feat(security): add gitleaks pre-commit scan, wire into task check (infra#39)

Ported from mathias/infra's .gitleaks.toml (2026-08-04) -- same homelab bearer/MCP-token rules, plus a BRAIN_PG_DSN pattern for the hyperguild#20 leak class. Triaged 10 initial findings: 9 were claudewatcher's own scrubber test fixtures (deliberately fake), 1 was gitleaks matching the literal placeholder word "REDACTED" in a plan doc. Both allowlisted with rationale, clean scan confirmed before wiring into `task check`. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_016FQX4RwxyxuQY4yf4XaACL
feat(capture): remove summary->ai-sessions write path
2026-08-04 08:32:42 +02:00 · 2026-07-27 23:17:56 +02:00 · 2026-07-27 22:29:57 +02:00 · 2026-07-27 22:16:00 +02:00 · 2026-07-27 22:09:52 +02:00 · 2026-07-27 22:03:07 +02:00
56 changed files with 1023 additions and 257 deletions
@@ -88,7 +88,7 @@ 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 +97,12 @@ 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,
@@ -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''']
@@ -83,7 +83,7 @@ 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 +92,12 @@ 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,
@@ -101,6 +101,37 @@ 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:
@@ -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

@@ -457,12 +457,8 @@ 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)
@@ -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}
@@ -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.
@@ -259,11 +241,6 @@ 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)
-		}
-	}
 	return effective, events
 }

@@ -309,60 +286,6 @@ 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 +304,3 @@ func firstLine(s string) string {
 	}
 	return s
 }
-
-func shortHash(s string) string {
-	sum := sha256.Sum256([]byte(s))
-	return hex.EncodeToString(sum[:])[:8]
-}
@@ -85,21 +85,6 @@ 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 }
@@ -135,8 +120,8 @@ 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 +136,7 @@ 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 +165,7 @@ 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 +182,7 @@ 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 +201,7 @@ 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 +224,7 @@ 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 +249,7 @@ 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 +272,7 @@ 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 +291,7 @@ 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 +304,6 @@ 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 +311,7 @@ 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 +333,7 @@ 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 +352,7 @@ 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 +372,7 @@ 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 +391,7 @@ 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 +408,7 @@ 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 +423,7 @@ 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(),
@@ -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)
 	}
@@ -58,17 +58,13 @@ func captureToolDescriptor() map[string]any {
 			},
 			"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"},
 		},
 	}
 	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
@@ -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 {
@@ -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/")
+}
@@ -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`.
Author	SHA1	Message	Date
mathiasandClaude Sonnet 5	6e0155a2ab	feat(security): add gitleaks pre-commit scan, wire into task check (infra#39) CI / Lint / Test / Vet (push) Successful in 1m41s Details CI / Mirror to GitHub (push) Successful in 5s Details Ported from mathias/infra's .gitleaks.toml (2026-08-04) -- same homelab bearer/MCP-token rules, plus a BRAIN_PG_DSN pattern for the hyperguild#20 leak class. Triaged 10 initial findings: 9 were claudewatcher's own scrubber test fixtures (deliberately fake), 1 was gitleaks matching the literal placeholder word "REDACTED" in a plan doc. Both allowlisted with rationale, clean scan confirmed before wiring into `task check`. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_016FQX4RwxyxuQY4yf4XaACL	2026-08-04 08:32:42 +02:00
mathiasandClaude Sonnet 5	1cea2c9f78	feat(capture): remove summary->ai-sessions write path CI / Lint / Test / Vet (push) Successful in 29s Details CI / Mirror to GitHub (push) Successful in 4s Details ai-sessions#13: capture's `summary` field wrote a frontmatter shape (title/harness/fidelity/captured_at/repos_touched) that ai-sessions' own extract/audit pipeline can't parse -- silently invisible to that repo's own audit tooling, and bypassing its redaction + Stage2 completeness gates by construction. Only 5 files ever landed this way over 3 weeks; the summary capability's whole value (speed) fights ai-sessions' whole value (redacted, audited, complete), so kill it rather than build a second parse branch. capture now persists insights -> brain and action items -> Gitea tickets only. Removes Summary/SummaryResult/SummaryWriter and all wiring (service, REST body, MCP tool schema); close-session updated to stop assembling a summary payload. specs/capture-*.md kept as historical record with a superseded note -- the feature shipped and is documented, just no longer current behaviour. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01WPdSHbp9Utb2hPFm9wDG59	2026-07-27 23:17:56 +02:00
mathiasandClaude Sonnet 5	9dcd60931a	chore: retrigger CI after gitea-runner RBAC fix (round 6 of the CI/CD outage chain) CI / Lint / Test / Vet (push) Successful in 30s Details CI / Mirror to GitHub (push) Has been skipped Details cd.yml's build+push+ssh chain fully worked last round (infra 707a3c0 landed via CD Bot). Final gap was RBAC: kubectl (new in baked-v6) had no ServiceAccount permissions. Fixed in infra@949b333 (dedicated SA + scoped Role/RoleBinding for flux-system + supervisor, verified live via kubectl auth can-i before this retrigger). No code change here. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Roq1ajWKR5f1hG5Df9wC6A	2026-07-27 22:29:57 +02:00
mathiasandClaude Sonnet 5	1fac90ed2a	fix(cd): pass git.d-ma.be SSH override as -o flags, not an appended ~/.ssh/config line CI / Lint / Test / Vet (push) Successful in 29s Details CI / Mirror to GitHub (push) Successful in 4s Details cd.yml's own $HOME (/data) is a PVC that persists across job runs on this runner. The previous fix (`cb9c251`) appended the corrected HostName to ~/.ssh/config, but a stale 127.0.0.1:30022 entry from an earlier failed run was already there — ssh_config is first-match-wins, so the stale entry silently shadowed the fix and the very next run failed identically. Cleaned the persisted stale entry on the runner directly; this commit removes the append entirely so the step no longer depends on file state surviving (or not surviving) between runs — CLI -o overrides always win. Verified end-to-end against the real infra repo from inside the runner pod (git ls-remote, correctly reached gitea and got a clean auth rejection, not a connection error). Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Roq1ajWKR5f1hG5Df9wC6A	2026-07-27 22:16:00 +02:00
mathiasandClaude Sonnet 5	cb9c2513a4	fix(cd): use in-cluster DNS for git.d-ma.be SSH, not 127.0.0.1:30022 CI / Lint / Test / Vet (push) Successful in 28s Details CI / Mirror to GitHub (push) Successful in 4s Details act_runner moved from koala's bare host network into a k3s pod (2026-07-26); loopback inside that pod's own network namespace never reaches the host, so the git.d-ma.be SSH override (used to push the infra repo update) failed with "Connection refused". Verified TCP+SSH-handshake reachability to gitea-ssh-nodeport.gitea.svc.cluster.local:22 from inside the actual runner pod before committing this. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Roq1ajWKR5f1hG5Df9wC6A	2026-07-27 22:09:52 +02:00
mathiasandClaude Sonnet 5	3617a6c386	chore: retrigger CI after gitea-runner baked-v6 (ssh/skopeo/buildctl/kubectl) CI / Lint / Test / Vet (push) Successful in 28s Details CI / Mirror to GitHub (push) Successful in 4s Details check job passed clean on baked-v5; mirror job then exposed missing ssh/ssh-keyscan. Fixed in infra@707a3c0, which also preemptively adds skopeo/buildctl/kubectl for cd.yml's deploy job. No code change here — retriggering for the full CI->CD end-to-end proof. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Roq1ajWKR5f1hG5Df9wC6A	2026-07-27 22:03:07 +02:00
mathiasandClaude Sonnet 5	1938170131	chore: retrigger CI after gitea-runner gcc/libc6-dev fix (baked-v5) CI / Lint / Test / Vet (push) Successful in 1m12s Details CI / Mirror to GitHub (push) Failing after 1s Details Runner was missing gcc/libc6-dev too (-race requires cgo). Added in infra@0f88aea. No code change here — retriggering CI. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Roq1ajWKR5f1hG5Df9wC6A	2026-07-27 21:55:20 +02:00
mathiasandClaude Sonnet 5	b34717e6b8	chore: retrigger CI after gitea-runner image fix (infra#task-baked-v4) CI / Lint / Test / Vet (push) Failing after 34s Details CI / Mirror to GitHub (push) Has been skipped Details Runner was missing task (taskfile.dev), added in infra@686c90f. No code change here — retriggering CI to confirm the fix. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Roq1ajWKR5f1hG5Df9wC6A	2026-07-27 21:49:33 +02:00
mathiasandClaude Sonnet 5	d8d7e9a307	chore(context): re-sync derived adapters (Python fallback stack, error-handling note) CI / Lint / Test / Vet (push) Failing after 1s Details CI / Mirror to GitHub (push) Has been skipped Details Canonical ~/dev/.context/AGENT.md drifted (Python fallback stack table row, Python error-handling convention) without a hyperguild commit re-running task context:sync since — task check's drift gate has been failing CI on every push since the sprint-1 commits landed, blocking CD entirely (unrelated to those commits' own content: lint/test/vet all pass clean, including -race). Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Roq1ajWKR5f1hG5Df9wC6A	2026-07-27 15:18:38 +02:00
mathiasandClaude Sonnet 5	f0055483a3	fix(watcher): never re-ingest AutoTunnel's own tunnel-candidates log (#88 ) CI / Lint / Test / Vet (push) Failing after 1s Details CI / Mirror to GitHub (push) Has been skipped Details Root cause was neither of the two mechanisms the issue named (CanonicalizeLinks over-canonicalizing, or a schema/prompt bias) — CanonicalizeLinks correctly resolved [[Mission]] because wiki/concepts/mission.md genuinely exists; the extraction prompt has no "mission" bias either. The real bug: watcher.processDir walks brain/raw/ and feeds every .md/.txt/.pdf file to pipeline.Run as source material to extract, with no exclusion for tunnel-candidates-.md — AutoTunnel's own fuzzy-match human-review queue (logFuzzyCandidates writes it into that same raw/ directory). The watcher's next poll re-ingested the raw candidate log itself, and the LLM naturally surfaced "mission" as a wikilink because the log literally lists `(term: "mission")` entries in its content — a generic-word title match DetectTunnels correctly flagged as fuzzy (not auto-tunneled) but which still leaked downstream once treated as real source material. api.ListPending already excludes tunnel-candidates- when listing raw/ for promotion; processDir gets the same exclusion. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Roq1ajWKR5f1hG5Df9wC6A	2026-07-27 14:37:50 +02:00
mathiasandClaude Sonnet 5	6d014c1d0f	fix(ingest): CanonicalizeLinks strips wing:/wiki/ prefix and repairs path-style links (#87 ) CI / Mirror to GitHub (push) Has been skipped Details CI / Lint / Test / Vet (push) Failing after 2s Details plainLinkRE matches any [[...]] without a pipe, including path-prefixed forms like [[wing:homelab/failures/foo]] or [[wiki/agentsquad/decisions/bar]] that the LLM extraction step occasionally emits. Title-lookup against titleToSlug always fails for these (they're paths, not titles), so they were silently left broken. Before falling to the unknown-wikilink warning, strip a known wing:/wiki/ root prefix and emit the clean wing/hall/slug path directly — matching the brain-graph path-style link convention. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Roq1ajWKR5f1hG5Df9wC6A	2026-07-27 14:32:31 +02:00
mathiasandClaude Sonnet 5	1001acfb44	fix(ingest): merge existing frontmatter in writeHallNote instead of stacking (#86 ) CI / Lint / Test / Vet (push) Failing after 1s Details CI / Mirror to GitHub (push) Has been skipped Details opts.Content can already carry its own "---\n...\n---" block (e.g. from an upstream extraction/promotion step). writeHallNote used to prepend a second block unconditionally, making a standard frontmatter parser blind to everything the first block declared (title, tags, ...). splitFrontmatter now pulls the existing block's fields out first; wing/hall/created_at are always fresh-injected, and type/domain/ source_type prefer the note's own existing value over the opts fallback. Remaining existing fields are carried through verbatim into the single merged block. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Roq1ajWKR5f1hG5Df9wC6A	2026-07-26 23:45:36 +02:00
mathiasandClaude Sonnet 5	6ad275b505	fix(ingest): thread source/author/published frontmatter through extraction (#85 ) CI / Lint / Test / Vet (push) Failing after 1s Details CI / Mirror to GitHub (push) Has been skipped Details pipeline.Run parses source/author/published from the raw content's own frontmatter and applies them deterministically to source-type RawPages after LLM extraction — never relies on the LLM to copy them through. buildFrontmatter now emits all three (source pages only) when present. Backfill of the 46 already-affected wiki/sources/*.md notes is a separate concern per the issue, not done here. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Roq1ajWKR5f1hG5Df9wC6A	2026-07-26 23:42:33 +02:00
mathiasandClaude Sonnet 5	b600cc986c	chore(module): rename module github.com/mathiasbq/supervisor -> git.d-ma.be/mathias/hyperguild (#42 ) CI / Lint / Test / Vet (push) Failing after 5s Details CI / Mirror to GitHub (push) Has been skipped Details Aligns module path with canonical Gitea source (infra ADR-0004) and repo name. Binary only, no downstream consumers. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Roq1ajWKR5f1hG5Df9wC6A	2026-07-26 23:37:11 +02:00
mathiasandClaude Opus 4.8	9bdab1c48c	fix(ingest): parse docmark's SSE-framed response, not bare JSON CI / Lint / Test / Vet (push) Successful in 16s Details CI / Mirror to GitHub (push) Has been skipped Details Found via a real live-cluster end-to-end test (POST /ingest-path with a real .docx against the deployed ingestion + docmark): 'decode docmark response: invalid character e looking for beginning of value'. docmark's Streamable-HTTP transport frames every response as SSE (event: message\r\ndata: {...}\r\n\r\n, Content-Type: text/event-stream) -- stateless_http=True removes the need for an initialize handshake/session ID, it does NOT change the wire framing to bare JSON. My original client + its own test mock both assumed bare JSON, so the unit tests passed while the real call failed. sseDataPayload() extracts the data: line before JSON-unmarshaling; falls back to the raw body if no SSE framing is present (forward-compatible). Test mock (docmark_test.go) now emits the SAME framing the live server actually sends, confirmed by directly probing docmark's live response before writing the fix. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-09 08:53:24 +02:00
mathiasandClaude Opus 4.8	6520c2fc4b	feat(ingest): route DOCX/XLSX/PPTX/images through docmark (ADR-0013) CI / Lint / Test / Vet (push) Successful in 16s Details CI / Mirror to GitHub (push) Successful in 4s Details Wires the sovereign docmark MCP server (git.d-ma.be/mathias/docmark) as the converter for formats ingestion previously couldn't handle at all -- DOCX, XLSX, PPTX, PNG/JPG. A single self-contained tools/call POST (docmark runs stateless_http, no session handshake needed) does the conversion. - internal/extract/docmark.go: extractViaDocmark(path) -- reads DOCMARK_URL + DOCMARK_BEARER_TOKEN from env, base64-encodes the file, calls docmark's convert_to_markdown tool, surfaces tool/HTTP errors with context. - internal/extract/extract.go: routes .docx/.xlsx/.pptx/.png/.jpg/.jpeg to it. - internal/api/handler.go: isSupportedExtension() replaces the static supportedExtensions map -- the new extensions are gated on DOCMARK_URL being set, checked per-request. When DOCMARK_URL is unset (e.g. this repo's current deployed state), behavior is byte-for-byte unchanged from today: same 400/silent-skip as before. Zero risk until the env var is actually wired in infra. TDD throughout: docmark.go tested via httptest mock (success, not-configured, tool-error, HTTP-error, all 6 new extensions route correctly); handler-level test proves the DOCMARK_URL gate (docx 400 when unset, 200 when a working mock is configured). Full task check green (fmt/vet/govulncheck/all tests). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-09 08:46:03 +02:00