Compare commits
14
Commits
fcbd1072b6
...
v0.13.2
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
9dcd60931a | ||
|
|
1fac90ed2a | ||
|
|
cb9c2513a4 | ||
|
|
3617a6c386 | ||
|
|
1938170131 | ||
|
|
b34717e6b8 | ||
|
|
d8d7e9a307 | ||
|
|
f0055483a3 | ||
|
|
6d014c1d0f | ||
|
|
1001acfb44 | ||
|
|
6ad275b505 | ||
|
|
b600cc986c | ||
|
|
9bdab1c48c | ||
|
|
6520c2fc4b |
@@ -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,
|
||||
|
||||
+17
-3
@@ -48,9 +48,23 @@ jobs:
|
||||
mkdir -p ~/.ssh
|
||||
echo "${{ secrets.INFRA_DEPLOY_KEY }}" > ~/.ssh/infra_deploy_key
|
||||
chmod 600 ~/.ssh/infra_deploy_key
|
||||
printf 'Host git.d-ma.be\n HostName 127.0.0.1\n Port 30022\n StrictHostKeyChecking no\n' >> ~/.ssh/config
|
||||
|
||||
GIT_SSH_COMMAND="ssh -i ~/.ssh/infra_deploy_key -o IdentitiesOnly=yes" \
|
||||
# In-cluster DNS to gitea's SSH NodePort service, not 127.0.0.1:30022
|
||||
# (that only worked when act_runner ran on koala's bare host network;
|
||||
# from inside the containerized runner's own pod netns, loopback
|
||||
# never reaches the host — "Connection refused", found 2026-07-27).
|
||||
#
|
||||
# Pass as -o overrides on the ssh invocation itself, NOT appended to
|
||||
# ~/.ssh/config: $HOME (/data) is a PVC that persists across job
|
||||
# runs on this runner (same "workspace not ephemeral" class as
|
||||
# brain: act-runner-host-executor-tmp-persists), so an appended
|
||||
# line here would pile up duplicate `Host git.d-ma.be` blocks
|
||||
# across every run — ssh_config is first-match-wins, so a stale
|
||||
# entry from an earlier failed run would silently shadow this
|
||||
# fix forever (exactly what happened once already: this fix's
|
||||
# own first attempt got appended AFTER an already-stale entry
|
||||
# and lost). CLI -o options always win regardless of file state,
|
||||
# so this step is safe to re-run any number of times.
|
||||
GIT_SSH_COMMAND="ssh -i ~/.ssh/infra_deploy_key -o IdentitiesOnly=yes -o HostName=gitea-ssh-nodeport.gitea.svc.cluster.local -o Port=22 -o StrictHostKeyChecking=no" \
|
||||
git clone "${INFRA_REPO}" /tmp/infra-update
|
||||
|
||||
cd /tmp/infra-update
|
||||
|
||||
@@ -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,
|
||||
|
||||
@@ -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
|
||||
|
||||
|
||||
@@ -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)
|
||||
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")
|
||||
}
|
||||
if opts.Domain != "" {
|
||||
fmt.Fprintf(&fm, "domain: %s\n", opts.Domain)
|
||||
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)
|
||||
}
|
||||
@@ -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)
|
||||
}
|
||||
|
||||
@@ -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 {
|
||||
|
||||
if slug, ok := titleToSlug[strings.ToLower(displayName)]; ok {
|
||||
return "[[" + slug + "|" + displayName + "]]"
|
||||
}
|
||||
|
||||
if stripped, hadPrefix := stripPathStylePrefix(displayName); hadPrefix {
|
||||
return "[[" + stripped + "]]"
|
||||
}
|
||||
|
||||
warnings = append(warnings, fmt.Sprintf("unknown wikilink: [[%s]]", displayName))
|
||||
return match
|
||||
}
|
||||
return "[[" + slug + "|" + displayName + "]]"
|
||||
})
|
||||
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"
|
||||
)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user