os.Stderr)
+		os.Exit(1)
+	}
+	fmt.Printf("✓ frontmatter: %d file(s) repaired, none broken\n", len(findings))
+}
@@ -32,6 +32,7 @@ import (
 	"github.com/mathiasbq/hyperguild/ingestion/internal/pipeline"
 	"github.com/mathiasbq/hyperguild/ingestion/internal/reranker"
 	"github.com/mathiasbq/hyperguild/ingestion/internal/search"
+	"github.com/mathiasbq/hyperguild/ingestion/internal/startupretry"
 	"github.com/mathiasbq/hyperguild/ingestion/internal/vectorstore"
 	"github.com/mathiasbq/hyperguild/ingestion/internal/watcher"
 	"github.com/mathiasbq/hyperguild/ingestion/internal/webhook"
@@ -143,6 +144,16 @@ func envInt(key string, fallback int) int {
 	return fallback
 }

+// buildNotifier returns the ntfy notifier, or a nil interface when
+// BRAIN_NTFY_URL is unset. A nil *interface* (not a typed-nil) is required so
+// DegradingSink/Reconcile and the governance observer skip it cleanly.
+func buildNotifier() audit.Notifier {
+	if n := audit.NewNtfyNotifier(os.Getenv("BRAIN_NTFY_URL"), os.Getenv("BRAIN_NTFY_TOKEN")); n != nil {
+		return n
+	}
+	return nil
+}
+
 // buildAuditSink selects the capture audit sink. When BRAIN_LOKI_URL is
 // set it builds the classification-aware DegradingSink (loki central +
 // durable file buffer + optional ntfy) and starts the reconcile loop;
@@ -160,12 +171,7 @@ func buildAuditSink(ctx context.Context, brainDir string, logger *slog.Logger) c
 		logger.Error("capture audit buffer init", "err", err)
 		os.Exit(1)
 	}
-	// Keep notifier as a nil interface (not a typed-nil) when unconfigured
-	// so DegradingSink/Reconcile skip it cleanly.
-	var notifier audit.Notifier
-	if n := audit.NewNtfyNotifier(os.Getenv("BRAIN_NTFY_URL"), os.Getenv("BRAIN_NTFY_TOKEN")); n != nil {
-		notifier = n
-	}
+	notifier := buildNotifier()
 	reconcileInterval := time.Duration(envInt("BRAIN_AUDIT_RECONCILE_INTERVAL", 60)) * time.Second
 	audit.StartReconcile(ctx, central, buffer, notifier, reconcileInterval)
 	logger.Info("capture audit: loki+buffer sink", "loki", lokiURL, "reconcile_s", int(reconcileInterval.Seconds()))
@@ -314,6 +320,36 @@ func main() {
 	}

 	ctx := context.Background()
+
+	// Built before the watcher, the graph backfill and session ingestion, and
+	// retried rather than fatal (#83). Two separate reasons:
+	//
+	//   - On a cold cluster boot this pod can beat dex to serving and gets a
+	//     502 from ingress. Nothing is misconfigured; it simply started first.
+	//     Exiting there meant CrashLoopBackOff redoing the backfill on every
+	//     attempt, with exponential backoff stretching the brain outage.
+	//   - Constructing it first means a genuine config error (wrong issuer,
+	//     bad audience) fails in seconds instead of after all that work.
+	//
+	// The budget stays bounded: retrying forever would turn a misconfiguration
+	// into a process that looks alive and never serves.
+	jwtValidator, err := startupretry.Do(ctx,
+		startupretry.Policy{Attempts: 8, Base: time.Second, Max: 30 * time.Second},
+		func(ctx context.Context) (*chassisauth.JWTValidator, error) {
+			v, err := chassisauth.NewJWTValidator(ctx, os.Getenv("DEX_ISSUER_URL"), os.Getenv("MCP_AUDIENCE"))
+			if err != nil {
+				logger.Warn("oidc discovery not ready, retrying", "err", err)
+			}
+			return v, err
+		})
+	if err != nil {
+		logger.Error("build jwt validator", "err", err)
+		os.Exit(1)
+	}
+	if jwtValidator != nil {
+		logger.Info("jwt auth enabled", "issuer", os.Getenv("DEX_ISSUER_URL"))
+	}
+
 	if watchInterval > 0 {
 		watcher.Start(ctx, watcher.Config{
 			BrainDir: brainDir,
@@ -418,15 +454,6 @@ func main() {
 	if webhookHandler != nil {
 		mux.Handle("POST /webhooks/brain-sync", webhookHandler)
 	}
-	jwtValidator, err := chassisauth.NewJWTValidator(ctx, os.Getenv("DEX_ISSUER_URL"), os.Getenv("MCP_AUDIENCE"))
-	if err != nil {
-		logger.Error("build jwt validator", "err", err)
-		os.Exit(1)
-	}
-	if jwtValidator != nil {
-		logger.Info("jwt auth enabled", "issuer", os.Getenv("DEX_ISSUER_URL"))
-	}
-
 	// Resource-metadata URL is only emitted on 401 when Dex OAuth is
 	// configured. Static-Bearer-only deployments leave this empty so
 	// clients never see an OAuth challenge.
@@ -457,12 +484,8 @@ func main() {
 			os.Exit(1)
 		}
 		auditSink := buildAuditSink(ctx, brainDir, logger)
-		// The Gitea client also satisfies SummaryWriter (#66): session
-		// summaries are written to mathias/ai-sessions over the same API
-		// token. nil only if a future tracker impl lacks file writes.
-		summaryWriter, _ := tracker.(capture.SummaryWriter)
 		captureSvc := capture.NewService(
-			mcpSrv.BrainStore(), tracker, summaryWriter, classCfg, auditSink)
+			mcpSrv.BrainStore(), tracker, classCfg, auditSink)
 		sovereign := splitList(os.Getenv("BRAIN_CAPTURE_SOVEREIGN_PRINCIPALS"))
 		resolver := capturehttp.NewOriginResolver(sovereign)
 		captureH := capturehttp.New(captureSvc, jwtValidator, mcpToken, "local-cli", resolver)
@@ -472,7 +495,13 @@ func main() {
 		// the existing /mcp OAuth connector. mcpSrv is already wrapped above;
 		// WithCapture mutates the same instance, so the tool appears live.
 		mcpSrv.WithCapture(captureSvc, jwtValidator, mcpToken, "local-cli", resolver)
-		logger.Info("capture enabled (REST + MCP tool)", "sovereign_principals", len(sovereign))
+		// hyperguild#97: a governance-file rewrite gets the same trail a
+		// capture already gets, plus an out-of-band alert. Wired here because
+		// brain_edit_root needs the capture plumbing anyway — that is what
+		// re-derives the static principal its gate checks.
+		mcpSrv.WithGovernanceObserver(auditSink, buildNotifier())
+		logger.Info("capture enabled (REST + MCP tool)", "sovereign_principals", len(sovereign),
+			"governance_observer", true)
 	} else {
 		logger.Info("capture endpoint disabled (BRAIN_GITEA_TOKEN unset)")
 	}
@@ -156,17 +156,40 @@ func writeHallNote(brainDir string, opts WriteNoteOptions) (string, error) {
 		return "", fmt.Errorf("create hall dir: %w", err)
 	}

+	existingFields, body := splitFrontmatter(opts.Content)
+	existingByKey := make(map[string]frontmatterField, len(existingFields))
+	for _, f := range existingFields {
+		existingByKey[f.key] = f
+	}
+	emitted := make(map[string]bool, 6)
+
 	var fm strings.Builder
 	fm.WriteString("---\n")
 	fmt.Fprintf(&fm, "wing: %s\n", brain.Sanitise(opts.Wing))
 	fmt.Fprintf(&fm, "hall: %s\n", opts.Hall)
 	fmt.Fprintf(&fm, "created_at: %s\n", time.Now().UTC().Format(time.RFC3339))
-	if opts.Type != "" {
-		fmt.Fprintf(&fm, "type: %s\n", opts.Type)
-	}
-	if opts.Domain != "" {
-		fmt.Fprintf(&fm, "domain: %s\n", opts.Domain)
+	emitted["wing"], emitted["hall"], emitted["created_at"] = true, true, true
+
+	// writeField merges one key: opts.Content's own value (if the note already
+	// carries this field in its own frontmatter) always wins over the fallback,
+	// so promotion/extraction-step metadata survives verbatim instead of being
+	// shadowed by a second, stacked frontmatter block (#86).
+	writeField := func(key, fallback string) {
+		emitted[key] = true
+		if f, ok := existingByKey[key]; ok {
+			for _, line := range f.lines {
+				fm.WriteString(line)
+				fm.WriteString("\n")
+			}
+			return
+		}
+		if fallback != "" {
+			fmt.Fprintf(&fm, "%s: %s\n", key, fallback)
+		}
 	}
+	writeField("type", opts.Type)
+	writeField("domain", opts.Domain)
+
 	sourceType := opts.SourceType
 	if sourceType == "" && opts.Hall == "facts" {
 		// Most hall=facts entries are first-party (an eval/benchmark the
@@ -175,18 +198,69 @@ func writeHallNote(brainDir string, opts WriteNoteOptions) (string, error) {
 		// citation-needing entry (brain-gardener#7).
 		sourceType = "internal"
 	}
-	if sourceType != "" {
-		fmt.Fprintf(&fm, "source_type: %s\n", sourceType)
+	writeField("source_type", sourceType)
+
+	for _, f := range existingFields {
+		if emitted[f.key] {
+			continue
+		}
+		for _, line := range f.lines {
+			fm.WriteString(line)
+			fm.WriteString("\n")
+		}
 	}
 	fm.WriteString("---\n")

-	if err := os.WriteFile(dest, []byte(fm.String()+opts.Content), 0o644); err != nil {
+	if err := os.WriteFile(dest, []byte(fm.String()+body), 0o644); err != nil {
 		return "", fmt.Errorf("write: %w", err)
 	}
 	rel, _ := filepath.Rel(brainDir, dest)
 	return filepath.ToSlash(rel), nil
 }

+// frontmatterField is one top-level YAML key from a frontmatter block,
+// along with its raw line and any indented continuation lines (e.g. a
+// bulleted list value spanning multiple lines).
+type frontmatterField struct {
+	key   string
+	lines []string
+}
+
+// splitFrontmatter splits a leading "---\n...\n---\n" YAML block out of
+// content, returning its top-level fields in original order and the
+// remaining body. If content has no leading frontmatter block, fields is
+// nil and body is content unchanged.
+func splitFrontmatter(content string) (fields []frontmatterField, body string) {
+	if !strings.HasPrefix(content, "---\n") {
+		return nil, content
+	}
+
+	lines := strings.Split(content, "\n")
+	i := 1
+	var cur *frontmatterField
+	for ; i < len(lines); i++ {
+		line := lines[i]
+		if strings.TrimSpace(line) == "---" {
+			i++
+			break
+		}
+		if line != "" && !strings.HasPrefix(line, " ") && !strings.HasPrefix(line, "\t") {
+			if cur != nil {
+				fields = append(fields, *cur)
+			}
+			key, _, _ := strings.Cut(line, ":")
+			cur = &frontmatterField{key: strings.TrimSpace(key), lines: []string{line}}
+		} else if cur != nil {
+			cur.lines = append(cur.lines, line)
+		}
+	}
+	if cur != nil {
+		fields = append(fields, *cur)
+	}
+	body = strings.Join(lines[i:], "\n")
+	return fields, body
+}
+
 // writeLegacyNote preserves the original brain/knowledge/ behaviour for
 // callers that have not adopted the wing/hall taxonomy.
 func writeLegacyNote(brainDir string, opts WriteNoteOptions) (string, error) {
@@ -345,11 +419,19 @@ func (h *Handler) Ingest(w http.ResponseWriter, r *http.Request) {
 	writeJSON(w, ingestResponse{Pages: pages, Warnings: warnings})
 }

-// supportedExtensions lists file extensions that IngestPath will process.
-var supportedExtensions = map[string]bool{
-	".md":  true,
-	".txt": true,
-	".pdf": true,
+// isSupportedExtension reports whether IngestPath will process ext.
+// .docx/.xlsx/.pptx/.png/.jpg/.jpeg require docmark (ADR-0013) and are only
+// supported when DOCMARK_URL is configured — checked per-call (not cached at
+// package init) so it reflects the environment at request time.
+func isSupportedExtension(ext string) bool {
+	switch ext {
+	case ".md", ".txt", ".pdf":
+		return true
+	case ".docx", ".xlsx", ".pptx", ".png", ".jpg", ".jpeg":
+		return os.Getenv("DOCMARK_URL") != ""
+	default:
+		return false
+	}
 }

 // IngestPath handles POST /ingest-path — ingest a file or directory.
@@ -382,7 +464,7 @@ func (h *Handler) IngestPath(w http.ResponseWriter, r *http.Request) {
 				return nil
 			}
 			ext := strings.ToLower(filepath.Ext(path))
-			if !supportedExtensions[ext] {
+			if !isSupportedExtension(ext) {
 				return nil
 			}
 			content, readErr := extract.Text(path)
@@ -410,7 +492,7 @@ func (h *Handler) IngestPath(w http.ResponseWriter, r *http.Request) {
 		}
 	} else {
 		ext := strings.ToLower(filepath.Ext(req.Path))
-		if !supportedExtensions[ext] {
+		if !isSupportedExtension(ext) {
 			writeError(w, http.StatusBadRequest, fmt.Sprintf("unsupported file extension: %s", ext))
 			return
 		}
@@ -186,6 +186,48 @@ func TestWriteNote_HallRouteOmitsSourceTypeForNonFactsHalls(t *testing.T) {
 	assert.NotContains(t, string(got), "source_type")
 }

+func TestWriteNote_HallRouteMergesExistingFrontmatterInsteadOfStacking(t *testing.T) {
+	dir := t.TempDir()
+
+	rel, err := api.WriteNote(dir, api.WriteNoteOptions{
+		Content:  "---\ntitle: act_runner host-executor\ntags: [gitea-actions, act_runner]\n---\n\n# Body\n\nSome content.\n",
+		Filename: "act-runner-host-executor",
+		Wing:     "homelab",
+		Hall:     "failures",
+	})
+	require.NoError(t, err)
+
+	got, err := os.ReadFile(filepath.Join(dir, filepath.FromSlash(rel)))
+	require.NoError(t, err)
+	body := string(got)
+
+	// exactly one frontmatter block: only two "---" delimiter lines total
+	assert.Equal(t, 2, strings.Count(body, "---\n"), "expected a single merged frontmatter block, not stacked blocks")
+	assert.Contains(t, body, "wing: homelab")
+	assert.Contains(t, body, "hall: failures")
+	assert.Contains(t, body, "title: act_runner host-executor")
+	assert.Contains(t, body, "tags: [gitea-actions, act_runner]")
+	assert.Contains(t, body, "# Body")
+}
+
+func TestWriteNote_HallRouteExistingTypeWinsOverOptsType(t *testing.T) {
+	dir := t.TempDir()
+
+	rel, err := api.WriteNote(dir, api.WriteNoteOptions{
+		Content:  "---\ntype: hypothesis\n---\n\nBody.\n",
+		Filename: "note",
+		Wing:     "agentsquad",
+		Hall:     "decisions",
+		Type:     "decision", // should lose to content's own "type: hypothesis"
+	})
+	require.NoError(t, err)
+
+	got, err := os.ReadFile(filepath.Join(dir, filepath.FromSlash(rel)))
+	require.NoError(t, err)
+	assert.Contains(t, string(got), "type: hypothesis")
+	assert.NotContains(t, string(got), "type: decision")
+}
+
 func TestWrite_GeneratesFilenameIfAbsent(t *testing.T) {
 	dir, h := setup(t)
 	body, _ := json.Marshal(map[string]any{"content": "auto name"})
@@ -0,0 +1,61 @@
+// ingestion/internal/api/ingestpath_docmark_test.go
+package api_test
+
+import (
+	"bytes"
+	"encoding/json"
+	"net/http"
+	"net/http/httptest"
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestIngestPath_DocxUnsupportedWhenDocmarkNotConfigured(t *testing.T) {
+	t.Setenv("DOCMARK_URL", "")
+	_, h := setup(t)
+
+	dir := t.TempDir()
+	f := filepath.Join(dir, "doc.docx")
+	require.NoError(t, os.WriteFile(f, []byte("fake docx"), 0o644))
+
+	body, _ := json.Marshal(map[string]any{"path": f, "source": "test-doc", "dry_run": true})
+	req := httptest.NewRequest(http.MethodPost, "/ingest-path", bytes.NewReader(body))
+	rec := httptest.NewRecorder()
+
+	h.IngestPath(rec, req)
+
+	assert.Equal(t, http.StatusBadRequest, rec.Code, rec.Body.String())
+}
+
+func TestIngestPath_DocxSupportedWhenDocmarkConfigured(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "application/json")
+		_, _ = w.Write([]byte(`{"jsonrpc":"2.0","id":1,"result":{"content":[{"type":"text","text":"# Converted Doc"}]}}`))
+	}))
+	defer srv.Close()
+	t.Setenv("DOCMARK_URL", srv.URL+"/mcp")
+	t.Setenv("DOCMARK_BEARER_TOKEN", "tok")
+
+	_, h := setup(t)
+
+	dir := t.TempDir()
+	f := filepath.Join(dir, "doc.docx")
+	require.NoError(t, os.WriteFile(f, []byte("fake docx"), 0o644))
+
+	body, _ := json.Marshal(map[string]any{"path": f, "source": "test-doc", "dry_run": true})
+	req := httptest.NewRequest(http.MethodPost, "/ingest-path", bytes.NewReader(body))
+	rec := httptest.NewRecorder()
+
+	h.IngestPath(rec, req)
+
+	require.Equal(t, http.StatusOK, rec.Code, rec.Body.String())
+	var resp map[string]any
+	require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &resp))
+	pages, ok := resp["pages"].([]any)
+	require.True(t, ok)
+	assert.NotEmpty(t, pages)
+}
@@ -1,8 +1,7 @@
 // Package capture is the Clean-Architecture use-case for the uniform
 // capture capability (issue #49/#51): persist a finished session's
-// valuable output — insights → brain, action items → Gitea tickets,
-// optional summary → ai-sessions — with one invocation, identical core
-// behaviour across every harness.
+// valuable output — insights → brain, action items → Gitea tickets —
+// with one invocation, identical core behaviour across every harness.
 //
 // This package is pure orchestration. It depends only on ports
 // (interfaces) and plain entities — no HTTP, no live Gitea, no embedding
@@ -83,19 +82,11 @@ type Ticket struct {
 	Body   string
 }

-// Summary is an optional session summary bound for ai-sessions.
-type Summary struct {
-	Title        string
-	Body         string
-	ReposTouched []string
-}
-
 // CaptureInput is the whole capture request.
 type CaptureInput struct {
 	Context  CaptureContext
 	Insights []Insight
 	Tickets  []Ticket
-	Summary  *Summary
 	DryRun   bool
 }

@@ -117,12 +108,6 @@ type TicketResult struct {
 	OK     bool   `json:"ok"`
 }

-// SummaryResult is the summary outcome in the receipt.
-type SummaryResult struct {
-	Path string `json:"path,omitempty"`
-	OK   bool   `json:"ok"`
-}
-
 // ItemError pins a failure to a specific request item for the partial
 // receipt. Item is a stable locator like "insight[1]" or "ticket[0]".
 type ItemError struct {
@@ -136,7 +121,6 @@ type ItemError struct {
 type CaptureReceipt struct {
 	Insights                []InsightResult `json:"insights"`
 	Tickets                 []TicketResult  `json:"tickets"`
-	Summary                 *SummaryResult  `json:"summary,omitempty"`
 	Errors                  []ItemError     `json:"errors"`
 	EffectiveClassification string          `json:"effective_classification,omitempty"`
 	DryRun                  bool            `json:"dry_run"`
@@ -69,11 +69,6 @@ type IssueTracker interface {
 	CommentIssue(ctx context.Context, repo string, number int, body string) (IssueRef, error)
 }

-// SummaryWriter is the ai-sessions summary port.
-type SummaryWriter interface {
-	WriteFile(ctx context.Context, repo, path, content string) error
-}
-
 // ClassificationPolicy derives a target's sensitivity (model C). The
 // "stricter wins" combination of declared vs derived is use-case policy
 // and lives in the service, so the port stays minimal. Satisfied by
@@ -2,8 +2,6 @@ package capture

 import (
 	"context"
-	"crypto/sha256"
-	"encoding/hex"
 	"fmt"
 	"strings"
 	"time"
@@ -14,22 +12,19 @@ import (

 // Service is the CaptureSession use-case. It depends only on ports.
 type Service struct {
-	brain     BrainStore
-	issues    IssueTracker
-	summaries SummaryWriter
-	policy    ClassificationPolicy
-	audit     AuditSink
+	brain  BrainStore
+	issues IssueTracker
+	policy ClassificationPolicy
+	audit  AuditSink

-	// now is the clock, injectable for deterministic summary paths and
-	// audit timestamps in tests.
+	// now is the clock, injectable for deterministic audit timestamps in
+	// tests.
 	now func() time.Time
 }

-// NewService constructs a Service from its ports. summaries may be nil
-// when no summary persistence is wired; a CaptureInput with a Summary
-// then fails that item rather than panicking.
-func NewService(b BrainStore, tr IssueTracker, sw SummaryWriter, p ClassificationPolicy, a AuditSink) *Service {
-	return &Service{brain: b, issues: tr, summaries: sw, policy: p, audit: a, now: time.Now}
+// NewService constructs a Service from its ports.
+func NewService(b BrainStore, tr IssueTracker, p ClassificationPolicy, a AuditSink) *Service {
+	return &Service{brain: b, issues: tr, policy: p, audit: a, now: time.Now}
 }

 var validActions = map[string]bool{"create": true, "close": true, "comment": true}
@@ -88,7 +83,7 @@ func (s *Service) Capture(ctx context.Context, in CaptureInput) (CaptureReceipt,
 		declared, _ = classification.ParseLevel(in.Context.Classification)
 	}

-	effective, securityEvents := s.resolveClassification(declared, in)
+	effective, securityEvents, escalators := s.resolveClassification(declared, in)

 	// Server-derived origin governs the I1 gate; a caller-asserted harness
 	// label that names a different zone is descriptive-only and logged as a
@@ -112,8 +107,8 @@ func (s *Service) Capture(ctx context.Context, in CaptureInput) (CaptureReceipt,
 			Items:                   nil, // refused before any write
 			SecurityEvents:          append(securityEvents, "I1 refusal: confidential capture via us-nexus origin"),
 		}, AuditCentral)
-		return CaptureReceipt{}, fmt.Errorf("%w: effective classification confidential through %s origin",
-			ErrSovereigntyRefused, in.Context.Origin)
+		return CaptureReceipt{}, fmt.Errorf("%w: effective classification confidential through %s origin (%s)",
+			ErrSovereigntyRefused, in.Context.Origin, escalationReason(escalators))
 	}

 	receipt := CaptureReceipt{
@@ -131,9 +126,6 @@ func (s *Service) Capture(ctx context.Context, in CaptureInput) (CaptureReceipt,
 		for _, tk := range in.Tickets {
 			receipt.Tickets = append(receipt.Tickets, TicketResult{Repo: tk.Repo, Action: tk.Action, Number: tk.Number, OK: true})
 		}
-		if in.Summary != nil {
-			receipt.Summary = &SummaryResult{Path: s.summaryPath(in.Context, in.Summary), OK: true}
-		}
 		return receipt, nil
 	}

@@ -169,16 +161,6 @@ func (s *Service) Capture(ctx context.Context, in CaptureInput) (CaptureReceipt,
 		landed = append(landed, fmt.Sprintf("ticket:%s#%d", tk.Repo, res.Number))
 	}

-	if in.Summary != nil {
-		res, err := s.persistSummary(ctx, in.Context, in.Summary)
-		receipt.Summary = &res
-		if err != nil {
-			receipt.Errors = append(receipt.Errors, ItemError{Item: "summary", Error: err.Error()})
-		} else {
-			landed = append(landed, "summary:"+res.Path)
-		}
-	}
-
 	// I5: persist the request-level audit record of exactly what landed,
 	// using the outcome reserved before the writes. AuditBuffered surfaces
 	// the degraded (locally-buffered) state on the receipt.
@@ -239,15 +221,28 @@ func (s *Service) validate(in CaptureInput) error {
 	return nil
 }

-// resolveClassification computes the effective level (stricter of
-// declared and every target's derived level) and collects a security
-// event whenever the caller under-declared relative to a target floor.
-func (s *Service) resolveClassification(declared classification.Level, in CaptureInput) (classification.Level, []string) {
+// resolveClassification computes the effective level (stricter of declared
+// and every target's derived level), collects a security event whenever the
+// caller under-declared relative to a target floor, and names the targets
+// that carry the strictest level.
+//
+// That third return is what makes an I1 refusal actionable. A caller sending
+// twenty tickets gets one refusal; without the offending target it cannot
+// tell which repo tripped the gate, and infra#265 shows what happens next —
+// the caller concluded the tickets ARRAY was broken, built a fallback of
+// twenty individual calls, and filed a bug against the wrong thing.
+func (s *Service) resolveClassification(declared classification.Level, in CaptureInput) (classification.Level, []string, []string) {
 	effective := declared
 	var events []string
+	derivedFor := map[string]classification.Level{}
+	var order []string
 	consider := func(kind classification.TargetKind, name string) {
 		derived := s.policy.Derive(classification.Target{Kind: kind, Name: name})
 		effective = classification.Stricter(effective, derived)
+		if _, seen := derivedFor[name]; !seen {
+			derivedFor[name] = derived
+			order = append(order, name)
+		}
 		if declared < derived {
 			events = append(events, fmt.Sprintf("classification under-declared: declared=%s target=%s(%s) derived=%s",
 				declared, name, kindString(kind), derived))
@@ -259,12 +254,28 @@ func (s *Service) resolveClassification(declared classification.Level, in Captur
 	for _, tk := range in.Tickets {
 		consider(classification.RepoTarget, tk.Repo)
 	}
-	if in.Summary != nil {
-		for _, repo := range in.Summary.ReposTouched {
-			consider(classification.RepoTarget, repo)
+
+	// Only targets that actually reach the effective level are named: at
+	// twenty tickets, listing the innocent ones is noise that hides the one
+	// that matters.
+	var escalators []string
+	for _, name := range order {
+		if derivedFor[name] == effective && effective > declared {
+			escalators = append(escalators, name)
 		}
 	}
-	return effective, events
+	return effective, events, escalators
+}
+
+// escalationReason renders why the effective classification landed where it
+// did, for an operator reading a refusal. Naming the caller's own declaration
+// matters as much as naming a target: "you asked for this" and "a repo you
+// touched required it" call for different fixes.
+func escalationReason(escalators []string) string {
+	if len(escalators) == 0 {
+		return "declared by the caller; no target required it"
+	}
+	return "required by: " + strings.Join(escalators, ", ")
 }

 func (s *Service) persistInsight(ctx context.Context, ins Insight) (InsightResult, string, error) {
@@ -309,60 +320,6 @@ func (s *Service) persistTicket(ctx context.Context, tk Ticket) (TicketResult, e
 	return res, nil
 }

-func (s *Service) persistSummary(ctx context.Context, c CaptureContext, sum *Summary) (SummaryResult, error) {
-	if s.summaries == nil {
-		return SummaryResult{OK: false}, fmt.Errorf("no summary writer configured")
-	}
-	path := s.summaryPath(c, sum)
-	content := s.renderSummary(c, sum)
-	repo := "ai-sessions"
-	if err := s.summaries.WriteFile(ctx, repo, path, content); err != nil {
-		return SummaryResult{Path: path, OK: false}, err
-	}
-	return SummaryResult{Path: path, OK: true}, nil
-}
-
-// summaryPath builds summaries/<harness>/<YYYY-MM>/<date>-<slug>-<ref8>.md.
-// The ref8 disambiguator is derived from the session_ref (or the title
-// when no ref is present) so distinct sessions never collide.
-func (s *Service) summaryPath(c CaptureContext, sum *Summary) string {
-	t := s.now().UTC()
-	slug := brain.Sanitise(sum.Title)
-	if slug == "" {
-		slug = "summary"
-	}
-	seed := c.SessionRef
-	if seed == "" {
-		seed = sum.Title + sum.Body
-	}
-	sum8 := shortHash(seed)
-	return fmt.Sprintf("summaries/%s/%s/%s-%s-%s.md",
-		brain.Sanitise(c.Harness), t.Format("2006-01"), t.Format("2006-01-02"), slug, sum8)
-}
-
-// renderSummary stamps fidelity + session metadata into frontmatter so the
-// richer-fidelity-supersedes-thinner collision rule has the data it needs.
-func (s *Service) renderSummary(c CaptureContext, sum *Summary) string {
-	var b strings.Builder
-	b.WriteString("---\n")
-	fmt.Fprintf(&b, "title: %s\n", sum.Title)
-	fmt.Fprintf(&b, "harness: %s\n", c.Harness)
-	if c.SessionRef != "" {
-		fmt.Fprintf(&b, "session_ref: %s\n", c.SessionRef)
-	}
-	fmt.Fprintf(&b, "fidelity: %s\n", c.Fidelity)
-	fmt.Fprintf(&b, "captured_at: %s\n", s.now().UTC().Format(time.RFC3339))
-	if len(sum.ReposTouched) > 0 {
-		fmt.Fprintf(&b, "repos_touched: [%s]\n", strings.Join(sum.ReposTouched, ", "))
-	}
-	b.WriteString("---\n\n")
-	b.WriteString(sum.Body)
-	if !strings.HasSuffix(sum.Body, "\n") {
-		b.WriteByte('\n')
-	}
-	return b.String()
-}
-
 func kindString(k classification.TargetKind) string {
 	if k == classification.RepoTarget {
 		return "repo"
@@ -381,8 +338,3 @@ func firstLine(s string) string {
 	}
 	return s
 }
-
-func shortHash(s string) string {
-	sum := sha256.Sum256([]byte(s))
-	return hex.EncodeToString(sum[:])[:8]
-}
@@ -3,6 +3,7 @@ package capture
 import (
 	"context"
 	"errors"
+	"fmt"
 	"strings"
 	"testing"
 	"time"
@@ -59,12 +60,18 @@ type fakeTracker struct {
 	closed   []int
 	comments []int
 	err      error
+	// failOnTitle makes CreateIssue fail for one specific title, so a
+	// partial-failure receipt can be exercised without failing every item.
+	failOnTitle string
 }

 func (f *fakeTracker) CreateIssue(_ context.Context, repo, title, _ string) (IssueRef, error) {
 	if f.err != nil {
 		return IssueRef{}, f.err
 	}
+	if f.failOnTitle != "" && title == f.failOnTitle {
+		return IssueRef{}, errors.New("tracker refused this one")
+	}
 	f.created = append(f.created, repo+":"+title)
 	return IssueRef{Repo: repo, Number: 100 + len(f.created), URL: "https://git/" + repo + "/issues/x"}, nil
 }
@@ -85,24 +92,11 @@ func (f *fakeTracker) CommentIssue(_ context.Context, repo string, number int, _
 	return IssueRef{Repo: repo, Number: number}, nil
 }

-type fakeSummary struct {
-	paths   []string
-	content []string
-	err     error
-}
-
-func (f *fakeSummary) WriteFile(_ context.Context, _, path, content string) error {
-	if f.err != nil {
-		return f.err
-	}
-	f.paths = append(f.paths, path)
-	f.content = append(f.content, content)
-	return nil
-}
-
 // fakePolicy derives from an explicit map; default Internal so tests pin
 // behaviour without depending on the real defaulting.
-type fakePolicy struct{ tags map[string]classification.Level }
+type fakePolicy struct {
+	tags map[string]classification.Level
+}

 func (p fakePolicy) Derive(t classification.Target) classification.Level {
 	if lvl, ok := p.tags[t.Name]; ok {
@@ -135,8 +129,8 @@ func (f *fakeAudit) Record(_ context.Context, e AuditEntry, _ AuditOutcome) erro

 // --- helpers ---

-func newSvc(b BrainStore, tr IssueTracker, sw SummaryWriter, p ClassificationPolicy, a AuditSink) *Service {
-	s := NewService(b, tr, sw, p, a)
+func newSvc(b BrainStore, tr IssueTracker, p ClassificationPolicy, a AuditSink) *Service {
+	s := NewService(b, tr, p, a)
 	s.now = func() time.Time { return time.Date(2026, 6, 22, 12, 0, 0, 0, time.UTC) }
 	return s
 }
@@ -151,7 +145,7 @@ func TestCaptureHappyPath(t *testing.T) {
 	b := &fakeBrain{}
 	tr := &fakeTracker{}
 	au := &fakeAudit{}
-	svc := newSvc(b, tr, nil, fakePolicy{}, au)
+	svc := newSvc(b, tr, fakePolicy{}, au)

 	rec, err := svc.Capture(context.Background(), CaptureInput{
 		Context: baseCtx(),
@@ -180,7 +174,7 @@ func TestCaptureHappyPath(t *testing.T) {

 func TestCaptureSupersedeNotDuplicate(t *testing.T) {
 	b := &fakeBrain{}
-	svc := newSvc(b, &fakeTracker{}, nil, fakePolicy{}, &fakeAudit{})
+	svc := newSvc(b, &fakeTracker{}, fakePolicy{}, &fakeAudit{})

 	rec, err := svc.Capture(context.Background(), CaptureInput{
 		Context:  baseCtx(),
@@ -197,7 +191,7 @@ func TestCaptureValidationFailClosed(t *testing.T) {
 	b := &fakeBrain{}
 	tr := &fakeTracker{}
 	au := &fakeAudit{}
-	svc := newSvc(b, tr, nil, fakePolicy{}, au)
+	svc := newSvc(b, tr, fakePolicy{}, au)

 	_, err := svc.Capture(context.Background(), CaptureInput{
 		Context: baseCtx(),
@@ -216,7 +210,7 @@ func TestCaptureValidationFailClosed(t *testing.T) {
 }

 func TestCaptureValidationRejectsBadTicket(t *testing.T) {
-	svc := newSvc(&fakeBrain{}, &fakeTracker{}, nil, fakePolicy{}, &fakeAudit{})
+	svc := newSvc(&fakeBrain{}, &fakeTracker{}, fakePolicy{}, &fakeAudit{})
 	_, err := svc.Capture(context.Background(), CaptureInput{
 		Context: baseCtx(),
 		Tickets: []Ticket{{Repo: "hyperguild", Action: "frobnicate"}}, // bad action
@@ -239,7 +233,7 @@ func TestCapturePartialFailureBestEffort(t *testing.T) {
 	}}
 	tr := &fakeTracker{}
 	au := &fakeAudit{}
-	svc := newSvc(b, tr, nil, fakePolicy{}, au)
+	svc := newSvc(b, tr, fakePolicy{}, au)

 	rec, err := svc.Capture(context.Background(), CaptureInput{
 		Context: baseCtx(),
@@ -264,7 +258,7 @@ func TestCaptureDryRunWritesNothing(t *testing.T) {
 	b := &fakeBrain{}
 	tr := &fakeTracker{}
 	au := &fakeAudit{}
-	svc := newSvc(b, tr, nil, fakePolicy{}, au)
+	svc := newSvc(b, tr, fakePolicy{}, au)

 	rec, err := svc.Capture(context.Background(), CaptureInput{
 		Context:  baseCtx(),
@@ -287,7 +281,7 @@ func TestCaptureStricterClassificationWins(t *testing.T) {
 	b := &fakeBrain{}
 	au := &fakeAudit{}
 	pol := fakePolicy{tags: map[string]classification.Level{"client-seb": classification.Confidential}}
-	svc := newSvc(b, &fakeTracker{}, nil, pol, au)
+	svc := newSvc(b, &fakeTracker{}, pol, au)

 	ctx := baseCtx()
 	ctx.Classification = "internal"
@@ -306,7 +300,7 @@ func TestCaptureCallerRaisingSensitivityHonoured(t *testing.T) {
 	// Caller declares confidential; target internal → effective confidential, NOT a security event.
 	au := &fakeAudit{}
 	pol := fakePolicy{tags: map[string]classification.Level{"hyperguild": classification.Internal}}
-	svc := newSvc(&fakeBrain{}, &fakeTracker{}, nil, pol, au)
+	svc := newSvc(&fakeBrain{}, &fakeTracker{}, pol, au)

 	ctx := baseCtx()
 	ctx.Classification = "confidential"
@@ -319,26 +313,6 @@ func TestCaptureCallerRaisingSensitivityHonoured(t *testing.T) {
 	assert.Empty(t, au.entries[0].SecurityEvents, "raising sensitivity is honoured, not flagged")
 }

-func TestCaptureSummaryPathAndFidelity(t *testing.T) {
-	sw := &fakeSummary{}
-	svc := newSvc(&fakeBrain{}, &fakeTracker{}, sw, fakePolicy{}, &fakeAudit{})
-
-	ctx := baseCtx()
-	ctx.Fidelity = "transcript-parse"
-	ctx.SessionRef = "abc123def456"
-	rec, err := svc.Capture(context.Background(), CaptureInput{
-		Context: ctx,
-		Summary: &Summary{Title: "Session Wrap", Body: "did stuff", ReposTouched: []string{"hyperguild"}},
-	})
-	require.NoError(t, err)
-	require.NotNil(t, rec.Summary)
-	assert.True(t, rec.Summary.OK)
-	require.Len(t, sw.paths, 1)
-	assert.True(t, strings.HasPrefix(sw.paths[0], "summaries/claude-code/2026-06/"), "path: %s", sw.paths[0])
-	assert.Contains(t, sw.paths[0], "session-wrap")
-	assert.Contains(t, sw.content[0], "fidelity: transcript-parse", "fidelity stamped in frontmatter")
-}
-
 // --- I1 sovereignty gate (#53) ---

 func TestCaptureRefusesConfidentialViaUSNexus(t *testing.T) {
@@ -346,7 +320,7 @@ func TestCaptureRefusesConfidentialViaUSNexus(t *testing.T) {
 	tr := &fakeTracker{}
 	au := &fakeAudit{}
 	pol := fakePolicy{tags: map[string]classification.Level{"client-seb": classification.Confidential}}
-	svc := newSvc(b, tr, nil, pol, au)
+	svc := newSvc(b, tr, pol, au)

 	ctx := baseCtx()
 	ctx.Classification = "confidential"
@@ -368,7 +342,7 @@ func TestCaptureRefusesConfidentialViaUSNexus(t *testing.T) {
 func TestCaptureAllowsConfidentialViaSovereign(t *testing.T) {
 	b := &fakeBrain{}
 	pol := fakePolicy{tags: map[string]classification.Level{"client-seb": classification.Confidential}}
-	svc := newSvc(b, &fakeTracker{}, nil, pol, &fakeAudit{})
+	svc := newSvc(b, &fakeTracker{}, pol, &fakeAudit{})

 	ctx := baseCtx()
 	ctx.Classification = "confidential"
@@ -387,7 +361,7 @@ func TestCaptureAssertedLabelIgnoredAndLogged(t *testing.T) {
 	// us-nexus; confidential ⇒ refused, and the discrepancy is a security event.
 	au := &fakeAudit{}
 	pol := fakePolicy{tags: map[string]classification.Level{"client-seb": classification.Confidential}}
-	svc := newSvc(&fakeBrain{}, &fakeTracker{}, nil, pol, au)
+	svc := newSvc(&fakeBrain{}, &fakeTracker{}, pol, au)

 	ctx := baseCtx()
 	ctx.Harness = "sovereign-soil" // asserted
@@ -407,7 +381,7 @@ func TestCaptureAssertedLabelIgnoredAndLogged(t *testing.T) {
 func TestCaptureInternalViaUSNexusAllowed(t *testing.T) {
 	// us-nexus origin is fine for non-confidential data.
 	b := &fakeBrain{}
-	svc := newSvc(b, &fakeTracker{}, nil, fakePolicy{}, &fakeAudit{})
+	svc := newSvc(b, &fakeTracker{}, fakePolicy{}, &fakeAudit{})
 	ctx := baseCtx()
 	ctx.Origin = ZoneUSNexus // internal classification, so gate doesn't fire
 	rec, err := svc.Capture(context.Background(), CaptureInput{
@@ -426,7 +400,7 @@ func TestCaptureRefusesWhenAuditReserveFails(t *testing.T) {
 	b := &fakeBrain{}
 	tr := &fakeTracker{}
 	au := &fakeAudit{reserveErr: errors.New("central sink unreachable")}
-	svc := newSvc(b, tr, nil, fakePolicy{}, au)
+	svc := newSvc(b, tr, fakePolicy{}, au)

 	_, err := svc.Capture(context.Background(), CaptureInput{
 		Context:  baseCtx(),
@@ -443,7 +417,7 @@ func TestCaptureFlagsLocallyBufferedAudit(t *testing.T) {
 	// proceeds and the receipt flags the degraded audit state.
 	b := &fakeBrain{}
 	au := &fakeAudit{reserveMode: AuditBuffered}
-	svc := newSvc(b, &fakeTracker{}, nil, fakePolicy{}, au)
+	svc := newSvc(b, &fakeTracker{}, fakePolicy{}, au)

 	rec, err := svc.Capture(context.Background(), CaptureInput{
 		Context:  baseCtx(),
@@ -458,7 +432,7 @@ func TestCaptureFlagsLocallyBufferedAudit(t *testing.T) {
 func TestCaptureDryRunSkipsAuditGate(t *testing.T) {
 	// dry_run must not even probe the audit sink (writes nothing anywhere).
 	au := &fakeAudit{reserveErr: errors.New("would refuse")}
-	svc := newSvc(&fakeBrain{}, &fakeTracker{}, nil, fakePolicy{}, au)
+	svc := newSvc(&fakeBrain{}, &fakeTracker{}, fakePolicy{}, au)

 	rec, err := svc.Capture(context.Background(), CaptureInput{
 		Context:  baseCtx(),
@@ -469,3 +443,98 @@ func TestCaptureDryRunSkipsAuditGate(t *testing.T) {
 	assert.True(t, rec.DryRun)
 	assert.Empty(t, au.entries)
 }
+
+// ---- hyperguild#91 part 1 -------------------------------------------------
+//
+// The reported symptom was "capture with a tickets array fails" (infra#265:
+// 20 tickets errored, 5 errored, caller fell back to 20 individual
+// issue_create calls). The array was never the failing dimension — every
+// ticket targeted a client repo, and the I1 gate refuses that through a
+// us-nexus origin at ANY length. The refusal did not say which target
+// escalated the classification, so it read as a malfunction.
+
+func TestCapture_TicketsArrayWorksAtLengthOne(t *testing.T) {
+	b, tr, au := &fakeBrain{}, &fakeTracker{}, &fakeAudit{}
+	svc := newSvc(b, tr, fakePolicy{}, au)
+
+	rec, err := svc.Capture(context.Background(), CaptureInput{
+		Context: baseCtx(),
+		Tickets: []Ticket{{Repo: "hyperguild", Action: "create", Title: "one", Body: "b"}},
+	})
+	require.NoError(t, err)
+	require.Len(t, rec.Tickets, 1)
+	assert.True(t, rec.Tickets[0].OK)
+	assert.Len(t, tr.created, 1)
+	assert.Empty(t, rec.Errors)
+}
+
+func TestCapture_TicketsArrayWorksAtLengthMany(t *testing.T) {
+	b, tr, au := &fakeBrain{}, &fakeTracker{}, &fakeAudit{}
+	svc := newSvc(b, tr, fakePolicy{}, au)
+
+	in := CaptureInput{Context: baseCtx()}
+	for i := range 20 {
+		in.Tickets = append(in.Tickets, Ticket{
+			Repo: "hyperguild", Action: "create", Title: fmt.Sprintf("t%02d", i), Body: "b",
+		})
+	}
+
+	rec, err := svc.Capture(context.Background(), in)
+	require.NoError(t, err)
+	require.Len(t, rec.Tickets, 20, "one receipt entry per ticket")
+	for i, r := range rec.Tickets {
+		assert.True(t, r.OK, "ticket %d failed: %+v", i, rec.Errors)
+	}
+	assert.Len(t, tr.created, 20)
+	assert.Empty(t, rec.Errors)
+}
+
+func TestCapture_OneFailingTicketDoesNotSinkTheRest(t *testing.T) {
+	// infra#265 asked explicitly: "if ticket 3 of 5 fails, what happened to
+	// 1 and 2?" They land, and the receipt says so per item.
+	b, au := &fakeBrain{}, &fakeAudit{}
+	tr := &fakeTracker{failOnTitle: "boom"}
+	svc := newSvc(b, tr, fakePolicy{}, au)
+
+	rec, err := svc.Capture(context.Background(), CaptureInput{
+		Context: baseCtx(),
+		Tickets: []Ticket{
+			{Repo: "hyperguild", Action: "create", Title: "ok-1", Body: "b"},
+			{Repo: "hyperguild", Action: "create", Title: "boom", Body: "b"},
+			{Repo: "hyperguild", Action: "create", Title: "ok-3", Body: "b"},
+		},
+	})
+	require.NoError(t, err, "a per-item failure is a partial receipt, not a call error")
+	require.Len(t, rec.Tickets, 3)
+	assert.True(t, rec.Tickets[0].OK)
+	assert.False(t, rec.Tickets[1].OK)
+	assert.True(t, rec.Tickets[2].OK)
+	require.Len(t, rec.Errors, 1)
+	assert.Contains(t, rec.Errors[0].Item, "ticket[1]")
+}
+
+func TestCapture_I1RefusalNamesWhatEscalatedTheClassification(t *testing.T) {
+	// The actual defect behind infra#265. Without the offending target in
+	// the message, a caller with 20 tickets cannot tell which repo tripped
+	// the gate — and reasonably concludes the array itself is broken.
+	b, tr, au := &fakeBrain{}, &fakeTracker{}, &fakeAudit{}
+	pol := fakePolicy{tags: map[string]classification.Level{"trucker-ecommerce": classification.Confidential}}
+	svc := newSvc(b, tr, pol, au)
+
+	ctx := baseCtx()
+	ctx.Origin = ZoneUSNexus
+	_, err := svc.Capture(context.Background(), CaptureInput{
+		Context: ctx,
+		Tickets: []Ticket{
+			{Repo: "hyperguild", Action: "create", Title: "fine", Body: "b"},
+			{Repo: "trucker-ecommerce", Action: "create", Title: "client work", Body: "b"},
+		},
+	})
+
+	require.ErrorIs(t, err, ErrSovereigntyRefused)
+	assert.Contains(t, err.Error(), "trucker-ecommerce",
+		"the refusal must name the target that escalated the classification")
+	assert.NotContains(t, err.Error(), "hyperguild",
+		"only the offending target, or the message is noise at 20 tickets")
+	assert.Empty(t, tr.created, "refused before any write")
+}
@@ -55,7 +55,6 @@ type request struct {
 	Context  contextBody   `json:"context"`
 	Insights []insightBody `json:"insights"`
 	Tickets  []ticketBody  `json:"tickets"`
-	Summary  *summaryBody  `json:"summary,omitempty"`
 	DryRun   bool          `json:"dry_run"`
 }

@@ -82,12 +81,6 @@ type ticketBody struct {
 	Body   string `json:"body,omitempty"`
 }

-type summaryBody struct {
-	Title        string   `json:"title"`
-	Body         string   `json:"body"`
-	ReposTouched []string `json:"repos_touched,omitempty"`
-}
-
 // ServeHTTP authenticates, derives origin, runs the use-case, and maps the
 // result to an HTTP status.
 func (h *Handler) ServeHTTP(w http.ResponseWriter, r *http.Request) {
@@ -183,11 +176,6 @@ func (b request) toInput() capture.CaptureInput {
 			Repo: t.Repo, Action: t.Action, Number: t.Number, Title: t.Title, Body: t.Body,
 		})
 	}
-	if b.Summary != nil {
-		in.Summary = &capture.Summary{
-			Title: b.Summary.Title, Body: b.Summary.Body, ReposTouched: b.Summary.ReposTouched,
-		}
-	}
 	return in
 }

@@ -204,9 +192,6 @@ func statusFor(rec capture.CaptureReceipt) int {
 	for _, t := range rec.Tickets {
 		count(&ok, &fail, t.OK)
 	}
-	if rec.Summary != nil {
-		count(&ok, &fail, rec.Summary.OK)
-	}
 	switch {
 	case fail == 0:
 		return http.StatusOK
@@ -49,7 +49,7 @@ func newHandler(t *testing.T, v capturehttp.Validator, tr capture.IssueTracker,
 	t.Helper()
 	cfg, err := classification.Load(t.TempDir())
 	require.NoError(t, err)
-	svc := capture.NewService(brainstore.New(t.TempDir()), tr, nil, cfg, audit.NewSlogSink(nil))
+	svc := capture.NewService(brainstore.New(t.TempDir()), tr, cfg, audit.NewSlogSink(nil))
 	return capturehttp.New(svc, v, staticTok, "local-cli", capturehttp.NewOriginResolver(sovereign))
 }

@@ -190,7 +190,7 @@ func (refusingAudit) Record(context.Context, capture.AuditEntry, capture.AuditOu
 func TestAuditUnavailableIs503(t *testing.T) {
 	cfg, err := classification.Load(t.TempDir())
 	require.NoError(t, err)
-	svc := capture.NewService(brainstore.New(t.TempDir()), fakeTracker{}, nil, cfg, refusingAudit{})
+	svc := capture.NewService(brainstore.New(t.TempDir()), fakeTracker{}, cfg, refusingAudit{})
 	h := capturehttp.New(svc, nil, staticTok, "local-cli", capturehttp.NewOriginResolver(nil))

 	rr := do(t, h, "Bearer "+staticTok, internalReq())
@@ -0,0 +1,148 @@
+// ingestion/internal/extract/docmark.go
+package extract
+
+import (
+	"bytes"
+	"encoding/base64"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net/http"
+	"os"
+	"time"
+)
+
+// docmarkRequest is a JSON-RPC 2.0 tools/call request for docmark's
+// convert_to_markdown tool.
+type docmarkRequest struct {
+	JSONRPC string `json:"jsonrpc"`
+	ID      int    `json:"id"`
+	Method  string `json:"method"`
+	Params  struct {
+		Name      string `json:"name"`
+		Arguments struct {
+			ContentBase64 string `json:"content_base64"`
+			Filename      string `json:"filename"`
+		} `json:"arguments"`
+	} `json:"params"`
+}
+
+type docmarkResponse struct {
+	Result *struct {
+		Content []struct {
+			Type string `json:"type"`
+			Text string `json:"text"`
+		} `json:"content"`
+		IsError bool `json:"isError"`
+	} `json:"result"`
+	Error *struct {
+		Message string `json:"message"`
+	} `json:"error"`
+}
+
+// extractViaDocmark converts path (PDF/DOCX/XLSX/PPTX/image) to Markdown by
+// calling the docmark MCP server with a single self-contained tools/call
+// request (docmark runs stateless_http -- no initialize handshake or session
+// ID needed). DOCMARK_URL must be set (e.g.
+// http://docmark.docmark.svc.cluster.local:3001/mcp); DOCMARK_BEARER_TOKEN
+// is docmark's static bearer (network is docmark's primary auth boundary,
+// this is defense-in-depth — ADR-0013).
+func extractViaDocmark(path string) (string, error) {
+	url := os.Getenv("DOCMARK_URL")
+	if url == "" {
+		return "", fmt.Errorf("extractViaDocmark: DOCMARK_URL is not set")
+	}
+
+	raw, err := os.ReadFile(path)
+	if err != nil {
+		return "", fmt.Errorf("read %s: %w", path, err)
+	}
+
+	var reqBody docmarkRequest
+	reqBody.JSONRPC = "2.0"
+	reqBody.ID = 1
+	reqBody.Method = "tools/call"
+	reqBody.Params.Name = "convert_to_markdown"
+	reqBody.Params.Arguments.ContentBase64 = base64.StdEncoding.EncodeToString(raw)
+	reqBody.Params.Arguments.Filename = fileBase(path)
+
+	payload, err := json.Marshal(reqBody)
+	if err != nil {
+		return "", fmt.Errorf("marshal docmark request: %w", err)
+	}
+
+	httpReq, err := http.NewRequest(http.MethodPost, url, bytes.NewReader(payload))
+	if err != nil {
+		return "", fmt.Errorf("build docmark request: %w", err)
+	}
+	httpReq.Header.Set("Content-Type", "application/json")
+	httpReq.Header.Set("Accept", "application/json, text/event-stream")
+	if tok := os.Getenv("DOCMARK_BEARER_TOKEN"); tok != "" {
+		httpReq.Header.Set("Authorization", "Bearer "+tok)
+	}
+
+	client := &http.Client{Timeout: 60 * time.Second}
+	resp, err := client.Do(httpReq)
+	if err != nil {
+		return "", fmt.Errorf("call docmark: %w", err)
+	}
+	defer func() { _ = resp.Body.Close() }()
+
+	body, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return "", fmt.Errorf("read docmark response: %w", err)
+	}
+
+	if resp.StatusCode != http.StatusOK {
+		return "", fmt.Errorf("docmark: HTTP %d: %s", resp.StatusCode, string(body))
+	}
+
+	jsonBody := body
+	if data := sseDataPayload(body); data != nil {
+		jsonBody = data
+	}
+
+	var out docmarkResponse
+	if err := json.Unmarshal(jsonBody, &out); err != nil {
+		return "", fmt.Errorf("decode docmark response: %w", err)
+	}
+	if out.Error != nil {
+		return "", fmt.Errorf("docmark: %s", out.Error.Message)
+	}
+	if out.Result == nil || len(out.Result.Content) == 0 {
+		return "", fmt.Errorf("docmark: empty response")
+	}
+	text := out.Result.Content[0].Text
+	if out.Result.IsError {
+		return "", fmt.Errorf("docmark: %s", text)
+	}
+	return text, nil
+}
+
+// sseDataPayload extracts the JSON payload from an SSE-framed response body
+// ("event: message\r\ndata: {...}\r\n\r\n"). docmark's Streamable-HTTP
+// transport frames every response this way (Content-Type: text/event-stream)
+// regardless of stateless_http — that flag removes the session/initialize
+// requirement, not the SSE wire framing. Returns nil if body isn't SSE-framed
+// (e.g. a plain-JSON response, kept as a fallback for forward-compatibility).
+func sseDataPayload(body []byte) []byte {
+	const prefix = "data: "
+	for _, line := range bytes.Split(body, []byte("\n")) {
+		line = bytes.TrimRight(line, "\r")
+		if bytes.HasPrefix(line, []byte(prefix)) {
+			return bytes.TrimPrefix(line, []byte(prefix))
+		}
+	}
+	return nil
+}
+
+// fileBase returns the final path segment (like filepath.Base, kept local to
+// avoid importing path/filepath just for this one call).
+func fileBase(path string) string {
+	for i := len(path) - 1; i >= 0; i-- {
+		if path[i] == '/' || path[i] == '\\' {
+			return path[i+1:]
+		}
+	}
+	return path
+}
@@ -0,0 +1,189 @@
+// ingestion/internal/extract/docmark_test.go
+package extract
+
+import (
+	"encoding/json"
+	"io"
+	"net/http"
+	"net/http/httptest"
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// mcpToolResult mirrors the shape of docmark's JSON-RPC tools/call response.
+type mcpToolResult struct {
+	JSONRPC string `json:"jsonrpc"`
+	ID      int    `json:"id"`
+	Result  *struct {
+		Content []struct {
+			Type string `json:"type"`
+			Text string `json:"text"`
+		} `json:"content"`
+		IsError bool `json:"isError"`
+	} `json:"result,omitempty"`
+	Error *struct {
+		Message string `json:"message"`
+	} `json:"error,omitempty"`
+}
+
+// writeMCPResponse mirrors docmark's REAL response framing (empirically
+// confirmed against the live server): Content-Type: text/event-stream,
+// body is SSE-framed ("event: message\r\ndata: {...}\r\n\r\n"), not bare
+// JSON -- inherent to MCP Streamable-HTTP, independent of stateless_http.
+func writeMCPResponse(w http.ResponseWriter, body mcpToolResult) {
+	payload, _ := json.Marshal(body)
+	w.Header().Set("Content-Type", "text/event-stream")
+	w.WriteHeader(http.StatusOK)
+	_, _ = w.Write([]byte("event: message\r\ndata: "))
+	_, _ = w.Write(payload)
+	_, _ = w.Write([]byte("\r\n\r\n"))
+}
+
+func TestExtractViaDocmark_Success(t *testing.T) {
+	var gotAuth, gotAccept string
+	var gotBody map[string]any
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		gotAuth = r.Header.Get("Authorization")
+		gotAccept = r.Header.Get("Accept")
+		b, _ := io.ReadAll(r.Body)
+		_ = json.Unmarshal(b, &gotBody)
+		writeMCPResponse(w, mcpToolResult{
+			JSONRPC: "2.0", ID: 1,
+			Result: &struct {
+				Content []struct {
+					Type string `json:"type"`
+					Text string `json:"text"`
+				} `json:"content"`
+				IsError bool `json:"isError"`
+			}{
+				Content: []struct {
+					Type string `json:"type"`
+					Text string `json:"text"`
+				}{{Type: "text", Text: "# Converted\n\nhello"}},
+			},
+		})
+	}))
+	defer srv.Close()
+
+	t.Setenv("DOCMARK_URL", srv.URL+"/mcp")
+	t.Setenv("DOCMARK_BEARER_TOKEN", "test-token-123")
+
+	dir := t.TempDir()
+	path := filepath.Join(dir, "doc.docx")
+	require.NoError(t, os.WriteFile(path, []byte("fake docx bytes"), 0o644))
+
+	got, err := extractViaDocmark(path)
+	require.NoError(t, err)
+	assert.Equal(t, "# Converted\n\nhello", got)
+	assert.Equal(t, "Bearer test-token-123", gotAuth)
+	assert.Contains(t, gotAccept, "application/json")
+	params, _ := gotBody["params"].(map[string]any)
+	require.NotNil(t, params)
+	assert.Equal(t, "convert_to_markdown", params["name"])
+	args, _ := params["arguments"].(map[string]any)
+	require.NotNil(t, args)
+	assert.Equal(t, "doc.docx", args["filename"])
+	assert.NotEmpty(t, args["content_base64"])
+}
+
+func TestExtractViaDocmark_NotConfigured(t *testing.T) {
+	t.Setenv("DOCMARK_URL", "")
+
+	dir := t.TempDir()
+	path := filepath.Join(dir, "doc.docx")
+	require.NoError(t, os.WriteFile(path, []byte("x"), 0o644))
+
+	_, err := extractViaDocmark(path)
+	require.Error(t, err)
+	assert.Contains(t, err.Error(), "DOCMARK_URL")
+}
+
+func TestExtractViaDocmark_ToolErrorSurfacesMessage(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		writeMCPResponse(w, mcpToolResult{
+			JSONRPC: "2.0", ID: 1,
+			Result: &struct {
+				Content []struct {
+					Type string `json:"type"`
+					Text string `json:"text"`
+				} `json:"content"`
+				IsError bool `json:"isError"`
+			}{
+				Content: []struct {
+					Type string `json:"type"`
+					Text string `json:"text"`
+				}{{Type: "text", Text: "unsupported format for 'doc.docx'"}},
+				IsError: true,
+			},
+		})
+	}))
+	defer srv.Close()
+
+	t.Setenv("DOCMARK_URL", srv.URL+"/mcp")
+	t.Setenv("DOCMARK_BEARER_TOKEN", "tok")
+
+	dir := t.TempDir()
+	path := filepath.Join(dir, "doc.docx")
+	require.NoError(t, os.WriteFile(path, []byte("x"), 0o644))
+
+	_, err := extractViaDocmark(path)
+	require.Error(t, err)
+	assert.Contains(t, err.Error(), "unsupported format")
+}
+
+func TestExtractViaDocmark_HTTPErrorSurfaces(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(http.StatusUnauthorized)
+		_, _ = w.Write([]byte("unauthorized"))
+	}))
+	defer srv.Close()
+
+	t.Setenv("DOCMARK_URL", srv.URL+"/mcp")
+	t.Setenv("DOCMARK_BEARER_TOKEN", "wrong")
+
+	dir := t.TempDir()
+	path := filepath.Join(dir, "doc.docx")
+	require.NoError(t, os.WriteFile(path, []byte("x"), 0o644))
+
+	_, err := extractViaDocmark(path)
+	require.Error(t, err)
+	assert.Contains(t, err.Error(), "401")
+}
+
+func TestText_RoutesDocxXlsxPptxImagesToDocmark(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		writeMCPResponse(w, mcpToolResult{
+			JSONRPC: "2.0", ID: 1,
+			Result: &struct {
+				Content []struct {
+					Type string `json:"type"`
+					Text string `json:"text"`
+				} `json:"content"`
+				IsError bool `json:"isError"`
+			}{
+				Content: []struct {
+					Type string `json:"type"`
+					Text string `json:"text"`
+				}{{Type: "text", Text: "converted"}},
+			},
+		})
+	}))
+	defer srv.Close()
+	t.Setenv("DOCMARK_URL", srv.URL+"/mcp")
+	t.Setenv("DOCMARK_BEARER_TOKEN", "tok")
+
+	for _, ext := range []string{".docx", ".xlsx", ".pptx", ".png", ".jpg", ".jpeg"} {
+		t.Run(ext, func(t *testing.T) {
+			dir := t.TempDir()
+			path := filepath.Join(dir, "f"+ext)
+			require.NoError(t, os.WriteFile(path, []byte("x"), 0o644))
+			got, err := Text(path)
+			require.NoError(t, err)
+			assert.Equal(t, "converted", got)
+		})
+	}
+}
@@ -8,7 +8,9 @@ import (
 )

 // Text reads the file at path and returns its plain-text content.
-// Supported extensions: .md, .txt (passthrough), .pdf (via pdftotext).
+// Supported extensions: .md, .txt (passthrough), .pdf (via pdftotext),
+// .docx/.xlsx/.pptx/.png/.jpg/.jpeg (via docmark, ADR-0013 -- requires
+// DOCMARK_URL to be set; see docmark.go).
 func Text(path string) (string, error) {
 	ext := strings.ToLower(fileExt(path))
 	switch ext {
@@ -20,6 +22,8 @@ func Text(path string) (string, error) {
 		return string(b), nil
 	case ".pdf":
 		return extractPDF(path)
+	case ".docx", ".xlsx", ".pptx", ".png", ".jpg", ".jpeg":
+		return extractViaDocmark(path)
 	default:
 		return "", fmt.Errorf("unsupported file extension: %s", ext)
 	}
@@ -0,0 +1,143 @@
+// Package frontmatter lints and repairs the YAML frontmatter block of a
+// markdown note.
+//
+// Notes written directly — hand-authored, or promoted from brain/raw/ — do not
+// pass through pipeline.BuildPages, so nothing quotes their scalars. A title
+// containing an unescaped ": " then produces a block that yaml.Unmarshal
+// rejects with "mapping values are not allowed here", and every consumer that
+// reads frontmatter silently skips the note.
+//
+// Fix is deliberately conservative: it only adds quoting, never reorders or
+// rewrites, and it refuses to return a document that still does not parse.
+package frontmatter
+
+import (
+	"bytes"
+	"fmt"
+	"regexp"
+	"strings"
+
+	"gopkg.in/yaml.v3"
+)
+
+const fence = "---"
+
+// Lint reports whether doc's frontmatter block parses as YAML.
+//
+// A document with no frontmatter block, or with an unterminated one, is not an
+// error: there is nothing claiming to be YAML.
+func Lint(doc []byte) error {
+	b, ok := block(doc)
+	if !ok {
+		return nil
+	}
+	var v any
+	if err := yaml.Unmarshal(b, &v); err != nil {
+		return fmt.Errorf("frontmatter: %w", err)
+	}
+	return nil
+}
+
+// Fix quotes unquoted scalars whose value breaks YAML parsing and returns the
+// repaired document.
+//
+// It returns (doc, false, nil) when the document already parses, and
+// (doc, false, err) when quoting cannot rescue it — an unfixable document is
+// always returned byte-identical, never half-repaired.
+func Fix(doc []byte) ([]byte, bool, error) {
+	if err := Lint(doc); err == nil {
+		return doc, false, nil
+	}
+
+	b, ok := block(doc)
+	if !ok {
+		// Lint only fails when there is a block, so this is unreachable in
+		// practice; return the original rather than guess.
+		return doc, false, nil
+	}
+
+	fixed := quoteScalars(b)
+	if bytes.Equal(fixed, b) {
+		return doc, false, fmt.Errorf("frontmatter: not repairable by quoting: %w", Lint(doc))
+	}
+
+	var v any
+	if err := yaml.Unmarshal(fixed, &v); err != nil {
+		return doc, false, fmt.Errorf("frontmatter: quoting did not repair the block: %w", err)
+	}
+
+	_, rest, _ := split(doc)
+	out := []byte(fence + "\n")
+	out = append(out, fixed...)
+	out = append(out, []byte(fence)...)
+	out = append(out, rest...)
+	return out, true, nil
+}
+
+// mappingLine matches "key: value" at any indentation, capturing the prefix so
+// it can be re-emitted untouched.
+//
+// Sequence items ("- value") are deliberately not handled: "- foo: bar" is
+// valid YAML, so a document containing one does not reach Fix in the first
+// place. See the Lint table for why that gap is left open.
+var mappingLine = regexp.MustCompile(`^(\s*[A-Za-z_][\w.-]*:[ \t]+)(\S.*)$`)
+
+// quoteScalars single-quotes every unquoted scalar value in the block that
+// contains a colon. Values that are already quoted, or that carry YAML syntax
+// this package has no business rewriting, are left alone.
+func quoteScalars(block []byte) []byte {
+	lines := strings.Split(string(block), "\n")
+	for i, line := range lines {
+		m := mappingLine.FindStringSubmatch(line)
+		if m == nil {
+			continue
+		}
+		prefix, value := m[1], m[2]
+		if !needsQuoting(value) {
+			continue
+		}
+		lines[i] = prefix + "'" + strings.ReplaceAll(value, "'", "''") + "'"
+	}
+	return []byte(strings.Join(lines, "\n"))
+}
+
+// needsQuoting reports whether a scalar value has to be quoted to load as the
+// string it plainly is.
+//
+// The test is YAML's own parser rather than a pattern: ask whether the value
+// stands alone as the right-hand side of a mapping. Heuristics get this wrong
+// in both directions — `title: "Foo" — bar` opens with a quote but is not
+// quoted, and a value may contain a colon inside quotes and be perfectly fine.
+//
+// Anything that already parses is left alone, whatever it parses into — a flow
+// collection, a number, a bool. It is not broken, and quoting would change its
+// type.
+func needsQuoting(value string) bool {
+	if strings.HasPrefix(value, "|") || strings.HasPrefix(value, ">") {
+		return false // block scalar; its content is not parsed as YAML
+	}
+	var probe map[string]any
+	return yaml.Unmarshal([]byte("v: "+value+"\n"), &probe) != nil
+}
+
+// block returns the raw YAML between the opening and closing fences.
+func block(doc []byte) ([]byte, bool) {
+	b, _, ok := split(doc)
+	return b, ok
+}
+
+// split returns the frontmatter block and everything from the closing fence
+// onward (the closing fence itself excluded, its trailing newline included).
+func split(doc []byte) (block, rest []byte, ok bool) {
+	s := string(doc)
+	if !strings.HasPrefix(s, fence+"\n") {
+		return nil, nil, false
+	}
+	body := s[len(fence)+1:]
+
+	idx := strings.Index(body, "\n"+fence)
+	if idx < 0 {
+		return nil, nil, false
+	}
+	return []byte(body[:idx+1]), []byte(body[idx+1+len(fence):]), true
+}
@@ -0,0 +1,188 @@
+// ingestion/internal/frontmatter/frontmatter_test.go
+package frontmatter
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"gopkg.in/yaml.v3"
+)
+
+func TestLint(t *testing.T) {
+	tests := []struct {
+		name    string
+		doc     string
+		wantErr bool
+	}{
+		{
+			name: "no frontmatter block is not an error",
+			doc:  "# Just a heading\n\nSome body text.\n",
+		},
+		{
+			name: "quoted title parses",
+			doc:  "---\ntitle: 'Headless dispatch runs: Bash is denied'\n---\n\nbody\n",
+		},
+		{
+			name: "plain title parses",
+			doc:  "---\ntitle: A simple title\nwing: homelab\n---\n\nbody\n",
+		},
+		{
+			name:    "unquoted colon in title does not parse",
+			doc:     "---\ntitle: Headless dispatch runs: Bash is denied — use gitea MCP\nwing: homelab\n---\n\nbody\n",
+			wantErr: true,
+		},
+		{
+			// Known gap, deliberately not fixed here: this parses, but the
+			// item becomes map[string]any{"Headless dispatch": "denied"}
+			// rather than a string. It is a silent type corruption, not a
+			// parse failure, so repairing it would rewrite documents that
+			// currently load — out of scope for a lint about broken YAML.
+			name: "unquoted colon in a list item parses as a mapping, not an error",
+			doc:  "---\ntitle: Fine\naliases:\n  - Headless dispatch: denied\n---\n\nbody\n",
+		},
+		{
+			name: "unterminated frontmatter is not treated as frontmatter",
+			doc:  "---\ntitle: no closing fence\n\nbody\n",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			err := Lint([]byte(tt.doc))
+			if tt.wantErr {
+				require.Error(t, err)
+				return
+			}
+			require.NoError(t, err)
+		})
+	}
+}
+
+func TestFix(t *testing.T) {
+	tests := []struct {
+		name        string
+		doc         string
+		wantChanged bool
+		wantKey     string
+		wantValue   string
+	}{
+		{
+			name:        "quotes an unquoted title containing a colon",
+			doc:         "---\ntitle: Headless dispatch runs: Bash is denied — use gitea MCP\nwing: homelab\n---\n\nbody\n",
+			wantChanged: true,
+			wantKey:     "title",
+			wantValue:   "Headless dispatch runs: Bash is denied — use gitea MCP",
+		},
+		{
+			// Parses already (see the Lint table), so Fix must leave it alone
+			// rather than rewrite a document that loads.
+			name:        "leaves a colon-bearing list item alone because it already parses",
+			doc:         "---\ntitle: Fine\naliases:\n  - Headless dispatch: denied\n---\n\nbody\n",
+			wantChanged: false,
+			wantKey:     "title",
+			wantValue:   "Fine",
+		},
+		{
+			name:        "escapes an embedded single quote when quoting",
+			doc:         "---\ntitle: Don't do this: it breaks\n---\n\nbody\n",
+			wantChanged: true,
+			wantKey:     "title",
+			wantValue:   "Don't do this: it breaks",
+		},
+		{
+			// The value opens with a double quote and then keeps going after
+			// the closing one, so YAML reads it as a quoted scalar followed by
+			// junk. Treating "starts with a quote" as "already quoted" leaves
+			// this broken forever.
+			name:        "quotes a value that only looks quoted",
+			doc:         "---\ntitle: \"Evaluation Driven Generation\" — a TDD-style scaffold\ntags: [a, b]\n---\n\nbody\n",
+			wantChanged: true,
+			wantKey:     "title",
+			wantValue:   "\"Evaluation Driven Generation\" — a TDD-style scaffold",
+		},
+		{
+			name:        "leaves an already-valid document untouched",
+			doc:         "---\ntitle: 'Already quoted: fine'\nwing: homelab\n---\n\nbody\n",
+			wantChanged: false,
+			wantKey:     "title",
+			wantValue:   "Already quoted: fine",
+		},
+		{
+			name:        "leaves a document with no frontmatter untouched",
+			doc:         "# Heading\n\nbody: with a colon\n",
+			wantChanged: false,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got, changed, err := Fix([]byte(tt.doc))
+			require.NoError(t, err)
+			assert.Equal(t, tt.wantChanged, changed)
+
+			if !tt.wantChanged {
+				assert.Equal(t, tt.doc, string(got), "unchanged docs must be returned byte-identical")
+			}
+
+			// Whatever came back must parse — that is the whole point.
+			require.NoError(t, Lint(got), "Fix must not return a document that still fails to parse")
+
+			if tt.wantKey == "" {
+				return
+			}
+			block, ok := block(got)
+			require.True(t, ok)
+			var m map[string]any
+			require.NoError(t, yaml.Unmarshal(block, &m))
+			assert.Equal(t, tt.wantValue, m[tt.wantKey], "the value must survive quoting unchanged")
+		})
+	}
+}
+
+func TestFix_LeavesStructuredValuesStructured(t *testing.T) {
+	// Only the broken scalar may be touched. A flow sequence on a neighbouring
+	// line still has to load as a sequence afterwards, not as a string.
+	doc := "---\ntitle: Broken: here\ntags: [prompting, llm]\ncount: 3\n---\n\nbody\n"
+
+	got, changed, err := Fix([]byte(doc))
+	require.NoError(t, err)
+	require.True(t, changed)
+
+	b, ok := block(got)
+	require.True(t, ok)
+	var m map[string]any
+	require.NoError(t, yaml.Unmarshal(b, &m))
+
+	assert.Equal(t, "Broken: here", m["title"])
+	assert.Equal(t, []any{"prompting", "llm"}, m["tags"])
+	assert.Equal(t, 3, m["count"])
+}
+
+func TestFix_PreservesBodyExactly(t *testing.T) {
+	body := "\nThe body has: colons, 'quotes', and\n---\na horizontal rule.\n"
+	doc := "---\ntitle: Broken: title\n---" + body
+
+	got, changed, err := Fix([]byte(doc))
+	require.NoError(t, err)
+	require.True(t, changed)
+	assert.True(t, len(got) > 0)
+
+	_, rest, ok := split([]byte(doc))
+	require.True(t, ok)
+	_, gotRest, ok := split(got)
+	require.True(t, ok)
+	assert.Equal(t, string(rest), string(gotRest), "the body must not be touched")
+}
+
+func TestFix_RefusesToReturnAnUnparseableResult(t *testing.T) {
+	// A frontmatter block that quoting cannot rescue: the structure itself is
+	// broken, not a scalar. Fix must return the original and an error rather
+	// than a half-repaired document.
+	doc := "---\ntitle: fine\n\tbad: tab-indented mapping\n  - stray list item\n---\n\nbody\n"
+
+	got, changed, err := Fix([]byte(doc))
+	require.Error(t, err)
+	assert.False(t, changed)
+	assert.Equal(t, doc, string(got), "an unfixable document must come back byte-identical")
+}
@@ -0,0 +1,84 @@
+// ingestion/internal/frontmatter/scan.go
+package frontmatter
+
+import (
+	"fmt"
+	"io/fs"
+	"os"
+	"path/filepath"
+	"strings"
+	"unicode/utf8"
+)
+
+// Finding is one markdown file whose frontmatter does not parse.
+type Finding struct {
+	Path     string // relative to the scanned root
+	Err      error  // why it does not parse, or why the repair was refused
+	Repaired bool   // true only when fix was requested and the file was rewritten
+}
+
+// Scan walks root for *.md files whose frontmatter fails to parse.
+//
+// With fix set, each finding that quoting can rescue is rewritten in place;
+// anything quoting cannot rescue is reported and left byte-identical. A file
+// that cannot be read or decoded is reported as a finding rather than aborting
+// the walk — one poisoned note must not hide the other findings.
+func Scan(root string, fix bool) ([]Finding, error) {
+	var found []Finding
+
+	err := filepath.WalkDir(root, func(path string, d fs.DirEntry, err error) error {
+		if err != nil {
+			return err
+		}
+		if d.IsDir() || !strings.EqualFold(filepath.Ext(path), ".md") {
+			return nil
+		}
+
+		rel, relErr := filepath.Rel(root, path)
+		if relErr != nil {
+			rel = path
+		}
+
+		doc, readErr := os.ReadFile(path)
+		if readErr != nil {
+			found = append(found, Finding{Path: rel, Err: readErr})
+			return nil
+		}
+		if !utf8.Valid(doc) {
+			found = append(found, Finding{Path: rel, Err: fmt.Errorf("not valid UTF-8")})
+			return nil
+		}
+		if lintErr := Lint(doc); lintErr == nil {
+			return nil
+		}
+
+		if !fix {
+			found = append(found, Finding{Path: rel, Err: Lint(doc)})
+			return nil
+		}
+
+		repaired, changed, fixErr := Fix(doc)
+		if fixErr != nil || !changed {
+			found = append(found, Finding{Path: rel, Err: fixErr})
+			return nil
+		}
+		if writeErr := writeFilePreservingMode(path, repaired); writeErr != nil {
+			found = append(found, Finding{Path: rel, Err: writeErr})
+			return nil
+		}
+		found = append(found, Finding{Path: rel, Repaired: true})
+		return nil
+	})
+	if err != nil {
+		return nil, fmt.Errorf("scan %s: %w", root, err)
+	}
+	return found, nil
+}
+
+func writeFilePreservingMode(path string, content []byte) error {
+	mode := fs.FileMode(0o644)
+	if info, err := os.Stat(path); err == nil {
+		mode = info.Mode().Perm()
+	}
+	return os.WriteFile(path, content, mode)
+}
@@ -0,0 +1,103 @@
+// ingestion/internal/frontmatter/scan_test.go
+package frontmatter
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func writeTree(t *testing.T, files map[string]string) string {
+	t.Helper()
+	root := t.TempDir()
+	for name, content := range files {
+		path := filepath.Join(root, name)
+		require.NoError(t, os.MkdirAll(filepath.Dir(path), 0o755))
+		require.NoError(t, os.WriteFile(path, []byte(content), 0o644))
+	}
+	return root
+}
+
+const (
+	brokenDoc = "---\ntitle: Broken: title here\nwing: homelab\n---\n\nbody\n"
+	validDoc  = "---\ntitle: 'Fine: quoted'\n---\n\nbody\n"
+)
+
+func TestScan_ReportsOnlyBrokenFiles(t *testing.T) {
+	root := writeTree(t, map[string]string{
+		"wiki/a/broken.md": brokenDoc,
+		"wiki/a/valid.md":  validDoc,
+		"wiki/b/plain.md":  "# no frontmatter\n\nbody: with colon\n",
+		"wiki/a/notes.txt": brokenDoc, // not markdown — must be ignored
+	})
+
+	found, err := Scan(root, false)
+	require.NoError(t, err)
+
+	require.Len(t, found, 1)
+	assert.Equal(t, "wiki/a/broken.md", found[0].Path)
+	assert.False(t, found[0].Repaired)
+	assert.Error(t, found[0].Err)
+
+	// Dry run must not touch the file.
+	got, err := os.ReadFile(filepath.Join(root, "wiki/a/broken.md"))
+	require.NoError(t, err)
+	assert.Equal(t, brokenDoc, string(got))
+}
+
+func TestScan_FixWritesRepairedFilesAndLeavesTheRestAlone(t *testing.T) {
+	root := writeTree(t, map[string]string{
+		"wiki/a/broken.md": brokenDoc,
+		"wiki/a/valid.md":  validDoc,
+	})
+
+	found, err := Scan(root, true)
+	require.NoError(t, err)
+	require.Len(t, found, 1)
+	assert.True(t, found[0].Repaired)
+	assert.NoError(t, found[0].Err)
+
+	repaired, err := os.ReadFile(filepath.Join(root, "wiki/a/broken.md"))
+	require.NoError(t, err)
+	require.NoError(t, Lint(repaired), "the repaired file must parse")
+	assert.Contains(t, string(repaired), "title: 'Broken: title here'")
+	assert.Contains(t, string(repaired), "wing: homelab", "untouched keys must survive")
+
+	untouched, err := os.ReadFile(filepath.Join(root, "wiki/a/valid.md"))
+	require.NoError(t, err)
+	assert.Equal(t, validDoc, string(untouched))
+
+	// Second pass finds nothing — the repair is idempotent and complete.
+	again, err := Scan(root, true)
+	require.NoError(t, err)
+	assert.Empty(t, again)
+}
+
+func TestScan_ReportsUnfixableWithoutWriting(t *testing.T) {
+	unfixable := "---\ntitle: fine\n\tbad: tab-indented\n  - stray\n---\n\nbody\n"
+	root := writeTree(t, map[string]string{"wiki/x.md": unfixable})
+
+	found, err := Scan(root, true)
+	require.NoError(t, err)
+	require.Len(t, found, 1)
+	assert.False(t, found[0].Repaired)
+	assert.Error(t, found[0].Err)
+
+	got, err := os.ReadFile(filepath.Join(root, "wiki/x.md"))
+	require.NoError(t, err)
+	assert.Equal(t, unfixable, string(got), "an unfixable file must be left exactly as it was")
+}
+
+func TestScan_ReportsUndecodableFilesInsteadOfFailingTheRun(t *testing.T) {
+	root := writeTree(t, map[string]string{"wiki/ok.md": validDoc})
+	require.NoError(t, os.WriteFile(filepath.Join(root, "wiki/bad-bytes.md"),
+		[]byte{'-', '-', '-', '\n', 0xff, 0xfe, '\n', '-', '-', '-', '\n'}, 0o644))
+
+	found, err := Scan(root, false)
+	require.NoError(t, err, "one unreadable file must not abort the whole scan")
+	require.Len(t, found, 1)
+	assert.Equal(t, "wiki/bad-bytes.md", found[0].Path)
+}
@@ -165,7 +165,7 @@ func TestBrainUpdateReembedsNewContent(t *testing.T) {
 	ctx := context.Background()

 	callResult(t, toolCall(t, srv, "brain_write", map[string]any{
-		"content": "# Note\n\nthe OLD distinctive payload\n",
+		"content":  "# Note\n\nthe OLD distinctive payload\n",
 		"filename": "n", "wing": "a", "hall": "facts",
 	}))

@@ -14,6 +14,7 @@ import (
 	"github.com/mathiasbq/hyperguild/ingestion/internal/capture"
 	"github.com/mathiasbq/hyperguild/ingestion/internal/extract"
 	"github.com/mathiasbq/hyperguild/ingestion/internal/graphsync"
+	"github.com/mathiasbq/hyperguild/ingestion/internal/notes"
 	"github.com/mathiasbq/hyperguild/ingestion/internal/pipeline"
 	"github.com/mathiasbq/hyperguild/ingestion/internal/search"
 	"github.com/mathiasbq/hyperguild/ingestion/internal/session"
@@ -97,6 +98,8 @@ func (s *Server) tools() []map[string]any {
 				"slug":     str("optional target slug; defaults to filename minus date prefix"),
 			}),
 		},
+		noteToolDescriptors()[0],
+		noteToolDescriptors()[1],
 		{
 			"name":        "brain_tunnel",
 			"description": "Create an explicit bidirectional [[wikilink]] between two notes in different wings. Idempotent.",
@@ -105,13 +108,6 @@ func (s *Server) tools() []map[string]any {
 				"target": str("path of target note (must be in a different wing)"),
 			}),
 		},
-		{
-			"name":        "brain_index",
-			"description": "Regenerate _index.md (Map of Content) for one or all wings under brain/wiki/. Auto-called after brain_write with wing+hall.",
-			"inputSchema": schema([]string{}, map[string]any{
-				"wing": str("optional wing to index; if absent, rebuilds every wing"),
-			}),
-		},
 		{
 			"name":        "brain_ingest_raw",
 			"description": "Ingest pre-structured pages into the brain wiki, bypassing the LLM extraction step.",
@@ -327,6 +323,15 @@ func (s *Server) brainGet(ctx context.Context, args json.RawMessage) (json.RawMe
 	if target == "" {
 		return nil, fmt.Errorf("id or path is required")
 	}
+	// Containment: the store resolves any brain-relative path, and
+	// parseFrontmatter returns the WHOLE file as body when there is no
+	// frontmatter fence — so without this, brain_get reads verbatim session
+	// transcripts under archive/ and sessions/, which BM25 never indexes and
+	// which nobody therefore thinks of as reachable. Same allowlist as
+	// brain_read (brain#4).
+	if _, err := notes.Resolve(s.brainDir, target, notes.ScopeNotes); err != nil {
+		return nil, err
+	}
 	note, err := s.store.Get(ctx, target)
 	if err != nil {
 		return nil, err
@@ -0,0 +1,76 @@
+package mcp
+
+import (
+	"time"
+
+	"github.com/mathiasbq/hyperguild/ingestion/internal/api"
+)
+
+// pendingNudgeThreshold is how old a raw/ note has to be before brain_context
+// mentions the queue. Two weeks: long enough that a note written this sprint
+// does not nag, short enough that four items cannot sit unnoticed for three
+// months again (#82).
+const pendingNudgeThreshold = 14 * 24 * time.Hour
+
+// PendingNudge is the in-session reminder that the promote/reject queue has
+// items waiting. It is advisory: a count, an age, and how to look.
+type PendingNudge struct {
+	Pending    int    `json:"pending"`     // everything in the queue
+	Aging      int    `json:"aging"`       // those past the threshold
+	Oldest     string `json:"oldest"`      // filename of the oldest pending note
+	OldestDays int    `json:"oldest_days"` // its age, in whole days
+	Hint       string `json:"hint"`
+}
+
+// pendingNudge summarises the raw/ review queue, or returns nil when there is
+// nothing worth saying.
+//
+// The trigger is the missing half of the queue (#82): brain_pending has always
+// existed, and four real items still sat unreviewed from 2026-04-23 to
+// 2026-07-15 because nothing ever prompted anyone to call it. The system
+// should be what remembers the queue exists.
+//
+// Threshold-gated on purpose. A notice on every context call is one people
+// learn to skip, which reproduces the original failure with extra steps.
+//
+// It never promotes, rejects, or reorders anything. Age is a reason to ask a
+// human, not a verdict — an old note may be exactly right to promote once
+// someone finally looks at it.
+func pendingNudge(brainDir string, now time.Time, threshold time.Duration) *PendingNudge {
+	pending, err := api.ListPending(brainDir)
+	if err != nil || len(pending) == 0 {
+		// brain_context is a hot path; a broken queue degrades to silence
+		// rather than failing the call that asked for project context.
+		return nil
+	}
+
+	var aging int
+	var oldestName string
+	var oldestAge time.Duration
+
+	for _, p := range pending {
+		created, perr := time.Parse(time.RFC3339, p.CreatedAt)
+		if perr != nil {
+			continue // an unparseable timestamp is not evidence of age
+		}
+		age := now.Sub(created)
+		if age >= threshold {
+			aging++
+		}
+		if age > oldestAge {
+			oldestAge, oldestName = age, p.Filename
+		}
+	}
+
+	if aging == 0 {
+		return nil
+	}
+
+	return &PendingNudge{
+		Pending:    len(pending),
+		Aging:      aging,
+		Oldest:     oldestName,
+		OldestDays: int(oldestAge.Hours() / 24),
+		Hint:       "call brain_pending to review; nothing is promoted or rejected automatically",
+	}
+}
@@ -0,0 +1,115 @@
+package mcp
+
+import (
+	"context"
+	"encoding/json"
+	"os"
+	"path/filepath"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// writePending drops a raw/ note whose created_at is age old.
+func writePending(t *testing.T, brainDir, name string, age time.Duration, now time.Time) {
+	t.Helper()
+	raw := filepath.Join(brainDir, "raw")
+	require.NoError(t, os.MkdirAll(raw, 0o755))
+	body := "---\ncreated_at: " + now.Add(-age).UTC().Format(time.RFC3339) + "\n---\n\nnote body\n"
+	require.NoError(t, os.WriteFile(filepath.Join(raw, name), []byte(body), 0o644))
+}
+
+func TestPendingNudge_SilentWhenNothingIsPending(t *testing.T) {
+	// No queue, no nudge. A notice that fires every session is one people
+	// learn to skip, which is how the queue got ignored for three months in
+	// the first place (#82).
+	got := pendingNudge(t.TempDir(), time.Now(), 14*24*time.Hour)
+	assert.Nil(t, got)
+}
+
+func TestPendingNudge_SilentWhileEverythingIsBelowTheThreshold(t *testing.T) {
+	now := time.Now()
+	dir := t.TempDir()
+	writePending(t, dir, "fresh.md", 2*24*time.Hour, now)
+
+	got := pendingNudge(dir, now, 14*24*time.Hour)
+	assert.Nil(t, got, "a two-day-old note is not aging")
+}
+
+func TestPendingNudge_ReportsCountAndOldestAgeOnceSomethingAges(t *testing.T) {
+	now := time.Now()
+	dir := t.TempDir()
+	writePending(t, dir, "old.md", 100*24*time.Hour, now)
+	writePending(t, dir, "older.md", 120*24*time.Hour, now)
+	writePending(t, dir, "fresh.md", 1*24*time.Hour, now)
+
+	got := pendingNudge(dir, now, 14*24*time.Hour)
+	require.NotNil(t, got)
+
+	// All three are pending; the threshold decides whether to speak, not
+	// what to count. Someone opening the queue sees the whole queue.
+	assert.Equal(t, 3, got.Pending)
+	assert.Equal(t, 2, got.Aging)
+	assert.Equal(t, 120, got.OldestDays)
+	assert.Equal(t, "older.md", got.Oldest)
+}
+
+func TestPendingNudge_NeverDecidesAnything(t *testing.T) {
+	// Aging is a trigger to ask a human, never a verdict. The nudge must
+	// carry no action and must leave the queue exactly as it found it.
+	now := time.Now()
+	dir := t.TempDir()
+	writePending(t, dir, "ancient.md", 365*24*time.Hour, now)
+
+	before, err := os.ReadDir(filepath.Join(dir, "raw"))
+	require.NoError(t, err)
+
+	got := pendingNudge(dir, now, 14*24*time.Hour)
+	require.NotNil(t, got)
+
+	after, err := os.ReadDir(filepath.Join(dir, "raw"))
+	require.NoError(t, err)
+	assert.Len(t, after, len(before), "the nudge must not promote or reject anything")
+	assert.Contains(t, got.Hint, "brain_pending", "the nudge should say how to look, not act")
+}
+
+func TestPendingNudge_SurvivesAnUnreadableQueue(t *testing.T) {
+	// brain_context is a hot path; a broken raw/ dir must degrade to silence
+	// rather than failing the whole context call.
+	dir := t.TempDir()
+	require.NoError(t, os.WriteFile(filepath.Join(dir, "raw"), []byte("not a directory"), 0o644))
+
+	assert.NotPanics(t, func() {
+		assert.Nil(t, pendingNudge(dir, time.Now(), 14*24*time.Hour))
+	})
+}
+
+func TestBrainContext_CarriesTheNudgeWithoutFailingWhenTheQueueIsEmpty(t *testing.T) {
+	// The wiring, not the summary: a nudge that never reaches a caller is the
+	// same as no nudge, and brain_context must still work with no queue.
+	dir := t.TempDir()
+	srv := NewServer(dir, nil, nil, nil)
+
+	raw, err := srv.brainContext(context.Background(),
+		json.RawMessage(`{"project_root":"/home/mathias/dev/AGENTS/hyperguild"}`))
+	require.NoError(t, err)
+
+	var empty map[string]any
+	require.NoError(t, json.Unmarshal(raw, &empty))
+	assert.NotContains(t, empty, "pending_review", "silence when nothing is aging")
+
+	writePending(t, dir, "ancient.md", 200*24*time.Hour, time.Now())
+
+	raw, err = srv.brainContext(context.Background(),
+		json.RawMessage(`{"project_root":"/home/mathias/dev/AGENTS/hyperguild"}`))
+	require.NoError(t, err)
+
+	var withQueue map[string]any
+	require.NoError(t, json.Unmarshal(raw, &withQueue))
+	nudge, ok := withQueue["pending_review"].(map[string]any)
+	require.True(t, ok, "the nudge must reach the caller: %v", withQueue)
+	assert.Equal(t, float64(1), nudge["aging"])
+	assert.Equal(t, "ancient.md", nudge["oldest"])
+}
@@ -1,9 +1,14 @@
 // Package mcp implements an MCP HTTP handler for the ingestion service.
 // Exposed tools: brain_query, brain_write, brain_update, brain_get,
-// brain_pending, brain_promote, brain_index, brain_tunnel, brain_ingest,
+// brain_pending, brain_promote, brain_tunnel, brain_ingest,
 // brain_ingest_raw, brain_answer, brain_classify, brain_graph,
 // brain_context, session_log, and capture (the #55 relay tool, registered
 // only when WithCapture is set).
+//
+// brain_index dispatches but is deliberately absent from tools/list: it is
+// auto-called after every write, so surfacing it as a caller verb is
+// cognitive load with no decision behind it (ADR-0012 rule 4, #78). It stays
+// callable for maintenance — de-surfacing hides the verb, not the operation.
 package mcp

 import (
@@ -44,6 +49,8 @@ type rpcError struct {
 // Server handles MCP JSON-RPC over HTTP for the ingestion service.
 type Server struct {
 	brainDir  string
+	govAudit  capture.AuditSink
+	govNotify govNotifier
 	pipeline  pipeline.Config
 	llm       pipeline.CompleteFunc
 	answerLLM pipeline.CompleteFunc // nil = brain_answer and brain_classify unavailable
@@ -270,6 +277,15 @@ func (s *Server) handleCall(ctx context.Context, name string, args json.RawMessa
 		return s.brainPromote(ctx, args)
 	case "capture":
 		return s.brainCapture(ctx, args)
+	case "brain_read":
+		return s.brainRead(ctx, args)
+	case "brain_edit":
+		return s.brainEdit(ctx, args)
+	case "brain_edit_root":
+		// Dispatches but is intentionally absent from tools/list — see
+		// tools_notes.go for why a governance-file editor must not be
+		// discoverable by a model.
+		return s.brainEditRoot(ctx, args)
 	case "brain_index":
 		return s.brainIndex(ctx, args)
 	case "brain_tunnel":
@@ -59,11 +59,43 @@ func TestServerToolsList(t *testing.T) {
 	assert.ElementsMatch(t, []string{
 		"brain_query", "brain_write", "brain_update", "brain_get",
 		"brain_pending", "brain_promote",
-		"brain_index", "brain_tunnel",
+		"brain_read", "brain_edit",
+		"brain_tunnel",
 		"brain_ingest_raw", "brain_ingest",
 		"brain_answer", "brain_classify", "brain_graph", "brain_context",
 		"session_log",
 	}, names)
+
+	// brain_index is auto-called after every brain_write, so surfacing it as
+	// a caller verb is cognitive load with no decision behind it (ADR-0012
+	// rule 4, #78). The capability stays reachable — see the admin test below.
+	assert.NotContains(t, names, "brain_index")
+
+	// brain_edit_root is de-surfaced for a sharper reason than brain_index:
+	// brain content is ingested from the outside world and reaches a model's
+	// context, so a listed governance-file editor would be a durable
+	// prompt-injection path — one poisoned page rewriting the CLAUDE.md a
+	// .dispatch-allow agent later loads as instructions.
+	assert.NotContains(t, names, "brain_edit_root")
+}
+
+func TestBrainIndexStaysCallableForAdminUseAfterDeSurfacing(t *testing.T) {
+	// De-surfacing hides the verb from the model-facing list; it must not
+	// remove the operation. A maintenance caller still needs to rebuild a
+	// Map of Content by hand.
+	srv := mcp.NewServer(t.TempDir(), nil, nil, nil)
+
+	req := httptest.NewRequest(http.MethodPost, "/mcp", body(t, map[string]any{
+		"jsonrpc": "2.0", "id": 3, "method": "tools/call",
+		"params": map[string]any{"name": "brain_index", "arguments": map[string]any{}},
+	}))
+	rr := httptest.NewRecorder()
+	srv.ServeHTTP(rr, req)
+
+	require.Equal(t, http.StatusOK, rr.Code)
+	var resp map[string]any
+	require.NoError(t, json.Unmarshal(rr.Body.Bytes(), &resp))
+	assert.NotContains(t, resp, "error", "brain_index must still dispatch: %v", resp["error"])
 }

 func TestServerNotificationGetsNoBody(t *testing.T) {
@@ -31,7 +31,7 @@ func captureToolDescriptor() map[string]any {
 		"type": "object",
 		"properties": map[string]any{
 			"text": str("the insight body"), "wing": str("brain wing"),
-			"hall": str("brain hall (facts/decisions/failures/hypotheses/sources)"),
+			"hall":           str("brain hall (facts/decisions/failures/hypotheses/sources)"),
 			"supersede_slug": str("optional: slug of a prior note to revise in place instead of creating"),
 		},
 		"required": []string{"text", "wing", "hall"},
@@ -41,7 +41,7 @@ func captureToolDescriptor() map[string]any {
 		"properties": map[string]any{
 			"repo": str("gitea repo (owner is always mathias)"), "action": str("create|close|comment"),
 			"number": map[string]any{"type": "integer", "description": "issue number (close/comment)"},
-			"title": str("issue title (create)"), "body": str("issue/comment body"),
+			"title":  str("issue title (create)"), "body": str("issue/comment body"),
 		},
 		"required": []string{"repo", "action"},
 	}
@@ -51,24 +51,20 @@ func captureToolDescriptor() map[string]any {
 			"context": map[string]any{
 				"type": "object",
 				"properties": map[string]any{
-					"harness": str("descriptive harness label (telemetry only, never a gate input)"),
+					"harness":     str("descriptive harness label (telemetry only, never a gate input)"),
 					"session_ref": str("optional session reference"), "fidelity": str("live-capture|transcript-parse|agent-runlog"),
 					"actor": str("acting user/agent"), "classification": str("caller-declared sensitivity: public|internal|confidential"),
 				},
 			},
 			"insights": map[string]any{"type": "array", "items": insightItem},
 			"tickets":  map[string]any{"type": "array", "items": ticketItem},
-			"summary": map[string]any{"type": "object", "properties": map[string]any{
-				"title": str("summary title"), "body": str("summary body"),
-				"repos_touched": map[string]any{"type": "array", "items": map[string]any{"type": "string"}},
-			}},
-			"dry_run": map[string]any{"type": "boolean", "description": "validate + return the would-be receipt, write nothing"},
+			"dry_run":  map[string]any{"type": "boolean", "description": "validate + return the would-be receipt, write nothing"},
 		},
 	}
 	b, _ := json.Marshal(schema)
 	return map[string]any{
 		"name":        "capture",
-		"description": "Persist a session's value uniformly: insights → brain (write or supersede), action items → Gitea tickets, optional summary → ai-sessions. The relay door for MCP-native harnesses. Origin is server-derived from your authenticated identity; confidential captures through a us-nexus surface are refused (I1). Returns a partial-aware receipt.",
+		"description": "Persist a session's value uniformly: insights → brain (write or supersede), action items → Gitea tickets. The relay door for MCP-native harnesses. Origin is server-derived from your authenticated identity; confidential captures through a us-nexus surface are refused (I1). Returns a partial-aware receipt.",
 		"inputSchema": json.RawMessage(b),
 	}
 }
@@ -49,7 +49,7 @@ func captureServer(t *testing.T, validator capturehttp.Validator, sovereign []st
 	brainDir := t.TempDir()
 	cfg, err := classification.Load(brainDir)
 	require.NoError(t, err)
-	svc := capture.NewService(brainstore.New(brainDir), capFakeTracker{}, nil, cfg, audit.NewSlogSink(nil))
+	svc := capture.NewService(brainstore.New(brainDir), capFakeTracker{}, cfg, audit.NewSlogSink(nil))
 	srv := mcp.NewServer(brainDir, nil, nil, nil)
 	srv.WithCapture(svc, validator, capStaticTok, "local-cli", capturehttp.NewOriginResolver(sovereign))
 	return srv, brainDir
@@ -8,8 +8,10 @@ import (
 	"path/filepath"
 	"sort"
 	"strings"
+	"time"

 	"github.com/mathiasbq/hyperguild/ingestion/internal/search"
+	"github.com/mathiasbq/hyperguild/ingestion/internal/textutil"
 )

 // brainContextArgs is the input shape of brain_context. project_root is
@@ -155,17 +157,21 @@ func (s *Server) brainContext(ctx context.Context, args json.RawMessage) (json.R
 		entries = entries[:limit]
 	}

-	return json.Marshal(map[string]any{"entries": entries})
+	out := map[string]any{"entries": entries}
+	// The queue nudge rides along with a call the session already makes, so
+	// noticing an aging note costs nobody a decision to go looking (#82).
+	// Advisory only, and absent entirely when there is nothing to say.
+	if n := pendingNudge(s.brainDir, time.Now(), pendingNudgeThreshold); n != nil {
+		out["pending_review"] = n
+	}
+	return json.Marshal(out)
 }

 // truncateExcerpt clamps an already-stripped excerpt to maxLen characters
 // without re-running the frontmatter parser. The ellipsis suffix matches
 // the convention used in search.excerpt.
 func truncateExcerpt(s string, maxLen int) string {
-	if len(s) <= maxLen {
-		return s
-	}
-	return s[:maxLen] + "…"
+	return textutil.Truncate(s, maxLen)
 }

 // readExcerpt loads a doc relative to brainDir, strips its frontmatter,
@@ -185,10 +191,7 @@ func readExcerpt(brainDir, relPath string, maxLen int) string {
 	if len(parts) == 3 {
 		body = strings.TrimSpace(parts[2])
 	}
-	if len(body) > maxLen {
-		return body[:maxLen] + "…"
-	}
-	return body
+	return textutil.Truncate(body, maxLen)
 }

 // max1 returns the maximum of n and 1, used to guard against divide-by-zero
@@ -0,0 +1,222 @@
+package mcp
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"log/slog"
+	"strings"
+	"time"
+
+	"github.com/mathiasbq/hyperguild/ingestion/internal/brain"
+	"github.com/mathiasbq/hyperguild/ingestion/internal/capture"
+	"github.com/mathiasbq/hyperguild/ingestion/internal/classification"
+	"github.com/mathiasbq/hyperguild/ingestion/internal/notes"
+)
+
+// noteToolDescriptors are the model-facing halves of brain#4.
+//
+// brain_edit_root is deliberately absent: it dispatches but is not listed, the
+// same de-surfacing ADR-0012 rule 4 applies to brain_index (#78). Hiding the
+// verb matters here for a specific reason — brain content is ingested from the
+// outside world and reaches a model's context, so a listed governance-file
+// editor is a durable prompt-injection path: one poisoned page could rewrite
+// the CLAUDE.md that a .dispatch-allow agent later obeys. A human who knows
+// the tool exists can still call it; a model reading tools/list cannot
+// discover it.
+func noteToolDescriptors() []map[string]any {
+	str := func(d string) map[string]any { return map[string]any{"type": "string", "description": d} }
+	schema := func(required []string, props map[string]any) json.RawMessage {
+		b, _ := json.Marshal(map[string]any{"type": "object", "required": required, "properties": props})
+		return b
+	}
+	return []map[string]any{
+		{
+			"name": "brain_read",
+			"description": "Return a note's raw markdown verbatim — no synthesis, no excerpting. " +
+				"Use this to obtain the exact text before brain_edit; never build old_str from a " +
+				"brain_query excerpt, which is truncated and normalised and will not match.",
+			"inputSchema": schema([]string{"path"}, map[string]any{
+				"path": str("brain-relative path under knowledge/ or wiki/, e.g. wiki/homelab/facts/x.md"),
+			}),
+		},
+		{
+			"name": "brain_edit",
+			"description": "Replace exactly one occurrence of old_str with new_str in a note, leaving " +
+				"every other byte identical. Fails loudly if old_str is absent or matches more than " +
+				"once — extend old_str until it is unique. Does NOT stamp updated_at or supersedes " +
+				"(brain_update does); it is a byte-level patch, not a metadata operation.",
+			"inputSchema": schema([]string{"path", "old_str", "new_str"}, map[string]any{
+				"path":    str("brain-relative path under knowledge/ or wiki/"),
+				"old_str": str("exact text to replace; must occur exactly once"),
+				"new_str": str("replacement text; empty string deletes old_str"),
+			}),
+		},
+	}
+}
+
+// --- hyperguild#97: governance-rewrite observability -----------------------
+
+// govNotifier raises an out-of-band alert. Declared here rather than importing
+// internal/audit so the MCP package keeps depending on capture alone.
+type govNotifier interface {
+	Notify(ctx context.Context, msg string) error
+}
+
+// WithGovernanceObserver attaches the audit sink and notifier that observe a
+// successful brain_edit_root. Both are optional; either may be nil.
+func (s *Server) WithGovernanceObserver(sink capture.AuditSink, n govNotifier) {
+	s.govAudit, s.govNotify = sink, n
+}
+
+type brainReadArgs struct {
+	Path string `json:"path"`
+}
+
+func (s *Server) brainRead(_ context.Context, args json.RawMessage) (json.RawMessage, error) {
+	var a brainReadArgs
+	if err := json.Unmarshal(args, &a); err != nil {
+		return nil, fmt.Errorf("parse args: %w", err)
+	}
+	content, err := notes.Read(s.brainDir, a.Path)
+	if err != nil {
+		return nil, err
+	}
+	return json.Marshal(map[string]any{"path": a.Path, "content": string(content)})
+}
+
+type brainEditArgs struct {
+	Path   string `json:"path"`
+	OldStr string `json:"old_str"`
+	NewStr string `json:"new_str"`
+}
+
+// brainEdit is the model-facing editor: notes only.
+//
+// Deliberately NOT audited (#97). A note edit is already fully reconstructible
+// from git history, which carries the same before/after bytes plus a diff.
+// Governance files get the extra trail because they change what later agents
+// obey — the asymmetry is about instruction-carrying content, not about how
+// hard the change is to reconstruct. Auditing every note edit would also bury
+// the rare governance record under routine traffic, which is how an alert
+// stops being read.
+func (s *Server) brainEdit(_ context.Context, args json.RawMessage) (json.RawMessage, error) {
+	_, out, err := s.editWithScope(args, notes.ScopeNotes)
+	return out, err
+}
+
+// brainEditRoot edits a governance file (CLAUDE.md). De-surfaced AND gated on
+// the authenticated principal: only the static local-CLI token may call it, so
+// a claude.ai-origin session — the one that may have just read an untrusted
+// page — cannot rewrite the instructions later agents load.
+func (s *Server) brainEditRoot(ctx context.Context, args json.RawMessage) (json.RawMessage, error) {
+	info, ok := ctx.Value(principalKey).(principalInfo)
+	if !ok || !info.viaStatic {
+		return nil, fmt.Errorf("brain_edit_root requires the local static principal; " +
+			"a governance file is not editable from a model-facing origin")
+	}
+	res, out, err := s.editWithScope(args, notes.ScopeRoot)
+	if err != nil {
+		// A refusal is not a rewrite. Recording or alerting on one would cry
+		// wolf, and the gate already logs its own denials.
+		return out, err
+	}
+	// A durable instruction rewrite should be loud, not silent.
+	slog.Warn("brain_edit_root applied", "principal", info.principal, "result", string(out))
+	s.observeGovernanceEdit(ctx, info.principal, res)
+	return out, err
+}
+
+// observeGovernanceEdit records and alerts on a rewrite that already landed.
+//
+// Best-effort by construction: the bytes are written and brain-sync will commit
+// them within the quarter hour, so failing the call here would report a
+// non-rewrite to the caller while the rewrite sits on disk. A failure to
+// observe is therefore logged at ERROR — the one case where the trail itself is
+// what broke, and the only remaining signal.
+func (s *Server) observeGovernanceEdit(ctx context.Context, principal string, res notes.Result) {
+	// Path and hashes only. The notification leaves the cluster for a phone
+	// via a third-party topic; a hash identifies the rewrite, the bytes would
+	// leak whatever was written into an instruction file.
+	msg := fmt.Sprintf("brain_edit_root applied\npath=%s\nprincipal=%s\nbefore=%s\nafter=%s",
+		res.Path, principal, res.PrevContentHash, res.ContentHash)
+
+	if s.govNotify != nil {
+		if err := s.govNotify.Notify(ctx, msg); err != nil {
+			slog.Error("brain_edit_root notify failed", "path", res.Path, "err", err)
+		}
+	}
+	if s.govAudit == nil {
+		return
+	}
+	// Internal, not Confidential: a governance file is not client data, and
+	// Confidential would make DegradingSink REFUSE to record while loki is
+	// down rather than buffer — losing exactly the record that matters most.
+	outcome, err := s.govAudit.Reserve(ctx, classification.Internal)
+	if err != nil {
+		slog.Error("brain_edit_root audit reserve failed", "path", res.Path, "err", err)
+		return
+	}
+	entry := capture.AuditEntry{
+		Timestamp:               time.Now().UTC(),
+		Principal:               principal,
+		Actor:                   "brain_edit_root",
+		Harness:                 "mcp",
+		EffectiveClassification: classification.Internal.String(),
+		Items:                   []string{res.Path},
+		SecurityEvents: []string{fmt.Sprintf(
+			"governance file rewritten: %s before=%s after=%s",
+			res.Path, res.PrevContentHash, res.ContentHash)},
+	}
+	if err := s.govAudit.Record(ctx, entry, outcome); err != nil {
+		slog.Error("brain_edit_root audit record failed", "path", res.Path, "err", err)
+	}
+}
+
+func (s *Server) editWithScope(args json.RawMessage, scope notes.Scope) (notes.Result, json.RawMessage, error) {
+	var a brainEditArgs
+	if err := json.Unmarshal(args, &a); err != nil {
+		return notes.Result{}, nil, fmt.Errorf("parse args: %w", err)
+	}
+	res, err := notes.Edit(s.brainDir, a.Path, a.OldStr, a.NewStr, scope)
+	if err != nil {
+		return notes.Result{}, nil, err
+	}
+
+	// Reindex only when the edit could have changed what the index reads.
+	// BuildWingIndex consumes title/created_at from the frontmatter block;
+	// BM25 walks the filesystem live and embeddings are mtime-driven, so an
+	// unconditional rebuild would buy nothing and dirty a second file —
+	// _index.md being precisely the class brain-sync already needs a bespoke
+	// conflict resolver for.
+	if wing := wingOf(res.Path); wing != "" && touchesFrontmatter(a.OldStr, a.NewStr) {
+		if ierr := brain.BuildWingIndex(s.brainDir, wing); ierr != nil {
+			// Best-effort, matching every other index hook here: the write
+			// already landed and will be committed, so failing the call would
+			// make the caller retry an edit whose old_str no longer exists.
+			res.ReindexError = ierr.Error()
+		}
+	}
+	out, merr := json.Marshal(res)
+	return res, out, merr
+}
+
+// wingOf returns the wing for a wiki path, or "" for knowledge/ and root.
+func wingOf(rel string) string {
+	parts := strings.Split(rel, "/")
+	if len(parts) < 3 || parts[0] != "wiki" {
+		return ""
+	}
+	return parts[1]
+}
+
+// touchesFrontmatter reports whether either side of the edit mentions a field
+// the wing index reads.
+func touchesFrontmatter(oldStr, newStr string) bool {
+	for _, s := range []string{oldStr, newStr} {
+		if strings.Contains(s, "title:") || strings.Contains(s, "created_at:") || strings.Contains(s, "---") {
+			return true
+		}
+	}
+	return false
+}
@@ -0,0 +1,297 @@
+// ingestion/internal/mcp/tools_notes_test.go
+package mcp_test
+
+import (
+	"context"
+	"crypto/sha256"
+	"encoding/hex"
+	"encoding/json"
+	"net/http"
+	"net/http/httptest"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+
+	"github.com/mathiasbq/hyperguild/ingestion/internal/audit"
+	"github.com/mathiasbq/hyperguild/ingestion/internal/brainstore"
+	"github.com/mathiasbq/hyperguild/ingestion/internal/capture"
+	"github.com/mathiasbq/hyperguild/ingestion/internal/capturehttp"
+	"github.com/mathiasbq/hyperguild/ingestion/internal/classification"
+	"github.com/mathiasbq/hyperguild/ingestion/internal/mcp"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// ---- brain#4: brain_read / brain_edit through the JSON-RPC surface --------
+
+func newBrainRepo(t *testing.T) string {
+	t.Helper()
+	dir := t.TempDir()
+	require.NoError(t, os.MkdirAll(filepath.Join(dir, ".git"), 0o755))
+	require.NoError(t, os.MkdirAll(filepath.Join(dir, "wiki/homelab/facts"), 0o755))
+	require.NoError(t, os.WriteFile(filepath.Join(dir, "wiki/homelab/facts/n.md"),
+		[]byte("---\ntitle: 'n'\n---\n\nalpha\nbeta\n"), 0o644))
+	require.NoError(t, os.WriteFile(filepath.Join(dir, "CLAUDE.md"), []byte("# rules\n"), 0o644))
+	return dir
+}
+
+func call(t *testing.T, srv *mcp.Server, name string, args map[string]any) map[string]any {
+	t.Helper()
+	req := httptest.NewRequest(http.MethodPost, "/mcp", body(t, map[string]any{
+		"jsonrpc": "2.0", "id": 1, "method": "tools/call",
+		"params": map[string]any{"name": name, "arguments": args},
+	}))
+	rr := httptest.NewRecorder()
+	srv.ServeHTTP(rr, req)
+	var resp map[string]any
+	require.NoError(t, json.Unmarshal(rr.Body.Bytes(), &resp))
+	return resp
+}
+
+func TestBrainReadAndEdit_RoundTripThroughJSONRPC(t *testing.T) {
+	// The Go functions are tested in internal/notes; this pins the transport,
+	// because a tool that works in-process and is unreachable over JSON-RPC
+	// is indistinguishable from a working one in a unit test.
+	dir := newBrainRepo(t)
+	srv := mcp.NewServer(dir, nil, nil, nil)
+
+	resp := call(t, srv, "brain_read", map[string]any{"path": "wiki/homelab/facts/n.md"})
+	require.NotContains(t, resp, "error", "%v", resp["error"])
+
+	resp = call(t, srv, "brain_edit", map[string]any{
+		"path": "wiki/homelab/facts/n.md", "old_str": "beta", "new_str": "BETA",
+	})
+	require.NotContains(t, resp, "error", "%v", resp["error"])
+
+	got, err := os.ReadFile(filepath.Join(dir, "wiki/homelab/facts/n.md"))
+	require.NoError(t, err)
+	assert.Equal(t, "---\ntitle: 'n'\n---\n\nalpha\nBETA\n", string(got),
+		"only the matched bytes may change")
+}
+
+func TestBrainEdit_RefusesGovernanceFilesFromTheModelFacingTool(t *testing.T) {
+	dir := newBrainRepo(t)
+	srv := mcp.NewServer(dir, nil, nil, nil)
+
+	resp := call(t, srv, "brain_edit", map[string]any{
+		"path": "CLAUDE.md", "old_str": "# rules", "new_str": "# rewritten",
+	})
+	require.Contains(t, resp, "error", "brain_edit must not reach CLAUDE.md")
+
+	got, err := os.ReadFile(filepath.Join(dir, "CLAUDE.md"))
+	require.NoError(t, err)
+	assert.Equal(t, "# rules\n", string(got))
+}
+
+func TestBrainEditRoot_RefusedWithoutTheLocalStaticPrincipal(t *testing.T) {
+	// No principal in context is the model-facing case (and the default in
+	// this test server): the privileged door must stay shut.
+	dir := newBrainRepo(t)
+	srv := mcp.NewServer(dir, nil, nil, nil)
+
+	resp := call(t, srv, "brain_edit_root", map[string]any{
+		"path": "CLAUDE.md", "old_str": "# rules", "new_str": "# rewritten",
+	})
+	require.Contains(t, resp, "error")
+
+	got, err := os.ReadFile(filepath.Join(dir, "CLAUDE.md"))
+	require.NoError(t, err)
+	assert.Equal(t, "# rules\n", string(got), "governance file must be untouched")
+}
+
+func TestBrainGet_CannotReachSessionTranscripts(t *testing.T) {
+	// Pre-existing hole, not introduced here: api.ReadNote resolves any
+	// brain-relative path and parseFrontmatter returns the WHOLE file as body
+	// when there is no frontmatter fence. archive/ holds verbatim Claude
+	// session transcripts (up to 500 KB) that BM25 never indexes, so they are
+	// invisible to search and trivially readable by path — and CLAUDE.md
+	// documents the layout.
+	dir := newBrainRepo(t)
+	require.NoError(t, os.MkdirAll(filepath.Join(dir, "archive/claude-sessions/koala"), 0o755))
+	require.NoError(t, os.WriteFile(
+		filepath.Join(dir, "archive/claude-sessions/koala/session-1.md"),
+		[]byte("verbatim transcript with tool output\n"), 0o644))
+
+	srv := mcp.NewServer(dir, nil, nil, nil)
+	resp := call(t, srv, "brain_get", map[string]any{"path": "archive/claude-sessions/koala/session-1.md"})
+
+	require.Contains(t, resp, "error", "brain_get must not read outside knowledge/ and wiki/")
+	assert.NotContains(t, string(mustJSON(t, resp)), "verbatim transcript")
+}
+
+func TestBrainGet_StillReadsNotes(t *testing.T) {
+	dir := newBrainRepo(t)
+	srv := mcp.NewServer(dir, nil, nil, nil)
+
+	resp := call(t, srv, "brain_get", map[string]any{"path": "wiki/homelab/facts/n.md"})
+	assert.NotContains(t, resp, "error", "%v", resp["error"])
+}
+
+func mustJSON(t *testing.T, v any) []byte {
+	t.Helper()
+	b, err := json.Marshal(v)
+	require.NoError(t, err)
+	return b
+}
+
+// ---- hyperguild#97: a governance rewrite must be observed, not just gated ----
+
+// govSink captures audit records. Governance edits are rare, so the whole
+// history is kept and asserted on rather than sampled.
+type govSink struct {
+	entries  []capture.AuditEntry
+	outcomes []capture.AuditOutcome
+	recErr   error
+}
+
+func (s *govSink) Reserve(context.Context, classification.Level) (capture.AuditOutcome, error) {
+	return capture.AuditCentral, nil
+}
+
+func (s *govSink) Record(_ context.Context, e capture.AuditEntry, o capture.AuditOutcome) error {
+	s.entries = append(s.entries, e)
+	s.outcomes = append(s.outcomes, o)
+	return s.recErr
+}
+
+type govNotifier struct {
+	msgs []string
+	err  error
+}
+
+func (n *govNotifier) Notify(_ context.Context, msg string) error {
+	n.msgs = append(n.msgs, msg)
+	return n.err
+}
+
+// govServer wires capture (which is what re-derives the static principal) plus
+// the #97 observer, and returns the brain dir so the test can read the file.
+func govServer(t *testing.T) (*mcp.Server, string, *govSink, *govNotifier) {
+	t.Helper()
+	dir := newBrainRepo(t)
+	cfg, err := classification.Load(dir)
+	require.NoError(t, err)
+	svc := capture.NewService(brainstore.New(dir), capFakeTracker{}, cfg, audit.NewSlogSink(nil))
+
+	srv := mcp.NewServer(dir, nil, nil, nil)
+	srv.WithCapture(svc, nil, capStaticTok, "local-cli", capturehttp.NewOriginResolver(nil))
+	sink, notifier := &govSink{}, &govNotifier{}
+	srv.WithGovernanceObserver(sink, notifier)
+	return srv, dir, sink, notifier
+}
+
+// authCall is call() with an Authorization header, so the static principal is
+// present and brain_edit_root's gate opens.
+func authCall(t *testing.T, srv *mcp.Server, authz, name string, args map[string]any) map[string]any {
+	t.Helper()
+	req := httptest.NewRequest(http.MethodPost, "/mcp", body(t, map[string]any{
+		"jsonrpc": "2.0", "id": 1, "method": "tools/call",
+		"params": map[string]any{"name": name, "arguments": args},
+	}))
+	if authz != "" {
+		req.Header.Set("Authorization", authz)
+	}
+	rr := httptest.NewRecorder()
+	srv.ServeHTTP(rr, req)
+	var resp map[string]any
+	require.NoError(t, json.Unmarshal(rr.Body.Bytes(), &resp))
+	return resp
+}
+
+func sha256hex(s string) string {
+	sum := sha256.Sum256([]byte(s))
+	return hex.EncodeToString(sum[:])
+}
+
+func TestBrainEditRoot_RecordsAnAuditEntryNamingPrincipalPathAndBothHashes(t *testing.T) {
+	// The gate proves a rewrite was ALLOWED. Only a record proves one HAPPENED
+	// — and brain-sync will commit it within 15 minutes authored `brain-sync`,
+	// so git history cannot tell it apart from routine note traffic.
+	srv, dir, sink, _ := govServer(t)
+
+	resp := authCall(t, srv, "Bearer "+capStaticTok, "brain_edit_root", map[string]any{
+		"path": "CLAUDE.md", "old_str": "# rules", "new_str": "# rewritten",
+	})
+	require.NotContains(t, resp, "error", "%v", resp["error"])
+
+	require.Len(t, sink.entries, 1, "exactly one audit record per governance rewrite")
+	e := sink.entries[0]
+	assert.Equal(t, "local-cli", e.Principal)
+	assert.Contains(t, e.Items, "CLAUDE.md", "the record must name what was rewritten")
+
+	joined := strings.Join(e.SecurityEvents, " ")
+	assert.Contains(t, joined, sha256hex("# rules\n"), "before-hash must be recorded")
+	assert.Contains(t, joined, sha256hex("# rewritten\n"), "after-hash must be recorded")
+	assert.NotZero(t, e.Timestamp)
+
+	got, err := os.ReadFile(filepath.Join(dir, "CLAUDE.md"))
+	require.NoError(t, err)
+	assert.Equal(t, "# rewritten\n", string(got))
+}
+
+func TestBrainEditRoot_NotifiesWithPathAndHashesButNeverContent(t *testing.T) {
+	srv, _, _, notifier := govServer(t)
+
+	resp := authCall(t, srv, "Bearer "+capStaticTok, "brain_edit_root", map[string]any{
+		"path": "CLAUDE.md", "old_str": "# rules", "new_str": "# rewritten",
+	})
+	require.NotContains(t, resp, "error", "%v", resp["error"])
+
+	require.Len(t, notifier.msgs, 1)
+	msg := notifier.msgs[0]
+	assert.Contains(t, msg, "CLAUDE.md")
+	assert.Contains(t, msg, "local-cli")
+	assert.Contains(t, msg, sha256hex("# rules\n"))
+	assert.Contains(t, msg, sha256hex("# rewritten\n"))
+
+	// The notification travels to a phone through a third-party topic. A hash
+	// identifies a rewrite; the bytes would leak whatever was written.
+	assert.NotContains(t, msg, "# rewritten", "no file content in the notification body")
+	assert.NotContains(t, msg, "# rules")
+}
+
+func TestBrainEditRoot_RefusedProducesNoRecordNoNotificationNoWrite(t *testing.T) {
+	srv, dir, sink, notifier := govServer(t)
+
+	// No Authorization header → no static principal → the gate stays shut.
+	resp := authCall(t, srv, "", "brain_edit_root", map[string]any{
+		"path": "CLAUDE.md", "old_str": "# rules", "new_str": "# rewritten",
+	})
+	require.Contains(t, resp, "error")
+
+	assert.Empty(t, sink.entries, "a refusal is not a rewrite — recording one would cry wolf")
+	assert.Empty(t, notifier.msgs)
+	got, err := os.ReadFile(filepath.Join(dir, "CLAUDE.md"))
+	require.NoError(t, err)
+	assert.Equal(t, "# rules\n", string(got))
+}
+
+func TestBrainEditRoot_FailedEditProducesNoRecordNoNotification(t *testing.T) {
+	// Authorised but no match: the door opened and nothing went through it.
+	srv, _, sink, notifier := govServer(t)
+
+	resp := authCall(t, srv, "Bearer "+capStaticTok, "brain_edit_root", map[string]any{
+		"path": "CLAUDE.md", "old_str": "absent-from-the-file", "new_str": "x",
+	})
+	require.Contains(t, resp, "error")
+
+	assert.Empty(t, sink.entries)
+	assert.Empty(t, notifier.msgs)
+}
+
+func TestBrainEdit_OnOrdinaryNotesIsNotAudited(t *testing.T) {
+	// The decided asymmetry (#97): note edits are covered by git history, which
+	// carries the same before/after bytes with a diff. Governance files get the
+	// extra trail because they change what later agents obey, not because they
+	// are harder to reconstruct.
+	srv, _, sink, notifier := govServer(t)
+
+	resp := authCall(t, srv, "Bearer "+capStaticTok, "brain_edit", map[string]any{
+		"path": "wiki/homelab/facts/n.md", "old_str": "beta", "new_str": "BETA",
+	})
+	require.NotContains(t, resp, "error", "%v", resp["error"])
+
+	assert.Empty(t, sink.entries, "note edits must not fill the governance audit trail")
+	assert.Empty(t, notifier.msgs)
+}
@@ -0,0 +1,282 @@
+package notes
+
+import (
+	"crypto/sha256"
+	"encoding/hex"
+	"errors"
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+	"sync"
+	"syscall"
+	"unicode/utf8"
+)
+
+// maxNoteBytes caps what Read will hand back. Generous for knowledge/ and
+// wiki/ (the largest note today is far under it) and small enough that a
+// pathological file cannot flood a caller's context.
+const maxNoteBytes = 256 << 10
+
+// Errors callers distinguish.
+var (
+	ErrNoMatch    = errors.New("notes: old_str not found")
+	ErrAmbiguous  = errors.New("notes: old_str matches more than once")
+	ErrNotUTF8    = errors.New("notes: content is not valid UTF-8")
+	ErrGitBusy    = errors.New("notes: a git operation is in progress")
+	ErrTooLarge   = errors.New("notes: file exceeds the readable size limit")
+	ErrDegenerate = errors.New("notes: edit is degenerate")
+	ErrInConflict = errors.New("notes: file contains unresolved conflict markers")
+)
+
+// pathLocks serialises edits per file within this process. The flock below
+// covers the cross-process case (two pods share the hostPath during a rolling
+// update, and brain-fix/brain-enrich write the same tree).
+var pathLocks sync.Map // string -> *sync.Mutex
+
+// Result is what a successful edit reports.
+type Result struct {
+	Path string `json:"path"`
+	// PrevContentHash is the sha256 of the file as it was before this edit.
+	// Paired with ContentHash it identifies a rewrite in an audit trail or an
+	// alert without carrying any of the bytes (hyperguild#97).
+	PrevContentHash string `json:"prev_content_hash"`
+	ContentHash     string `json:"content_hash"`
+	BytesBefore     int    `json:"bytes_before"`
+	BytesAfter      int    `json:"bytes_after"`
+	ReindexError    string `json:"reindex_error,omitempty"`
+}
+
+// Read returns a note's bytes verbatim.
+//
+// No frontmatter parsing, no excerpting, no normalisation: the entire purpose
+// is to give a caller an exact basis for an edit. An excerpt from brain_query
+// would be truncated and normalised, and every old_str built from one would
+// miss.
+func Read(brainDir, path string) ([]byte, error) {
+	t, err := Resolve(brainDir, path, ScopeNotes)
+	if err != nil {
+		return nil, err
+	}
+	return readContained(t)
+}
+
+// ReadScoped is Read for a caller already holding the privileged scope.
+func ReadScoped(brainDir, path string, scope Scope) ([]byte, error) {
+	t, err := Resolve(brainDir, path, scope)
+	if err != nil {
+		return nil, err
+	}
+	return readContained(t)
+}
+
+func readContained(t Target) ([]byte, error) {
+	fi, err := os.Stat(t.Abs)
+	if err != nil {
+		return nil, fmt.Errorf("notes: stat %s: %w", t.Rel, err)
+	}
+	if fi.Size() > maxNoteBytes {
+		return nil, fmt.Errorf("%w: %s is %d bytes (limit %d)", ErrTooLarge, t.Rel, fi.Size(), maxNoteBytes)
+	}
+	b, err := os.ReadFile(t.Abs)
+	if err != nil {
+		return nil, fmt.Errorf("notes: read %s: %w", t.Rel, err)
+	}
+	// The MCP response marshals this into a JSON string, and encoding/json
+	// substitutes U+FFFD for invalid UTF-8 — silently returning different
+	// bytes than the file holds, which defeats "verbatim" entirely.
+	if !utf8.Valid(b) {
+		return nil, fmt.Errorf("%w: %s", ErrNotUTF8, t.Rel)
+	}
+	return b, nil
+}
+
+// Edit replaces exactly one occurrence of oldStr with newStr, in place.
+//
+// Fails loudly and writes nothing on: zero matches, more than one match
+// (counted with overlap), degenerate arguments, invalid UTF-8, a git operation
+// in flight, or unresolved conflict markers in the target.
+func Edit(brainDir, path, oldStr, newStr string, scope Scope) (Result, error) {
+	t, err := Resolve(brainDir, path, scope)
+	if err != nil {
+		return Result{}, err
+	}
+	if oldStr == "" {
+		return Result{}, fmt.Errorf("%w: old_str is empty", ErrDegenerate)
+	}
+	if oldStr == newStr {
+		return Result{}, fmt.Errorf("%w: old_str equals new_str", ErrDegenerate)
+	}
+	if !utf8.ValidString(newStr) {
+		return Result{}, fmt.Errorf("%w: new_str", ErrNotUTF8)
+	}
+	// brain#2 guard: refuse to write to a tree the sync does not commit from.
+	if err := assertSyncSource(brainDir); err != nil {
+		return Result{}, err
+	}
+	if err := assertGitIdle(brainDir); err != nil {
+		return Result{}, err
+	}
+
+	mu := lockFor(t.Abs)
+	mu.Lock()
+	defer mu.Unlock()
+
+	unlock, err := flockFile(t.Abs)
+	if err != nil {
+		return Result{}, err
+	}
+	defer unlock()
+
+	// Read INSIDE the lock: the match count must be evaluated against the
+	// bytes we are about to overwrite, or a concurrent edit is silently lost
+	// while both callers are told they succeeded.
+	before, err := readContained(t)
+	if err != nil {
+		return Result{}, err
+	}
+	if hasConflictMarkers(before) {
+		return Result{}, fmt.Errorf("%w: %s", ErrInConflict, t.Rel)
+	}
+
+	switch n := countOverlapping(string(before), oldStr); {
+	case n == 0:
+		return Result{}, fmt.Errorf("%w in %s (0 matches)%s", ErrNoMatch, t.Rel, crlfHint(string(before), oldStr))
+	case n > 1:
+		return Result{}, fmt.Errorf("%w in %s (%d matches) — extend old_str until it is unique",
+			ErrAmbiguous, t.Rel, n)
+	}
+
+	after := strings.Replace(string(before), oldStr, newStr, 1)
+	if err := writeAtomic(t.Abs, []byte(after)); err != nil {
+		return Result{}, err
+	}
+
+	sum := sha256.Sum256([]byte(after))
+	prev := sha256.Sum256(before)
+	return Result{
+		Path:            t.Rel,
+		PrevContentHash: hex.EncodeToString(prev[:]),
+		ContentHash:     hex.EncodeToString(sum[:]),
+		BytesBefore:     len(before),
+		BytesAfter:      len(after),
+	}, nil
+}
+
+// countOverlapping counts occurrences allowing overlap. bytes.Count does not:
+// "aa" occurs once in "aaa" by its reckoning, so a Count-based uniqueness
+// check accepts an ambiguous edit as unique.
+func countOverlapping(s, sub string) int {
+	var n, from int
+	for {
+		i := strings.Index(s[from:], sub)
+		if i < 0 {
+			return n
+		}
+		n++
+		from += i + 1
+	}
+}
+
+// crlfHint reports whether the caller's old_str would have matched if line
+// endings agreed. It never normalises — that would break byte-identity — but
+// an opaque "no match" is unfixable from the caller's side, and a stripped \r
+// is the likeliest cause.
+func crlfHint(content, oldStr string) string {
+	if strings.Contains(content, "\r\n") && !strings.Contains(oldStr, "\r\n") {
+		if strings.Contains(strings.ReplaceAll(content, "\r\n", "\n"), oldStr) {
+			return " — the file uses CRLF line endings and old_str does not; include the \\r"
+		}
+	}
+	return ""
+}
+
+func hasConflictMarkers(b []byte) bool {
+	s := string(b)
+	return strings.Contains(s, "\n<<<<<<< ") || strings.HasPrefix(s, "<<<<<<< ")
+}
+
+// assertGitIdle refuses while brain-sync (or brain-fix, or a human) has a git
+// operation in flight. An edit landing between `git merge` and its abort is
+// either hard-reset away or committed as a wrongly resolved conflict — and the
+// caller was told it succeeded.
+func assertGitIdle(brainDir string) error {
+	for _, marker := range []string{"MERGE_HEAD", "REBASE_HEAD", "CHERRY_PICK_HEAD", "index.lock"} {
+		if _, err := os.Stat(filepath.Join(brainDir, ".git", marker)); err == nil {
+			return fmt.Errorf("%w (.git/%s present) — retry after the sync settles", ErrGitBusy, marker)
+		}
+	}
+	return nil
+}
+
+func lockFor(abs string) *sync.Mutex {
+	v, _ := pathLocks.LoadOrStore(abs, &sync.Mutex{})
+	return v.(*sync.Mutex)
+}
+
+// flockFile takes an advisory lock covering other processes sharing the
+// hostPath — during a RollingUpdate two ingestion pods do.
+func flockFile(abs string) (func(), error) {
+	f, err := os.OpenFile(abs+".lock", os.O_CREATE|os.O_RDWR, 0o644)
+	if err != nil {
+		return nil, fmt.Errorf("notes: lock %s: %w", filepath.Base(abs), err)
+	}
+	if err := syscall.Flock(int(f.Fd()), syscall.LOCK_EX); err != nil {
+		_ = f.Close()
+		return nil, fmt.Errorf("notes: flock %s: %w", filepath.Base(abs), err)
+	}
+	return func() {
+		_ = syscall.Flock(int(f.Fd()), syscall.LOCK_UN)
+		_ = f.Close()
+		_ = os.Remove(abs + ".lock")
+	}, nil
+}
+
+// writeAtomic replaces the file via a same-directory temp + rename, then
+// fsyncs the directory so the rename survives a node crash.
+//
+// Same directory because a rename across the hostPath boundary fails with
+// EXDEV; the ".tmp" suffix because the tree's .gitignore already covers it, so
+// a leaked temp is not committed by `git add -A`.
+func writeAtomic(abs string, content []byte) error {
+	dir := filepath.Dir(abs)
+	tmp, err := os.CreateTemp(dir, filepath.Base(abs)+".*.tmp")
+	if err != nil {
+		return fmt.Errorf("notes: temp file: %w", err)
+	}
+	tmpName := tmp.Name()
+	defer func() { _ = os.Remove(tmpName) }() // no-op once renamed
+
+	if _, err := tmp.Write(content); err != nil {
+		_ = tmp.Close()
+		return fmt.Errorf("notes: write temp: %w", err)
+	}
+	if err := tmp.Sync(); err != nil {
+		_ = tmp.Close()
+		return fmt.Errorf("notes: sync temp: %w", err)
+	}
+	if err := tmp.Close(); err != nil {
+		return fmt.Errorf("notes: close temp: %w", err)
+	}
+	// CreateTemp makes 0600; every other writer of this tree uses 0644 and
+	// other uids read it.
+	if err := os.Chmod(tmpName, 0o644); err != nil {
+		return fmt.Errorf("notes: chmod temp: %w", err)
+	}
+	if err := os.Rename(tmpName, abs); err != nil {
+		return fmt.Errorf("notes: rename: %w", err)
+	}
+	return fsyncDir(dir)
+}
+
+func fsyncDir(dir string) error {
+	d, err := os.Open(dir)
+	if err != nil {
+		return fmt.Errorf("notes: open dir: %w", err)
+	}
+	defer func() { _ = d.Close() }()
+	if err := d.Sync(); err != nil {
+		return fmt.Errorf("notes: fsync dir: %w", err)
+	}
+	return nil
+}
@@ -0,0 +1,256 @@
+package notes
+
+import (
+	"os"
+	"path/filepath"
+	"strings"
+	"sync"
+	"testing"
+)
+
+func seed(t *testing.T, dir, rel, content string) string {
+	t.Helper()
+	abs := filepath.Join(dir, rel)
+	if err := os.MkdirAll(filepath.Dir(abs), 0o755); err != nil {
+		t.Fatal(err)
+	}
+	if err := os.WriteFile(abs, []byte(content), 0o644); err != nil {
+		t.Fatal(err)
+	}
+	return abs
+}
+
+func read(t *testing.T, abs string) string {
+	t.Helper()
+	b, err := os.ReadFile(abs)
+	if err != nil {
+		t.Fatal(err)
+	}
+	return string(b)
+}
+
+func TestRead_ReturnsVerbatimBytes(t *testing.T) {
+	dir := newBrain(t)
+	const body = "---\ntitle: 'x'\n---\n\nbody with  double  spaces\r\nand a CRLF line\nno trailing newline"
+	seed(t, dir, "knowledge/verbatim.md", body)
+
+	got, err := Read(dir, "knowledge/verbatim.md")
+	if err != nil {
+		t.Fatalf("Read: %v", err)
+	}
+	if string(got) != body {
+		t.Errorf("Read returned %q, want the file byte-for-byte", got)
+	}
+}
+
+func TestRead_RefusesNonUTF8RatherThanCorruptingIt(t *testing.T) {
+	// The response is marshalled into a JSON string, and encoding/json
+	// replaces invalid UTF-8 with U+FFFD. Returning it would mean every
+	// old_str the caller derives from that region can never match, and
+	// pasting it back would write the corruption to disk permanently.
+	dir := newBrain(t)
+	seed(t, dir, "knowledge/bad.md", "ok \xff\xfe broken\n")
+
+	if _, err := Read(dir, "knowledge/bad.md"); err == nil {
+		t.Fatal("Read accepted invalid UTF-8; it must refuse rather than silently substitute")
+	}
+}
+
+func TestEdit_ReplacesExactlyOnceAndLeavesEveryOtherByteAlone(t *testing.T) {
+	dir := newBrain(t)
+	const body = "---\ntitle: 'x'\n---\n\nalpha\nbeta\ngamma\n"
+	abs := seed(t, dir, "knowledge/n.md", body)
+
+	res, err := Edit(dir, "knowledge/n.md", "beta", "BETA", ScopeNotes)
+	if err != nil {
+		t.Fatalf("Edit: %v", err)
+	}
+	want := strings.Replace(body, "beta", "BETA", 1)
+	if got := read(t, abs); got != want {
+		t.Errorf("file = %q, want %q", got, want)
+	}
+	if res.ContentHash == "" {
+		t.Error("result should carry a content hash for read-after-write confirmation")
+	}
+}
+
+func TestEdit_RefusesAmbiguousAndAbsentMatchesWithoutWriting(t *testing.T) {
+	dir := newBrain(t)
+	const body = "alpha\nalpha\n"
+	abs := seed(t, dir, "knowledge/n.md", body)
+
+	cases := []struct{ name, old, want string }{
+		{"two matches", "alpha", "2"},
+		{"no match", "delta", "0"},
+	}
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			_, err := Edit(dir, "knowledge/n.md", tc.old, "x", ScopeNotes)
+			if err == nil {
+				t.Fatal("want a loud refusal")
+			}
+			if !strings.Contains(err.Error(), tc.want) {
+				t.Errorf("error must state the match count, got %v", err)
+			}
+			if got := read(t, abs); got != body {
+				t.Errorf("file changed on a refused edit: %q", got)
+			}
+		})
+	}
+}
+
+func TestEdit_CountsOverlappingMatches(t *testing.T) {
+	// bytes.Count counts NON-overlapping occurrences: "aa" in "aaa" is 1, so
+	// a Count-based uniqueness check calls an ambiguous edit unique.
+	dir := newBrain(t)
+	seed(t, dir, "knowledge/n.md", "aaa\n")
+
+	if _, err := Edit(dir, "knowledge/n.md", "aa", "b", ScopeNotes); err == nil {
+		t.Fatal("overlapping matches must be reported as ambiguous")
+	}
+}
+
+func TestEdit_RejectsDegenerateArguments(t *testing.T) {
+	dir := newBrain(t)
+	seed(t, dir, "knowledge/n.md", "alpha\n")
+
+	if _, err := Edit(dir, "knowledge/n.md", "", "x", ScopeNotes); err == nil {
+		t.Error("empty old_str must be rejected")
+	}
+	if _, err := Edit(dir, "knowledge/n.md", "alpha", "alpha", ScopeNotes); err == nil {
+		t.Error("a no-op edit must be rejected rather than burning a sync cycle")
+	}
+}
+
+func TestEdit_DeletionIsLegal(t *testing.T) {
+	dir := newBrain(t)
+	abs := seed(t, dir, "knowledge/n.md", "keep\ndrop\n")
+
+	if _, err := Edit(dir, "knowledge/n.md", "drop\n", "", ScopeNotes); err != nil {
+		t.Fatalf("Edit: %v", err)
+	}
+	if got := read(t, abs); got != "keep\n" {
+		t.Errorf("file = %q, want %q", got, "keep\n")
+	}
+}
+
+func TestEdit_ReportsWhenOnlyLineEndingsDiffer(t *testing.T) {
+	// The likeliest real failure: the caller's old_str lost its \r. Never
+	// normalise silently — that breaks byte-identity — but say so, because an
+	// opaque "no match" is unfixable from the caller's side.
+	dir := newBrain(t)
+	seed(t, dir, "knowledge/n.md", "alpha\r\nbeta\r\n")
+
+	_, err := Edit(dir, "knowledge/n.md", "alpha\nbeta", "x", ScopeNotes)
+	if err == nil {
+		t.Fatal("want a refusal")
+	}
+	if !strings.Contains(err.Error(), "line ending") {
+		t.Errorf("error should point at CRLF, got %v", err)
+	}
+}
+
+func TestEdit_RefusesWhileGitIsMidOperation(t *testing.T) {
+	// brain-sync runs `git merge -X ours origin/main`, and aborts on conflict
+	// with a hard reset. An edit landing inside that window is either erased
+	// or committed as a wrongly-resolved conflict, and the caller was told it
+	// succeeded.
+	dir := newBrain(t)
+	seed(t, dir, "knowledge/n.md", "alpha\n")
+
+	for _, marker := range []string{"MERGE_HEAD", "index.lock", "REBASE_HEAD"} {
+		t.Run(marker, func(t *testing.T) {
+			p := filepath.Join(dir, ".git", marker)
+			if err := os.WriteFile(p, []byte("x"), 0o644); err != nil {
+				t.Fatal(err)
+			}
+			defer func() { _ = os.Remove(p) }()
+
+			if _, err := Edit(dir, "knowledge/n.md", "alpha", "beta", ScopeNotes); err == nil {
+				t.Errorf("edit accepted while %s exists", marker)
+			}
+		})
+	}
+}
+
+func TestEdit_RefusesAFileHoldingConflictMarkers(t *testing.T) {
+	dir := newBrain(t)
+	seed(t, dir, "knowledge/n.md", "<<<<<<< HEAD\nours\n=======\ntheirs\n>>>>>>> origin/main\n")
+
+	if _, err := Edit(dir, "knowledge/n.md", "ours", "x", ScopeNotes); err == nil {
+		t.Fatal("editing one side of an unresolved conflict must be refused")
+	}
+}
+
+func TestEdit_ConcurrentEditsBothApply(t *testing.T) {
+	// Read-modify-write with no lock loses one update AND reports success for
+	// both. old_str uniqueness does not protect against it: uniqueness is
+	// evaluated against the stale read.
+	dir := newBrain(t)
+	abs := seed(t, dir, "knowledge/n.md", "alpha\nbeta\n")
+
+	var wg sync.WaitGroup
+	errs := make([]error, 2)
+	for i, pair := range [][2]string{{"alpha", "ALPHA"}, {"beta", "BETA"}} {
+		wg.Add(1)
+		go func(i int, old, new string) {
+			defer wg.Done()
+			_, errs[i] = Edit(dir, "knowledge/n.md", old, new, ScopeNotes)
+		}(i, pair[0], pair[1])
+	}
+	wg.Wait()
+
+	for i, err := range errs {
+		if err != nil {
+			t.Fatalf("edit %d failed: %v", i, err)
+		}
+	}
+	if got := read(t, abs); got != "ALPHA\nBETA\n" {
+		t.Errorf("file = %q, want both edits applied", got)
+	}
+}
+
+func TestEdit_LeavesNoTemporaryFileBehind(t *testing.T) {
+	dir := newBrain(t)
+	seed(t, dir, "knowledge/n.md", "alpha\n")
+
+	if _, err := Edit(dir, "knowledge/n.md", "alpha", "beta", ScopeNotes); err != nil {
+		t.Fatal(err)
+	}
+	entries, err := os.ReadDir(filepath.Join(dir, "knowledge"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	for _, e := range entries {
+		if e.Name() != "note.md" && e.Name() != "n.md" {
+			t.Errorf("stray file left in the tree: %q (git add -A would commit it)", e.Name())
+		}
+	}
+}
+
+func TestEdit_PreservesReadableMode(t *testing.T) {
+	// Other uids write this tree (brain-fix, brain-enrich). os.CreateTemp
+	// yields 0600 and rename preserves it, which would break them silently.
+	dir := newBrain(t)
+	abs := seed(t, dir, "knowledge/n.md", "alpha\n")
+
+	if _, err := Edit(dir, "knowledge/n.md", "alpha", "beta", ScopeNotes); err != nil {
+		t.Fatal(err)
+	}
+	fi, err := os.Stat(abs)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if fi.Mode().Perm() != 0o644 {
+		t.Errorf("mode = %v, want 0644", fi.Mode().Perm())
+	}
+}
+
+func TestEdit_RefusesNonUTF8Replacement(t *testing.T) {
+	dir := newBrain(t)
+	seed(t, dir, "knowledge/n.md", "alpha\n")
+
+	if _, err := Edit(dir, "knowledge/n.md", "alpha", "bad \xff", ScopeNotes); err == nil {
+		t.Fatal("new_str with invalid UTF-8 must be refused, not written")
+	}
+}
@@ -0,0 +1,201 @@
+// Package notes provides containment-checked read and surgical edit of brain
+// notes on the live tree that brain-sync commits from.
+//
+// Everything here is defensive for one reason: brain content is ingested from
+// the outside world, that content reaches a model's context via brain_query /
+// brain_context, and these primitives are callable by that model. A path bug
+// is therefore not a path bug — it is an outside author choosing a file.
+package notes
+
+import (
+	"errors"
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+)
+
+// Scope is which part of the tree a caller is allowed to touch.
+type Scope int
+
+const (
+	// ScopeNotes is the model-facing scope: markdown under knowledge/ and
+	// wiki/ only.
+	ScopeNotes Scope = iota
+	// ScopeRoot admits the named governance files and NOTHING else. It exists so
+	// there is an MCP path to CLAUDE.md at all — the absence of one is what
+	// pushed a session to edit via the gitea REST API on 2026-06-16, which
+	// never reached the live tree and wedged brain-sync for hours. It is NOT
+	// reachable from the model-facing toolset; see tools_notes.go.
+	ScopeRoot
+)
+
+// rootFiles is an exact-name allowlist, deliberately not a "root *.md" glob.
+//
+// Two reasons. log.md is gitignored, so an edit to it applies to the live tree
+// and never reaches gitea — the exact shape of brain#2, admitted by a glob. And
+// a glob auto-admits whatever governance file appears next (AGENTS.md, a
+// bootstrap doc) with nobody reviewing that decision.
+var rootFiles = map[string]bool{"CLAUDE.md": true}
+
+// noteDirs are the two trees that hold notes.
+var noteDirs = []string{"knowledge/", "wiki/"}
+
+// deniedPrefixes are refused in every scope, independent of the allowlist.
+//
+// A static backstop rather than a consequence of the allowlist being right:
+// .git/hooks/post-commit is executed by brain-sync inside a pod holding the
+// Gitea push credentials, and archive/ + sessions/ hold verbatim session
+// transcripts that BM25 never indexes and so nobody thinks of as reachable.
+var deniedPrefixes = []string{".git/", "archive/", "sessions/", "raw/", "training-data/", ".obsidian/"}
+
+// Errors are sentinels so callers can distinguish a refusal from an I/O fault.
+var (
+	ErrOutsideBrain  = errors.New("notes: path escapes the brain dir")
+	ErrNotAllowed    = errors.New("notes: path is not editable through this tool")
+	ErrNotSyncSource = errors.New("notes: brain dir is not the sync source")
+)
+
+// Target is a resolved, contained path.
+type Target struct {
+	Rel string // brain-relative, cleaned
+	Abs string // absolute, symlink-checked
+}
+
+// Resolve canonicalises path, then checks it against the scope's allowlist,
+// then re-checks containment after symlink evaluation.
+//
+// Order matters and is the point: a prefix test on the raw argument accepts
+// "knowledge/../.git/hooks/post-commit", because Clean only collapses it
+// afterwards.
+func Resolve(brainDir, path string, scope Scope) (Target, error) {
+	// Note: the sync-source assertion lives on the WRITE path (Edit), not
+	// here. brain#2 was an edit landing where the sync could not commit it; a
+	// read from such a tree is merely a read.
+
+	// 1. Canonicalise. Rooting at "/" makes Clean collapse every ".." that
+	//    would otherwise escape, and ToSlash normalises separators first.
+	clean := strings.TrimPrefix(filepath.Clean("/"+filepath.ToSlash(path)), "/")
+	if clean == "" || clean == "." {
+		return Target{}, fmt.Errorf("%w: empty path", ErrNotAllowed)
+	}
+
+	// 2. Static denials, before any allowlist reasoning.
+	for _, d := range deniedPrefixes {
+		if strings.HasPrefix(clean+"/", d) {
+			return Target{}, fmt.Errorf("%w: %q is not note content", ErrNotAllowed, clean)
+		}
+	}
+	if strings.HasPrefix(filepath.Base(clean), ".") {
+		return Target{}, fmt.Errorf("%w: dotfiles are not editable", ErrNotAllowed)
+	}
+
+	// 3. Scope allowlist.
+	if err := allow(clean, scope); err != nil {
+		return Target{}, err
+	}
+
+	// 4. Containment, lexically.
+	abs := filepath.Join(brainDir, filepath.FromSlash(clean))
+	if !within(brainDir, abs) {
+		return Target{}, fmt.Errorf("%w: %q", ErrOutsideBrain, path)
+	}
+
+	// 5. Containment again, after resolving symlinks. The tree is Syncthing
+	//    managed, so a link can appear without anyone adding one on purpose;
+	//    a symlinked note or directory would otherwise read and write outside
+	//    the brain entirely.
+	if err := assertNoSymlinkEscape(brainDir, abs); err != nil {
+		return Target{}, err
+	}
+
+	return Target{Rel: clean, Abs: abs}, nil
+}
+
+// allow enforces the scope's allowlist. The two scopes are DISJOINT, not
+// nested: the privileged root scope reaches governance files and nothing else,
+// so the tool that carries the higher privilege carries the smaller reach.
+func allow(clean string, scope Scope) error {
+	if scope == ScopeRoot {
+		if !rootFiles[clean] {
+			return fmt.Errorf("%w: %q is not a governance file", ErrNotAllowed, clean)
+		}
+		return nil
+	}
+	if !isNotePath(clean) {
+		return fmt.Errorf("%w: %q is outside knowledge/ and wiki/", ErrNotAllowed, clean)
+	}
+	return nil
+}
+
+func isNotePath(clean string) bool {
+	var inDir bool
+	for _, d := range noteDirs {
+		if strings.HasPrefix(clean, d) {
+			inDir = true
+			break
+		}
+	}
+	if !inDir || filepath.Ext(clean) != ".md" {
+		return false
+	}
+	// _index.md is generated per wing, and brain-sync's conflict resolver
+	// deliberately resolves it in origin's favour — an edit here is reverted
+	// by design, so accepting one would be a lie.
+	return filepath.Base(clean) != "_index.md"
+}
+
+func within(root, abs string) bool {
+	rel, err := filepath.Rel(root, abs)
+	if err != nil {
+		return false
+	}
+	return rel != ".." && !strings.HasPrefix(rel, ".."+string(filepath.Separator))
+}
+
+// assertNoSymlinkEscape resolves the deepest existing ancestor of abs and
+// requires it to still be inside brainDir. The file itself need not exist
+// (a create is legal); its directory chain must be real and contained.
+func assertNoSymlinkEscape(brainDir, abs string) error {
+	if fi, err := os.Lstat(abs); err == nil && fi.Mode()&os.ModeSymlink != 0 {
+		return fmt.Errorf("%w: %q is a symlink", ErrNotAllowed, abs)
+	}
+
+	realRoot, err := filepath.EvalSymlinks(brainDir)
+	if err != nil {
+		return fmt.Errorf("notes: resolve brain dir: %w", err)
+	}
+
+	dir := filepath.Dir(abs)
+	for {
+		resolved, err := filepath.EvalSymlinks(dir)
+		if err == nil {
+			if !within(realRoot, resolved) {
+				return fmt.Errorf("%w: %q resolves outside the brain dir", ErrOutsideBrain, dir)
+			}
+			return nil
+		}
+		if !os.IsNotExist(err) {
+			return fmt.Errorf("notes: resolve %q: %w", dir, err)
+		}
+		parent := filepath.Dir(dir)
+		if parent == dir {
+			return fmt.Errorf("%w: no existing ancestor for %q", ErrOutsideBrain, abs)
+		}
+		dir = parent
+	}
+}
+
+// assertSyncSource refuses a brain dir that is not a git working tree.
+//
+// brain#2 was an edit landing on a directory the sync does not commit from.
+// That cannot be prevented by review — a wrong INGEST_BRAIN_DIR in a future
+// manifest reintroduces it while every unit test still passes — so it is
+// asserted at runtime, the same check brain-sync itself makes before running.
+func assertSyncSource(brainDir string) error {
+	if fi, err := os.Stat(filepath.Join(brainDir, ".git")); err != nil || !fi.IsDir() {
+		return fmt.Errorf("%w: %q has no .git, so an edit there would never be committed",
+			ErrNotSyncSource, brainDir)
+	}
+	return nil
+}
@@ -0,0 +1,146 @@
+package notes
+
+import (
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+)
+
+// newBrain lays out a tree shaped like the live one: a git dir, note dirs,
+// and the non-note areas that must never be reachable.
+func newBrain(t *testing.T) string {
+	t.Helper()
+	dir := t.TempDir()
+	for _, d := range []string{
+		".git/hooks", "knowledge", "wiki/homelab/facts", "archive/claude-sessions/koala",
+		"sessions", "raw", ".obsidian",
+	} {
+		if err := os.MkdirAll(filepath.Join(dir, d), 0o755); err != nil {
+			t.Fatal(err)
+		}
+	}
+	write := func(p, s string) {
+		t.Helper()
+		if err := os.WriteFile(filepath.Join(dir, p), []byte(s), 0o644); err != nil {
+			t.Fatal(err)
+		}
+	}
+	write("CLAUDE.md", "# instructions\n")
+	write("log.md", "ignored scratch\n")
+	write("knowledge/note.md", "# note\n")
+	write("wiki/homelab/facts/f.md", "# fact\n")
+	write("wiki/homelab/_index.md", "# index\n")
+	write("archive/claude-sessions/koala/session-1.md", "verbatim transcript\n")
+	write("sessions/s.jsonl", "{}\n")
+	write(".git/hooks/post-commit", "#!/bin/sh\n")
+	return dir
+}
+
+func TestResolve_AcceptsNotePaths(t *testing.T) {
+	dir := newBrain(t)
+	for _, p := range []string{"knowledge/note.md", "wiki/homelab/facts/f.md"} {
+		got, err := Resolve(dir, p, ScopeNotes)
+		if err != nil {
+			t.Errorf("Resolve(%q): %v", p, err)
+			continue
+		}
+		if !strings.HasPrefix(got.Abs, dir) {
+			t.Errorf("Resolve(%q).Abs = %q, want inside %q", p, got.Abs, dir)
+		}
+	}
+}
+
+func TestResolve_RefusesEscapesAndNonNoteAreas(t *testing.T) {
+	dir := newBrain(t)
+
+	// Canonicalisation must happen BEFORE the allowlist check. A prefix test
+	// on the raw argument accepts every one of these: "knowledge/..%2f" style
+	// inputs collapse to .git, and .git/hooks/post-commit is executed by
+	// brain-sync inside a pod holding the Gitea push credentials.
+	refuse := []string{
+		"knowledge/../.git/hooks/post-commit",
+		"wiki/../.git/config",
+		"./knowledge/../.git/config",
+		"knowledge//../.git/config",
+		"../../etc/passwd",
+		"/etc/passwd",
+		".git/config",
+		"archive/claude-sessions/koala/session-1.md", // verbatim transcripts
+		"sessions/s.jsonl",
+		"raw/x.md",
+		".obsidian/workspace.json",
+		"log.md",                 // gitignored: an edit here would never sync (brain#2)
+		"wiki/homelab/_index.md", // generated; brain-sync resolves it in origin's favour
+		"knowledge/note.txt",     // not markdown
+		"CLAUDE.md",              // root file — not reachable in the notes scope
+	}
+	for _, p := range refuse {
+		if _, err := Resolve(dir, p, ScopeNotes); err == nil {
+			t.Errorf("Resolve(%q) = nil error, want refusal", p)
+		}
+	}
+}
+
+func TestResolve_RootScopeAdmitsOnlyNamedFiles(t *testing.T) {
+	dir := newBrain(t)
+
+	if _, err := Resolve(dir, "CLAUDE.md", ScopeRoot); err != nil {
+		t.Errorf("Resolve(CLAUDE.md, ScopeRoot): %v", err)
+	}
+	// log.md is the reason this is an exact-name list and not "root *.md":
+	// it is gitignored, so an edit would apply locally and never reach gitea.
+	for _, p := range []string{"log.md", "AGENTS.md", "knowledge/note.md", ".git/config"} {
+		if _, err := Resolve(dir, p, ScopeRoot); err == nil {
+			t.Errorf("Resolve(%q, ScopeRoot) = nil error, want refusal", p)
+		}
+	}
+}
+
+func TestResolve_RefusesSymlinkedTargets(t *testing.T) {
+	dir := newBrain(t)
+	outside := filepath.Join(t.TempDir(), "secret.md")
+	if err := os.WriteFile(outside, []byte("secret\n"), 0o644); err != nil {
+		t.Fatal(err)
+	}
+	// The tree is Syncthing-managed, so a symlink can appear without anyone
+	// adding one deliberately. Containment must survive it.
+	if err := os.Symlink(outside, filepath.Join(dir, "knowledge/link.md")); err != nil {
+		t.Skipf("symlinks unavailable: %v", err)
+	}
+	if _, err := Resolve(dir, "knowledge/link.md", ScopeNotes); err == nil {
+		t.Error("Resolve followed a symlink out of the brain dir")
+	}
+
+	if err := os.Symlink(filepath.Dir(outside), filepath.Join(dir, "wiki/escape")); err != nil {
+		t.Skipf("symlinks unavailable: %v", err)
+	}
+	if _, err := Resolve(dir, "wiki/escape/secret.md", ScopeNotes); err == nil {
+		t.Error("Resolve followed a symlinked directory out of the brain dir")
+	}
+}
+
+func TestResolve_RefusesWhenTheTreeIsNotTheSyncSource(t *testing.T) {
+	// brain#2 was "wrote to a directory the sync does not commit from". No
+	// code review prevents that recurring — a wrong INGEST_BRAIN_DIR in a
+	// future manifest reintroduces it and every unit test still passes. So
+	// assert the property at runtime, the way brain-sync itself does.
+	dir := t.TempDir()
+	if err := os.MkdirAll(filepath.Join(dir, "knowledge"), 0o755); err != nil {
+		t.Fatal(err)
+	}
+	if err := os.WriteFile(filepath.Join(dir, "knowledge/note.md"), []byte("x"), 0o644); err != nil {
+		t.Fatal(err)
+	}
+	// Reads are fine anywhere; the guard belongs to writes.
+	if _, err := Resolve(dir, "knowledge/note.md", ScopeNotes); err != nil {
+		t.Fatalf("Resolve should not require .git for a read: %v", err)
+	}
+	_, err := Edit(dir, "knowledge/note.md", "x", "y", ScopeNotes)
+	if err == nil {
+		t.Fatal("Edit accepted a tree with no .git — the write would never be committed")
+	}
+	if !strings.Contains(err.Error(), "sync source") {
+		t.Errorf("error should name the cause, got %v", err)
+	}
+}
@@ -76,6 +76,15 @@ func buildFrontmatter(rp RawPage, date string) string {
 		}
 		fmt.Fprintf(&sb, "date_ingested: %s\n", date)
 		fmt.Fprintf(&sb, "last_updated: %s\n", date)
+		if rp.Source != "" {
+			fmt.Fprintf(&sb, "source: %s\n", yamlScalar(rp.Source))
+		}
+		if rp.Author != "" {
+			fmt.Fprintf(&sb, "author: %s\n", yamlScalar(rp.Author))
+		}
+		if rp.Published != "" {
+			fmt.Fprintf(&sb, "published: %s\n", yamlScalar(rp.Published))
+		}
 	case "concept":
 		if rp.Domain != "" {
 			fmt.Fprintf(&sb, "domain: %s\n", yamlScalar(rp.Domain))
@@ -154,6 +154,52 @@ func TestBuildPages_EntityNoSubtype(t *testing.T) {
 	assert.Contains(t, pages[0].Content, "title: 'Basecamp'")
 }

+func TestBuildPages_SourcePageCarriesSourceAuthorPublished(t *testing.T) {
+	raw := []RawPage{
+		{
+			Title:     "Ornith",
+			Type:      "source",
+			Subtype:   "article",
+			Content:   "## Summary\n\nAn agentic coding model.\n",
+			Source:    "https://example.com/ornith",
+			Author:    "Jane Doe",
+			Published: "2026-07-20",
+		},
+	}
+	pages, warnings := BuildPages(raw, "ornith", "2026-07-26")
+	require.Len(t, pages, 1)
+	assert.Empty(t, warnings)
+
+	p := pages[0]
+	assert.Contains(t, p.Content, "source: 'https://example.com/ornith'")
+	assert.Contains(t, p.Content, "author: 'Jane Doe'")
+	assert.Contains(t, p.Content, "published: '2026-07-20'")
+}
+
+func TestBuildPages_SourcePageOmitsSourceAuthorPublishedWhenEmpty(t *testing.T) {
+	raw := []RawPage{
+		{Title: "Shape Up", Type: "source", Subtype: "book", Content: "## Summary\n\nA book.\n"},
+	}
+	pages, _ := BuildPages(raw, "shape-up", "2026-04-23")
+	require.Len(t, pages, 1)
+	assert.NotContains(t, pages[0].Content, "source:")
+	assert.NotContains(t, pages[0].Content, "author:")
+	assert.NotContains(t, pages[0].Content, "published:")
+}
+
+func TestBuildPages_ConceptPageIgnoresSourceAuthorPublished(t *testing.T) {
+	// source/author/published are source-note-only metadata; a concept page
+	// shouldn't carry them even if somehow set on the RawPage.
+	raw := []RawPage{
+		{Title: "Betting", Type: "concept", Content: "## Definition\n\nFoo.\n", Source: "x", Author: "y", Published: "z"},
+	}
+	pages, _ := BuildPages(raw, "src", "2026-04-23")
+	require.Len(t, pages, 1)
+	assert.NotContains(t, pages[0].Content, "source:")
+	assert.NotContains(t, pages[0].Content, "author:")
+	assert.NotContains(t, pages[0].Content, "published:")
+}
+
 func TestBuildPages_EmptyTitleSkippedWithWarning(t *testing.T) {
 	raw := []RawPage{
 		{Title: "", Type: "concept", Content: "## Definition\n\nFoo.\n"},
@@ -51,6 +51,21 @@ func buildTitleMap(pages []wiki.Page, inventory map[wiki.PageType][]wiki.Entry)
 	return m
 }

+// pathStylePrefixes are known root prefixes the LLM extraction step
+// sometimes bakes into a wikilink target instead of emitting a clean
+// wing/hall/slug path (or bare title). Stripping them repairs the link
+// in place — see hyperguild#87.
+var pathStylePrefixes = []string{"wing:", "wiki/"}
+
+func stripPathStylePrefix(displayName string) (string, bool) {
+	for _, prefix := range pathStylePrefixes {
+		if stripped, ok := strings.CutPrefix(displayName, prefix); ok {
+			return stripped, true
+		}
+	}
+	return displayName, false
+}
+
 func canonicalizeContent(content string, titleToSlug map[string]string) (string, []string) {
 	var warnings []string
 	result := plainLinkRE.ReplaceAllStringFunc(content, func(match string) string {
@@ -59,12 +74,17 @@ func canonicalizeContent(content string, titleToSlug map[string]string) (string,
 			return match
 		}
 		displayName := sub[1]
-		slug, ok := titleToSlug[strings.ToLower(displayName)]
-		if !ok {
-			warnings = append(warnings, fmt.Sprintf("unknown wikilink: [[%s]]", displayName))
-			return match
+
+		if slug, ok := titleToSlug[strings.ToLower(displayName)]; ok {
+			return "[[" + slug + "|" + displayName + "]]"
 		}
-		return "[[" + slug + "|" + displayName + "]]"
+
+		if stripped, hadPrefix := stripPathStylePrefix(displayName); hadPrefix {
+			return "[[" + stripped + "]]"
+		}
+
+		warnings = append(warnings, fmt.Sprintf("unknown wikilink: [[%s]]", displayName))
+		return match
 	})
 	return result, warnings
 }
@@ -102,6 +102,53 @@ func TestCanonicalizeLinks_CurrentBatchPagesResolved(t *testing.T) {
 	assert.Contains(t, got[0].Content, "[[betting|Betting]]")
 }

+func TestCanonicalizeLinks_StripsWingColonPrefix(t *testing.T) {
+	pages := []wiki.Page{
+		{
+			Path:    "wiki/homelab/failures/act-runner-host-mode-container-needs-node-and-libatomic.md",
+			Content: "---\ntitle: 'act_runner host-mode'\n---\n\nSee [[wing:homelab/failures/rootless-buildah-act-runner-run-containers-denied]].\n",
+		},
+	}
+	got, warnings := CanonicalizeLinks(pages, map[wiki.PageType][]wiki.Entry{})
+	require.Len(t, got, 1)
+	assert.Empty(t, warnings)
+	assert.Contains(t, got[0].Content, "[[homelab/failures/rootless-buildah-act-runner-run-containers-denied]]")
+	assert.NotContains(t, got[0].Content, "wing:")
+}
+
+func TestCanonicalizeLinks_StripsWikiSlashPrefix(t *testing.T) {
+	pages := []wiki.Page{
+		{
+			Path:    "wiki/agentsquad/hypotheses/council-consolidation-standalone-deliberation-service.md",
+			Content: "---\ntitle: 'council consolidation'\n---\n\nSee [[wiki/agentsquad/decisions/autoresearch-council-sibling-pipe]].\n",
+		},
+	}
+	got, warnings := CanonicalizeLinks(pages, map[wiki.PageType][]wiki.Entry{})
+	require.Len(t, got, 1)
+	assert.Empty(t, warnings)
+	assert.Contains(t, got[0].Content, "[[agentsquad/decisions/autoresearch-council-sibling-pipe]]")
+	assert.NotContains(t, got[0].Content, "wiki/agentsquad/decisions/autoresearch-council-sibling-pipe]]\n\n") // no leftover wiki/ prefix
+	assert.NotContains(t, got[0].Content, "[[wiki/")
+}
+
+func TestCanonicalizeLinks_TitleLookupStillTakesPriorityOverPrefixStrip(t *testing.T) {
+	// A plain link that resolves via the title map must still use the
+	// normal slug|Display form, not fall through to prefix-strip repair.
+	pages := []wiki.Page{
+		{
+			Path:    "wiki/sources/shape-up.md",
+			Content: "---\ntitle: 'Shape Up'\n---\n\nSee [[Betting]].\n",
+		},
+	}
+	inventory := map[wiki.PageType][]wiki.Entry{
+		wiki.PageTypeConcept: {{Slug: "betting", Title: "Betting"}},
+	}
+	got, warnings := CanonicalizeLinks(pages, inventory)
+	require.Len(t, got, 1)
+	assert.Empty(t, warnings)
+	assert.Contains(t, got[0].Content, "[[betting|Betting]]")
+}
+
 func TestCanonicalizeLinks_MultipleLinksInOnePage(t *testing.T) {
 	pages := []wiki.Page{
 		{
@@ -15,6 +15,14 @@ type RawPage struct {
 	Subtype string `json:"subtype"` // entity: person|company|tool|model|framework|technology; source: article|pdf|book|video|note|project
 	Domain  string `json:"domain"`
 	Content string `json:"content"` // Markdown body only — no frontmatter
+
+	// Source, Author, Published are deterministic passthrough from the raw
+	// ingested content's own frontmatter (see parseContentFrontmatter) — never
+	// set by the LLM. json:"-" keeps them immune to same-named keys the LLM
+	// might emit. Only meaningful for Type == "source".
+	Source    string `json:"-"`
+	Author    string `json:"-"`
+	Published string `json:"-"`
 }

 // ParseRawPages parses LLM output as a JSON array of RawPage objects.
@@ -98,6 +106,60 @@ func repairJSON(s string) string {
 	return b.String()
 }

+// sourceMeta is source/author/published pulled from the raw ingested
+// content's own frontmatter — deterministic passthrough, never LLM output.
+type sourceMeta struct {
+	Source    string
+	Author    string
+	Published string
+}
+
+// parseContentFrontmatter extracts source/author/published from a leading
+// "---\n...\n---" YAML block in raw ingested content. Only these three flat
+// scalar keys are recognised; anything else in the block is ignored. Returns
+// a zero-value sourceMeta if content has no frontmatter block.
+func parseContentFrontmatter(content string) sourceMeta {
+	var meta sourceMeta
+	if !strings.HasPrefix(content, "---\n") && !strings.HasPrefix(content, "---\r\n") {
+		return meta
+	}
+
+	lines := strings.Split(content, "\n")
+	for _, line := range lines[1:] {
+		if strings.TrimSpace(line) == "---" {
+			break
+		}
+		key, val, ok := strings.Cut(line, ":")
+		if !ok {
+			continue
+		}
+		key = strings.TrimSpace(key)
+		val = strings.Trim(strings.TrimSpace(val), `"'`)
+		switch key {
+		case "source":
+			meta.Source = val
+		case "author":
+			meta.Author = val
+		case "published":
+			meta.Published = val
+		}
+	}
+	return meta
+}
+
+// applySourceMeta deterministically overwrites Source/Author/Published on
+// every "source"-type page with meta — the LLM never controls these fields.
+func applySourceMeta(pages []RawPage, meta sourceMeta) {
+	for i := range pages {
+		if pages[i].Type != "source" {
+			continue
+		}
+		pages[i].Source = meta.Source
+		pages[i].Author = meta.Author
+		pages[i].Published = meta.Published
+	}
+}
+
 func stripFences(s string) string {
 	for _, prefix := range []string{"```json\n", "```json\r\n", "```\n", "```\r\n"} {
 		if strings.HasPrefix(s, prefix) {
@@ -59,6 +59,8 @@ func Run(ctx context.Context, cfg Config, brainDir, content, source string, dryR
 		allWarnings = append(allWarnings, warnings...)
 	}

+	applySourceMeta(allRaw, parseContentFrontmatter(content))
+
 	return buildAndWrite(allRaw, sourceSlug, date, brainDir, source, inventory, allWarnings, dryRun)
 }

@@ -130,6 +130,40 @@ func TestRun_MergesDuplicatePaths(t *testing.T) {
 	assert.Contains(t, string(content), "[[Baz]]")
 }

+func TestRun_ThreadsSourceAuthorPublishedFromContentFrontmatter(t *testing.T) {
+	brainDir := t.TempDir()
+	for _, sub := range []string{"wiki/concepts", "wiki/entities", "wiki/sources"} {
+		require.NoError(t, os.MkdirAll(filepath.Join(brainDir, sub), 0o755))
+	}
+
+	llmResponse := mustJSON([]RawPage{{
+		Title:   "Ornith",
+		Type:    "source",
+		Subtype: "article",
+		Content: "## Summary\n\nAn agentic coding model.\n",
+	}})
+
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		_ = json.NewEncoder(w).Encode(map[string]any{
+			"choices": []map[string]any{{"message": map[string]any{"content": llmResponse}}},
+		})
+	}))
+	defer srv.Close()
+
+	cfg := Config{Complete: llm.New(srv.URL, "", "m", 30*time.Second).Complete}
+	rawContent := "---\nsource: https://example.com/ornith\nauthor: Jane Doe\npublished: 2026-07-20\n---\n\nAn agentic coding model that runs on your laptop.\n"
+
+	result, err := Run(context.Background(), cfg, brainDir, rawContent, "ornith", false)
+	require.NoError(t, err)
+	require.Len(t, result.Pages, 1)
+
+	content, err := os.ReadFile(filepath.Join(brainDir, "wiki", "sources", "ornith.md"))
+	require.NoError(t, err)
+	assert.Contains(t, string(content), "source: 'https://example.com/ornith'")
+	assert.Contains(t, string(content), "author: 'Jane Doe'")
+	assert.Contains(t, string(content), "published: '2026-07-20'")
+}
+
 func mustJSON(v any) string {
 	b, err := json.Marshal(v)
 	if err != nil {
@@ -12,6 +12,7 @@ import (
 	"strings"

 	"github.com/mathiasbq/hyperguild/ingestion/internal/brain"
+	"github.com/mathiasbq/hyperguild/ingestion/internal/textutil"
 	"github.com/mathiasbq/hyperguild/ingestion/internal/vectorstore"
 )

@@ -427,8 +428,5 @@ func excerpt(content string, maxLen int) string {
 	if len(parts) == 3 {
 		body = strings.TrimSpace(parts[2])
 	}
-	if len(body) > maxLen {
-		return body[:maxLen] + "…"
-	}
-	return body
+	return textutil.Truncate(body, maxLen)
 }
@@ -0,0 +1,75 @@
+// Package startupretry retries a startup dependency that may not be serving
+// yet, instead of exiting on its first failure.
+//
+// It exists for the cold-boot ordering race (#83): on a cluster restart the
+// ingestion pod can reach OIDC discovery before dex is answering, gets a 502
+// from ingress, and dies — after having already connected postgres, backfilled
+// the graph and ingested session batches, all of which the restart redoes.
+// Nothing is misconfigured in that scenario; the pod simply started first.
+//
+// The budget is bounded on purpose. Retrying forever would turn a genuine
+// misconfiguration (wrong issuer URL, bad audience) into a process that looks
+// healthy and never serves, which is harder to diagnose than a crash loop.
+package startupretry
+
+import (
+	"context"
+	"fmt"
+	"time"
+)
+
+// Policy bounds the retry: at most Attempts calls, with the delay doubling
+// from Base and capped at Max.
+type Policy struct {
+	Attempts int           // total calls, including the first; < 1 means 1
+	Base     time.Duration // delay before the second attempt
+	Max      time.Duration // ceiling for the doubling delay
+}
+
+// Do calls fn until it succeeds, the attempt budget is spent, or ctx ends.
+//
+// The returned error wraps the last failure, so callers keep the diagnosis
+// they would have had without the retry.
+func Do[T any](ctx context.Context, p Policy, fn func(context.Context) (T, error)) (T, error) {
+	var zero T
+
+	attempts := p.Attempts
+	if attempts < 1 {
+		attempts = 1
+	}
+
+	delay := p.Base
+	var lastErr error
+
+	for i := range attempts {
+		if err := ctx.Err(); err != nil {
+			return zero, fmt.Errorf("startupretry: %w", err)
+		}
+
+		v, err := fn(ctx)
+		if err == nil {
+			return v, nil
+		}
+		lastErr = err
+
+		if i == attempts-1 {
+			break
+		}
+
+		if delay <= 0 {
+			delay = time.Second
+		}
+		if p.Max > 0 && delay > p.Max {
+			delay = p.Max
+		}
+
+		select {
+		case <-ctx.Done():
+			return zero, fmt.Errorf("startupretry: %w", ctx.Err())
+		case <-time.After(delay):
+		}
+		delay *= 2
+	}
+
+	return zero, fmt.Errorf("startupretry: gave up after %d attempts: %w", attempts, lastErr)
+}
@@ -0,0 +1,144 @@
+// ingestion/internal/startupretry/startupretry_test.go
+package startupretry
+
+import (
+	"context"
+	"errors"
+	"testing"
+	"time"
+)
+
+func fastPolicy(attempts int) Policy {
+	return Policy{Attempts: attempts, Base: time.Millisecond, Max: 2 * time.Millisecond}
+}
+
+func TestDo_ReturnsImmediatelyOnFirstSuccess(t *testing.T) {
+	calls := 0
+	got, err := Do(context.Background(), fastPolicy(5), func(context.Context) (string, error) {
+		calls++
+		return "ready", nil
+	})
+
+	if err != nil {
+		t.Fatalf("Do: %v", err)
+	}
+	if got != "ready" {
+		t.Errorf("got %q, want %q", got, "ready")
+	}
+	if calls != 1 {
+		t.Errorf("calls = %d, want 1", calls)
+	}
+}
+
+func TestDo_SurvivesTransientFailuresThenSucceeds(t *testing.T) {
+	// The observed cold-boot race: dex is not serving yet, ingress answers
+	// 502 for the first few attempts, then discovery works.
+	calls := 0
+	got, err := Do(context.Background(), fastPolicy(5), func(context.Context) (string, error) {
+		calls++
+		if calls < 4 {
+			return "", errors.New("oidc discovery: status 502")
+		}
+		return "ready", nil
+	})
+
+	if err != nil {
+		t.Fatalf("Do returned %v — a transient 502 must not be fatal", err)
+	}
+	if got != "ready" {
+		t.Errorf("got %q, want %q", got, "ready")
+	}
+	if calls != 4 {
+		t.Errorf("calls = %d, want 4", calls)
+	}
+}
+
+func TestDo_GivesUpAfterTheAttemptBudgetAndReportsTheLastError(t *testing.T) {
+	// A genuinely broken issuer must still fail — retrying forever would turn
+	// a config error into a silent hang, which is worse than crash-looping.
+	last := errors.New("oidc discovery: status 404")
+	calls := 0
+
+	_, err := Do(context.Background(), fastPolicy(3), func(context.Context) (string, error) {
+		calls++
+		return "", last
+	})
+
+	if !errors.Is(err, last) {
+		t.Fatalf("err = %v, want it to wrap the last failure", err)
+	}
+	if calls != 3 {
+		t.Errorf("calls = %d, want 3 (the attempt budget)", calls)
+	}
+}
+
+func TestDo_StopsPromptlyWhenTheContextIsCancelled(t *testing.T) {
+	ctx, cancel := context.WithCancel(context.Background())
+	calls := 0
+
+	done := make(chan struct{})
+	var err error
+	go func() {
+		defer close(done)
+		_, err = Do(ctx, Policy{Attempts: 100, Base: 50 * time.Millisecond, Max: time.Second},
+			func(context.Context) (string, error) {
+				calls++
+				if calls == 1 {
+					cancel()
+				}
+				return "", errors.New("still down")
+			})
+	}()
+
+	select {
+	case <-done:
+	case <-time.After(2 * time.Second):
+		t.Fatal("Do did not return after context cancellation")
+	}
+	if !errors.Is(err, context.Canceled) {
+		t.Errorf("err = %v, want context.Canceled", err)
+	}
+}
+
+func TestDo_BacksOffAndIsCappedByMax(t *testing.T) {
+	var delays []time.Duration
+	p := Policy{Attempts: 5, Base: 10 * time.Millisecond, Max: 25 * time.Millisecond}
+
+	last := time.Now()
+	_, _ = Do(context.Background(), p, func(context.Context) (string, error) {
+		now := time.Now()
+		delays = append(delays, now.Sub(last))
+		last = now
+		return "", errors.New("down")
+	})
+
+	// delays[0] is the first call (no wait); the rest are the sleeps.
+	if len(delays) != 5 {
+		t.Fatalf("attempts = %d, want 5", len(delays))
+	}
+	if delays[1] >= delays[2] {
+		t.Errorf("backoff is not growing: %v then %v", delays[1], delays[2])
+	}
+	for i, d := range delays[1:] {
+		if d > 2*p.Max {
+			t.Errorf("delay %d = %v, exceeds the Max cap %v with slack", i+1, d, p.Max)
+		}
+	}
+}
+
+func TestPolicy_ZeroValueStillMakesOneAttempt(t *testing.T) {
+	// A caller that forgets to configure the policy must not silently get a
+	// no-op that returns a nil validator and a nil error.
+	calls := 0
+	_, err := Do(context.Background(), Policy{}, func(context.Context) (string, error) {
+		calls++
+		return "", errors.New("down")
+	})
+
+	if calls != 1 {
+		t.Errorf("calls = %d, want 1", calls)
+	}
+	if err == nil {
+		t.Error("err = nil, want the failure surfaced")
+	}
+}
@@ -0,0 +1,45 @@
+// Package textutil holds small text helpers shared across the ingestion
+// service.
+package textutil
+
+import "unicode/utf8"
+
+// Ellipsis marks a value that was cut short.
+const Ellipsis = "…"
+
+// Truncate shortens s to at most limit CHARACTERS, appending an ellipsis when
+// anything was dropped.
+//
+// It exists because four call sites did `s[:limit] + "…"` (#93). Both halves
+// of that are byte operations: len() counts bytes and a slice cuts bytes, so
+// on Swedish text — where å ä ö are two bytes and an em dash is three — the
+// cut lands mid-character and leaves an orphaned lead byte. The result is
+// invalid UTF-8.
+//
+// That failed loudly in exactly one place, wiki/index.md, which is written
+// raw to disk and then rejected by every strict decoder. The other three fed
+// 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.
+//
+// The marker is appended only when content was actually dropped: an ellipsis
+// on complete text is a lie about the content.
+func Truncate(s string, limit int) string {
+	if limit <= 0 {
+		return ""
+	}
+	if utf8.RuneCountInString(s) <= limit {
+		return s
+	}
+
+	// Walk runes rather than converting to []rune: the input can be a whole
+	// note body, and this runs on the read path.
+	count := 0
+	for i := range s {
+		if count == limit {
+			return s[:i] + Ellipsis
+		}
+		count++
+	}
+	return s + Ellipsis
+}
@@ -0,0 +1,66 @@
+// ingestion/internal/textutil/truncate_test.go
+package textutil_test
+
+import (
+	"strings"
+	"testing"
+	"unicode/utf8"
+
+	"github.com/mathiasbq/hyperguild/ingestion/internal/textutil"
+)
+
+func TestTruncate_ShortStringsAreUntouched(t *testing.T) {
+	for _, s := range []string{"", "kort", "räv", "a — b"} {
+		if got := textutil.Truncate(s, 100); got != s {
+			t.Errorf("Truncate(%q, 100) = %q, want it unchanged", s, got)
+		}
+	}
+}
+
+func TestTruncate_NeverCutsInsideACharacter(t *testing.T) {
+	// The property, not an example: whatever the limit, the result must be
+	// valid UTF-8. Byte-slicing Swedish text (å ä ö) or an em dash produces
+	// an orphaned lead byte, which is what corrupted wiki/index.md (#93).
+	s := strings.Repeat("räv — ål — ökäd ", 20)
+
+	for limit := 0; limit <= len(s)+5; limit++ {
+		got := textutil.Truncate(s, limit)
+		if !utf8.ValidString(got) {
+			t.Fatalf("Truncate(s, %d) produced invalid UTF-8: %q", limit, got)
+		}
+	}
+}
+
+func TestTruncate_CountsCharactersNotBytes(t *testing.T) {
+	// "räv" is 4 bytes, 3 runes. A byte-based limit of 3 would cut inside the
+	// "ä"; a rune-based one returns it whole.
+	if got := textutil.Truncate("räv", 3); got != "räv" {
+		t.Errorf("Truncate(\"räv\", 3) = %q, want the whole word", got)
+	}
+
+	got := textutil.Truncate("räven springer", 5)
+	if utf8.RuneCountInString(got) != 6 { // 5 runes + the ellipsis
+		t.Errorf("Truncate(...) = %q, want 5 runes plus the marker", got)
+	}
+	if !strings.HasSuffix(got, "…") {
+		t.Errorf("Truncate(...) = %q, want it marked as truncated", got)
+	}
+}
+
+func TestTruncate_MarksOnlyWhenSomethingWasDropped(t *testing.T) {
+	// An ellipsis on text that was not cut is a lie about the content.
+	if got := textutil.Truncate("räv", 10); strings.HasSuffix(got, "…") {
+		t.Errorf("Truncate(%q, 10) = %q, want no truncation marker", "räv", got)
+	}
+	if got := textutil.Truncate("räv", 3); strings.HasSuffix(got, "…") {
+		t.Errorf("exact-length input must not be marked: %q", got)
+	}
+}
+
+func TestTruncate_NonPositiveLimitYieldsNothingRatherThanPanicking(t *testing.T) {
+	for _, limit := range []int{0, -1, -100} {
+		if got := textutil.Truncate("räven", limit); got != "" {
+			t.Errorf("Truncate(_, %d) = %q, want empty", limit, got)
+		}
+	}
+}
@@ -74,6 +74,13 @@ func processDir(ctx context.Context, cfg Config, date string) []error {
 			return nil
 		}

+		// AutoTunnel's own fuzzy-match human-review queue, not source
+		// material to extract (hyperguild#88) — same exclusion as
+		// api.ListPending already applies when listing raw/ for promotion.
+		if strings.HasPrefix(d.Name(), "tunnel-candidates-") {
+			return nil
+		}
+
 		// Skip files that have already been processed or permanently failed.
 		if _, err := os.Stat(path + ".processed"); err == nil {
 			return nil
@@ -229,3 +229,49 @@ func TestProcessDir_SkipsSubdirs(t *testing.T) {
 	_, err = os.Stat(failedFile)
 	assert.NoError(t, err, "failed subdir file should be untouched")
 }
+
+// TestProcessDir_SkipsTunnelCandidateFiles guards against hyperguild#88:
+// AutoTunnel's own human-review queue (brain/raw/tunnel-candidates-*.md)
+// must never be re-ingested as if it were external source material — doing
+// so fed the raw "(term: X)" log entries back through the LLM extraction
+// pipeline, which then legitimately (from its own perspective) surfaced
+// [[X]] as a wikilink for any term that happened to match a real page
+// title, however generic (e.g. "mission").
+func TestProcessDir_SkipsTunnelCandidateFiles(t *testing.T) {
+	brainDir := setupBrainDir(t)
+
+	tunnelFile := filepath.Join(brainDir, "raw", "tunnel-candidates-2026-07-19.md")
+	require.NoError(t, os.WriteFile(tunnelFile, []byte(
+		"# Tunnel candidates 2026-07-19\n\n- `wiki/homelab/decisions/foo.md` ↔ `wiki/telos/decisions/mission.md` (term: \"mission\")\n",
+	), 0o644))
+
+	var completeCalls int
+	completeFn := func(ctx context.Context, system, user string) (string, error) {
+		completeCalls++
+		raw := pipeline.RawPage{Title: "Should not be written", Type: "source", Subtype: "article", Content: "## Summary\n\nx.\n"}
+		b, _ := json.Marshal([]pipeline.RawPage{raw})
+		return string(b), nil
+	}
+
+	cfg := Config{
+		BrainDir: brainDir,
+		Interval: time.Hour, // not used; we call processDir directly
+		Pipeline: pipeline.Config{
+			Complete:  completeFn,
+			ChunkSize: 0,
+			Schema:    "# Schema\nThree page types.",
+		},
+	}
+
+	date := time.Now().UTC().Format("2006-01-02")
+	errs := processDir(context.Background(), cfg, date)
+	assert.Empty(t, errs)
+
+	assert.Zero(t, completeCalls, "tunnel-candidates file must never reach the LLM extraction pipeline")
+
+	// File must be left alone in raw/ — not moved to processed/, no marker written.
+	_, err := os.Stat(tunnelFile + ".processed")
+	assert.True(t, os.IsNotExist(err), "tunnel-candidates file should not get a .processed marker")
+	_, err = os.Stat(filepath.Join(brainDir, "raw", "processed", date, "tunnel-candidates-2026-07-19.md"))
+	assert.True(t, os.IsNotExist(err), "tunnel-candidates file should not be copied to processed/")
+}
@@ -6,6 +6,8 @@ import (
 	"os"
 	"path/filepath"
 	"strings"
+
+	"github.com/mathiasbq/hyperguild/ingestion/internal/textutil"
 )

 // RebuildIndex writes brain/wiki/index.md from the current wiki contents.
@@ -62,10 +64,7 @@ func pageFirstSentence(brainDir string, e Entry) string {
 		if line == "" || strings.HasPrefix(line, "#") {
 			continue
 		}
-		if len(line) > 100 {
-			return line[:100] + "…"
-		}
-		return line
+		return textutil.Truncate(line, 100)
 	}
 	return ""
 }
@@ -13,7 +13,7 @@ import (
 	"github.com/lestrrat-go/jwx/v2/jwa"
 	"github.com/lestrrat-go/jwx/v2/jwk"
 	"github.com/lestrrat-go/jwx/v2/jwt"
-	"github.com/mathiasbq/supervisor/internal/auth"
+	"git.d-ma.be/mathias/hyperguild/internal/auth"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 )
@@ -6,7 +6,7 @@ import (
 	"net/http/httptest"
 	"testing"

-	"github.com/mathiasbq/supervisor/internal/auth"
+	"git.d-ma.be/mathias/hyperguild/internal/auth"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 )
@@ -7,7 +7,7 @@ import (
 	"net/http/httptest"
 	"testing"

-	"github.com/mathiasbq/supervisor/internal/brain"
+	"git.d-ma.be/mathias/hyperguild/internal/brain"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 )
@@ -3,7 +3,7 @@ package config_test
 import (
 	"testing"

-	"github.com/mathiasbq/supervisor/internal/config"
+	"git.d-ma.be/mathias/hyperguild/internal/config"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 )
@@ -5,7 +5,7 @@ import (
 	"path/filepath"
 	"testing"

-	"github.com/mathiasbq/supervisor/internal/config"
+	"git.d-ma.be/mathias/hyperguild/internal/config"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 )
@@ -3,7 +3,7 @@ package config_test
 import (
 	"testing"

-	"github.com/mathiasbq/supervisor/internal/config"
+	"git.d-ma.be/mathias/hyperguild/internal/config"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 )
@@ -8,7 +8,7 @@ import (
 	"testing"
 	"time"

-	iexec "github.com/mathiasbq/supervisor/internal/exec"
+	iexec "git.d-ma.be/mathias/hyperguild/internal/exec"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 )
@@ -9,7 +9,7 @@ import (
 	"net/http/httptest"
 	"testing"

-	"github.com/mathiasbq/supervisor/internal/githubclient"
+	"git.d-ma.be/mathias/hyperguild/internal/githubclient"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 )
@@ -8,8 +8,8 @@ import (
 	"net/http"
 	"strings"

-	"github.com/mathiasbq/supervisor/internal/auth"
-	"github.com/mathiasbq/supervisor/internal/registry"
+	"git.d-ma.be/mathias/hyperguild/internal/auth"
+	"git.d-ma.be/mathias/hyperguild/internal/registry"
 )

 type request struct {
@@ -8,8 +8,8 @@ import (
 	"strings"
 	"testing"

-	"github.com/mathiasbq/supervisor/internal/mcp"
-	"github.com/mathiasbq/supervisor/internal/registry"
+	"git.d-ma.be/mathias/hyperguild/internal/mcp"
+	"git.d-ma.be/mathias/hyperguild/internal/registry"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 )
@@ -9,7 +9,7 @@ import (
 	"net/http/httptest"
 	"testing"

-	"github.com/mathiasbq/supervisor/internal/mcpclient"
+	"git.d-ma.be/mathias/hyperguild/internal/mcpclient"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 )
@@ -5,7 +5,7 @@ import (
 	"encoding/json"
 	"testing"

-	"github.com/mathiasbq/supervisor/internal/registry"
+	"git.d-ma.be/mathias/hyperguild/internal/registry"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 )
@@ -6,7 +6,7 @@ import (
 	"testing"
 	"time"

-	"github.com/mathiasbq/supervisor/internal/session"
+	"git.d-ma.be/mathias/hyperguild/internal/session"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 )
@@ -8,7 +8,7 @@ import (
 	"testing"
 	"time"

-	"github.com/mathiasbq/supervisor/internal/session"
+	"git.d-ma.be/mathias/hyperguild/internal/session"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 )
@@ -8,7 +8,7 @@ import (
 	"net/http/httptest"
 	"testing"

-	"github.com/mathiasbq/supervisor/internal/skills/brain"
+	"git.d-ma.be/mathias/hyperguild/internal/skills/brain"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 )
@@ -4,7 +4,7 @@ package brain
 import (
 	"encoding/json"

-	"github.com/mathiasbq/supervisor/internal/registry"
+	"git.d-ma.be/mathias/hyperguild/internal/registry"
 )

 // Config holds brain skill configuration.
@@ -6,8 +6,8 @@ import (
 	"encoding/json"
 	"testing"

-	"github.com/mathiasbq/supervisor/internal/skills/org"
-	"github.com/mathiasbq/supervisor/internal/tier"
+	"git.d-ma.be/mathias/hyperguild/internal/skills/org"
+	"git.d-ma.be/mathias/hyperguild/internal/tier"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 )
@@ -5,8 +5,8 @@ import (
 	"context"
 	"encoding/json"

-	"github.com/mathiasbq/supervisor/internal/registry"
-	"github.com/mathiasbq/supervisor/internal/tier"
+	"git.d-ma.be/mathias/hyperguild/internal/registry"
+	"git.d-ma.be/mathias/hyperguild/internal/tier"
 )

 // TierFn returns the current tier. Injected for testability.
@@ -7,7 +7,7 @@ import (
 	"fmt"
 	"time"

-	"github.com/mathiasbq/supervisor/internal/session"
+	"git.d-ma.be/mathias/hyperguild/internal/session"
 )

 type logArgs struct {
@@ -8,7 +8,7 @@ import (
 	"path/filepath"
 	"testing"

-	"github.com/mathiasbq/supervisor/internal/skills/sessionlog"
+	"git.d-ma.be/mathias/hyperguild/internal/skills/sessionlog"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 )
@@ -4,7 +4,7 @@ package sessionlog
 import (
 	"encoding/json"

-	"github.com/mathiasbq/supervisor/internal/registry"
+	"git.d-ma.be/mathias/hyperguild/internal/registry"
 )

 // Config holds sessionlog skill configuration.
@@ -7,7 +7,7 @@ import (
 	"net/http/httptest"
 	"testing"

-	"github.com/mathiasbq/supervisor/internal/tier"
+	"git.d-ma.be/mathias/hyperguild/internal/tier"
 	"github.com/stretchr/testify/assert"
 )

@@ -42,34 +42,35 @@ These actions are **carried into the Phase 4 capture call** as `tickets[]` rathe

 ## Phase 4 — Capture (one uniform call)

-Persist the session via a **single `capture` call** (the `brain:capture` MCP tool, live on the Claude.ai connector). Capture owns the writes server-side — insights → brain, action items → Gitea tickets, summary → ai-sessions — plus the I1 sovereignty gate, the I5 audit record, and the supersession/read-after-write discipline. The skill's job is to *assemble the payload*, not to write each store itself. Do NOT fall back to separate `gitea:file_write_branch` + `brain_write` steps unless `capture` is unreachable (see fallback below).
+Persist the session via a **single `capture` call** (the `brain:capture` MCP tool, live on the Claude.ai connector). Capture owns the writes server-side — insights → brain, action items → Gitea tickets — plus the I1 sovereignty gate, the I5 audit record, and the supersession/read-after-write discipline. The skill's job is to *assemble the payload*, not to write each store itself. Do NOT fall back to separate `gitea:file_write_branch` + `brain_write` steps unless `capture` is unreachable (see fallback below).
+
+**Note:** capture no longer writes a session summary anywhere (the `summary` → `ai-sessions` write path was removed — it produced a frontmatter shape `ai-sessions`' own pipeline couldn't parse, silently invisible to that repo's own audit tooling; see `ai-sessions#13`). If the session's decisions/artifacts are worth a durable narrative beyond the `insights[]` this skill writes to the brain, that's a separate, explicit call — not something this skill does implicitly.

 **Assemble one payload:**

 - **`insights[]`** — the generalizable learnings from Phase 1 (decisions/failures worth re-reading). Each: `{text, wing, hall}`; add `supersede_slug` to revise a prior note in place instead of creating a duplicate. `hall` ∈ facts/decisions/failures/hypotheses/sources.
 - **`tickets[]`** — the issue actions from Phase 3: `{repo, action, ...}` where action ∈ create/close/comment. Owner is always `mathias` (server-forced).
- **`summary`** — `{title, body, repos_touched}`. Capture writes it to `ai-sessions` and stamps `fidelity` in frontmatter. Body stays reconstructable: one-paragraph summary, decisions, key artifacts, open threads.
 - **`context`** — `{harness: "claudeai-chat", session_ref: <chatid8-or-slug>, fidelity: "live-capture", actor: "mathias", classification: <see gate below>}`.

 **THE CLASSIFICATION GATE (read before calling — this is where capture refuses).**
-Capture computes an **effective classification = the strictest across EVERY target it touches** (each insight's `wing`, each ticket's `repo`, and every entry in `summary.repos_touched`), then refuses if that effective level is `confidential` and the origin is us-nexus (claude.ai is us-nexus). Levels come from `classification.yaml` at the brain root (source of truth, #67), with the code defaults as the floor: `hyperguild`/`homelab` → internal; `client-*` → confidential; **anything untagged → confidential (fail-safe)**.
+Capture computes an **effective classification = the strictest across EVERY target it touches** (each insight's `wing`, each ticket's `repo`), then refuses if that effective level is `confidential` and the origin is us-nexus (claude.ai is us-nexus). Levels come from `classification.yaml` at the brain root (source of truth, #67), with the code defaults as the floor: `hyperguild`/`homelab` → internal; `client-*` → confidential; **anything untagged → confidential (fail-safe)**.
 - **Tagged `internal` today** (safe through claude.ai): wings `hyperguild`, `homelab`; repos `brain`, `ai-sessions`, `infra`, `hyperguild`, `homelab`, `tapir`, `agentsquad`, `jepa-fx-risk`, `swedsl`. Treat `classification.yaml` as authoritative — this list is a hint, not gospel.
 - Declare `context.classification: "internal"` for normal homelab work.
- `summary.repos_touched`, insight `wing`s, and ticket `repo`s are classification INPUTS, not free-form metadata — every target must resolve `internal` or the whole capture escalates to `confidential` and the gate refuses via claude.ai. Listing the central homelab repos (incl. `brain`/`ai-sessions`) is now fine; they're tagged. The summary always lands in `ai-sessions` (internal), so the summary path itself never escalates.
+- Insight `wing`s and ticket `repo`s are classification INPUTS, not free-form metadata — every target must resolve `internal` or the whole capture escalates to `confidential` and the gate refuses via claude.ai. Listing the central homelab repos (incl. `brain`/`ai-sessions`) is now fine; they're tagged.
 - If a session genuinely touched **`client-*` or otherwise-untagged** material, it cannot be captured through claude.ai — note that in the verdict rather than trying to force it.

 **GATE — dry-run first, then execute.**
 1. Call `capture` with `dry_run: true`. It validates the whole payload and returns the would-be receipt + `effective_classification`, writing nothing.
-2. **STOP. Show the dry-run receipt** (effective classification, the insights/tickets/summary that would land) and get explicit confirmation.
+2. **STOP. Show the dry-run receipt** (effective classification, the insights/tickets that would land) and get explicit confirmation.
 3. On confirmation, call `capture` again with `dry_run: false`. Read the returned receipt: it is partial-aware (`errors[]`, per-item `ok`). Report exactly what landed.

-If `capture` is **unreachable** (tool not on the connector — e.g. a session that started before a deploy; a tool-list refresh usually fixes it): say so. Only then fall back to the legacy inline path (`gitea:file_write_branch` summary + `brain_write`/`brain_update` + `brain_get` confirm), and note in the verdict that the I5 audit record was NOT produced.
+If `capture` is **unreachable** (tool not on the connector — e.g. a session that started before a deploy; a tool-list refresh usually fixes it): say so. Only then fall back to the legacy inline path (`brain_write`/`brain_update` + `brain_get` confirm), and note in the verdict that the I5 audit record was NOT produced.

 ## Phase 5 — Verdict

 Deliver a final "safe to archive" verdict in the chat. Either:

- **SAFE TO ARCHIVE** — list what landed from the capture receipt (issues closed/filed with numbers, summary path, brain note ids/paths) so the trail is auditable. Then list anything still in the user's queue (e.g. a PR awaiting their merge, a decision owed next session).
+- **SAFE TO ARCHIVE** — list what landed from the capture receipt (issues closed/filed with numbers, brain note ids/paths) so the trail is auditable. Then list anything still in the user's queue (e.g. a PR awaiting their merge, a decision owed next session).
 - **NOT YET** — name the specific gate that wasn't passed, the capture refusal reason, or the per-item error from the receipt, and what to do about it.

 Never claim safe-to-archive if the capture refused, any receipt item errored, or a gated confirmation was declined. The verdict is the skill's contract: if it says safe, the session can be lost without losing the work.
@@ -2,6 +2,8 @@

 **Status:** Decisions resolved 2026-06-22 (§4). Ready for implementation scoping. `capture` is a
 privileged cross-harness write path touching brain + Gitea + ai-sessions.
+**Superseded 2026-07-27:** the ai-sessions summary write path specified below was removed post-ship
+(see `specs/capture-implementation-report.md`). `capture` now touches brain + Gitea only.
 **Tracks:** hyperguild #49.
 **Governed by:** `infra/docs/architecture/01-invariants.md` (I1–I5), the admissibility test in
 `00-synthesis-model.md`, and the distributed-consolidation shape mandated by
@@ -1,6 +1,13 @@
 # Capture capability — implementation report (as-built)

 **Status:** Shipped 2026-06-23, tagged `v0.11.0`. Epic hyperguild #49 (sub-issues #50–#55) closed.
+**Superseded 2026-07-27:** the `summary` → `ai-sessions` write path documented below was removed.
+It wrote a frontmatter shape (`title`/`harness`/`fidelity`/`captured_at`/`repos_touched`) that
+`ai-sessions`' own extract/audit pipeline couldn't parse — invisible to that repo's own audit
+tooling and bypassing its redaction/completeness gates (`ai-sessions#13`). `capture` now persists
+insights → brain and action items → Gitea tickets only. This document is kept as the historical
+as-built record of what shipped in #49; treat every `summary`/ai-sessions reference below as
+retired, not current behaviour.
 **Spec:** `specs/capture-bdd-spec.md` (the design contract this implements).
 **Governed by:** `infra/docs/architecture/01-invariants.md` (I1–I5) + the I2 acceptance ledger entry in `infra/docs/security-baseline.md`.