Compare commits

..
Author SHA1 Message Date
renovate-bot 5b7def5a80 Add renovate.json
CI / Lint / Test / Vet (pull_request) Successful in 1m38s
CI / Mirror to GitHub (pull_request) Skipped
2026-08-15 05:28:45 +00:00
24 changed files with 47 additions and 1339 deletions
-8
View File
@@ -78,14 +78,6 @@ These rules apply to every task across every project, regardless of harness.
- Surface the brain entries and issue numbers in the closing summary so the - Surface the brain entries and issue numbers in the closing summary so the
trail is auditable. trail is auditable.
## CAD sprint patterns
Two CAD sprint archetypes (defs: brain `wiki/homelab/decisions/continuous-agentic-development-cad-concept-2026-06-16`):
- **Inception Sprint** — birth a new repo. Oath-gated close; tag only once every clause holds. Brain: `.../inception-sprint-and-oath`.
- **Sweep Sprint** — clear an existing backlog. Parallel read-only research per issue → sequential one-issue-per-commit execution. Brain: `.../sweep-sprint-and-oath`.
Shared: decisions that are yours, not the agent's, surface as `DECISION NEEDED` (question/options/recommendation/blocks) — ask live if you're present, else comment and wait, never act past it. Live-breaking regressions get `git revert`, never forward-fixed; host-network work skips even read-only research (solo, synchronous, you present). Rule 6's closing ritual only fires once every Oath clause genuinely holds — blocked = descoped-and-tracked, never marked done.
## Default stack ## Default stack
| Layer | Default | Fallback | Last resort | | Layer | Default | Fallback | Last resort |
-8
View File
@@ -73,14 +73,6 @@ These rules apply to every task across every project, regardless of harness.
- Surface the brain entries and issue numbers in the closing summary so the - Surface the brain entries and issue numbers in the closing summary so the
trail is auditable. trail is auditable.
## CAD sprint patterns
Two CAD sprint archetypes (defs: brain `wiki/homelab/decisions/continuous-agentic-development-cad-concept-2026-06-16`):
- **Inception Sprint** — birth a new repo. Oath-gated close; tag only once every clause holds. Brain: `.../inception-sprint-and-oath`.
- **Sweep Sprint** — clear an existing backlog. Parallel read-only research per issue → sequential one-issue-per-commit execution. Brain: `.../sweep-sprint-and-oath`.
Shared: decisions that are yours, not the agent's, surface as `DECISION NEEDED` (question/options/recommendation/blocks) — ask live if you're present, else comment and wait, never act past it. Live-breaking regressions get `git revert`, never forward-fixed; host-network work skips even read-only research (solo, synchronous, you present). Rule 6's closing ritual only fires once every Oath clause genuinely holds — blocked = descoped-and-tracked, never marked done.
## Default stack ## Default stack
| Layer | Default | Fallback | Last resort | | Layer | Default | Fallback | Last resort |
-5
View File
@@ -138,11 +138,6 @@ tasks:
- golangci-lint run ./... - golangci-lint run ./...
- cd ingestion && golangci-lint run ./... - cd ingestion && golangci-lint run ./...
lint:frontmatter:
desc: Report brain notes whose YAML frontmatter does not parse (BRAIN=path, FIX=1 repairs in place)
cmds:
- cd ingestion && go run ./cmd/frontmatterlint {{if .FIX}}-fix{{end}} {{.BRAIN | default "../../brain"}}
test: test:
cmds: cmds:
- go test -race -count=1 ./... - go test -race -count=1 ./...
-53
View File
@@ -1,53 +0,0 @@
// Command frontmatterlint reports markdown notes whose YAML frontmatter does
// not parse, and optionally repairs the ones that only need quoting.
//
// go run ./cmd/frontmatterlint ../../brain # report
// go run ./cmd/frontmatterlint -fix ../../brain # repair in place
//
// Exit codes: 0 clean (or everything repaired), 1 findings remain, 2 the scan
// itself failed.
package main
import (
"flag"
"fmt"
"os"
"github.com/mathiasbq/hyperguild/ingestion/internal/frontmatter"
)
func main() {
fix := flag.Bool("fix", false, "repair files that quoting can rescue, in place")
flag.Parse()
root := "."
if flag.NArg() > 0 {
root = flag.Arg(0)
}
findings, err := frontmatter.Scan(root, *fix)
if err != nil {
fmt.Fprintln(os.Stderr, "frontmatterlint:", err)
os.Exit(2)
}
var unresolved int
for _, f := range findings {
if f.Repaired {
fmt.Printf("repaired %s\n", f.Path)
continue
}
unresolved++
fmt.Printf("BROKEN %s: %v\n", f.Path, f.Err)
}
if unresolved > 0 {
fmt.Fprintf(os.Stderr, "\n%d file(s) with unparseable frontmatter", unresolved)
if !*fix {
fmt.Fprint(os.Stderr, " — re-run with -fix")
}
fmt.Fprintln(os.Stderr)
os.Exit(1)
}
fmt.Printf("✓ frontmatter: %d file(s) repaired, none broken\n", len(findings))
}
+9 -31
View File
@@ -32,7 +32,6 @@ import (
"github.com/mathiasbq/hyperguild/ingestion/internal/pipeline" "github.com/mathiasbq/hyperguild/ingestion/internal/pipeline"
"github.com/mathiasbq/hyperguild/ingestion/internal/reranker" "github.com/mathiasbq/hyperguild/ingestion/internal/reranker"
"github.com/mathiasbq/hyperguild/ingestion/internal/search" "github.com/mathiasbq/hyperguild/ingestion/internal/search"
"github.com/mathiasbq/hyperguild/ingestion/internal/startupretry"
"github.com/mathiasbq/hyperguild/ingestion/internal/vectorstore" "github.com/mathiasbq/hyperguild/ingestion/internal/vectorstore"
"github.com/mathiasbq/hyperguild/ingestion/internal/watcher" "github.com/mathiasbq/hyperguild/ingestion/internal/watcher"
"github.com/mathiasbq/hyperguild/ingestion/internal/webhook" "github.com/mathiasbq/hyperguild/ingestion/internal/webhook"
@@ -315,36 +314,6 @@ func main() {
} }
ctx := context.Background() ctx := context.Background()
// Built before the watcher, the graph backfill and session ingestion, and
// retried rather than fatal (#83). Two separate reasons:
//
// - On a cold cluster boot this pod can beat dex to serving and gets a
// 502 from ingress. Nothing is misconfigured; it simply started first.
// Exiting there meant CrashLoopBackOff redoing the backfill on every
// attempt, with exponential backoff stretching the brain outage.
// - Constructing it first means a genuine config error (wrong issuer,
// bad audience) fails in seconds instead of after all that work.
//
// The budget stays bounded: retrying forever would turn a misconfiguration
// into a process that looks alive and never serves.
jwtValidator, err := startupretry.Do(ctx,
startupretry.Policy{Attempts: 8, Base: time.Second, Max: 30 * time.Second},
func(ctx context.Context) (*chassisauth.JWTValidator, error) {
v, err := chassisauth.NewJWTValidator(ctx, os.Getenv("DEX_ISSUER_URL"), os.Getenv("MCP_AUDIENCE"))
if err != nil {
logger.Warn("oidc discovery not ready, retrying", "err", err)
}
return v, err
})
if err != nil {
logger.Error("build jwt validator", "err", err)
os.Exit(1)
}
if jwtValidator != nil {
logger.Info("jwt auth enabled", "issuer", os.Getenv("DEX_ISSUER_URL"))
}
if watchInterval > 0 { if watchInterval > 0 {
watcher.Start(ctx, watcher.Config{ watcher.Start(ctx, watcher.Config{
BrainDir: brainDir, BrainDir: brainDir,
@@ -449,6 +418,15 @@ func main() {
if webhookHandler != nil { if webhookHandler != nil {
mux.Handle("POST /webhooks/brain-sync", webhookHandler) mux.Handle("POST /webhooks/brain-sync", webhookHandler)
} }
jwtValidator, err := chassisauth.NewJWTValidator(ctx, os.Getenv("DEX_ISSUER_URL"), os.Getenv("MCP_AUDIENCE"))
if err != nil {
logger.Error("build jwt validator", "err", err)
os.Exit(1)
}
if jwtValidator != nil {
logger.Info("jwt auth enabled", "issuer", os.Getenv("DEX_ISSUER_URL"))
}
// Resource-metadata URL is only emitted on 401 when Dex OAuth is // Resource-metadata URL is only emitted on 401 when Dex OAuth is
// configured. Static-Bearer-only deployments leave this empty so // configured. Static-Bearer-only deployments leave this empty so
// clients never see an OAuth challenge. // clients never see an OAuth challenge.
+8 -42
View File
@@ -83,7 +83,7 @@ func (s *Service) Capture(ctx context.Context, in CaptureInput) (CaptureReceipt,
declared, _ = classification.ParseLevel(in.Context.Classification) declared, _ = classification.ParseLevel(in.Context.Classification)
} }
effective, securityEvents, escalators := s.resolveClassification(declared, in) effective, securityEvents := s.resolveClassification(declared, in)
// Server-derived origin governs the I1 gate; a caller-asserted harness // Server-derived origin governs the I1 gate; a caller-asserted harness
// label that names a different zone is descriptive-only and logged as a // label that names a different zone is descriptive-only and logged as a
@@ -107,8 +107,8 @@ func (s *Service) Capture(ctx context.Context, in CaptureInput) (CaptureReceipt,
Items: nil, // refused before any write Items: nil, // refused before any write
SecurityEvents: append(securityEvents, "I1 refusal: confidential capture via us-nexus origin"), SecurityEvents: append(securityEvents, "I1 refusal: confidential capture via us-nexus origin"),
}, AuditCentral) }, AuditCentral)
return CaptureReceipt{}, fmt.Errorf("%w: effective classification confidential through %s origin (%s)", return CaptureReceipt{}, fmt.Errorf("%w: effective classification confidential through %s origin",
ErrSovereigntyRefused, in.Context.Origin, escalationReason(escalators)) ErrSovereigntyRefused, in.Context.Origin)
} }
receipt := CaptureReceipt{ receipt := CaptureReceipt{
@@ -221,28 +221,15 @@ func (s *Service) validate(in CaptureInput) error {
return nil return nil
} }
// resolveClassification computes the effective level (stricter of declared // resolveClassification computes the effective level (stricter of
// and every target's derived level), collects a security event whenever the // declared and every target's derived level) and collects a security
// caller under-declared relative to a target floor, and names the targets // event whenever the caller under-declared relative to a target floor.
// that carry the strictest level. func (s *Service) resolveClassification(declared classification.Level, in CaptureInput) (classification.Level, []string) {
//
// That third return is what makes an I1 refusal actionable. A caller sending
// twenty tickets gets one refusal; without the offending target it cannot
// tell which repo tripped the gate, and infra#265 shows what happens next —
// the caller concluded the tickets ARRAY was broken, built a fallback of
// twenty individual calls, and filed a bug against the wrong thing.
func (s *Service) resolveClassification(declared classification.Level, in CaptureInput) (classification.Level, []string, []string) {
effective := declared effective := declared
var events []string var events []string
derivedFor := map[string]classification.Level{}
var order []string
consider := func(kind classification.TargetKind, name string) { consider := func(kind classification.TargetKind, name string) {
derived := s.policy.Derive(classification.Target{Kind: kind, Name: name}) derived := s.policy.Derive(classification.Target{Kind: kind, Name: name})
effective = classification.Stricter(effective, derived) effective = classification.Stricter(effective, derived)
if _, seen := derivedFor[name]; !seen {
derivedFor[name] = derived
order = append(order, name)
}
if declared < derived { if declared < derived {
events = append(events, fmt.Sprintf("classification under-declared: declared=%s target=%s(%s) derived=%s", events = append(events, fmt.Sprintf("classification under-declared: declared=%s target=%s(%s) derived=%s",
declared, name, kindString(kind), derived)) declared, name, kindString(kind), derived))
@@ -254,28 +241,7 @@ func (s *Service) resolveClassification(declared classification.Level, in Captur
for _, tk := range in.Tickets { for _, tk := range in.Tickets {
consider(classification.RepoTarget, tk.Repo) consider(classification.RepoTarget, tk.Repo)
} }
return effective, events
// Only targets that actually reach the effective level are named: at
// twenty tickets, listing the innocent ones is noise that hides the one
// that matters.
var escalators []string
for _, name := range order {
if derivedFor[name] == effective && effective > declared {
escalators = append(escalators, name)
}
}
return effective, events, escalators
}
// escalationReason renders why the effective classification landed where it
// did, for an operator reading a refusal. Naming the caller's own declaration
// matters as much as naming a target: "you asked for this" and "a repo you
// touched required it" call for different fixes.
func escalationReason(escalators []string) string {
if len(escalators) == 0 {
return "declared by the caller; no target required it"
}
return "required by: " + strings.Join(escalators, ", ")
} }
func (s *Service) persistInsight(ctx context.Context, ins Insight) (InsightResult, string, error) { func (s *Service) persistInsight(ctx context.Context, ins Insight) (InsightResult, string, error) {
+1 -105
View File
@@ -3,7 +3,6 @@ package capture
import ( import (
"context" "context"
"errors" "errors"
"fmt"
"strings" "strings"
"testing" "testing"
"time" "time"
@@ -60,18 +59,12 @@ type fakeTracker struct {
closed []int closed []int
comments []int comments []int
err error err error
// failOnTitle makes CreateIssue fail for one specific title, so a
// partial-failure receipt can be exercised without failing every item.
failOnTitle string
} }
func (f *fakeTracker) CreateIssue(_ context.Context, repo, title, _ string) (IssueRef, error) { func (f *fakeTracker) CreateIssue(_ context.Context, repo, title, _ string) (IssueRef, error) {
if f.err != nil { if f.err != nil {
return IssueRef{}, f.err return IssueRef{}, f.err
} }
if f.failOnTitle != "" && title == f.failOnTitle {
return IssueRef{}, errors.New("tracker refused this one")
}
f.created = append(f.created, repo+":"+title) f.created = append(f.created, repo+":"+title)
return IssueRef{Repo: repo, Number: 100 + len(f.created), URL: "https://git/" + repo + "/issues/x"}, nil return IssueRef{Repo: repo, Number: 100 + len(f.created), URL: "https://git/" + repo + "/issues/x"}, nil
} }
@@ -94,9 +87,7 @@ func (f *fakeTracker) CommentIssue(_ context.Context, repo string, number int, _
// fakePolicy derives from an explicit map; default Internal so tests pin // fakePolicy derives from an explicit map; default Internal so tests pin
// behaviour without depending on the real defaulting. // behaviour without depending on the real defaulting.
type fakePolicy struct { type fakePolicy struct{ tags map[string]classification.Level }
tags map[string]classification.Level
}
func (p fakePolicy) Derive(t classification.Target) classification.Level { func (p fakePolicy) Derive(t classification.Target) classification.Level {
if lvl, ok := p.tags[t.Name]; ok { if lvl, ok := p.tags[t.Name]; ok {
@@ -443,98 +434,3 @@ func TestCaptureDryRunSkipsAuditGate(t *testing.T) {
assert.True(t, rec.DryRun) assert.True(t, rec.DryRun)
assert.Empty(t, au.entries) assert.Empty(t, au.entries)
} }
// ---- hyperguild#91 part 1 -------------------------------------------------
//
// The reported symptom was "capture with a tickets array fails" (infra#265:
// 20 tickets errored, 5 errored, caller fell back to 20 individual
// issue_create calls). The array was never the failing dimension — every
// ticket targeted a client repo, and the I1 gate refuses that through a
// us-nexus origin at ANY length. The refusal did not say which target
// escalated the classification, so it read as a malfunction.
func TestCapture_TicketsArrayWorksAtLengthOne(t *testing.T) {
b, tr, au := &fakeBrain{}, &fakeTracker{}, &fakeAudit{}
svc := newSvc(b, tr, fakePolicy{}, au)
rec, err := svc.Capture(context.Background(), CaptureInput{
Context: baseCtx(),
Tickets: []Ticket{{Repo: "hyperguild", Action: "create", Title: "one", Body: "b"}},
})
require.NoError(t, err)
require.Len(t, rec.Tickets, 1)
assert.True(t, rec.Tickets[0].OK)
assert.Len(t, tr.created, 1)
assert.Empty(t, rec.Errors)
}
func TestCapture_TicketsArrayWorksAtLengthMany(t *testing.T) {
b, tr, au := &fakeBrain{}, &fakeTracker{}, &fakeAudit{}
svc := newSvc(b, tr, fakePolicy{}, au)
in := CaptureInput{Context: baseCtx()}
for i := range 20 {
in.Tickets = append(in.Tickets, Ticket{
Repo: "hyperguild", Action: "create", Title: fmt.Sprintf("t%02d", i), Body: "b",
})
}
rec, err := svc.Capture(context.Background(), in)
require.NoError(t, err)
require.Len(t, rec.Tickets, 20, "one receipt entry per ticket")
for i, r := range rec.Tickets {
assert.True(t, r.OK, "ticket %d failed: %+v", i, rec.Errors)
}
assert.Len(t, tr.created, 20)
assert.Empty(t, rec.Errors)
}
func TestCapture_OneFailingTicketDoesNotSinkTheRest(t *testing.T) {
// infra#265 asked explicitly: "if ticket 3 of 5 fails, what happened to
// 1 and 2?" They land, and the receipt says so per item.
b, au := &fakeBrain{}, &fakeAudit{}
tr := &fakeTracker{failOnTitle: "boom"}
svc := newSvc(b, tr, fakePolicy{}, au)
rec, err := svc.Capture(context.Background(), CaptureInput{
Context: baseCtx(),
Tickets: []Ticket{
{Repo: "hyperguild", Action: "create", Title: "ok-1", Body: "b"},
{Repo: "hyperguild", Action: "create", Title: "boom", Body: "b"},
{Repo: "hyperguild", Action: "create", Title: "ok-3", Body: "b"},
},
})
require.NoError(t, err, "a per-item failure is a partial receipt, not a call error")
require.Len(t, rec.Tickets, 3)
assert.True(t, rec.Tickets[0].OK)
assert.False(t, rec.Tickets[1].OK)
assert.True(t, rec.Tickets[2].OK)
require.Len(t, rec.Errors, 1)
assert.Contains(t, rec.Errors[0].Item, "ticket[1]")
}
func TestCapture_I1RefusalNamesWhatEscalatedTheClassification(t *testing.T) {
// The actual defect behind infra#265. Without the offending target in
// the message, a caller with 20 tickets cannot tell which repo tripped
// the gate — and reasonably concludes the array itself is broken.
b, tr, au := &fakeBrain{}, &fakeTracker{}, &fakeAudit{}
pol := fakePolicy{tags: map[string]classification.Level{"trucker-ecommerce": classification.Confidential}}
svc := newSvc(b, tr, pol, au)
ctx := baseCtx()
ctx.Origin = ZoneUSNexus
_, err := svc.Capture(context.Background(), CaptureInput{
Context: ctx,
Tickets: []Ticket{
{Repo: "hyperguild", Action: "create", Title: "fine", Body: "b"},
{Repo: "trucker-ecommerce", Action: "create", Title: "client work", Body: "b"},
},
})
require.ErrorIs(t, err, ErrSovereigntyRefused)
assert.Contains(t, err.Error(), "trucker-ecommerce",
"the refusal must name the target that escalated the classification")
assert.NotContains(t, err.Error(), "hyperguild",
"only the offending target, or the message is noise at 20 tickets")
assert.Empty(t, tr.created, "refused before any write")
}
@@ -1,143 +0,0 @@
// Package frontmatter lints and repairs the YAML frontmatter block of a
// markdown note.
//
// Notes written directly — hand-authored, or promoted from brain/raw/ — do not
// pass through pipeline.BuildPages, so nothing quotes their scalars. A title
// containing an unescaped ": " then produces a block that yaml.Unmarshal
// rejects with "mapping values are not allowed here", and every consumer that
// reads frontmatter silently skips the note.
//
// Fix is deliberately conservative: it only adds quoting, never reorders or
// rewrites, and it refuses to return a document that still does not parse.
package frontmatter
import (
"bytes"
"fmt"
"regexp"
"strings"
"gopkg.in/yaml.v3"
)
const fence = "---"
// Lint reports whether doc's frontmatter block parses as YAML.
//
// A document with no frontmatter block, or with an unterminated one, is not an
// error: there is nothing claiming to be YAML.
func Lint(doc []byte) error {
b, ok := block(doc)
if !ok {
return nil
}
var v any
if err := yaml.Unmarshal(b, &v); err != nil {
return fmt.Errorf("frontmatter: %w", err)
}
return nil
}
// Fix quotes unquoted scalars whose value breaks YAML parsing and returns the
// repaired document.
//
// It returns (doc, false, nil) when the document already parses, and
// (doc, false, err) when quoting cannot rescue it — an unfixable document is
// always returned byte-identical, never half-repaired.
func Fix(doc []byte) ([]byte, bool, error) {
if err := Lint(doc); err == nil {
return doc, false, nil
}
b, ok := block(doc)
if !ok {
// Lint only fails when there is a block, so this is unreachable in
// practice; return the original rather than guess.
return doc, false, nil
}
fixed := quoteScalars(b)
if bytes.Equal(fixed, b) {
return doc, false, fmt.Errorf("frontmatter: not repairable by quoting: %w", Lint(doc))
}
var v any
if err := yaml.Unmarshal(fixed, &v); err != nil {
return doc, false, fmt.Errorf("frontmatter: quoting did not repair the block: %w", err)
}
_, rest, _ := split(doc)
out := []byte(fence + "\n")
out = append(out, fixed...)
out = append(out, []byte(fence)...)
out = append(out, rest...)
return out, true, nil
}
// mappingLine matches "key: value" at any indentation, capturing the prefix so
// it can be re-emitted untouched.
//
// Sequence items ("- value") are deliberately not handled: "- foo: bar" is
// valid YAML, so a document containing one does not reach Fix in the first
// place. See the Lint table for why that gap is left open.
var mappingLine = regexp.MustCompile(`^(\s*[A-Za-z_][\w.-]*:[ \t]+)(\S.*)$`)
// quoteScalars single-quotes every unquoted scalar value in the block that
// contains a colon. Values that are already quoted, or that carry YAML syntax
// this package has no business rewriting, are left alone.
func quoteScalars(block []byte) []byte {
lines := strings.Split(string(block), "\n")
for i, line := range lines {
m := mappingLine.FindStringSubmatch(line)
if m == nil {
continue
}
prefix, value := m[1], m[2]
if !needsQuoting(value) {
continue
}
lines[i] = prefix + "'" + strings.ReplaceAll(value, "'", "''") + "'"
}
return []byte(strings.Join(lines, "\n"))
}
// needsQuoting reports whether a scalar value has to be quoted to load as the
// string it plainly is.
//
// The test is YAML's own parser rather than a pattern: ask whether the value
// stands alone as the right-hand side of a mapping. Heuristics get this wrong
// in both directions — `title: "Foo" — bar` opens with a quote but is not
// quoted, and a value may contain a colon inside quotes and be perfectly fine.
//
// Anything that already parses is left alone, whatever it parses into — a flow
// collection, a number, a bool. It is not broken, and quoting would change its
// type.
func needsQuoting(value string) bool {
if strings.HasPrefix(value, "|") || strings.HasPrefix(value, ">") {
return false // block scalar; its content is not parsed as YAML
}
var probe map[string]any
return yaml.Unmarshal([]byte("v: "+value+"\n"), &probe) != nil
}
// block returns the raw YAML between the opening and closing fences.
func block(doc []byte) ([]byte, bool) {
b, _, ok := split(doc)
return b, ok
}
// split returns the frontmatter block and everything from the closing fence
// onward (the closing fence itself excluded, its trailing newline included).
func split(doc []byte) (block, rest []byte, ok bool) {
s := string(doc)
if !strings.HasPrefix(s, fence+"\n") {
return nil, nil, false
}
body := s[len(fence)+1:]
idx := strings.Index(body, "\n"+fence)
if idx < 0 {
return nil, nil, false
}
return []byte(body[:idx+1]), []byte(body[idx+1+len(fence):]), true
}
@@ -1,188 +0,0 @@
// ingestion/internal/frontmatter/frontmatter_test.go
package frontmatter
import (
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"gopkg.in/yaml.v3"
)
func TestLint(t *testing.T) {
tests := []struct {
name string
doc string
wantErr bool
}{
{
name: "no frontmatter block is not an error",
doc: "# Just a heading\n\nSome body text.\n",
},
{
name: "quoted title parses",
doc: "---\ntitle: 'Headless dispatch runs: Bash is denied'\n---\n\nbody\n",
},
{
name: "plain title parses",
doc: "---\ntitle: A simple title\nwing: homelab\n---\n\nbody\n",
},
{
name: "unquoted colon in title does not parse",
doc: "---\ntitle: Headless dispatch runs: Bash is denied — use gitea MCP\nwing: homelab\n---\n\nbody\n",
wantErr: true,
},
{
// Known gap, deliberately not fixed here: this parses, but the
// item becomes map[string]any{"Headless dispatch": "denied"}
// rather than a string. It is a silent type corruption, not a
// parse failure, so repairing it would rewrite documents that
// currently load — out of scope for a lint about broken YAML.
name: "unquoted colon in a list item parses as a mapping, not an error",
doc: "---\ntitle: Fine\naliases:\n - Headless dispatch: denied\n---\n\nbody\n",
},
{
name: "unterminated frontmatter is not treated as frontmatter",
doc: "---\ntitle: no closing fence\n\nbody\n",
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
err := Lint([]byte(tt.doc))
if tt.wantErr {
require.Error(t, err)
return
}
require.NoError(t, err)
})
}
}
func TestFix(t *testing.T) {
tests := []struct {
name string
doc string
wantChanged bool
wantKey string
wantValue string
}{
{
name: "quotes an unquoted title containing a colon",
doc: "---\ntitle: Headless dispatch runs: Bash is denied — use gitea MCP\nwing: homelab\n---\n\nbody\n",
wantChanged: true,
wantKey: "title",
wantValue: "Headless dispatch runs: Bash is denied — use gitea MCP",
},
{
// Parses already (see the Lint table), so Fix must leave it alone
// rather than rewrite a document that loads.
name: "leaves a colon-bearing list item alone because it already parses",
doc: "---\ntitle: Fine\naliases:\n - Headless dispatch: denied\n---\n\nbody\n",
wantChanged: false,
wantKey: "title",
wantValue: "Fine",
},
{
name: "escapes an embedded single quote when quoting",
doc: "---\ntitle: Don't do this: it breaks\n---\n\nbody\n",
wantChanged: true,
wantKey: "title",
wantValue: "Don't do this: it breaks",
},
{
// The value opens with a double quote and then keeps going after
// the closing one, so YAML reads it as a quoted scalar followed by
// junk. Treating "starts with a quote" as "already quoted" leaves
// this broken forever.
name: "quotes a value that only looks quoted",
doc: "---\ntitle: \"Evaluation Driven Generation\" — a TDD-style scaffold\ntags: [a, b]\n---\n\nbody\n",
wantChanged: true,
wantKey: "title",
wantValue: "\"Evaluation Driven Generation\" — a TDD-style scaffold",
},
{
name: "leaves an already-valid document untouched",
doc: "---\ntitle: 'Already quoted: fine'\nwing: homelab\n---\n\nbody\n",
wantChanged: false,
wantKey: "title",
wantValue: "Already quoted: fine",
},
{
name: "leaves a document with no frontmatter untouched",
doc: "# Heading\n\nbody: with a colon\n",
wantChanged: false,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
got, changed, err := Fix([]byte(tt.doc))
require.NoError(t, err)
assert.Equal(t, tt.wantChanged, changed)
if !tt.wantChanged {
assert.Equal(t, tt.doc, string(got), "unchanged docs must be returned byte-identical")
}
// Whatever came back must parse — that is the whole point.
require.NoError(t, Lint(got), "Fix must not return a document that still fails to parse")
if tt.wantKey == "" {
return
}
block, ok := block(got)
require.True(t, ok)
var m map[string]any
require.NoError(t, yaml.Unmarshal(block, &m))
assert.Equal(t, tt.wantValue, m[tt.wantKey], "the value must survive quoting unchanged")
})
}
}
func TestFix_LeavesStructuredValuesStructured(t *testing.T) {
// Only the broken scalar may be touched. A flow sequence on a neighbouring
// line still has to load as a sequence afterwards, not as a string.
doc := "---\ntitle: Broken: here\ntags: [prompting, llm]\ncount: 3\n---\n\nbody\n"
got, changed, err := Fix([]byte(doc))
require.NoError(t, err)
require.True(t, changed)
b, ok := block(got)
require.True(t, ok)
var m map[string]any
require.NoError(t, yaml.Unmarshal(b, &m))
assert.Equal(t, "Broken: here", m["title"])
assert.Equal(t, []any{"prompting", "llm"}, m["tags"])
assert.Equal(t, 3, m["count"])
}
func TestFix_PreservesBodyExactly(t *testing.T) {
body := "\nThe body has: colons, 'quotes', and\n---\na horizontal rule.\n"
doc := "---\ntitle: Broken: title\n---" + body
got, changed, err := Fix([]byte(doc))
require.NoError(t, err)
require.True(t, changed)
assert.True(t, len(got) > 0)
_, rest, ok := split([]byte(doc))
require.True(t, ok)
_, gotRest, ok := split(got)
require.True(t, ok)
assert.Equal(t, string(rest), string(gotRest), "the body must not be touched")
}
func TestFix_RefusesToReturnAnUnparseableResult(t *testing.T) {
// A frontmatter block that quoting cannot rescue: the structure itself is
// broken, not a scalar. Fix must return the original and an error rather
// than a half-repaired document.
doc := "---\ntitle: fine\n\tbad: tab-indented mapping\n - stray list item\n---\n\nbody\n"
got, changed, err := Fix([]byte(doc))
require.Error(t, err)
assert.False(t, changed)
assert.Equal(t, doc, string(got), "an unfixable document must come back byte-identical")
}
-84
View File
@@ -1,84 +0,0 @@
// ingestion/internal/frontmatter/scan.go
package frontmatter
import (
"fmt"
"io/fs"
"os"
"path/filepath"
"strings"
"unicode/utf8"
)
// Finding is one markdown file whose frontmatter does not parse.
type Finding struct {
Path string // relative to the scanned root
Err error // why it does not parse, or why the repair was refused
Repaired bool // true only when fix was requested and the file was rewritten
}
// Scan walks root for *.md files whose frontmatter fails to parse.
//
// With fix set, each finding that quoting can rescue is rewritten in place;
// anything quoting cannot rescue is reported and left byte-identical. A file
// that cannot be read or decoded is reported as a finding rather than aborting
// the walk — one poisoned note must not hide the other findings.
func Scan(root string, fix bool) ([]Finding, error) {
var found []Finding
err := filepath.WalkDir(root, func(path string, d fs.DirEntry, err error) error {
if err != nil {
return err
}
if d.IsDir() || !strings.EqualFold(filepath.Ext(path), ".md") {
return nil
}
rel, relErr := filepath.Rel(root, path)
if relErr != nil {
rel = path
}
doc, readErr := os.ReadFile(path)
if readErr != nil {
found = append(found, Finding{Path: rel, Err: readErr})
return nil
}
if !utf8.Valid(doc) {
found = append(found, Finding{Path: rel, Err: fmt.Errorf("not valid UTF-8")})
return nil
}
if lintErr := Lint(doc); lintErr == nil {
return nil
}
if !fix {
found = append(found, Finding{Path: rel, Err: Lint(doc)})
return nil
}
repaired, changed, fixErr := Fix(doc)
if fixErr != nil || !changed {
found = append(found, Finding{Path: rel, Err: fixErr})
return nil
}
if writeErr := writeFilePreservingMode(path, repaired); writeErr != nil {
found = append(found, Finding{Path: rel, Err: writeErr})
return nil
}
found = append(found, Finding{Path: rel, Repaired: true})
return nil
})
if err != nil {
return nil, fmt.Errorf("scan %s: %w", root, err)
}
return found, nil
}
func writeFilePreservingMode(path string, content []byte) error {
mode := fs.FileMode(0o644)
if info, err := os.Stat(path); err == nil {
mode = info.Mode().Perm()
}
return os.WriteFile(path, content, mode)
}
-103
View File
@@ -1,103 +0,0 @@
// ingestion/internal/frontmatter/scan_test.go
package frontmatter
import (
"os"
"path/filepath"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func writeTree(t *testing.T, files map[string]string) string {
t.Helper()
root := t.TempDir()
for name, content := range files {
path := filepath.Join(root, name)
require.NoError(t, os.MkdirAll(filepath.Dir(path), 0o755))
require.NoError(t, os.WriteFile(path, []byte(content), 0o644))
}
return root
}
const (
brokenDoc = "---\ntitle: Broken: title here\nwing: homelab\n---\n\nbody\n"
validDoc = "---\ntitle: 'Fine: quoted'\n---\n\nbody\n"
)
func TestScan_ReportsOnlyBrokenFiles(t *testing.T) {
root := writeTree(t, map[string]string{
"wiki/a/broken.md": brokenDoc,
"wiki/a/valid.md": validDoc,
"wiki/b/plain.md": "# no frontmatter\n\nbody: with colon\n",
"wiki/a/notes.txt": brokenDoc, // not markdown — must be ignored
})
found, err := Scan(root, false)
require.NoError(t, err)
require.Len(t, found, 1)
assert.Equal(t, "wiki/a/broken.md", found[0].Path)
assert.False(t, found[0].Repaired)
assert.Error(t, found[0].Err)
// Dry run must not touch the file.
got, err := os.ReadFile(filepath.Join(root, "wiki/a/broken.md"))
require.NoError(t, err)
assert.Equal(t, brokenDoc, string(got))
}
func TestScan_FixWritesRepairedFilesAndLeavesTheRestAlone(t *testing.T) {
root := writeTree(t, map[string]string{
"wiki/a/broken.md": brokenDoc,
"wiki/a/valid.md": validDoc,
})
found, err := Scan(root, true)
require.NoError(t, err)
require.Len(t, found, 1)
assert.True(t, found[0].Repaired)
assert.NoError(t, found[0].Err)
repaired, err := os.ReadFile(filepath.Join(root, "wiki/a/broken.md"))
require.NoError(t, err)
require.NoError(t, Lint(repaired), "the repaired file must parse")
assert.Contains(t, string(repaired), "title: 'Broken: title here'")
assert.Contains(t, string(repaired), "wing: homelab", "untouched keys must survive")
untouched, err := os.ReadFile(filepath.Join(root, "wiki/a/valid.md"))
require.NoError(t, err)
assert.Equal(t, validDoc, string(untouched))
// Second pass finds nothing — the repair is idempotent and complete.
again, err := Scan(root, true)
require.NoError(t, err)
assert.Empty(t, again)
}
func TestScan_ReportsUnfixableWithoutWriting(t *testing.T) {
unfixable := "---\ntitle: fine\n\tbad: tab-indented\n - stray\n---\n\nbody\n"
root := writeTree(t, map[string]string{"wiki/x.md": unfixable})
found, err := Scan(root, true)
require.NoError(t, err)
require.Len(t, found, 1)
assert.False(t, found[0].Repaired)
assert.Error(t, found[0].Err)
got, err := os.ReadFile(filepath.Join(root, "wiki/x.md"))
require.NoError(t, err)
assert.Equal(t, unfixable, string(got), "an unfixable file must be left exactly as it was")
}
func TestScan_ReportsUndecodableFilesInsteadOfFailingTheRun(t *testing.T) {
root := writeTree(t, map[string]string{"wiki/ok.md": validDoc})
require.NoError(t, os.WriteFile(filepath.Join(root, "wiki/bad-bytes.md"),
[]byte{'-', '-', '-', '\n', 0xff, 0xfe, '\n', '-', '-', '-', '\n'}, 0o644))
found, err := Scan(root, false)
require.NoError(t, err, "one unreadable file must not abort the whole scan")
require.Len(t, found, 1)
assert.Equal(t, "wiki/bad-bytes.md", found[0].Path)
}
+7
View File
@@ -105,6 +105,13 @@ func (s *Server) tools() []map[string]any {
"target": str("path of target note (must be in a different wing)"), "target": str("path of target note (must be in a different wing)"),
}), }),
}, },
{
"name": "brain_index",
"description": "Regenerate _index.md (Map of Content) for one or all wings under brain/wiki/. Auto-called after brain_write with wing+hall.",
"inputSchema": schema([]string{}, map[string]any{
"wing": str("optional wing to index; if absent, rebuilds every wing"),
}),
},
{ {
"name": "brain_ingest_raw", "name": "brain_ingest_raw",
"description": "Ingest pre-structured pages into the brain wiki, bypassing the LLM extraction step.", "description": "Ingest pre-structured pages into the brain wiki, bypassing the LLM extraction step.",
-76
View File
@@ -1,76 +0,0 @@
package mcp
import (
"time"
"github.com/mathiasbq/hyperguild/ingestion/internal/api"
)
// pendingNudgeThreshold is how old a raw/ note has to be before brain_context
// mentions the queue. Two weeks: long enough that a note written this sprint
// does not nag, short enough that four items cannot sit unnoticed for three
// months again (#82).
const pendingNudgeThreshold = 14 * 24 * time.Hour
// PendingNudge is the in-session reminder that the promote/reject queue has
// items waiting. It is advisory: a count, an age, and how to look.
type PendingNudge struct {
Pending int `json:"pending"` // everything in the queue
Aging int `json:"aging"` // those past the threshold
Oldest string `json:"oldest"` // filename of the oldest pending note
OldestDays int `json:"oldest_days"` // its age, in whole days
Hint string `json:"hint"`
}
// pendingNudge summarises the raw/ review queue, or returns nil when there is
// nothing worth saying.
//
// The trigger is the missing half of the queue (#82): brain_pending has always
// existed, and four real items still sat unreviewed from 2026-04-23 to
// 2026-07-15 because nothing ever prompted anyone to call it. The system
// should be what remembers the queue exists.
//
// Threshold-gated on purpose. A notice on every context call is one people
// learn to skip, which reproduces the original failure with extra steps.
//
// It never promotes, rejects, or reorders anything. Age is a reason to ask a
// human, not a verdict — an old note may be exactly right to promote once
// someone finally looks at it.
func pendingNudge(brainDir string, now time.Time, threshold time.Duration) *PendingNudge {
pending, err := api.ListPending(brainDir)
if err != nil || len(pending) == 0 {
// brain_context is a hot path; a broken queue degrades to silence
// rather than failing the call that asked for project context.
return nil
}
var aging int
var oldestName string
var oldestAge time.Duration
for _, p := range pending {
created, perr := time.Parse(time.RFC3339, p.CreatedAt)
if perr != nil {
continue // an unparseable timestamp is not evidence of age
}
age := now.Sub(created)
if age >= threshold {
aging++
}
if age > oldestAge {
oldestAge, oldestName = age, p.Filename
}
}
if aging == 0 {
return nil
}
return &PendingNudge{
Pending: len(pending),
Aging: aging,
Oldest: oldestName,
OldestDays: int(oldestAge.Hours() / 24),
Hint: "call brain_pending to review; nothing is promoted or rejected automatically",
}
}
@@ -1,115 +0,0 @@
package mcp
import (
"context"
"encoding/json"
"os"
"path/filepath"
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// writePending drops a raw/ note whose created_at is age old.
func writePending(t *testing.T, brainDir, name string, age time.Duration, now time.Time) {
t.Helper()
raw := filepath.Join(brainDir, "raw")
require.NoError(t, os.MkdirAll(raw, 0o755))
body := "---\ncreated_at: " + now.Add(-age).UTC().Format(time.RFC3339) + "\n---\n\nnote body\n"
require.NoError(t, os.WriteFile(filepath.Join(raw, name), []byte(body), 0o644))
}
func TestPendingNudge_SilentWhenNothingIsPending(t *testing.T) {
// No queue, no nudge. A notice that fires every session is one people
// learn to skip, which is how the queue got ignored for three months in
// the first place (#82).
got := pendingNudge(t.TempDir(), time.Now(), 14*24*time.Hour)
assert.Nil(t, got)
}
func TestPendingNudge_SilentWhileEverythingIsBelowTheThreshold(t *testing.T) {
now := time.Now()
dir := t.TempDir()
writePending(t, dir, "fresh.md", 2*24*time.Hour, now)
got := pendingNudge(dir, now, 14*24*time.Hour)
assert.Nil(t, got, "a two-day-old note is not aging")
}
func TestPendingNudge_ReportsCountAndOldestAgeOnceSomethingAges(t *testing.T) {
now := time.Now()
dir := t.TempDir()
writePending(t, dir, "old.md", 100*24*time.Hour, now)
writePending(t, dir, "older.md", 120*24*time.Hour, now)
writePending(t, dir, "fresh.md", 1*24*time.Hour, now)
got := pendingNudge(dir, now, 14*24*time.Hour)
require.NotNil(t, got)
// All three are pending; the threshold decides whether to speak, not
// what to count. Someone opening the queue sees the whole queue.
assert.Equal(t, 3, got.Pending)
assert.Equal(t, 2, got.Aging)
assert.Equal(t, 120, got.OldestDays)
assert.Equal(t, "older.md", got.Oldest)
}
func TestPendingNudge_NeverDecidesAnything(t *testing.T) {
// Aging is a trigger to ask a human, never a verdict. The nudge must
// carry no action and must leave the queue exactly as it found it.
now := time.Now()
dir := t.TempDir()
writePending(t, dir, "ancient.md", 365*24*time.Hour, now)
before, err := os.ReadDir(filepath.Join(dir, "raw"))
require.NoError(t, err)
got := pendingNudge(dir, now, 14*24*time.Hour)
require.NotNil(t, got)
after, err := os.ReadDir(filepath.Join(dir, "raw"))
require.NoError(t, err)
assert.Len(t, after, len(before), "the nudge must not promote or reject anything")
assert.Contains(t, got.Hint, "brain_pending", "the nudge should say how to look, not act")
}
func TestPendingNudge_SurvivesAnUnreadableQueue(t *testing.T) {
// brain_context is a hot path; a broken raw/ dir must degrade to silence
// rather than failing the whole context call.
dir := t.TempDir()
require.NoError(t, os.WriteFile(filepath.Join(dir, "raw"), []byte("not a directory"), 0o644))
assert.NotPanics(t, func() {
assert.Nil(t, pendingNudge(dir, time.Now(), 14*24*time.Hour))
})
}
func TestBrainContext_CarriesTheNudgeWithoutFailingWhenTheQueueIsEmpty(t *testing.T) {
// The wiring, not the summary: a nudge that never reaches a caller is the
// same as no nudge, and brain_context must still work with no queue.
dir := t.TempDir()
srv := NewServer(dir, nil, nil, nil)
raw, err := srv.brainContext(context.Background(),
json.RawMessage(`{"project_root":"/home/mathias/dev/AGENTS/hyperguild"}`))
require.NoError(t, err)
var empty map[string]any
require.NoError(t, json.Unmarshal(raw, &empty))
assert.NotContains(t, empty, "pending_review", "silence when nothing is aging")
writePending(t, dir, "ancient.md", 200*24*time.Hour, time.Now())
raw, err = srv.brainContext(context.Background(),
json.RawMessage(`{"project_root":"/home/mathias/dev/AGENTS/hyperguild"}`))
require.NoError(t, err)
var withQueue map[string]any
require.NoError(t, json.Unmarshal(raw, &withQueue))
nudge, ok := withQueue["pending_review"].(map[string]any)
require.True(t, ok, "the nudge must reach the caller: %v", withQueue)
assert.Equal(t, float64(1), nudge["aging"])
assert.Equal(t, "ancient.md", nudge["oldest"])
}
+1 -6
View File
@@ -1,14 +1,9 @@
// Package mcp implements an MCP HTTP handler for the ingestion service. // Package mcp implements an MCP HTTP handler for the ingestion service.
// Exposed tools: brain_query, brain_write, brain_update, brain_get, // Exposed tools: brain_query, brain_write, brain_update, brain_get,
// brain_pending, brain_promote, brain_tunnel, brain_ingest, // brain_pending, brain_promote, brain_index, brain_tunnel, brain_ingest,
// brain_ingest_raw, brain_answer, brain_classify, brain_graph, // brain_ingest_raw, brain_answer, brain_classify, brain_graph,
// brain_context, session_log, and capture (the #55 relay tool, registered // brain_context, session_log, and capture (the #55 relay tool, registered
// only when WithCapture is set). // only when WithCapture is set).
//
// brain_index dispatches but is deliberately absent from tools/list: it is
// auto-called after every write, so surfacing it as a caller verb is
// cognitive load with no decision behind it (ADR-0012 rule 4, #78). It stays
// callable for maintenance — de-surfacing hides the verb, not the operation.
package mcp package mcp
import ( import (
+1 -25
View File
@@ -59,35 +59,11 @@ func TestServerToolsList(t *testing.T) {
assert.ElementsMatch(t, []string{ assert.ElementsMatch(t, []string{
"brain_query", "brain_write", "brain_update", "brain_get", "brain_query", "brain_write", "brain_update", "brain_get",
"brain_pending", "brain_promote", "brain_pending", "brain_promote",
"brain_tunnel", "brain_index", "brain_tunnel",
"brain_ingest_raw", "brain_ingest", "brain_ingest_raw", "brain_ingest",
"brain_answer", "brain_classify", "brain_graph", "brain_context", "brain_answer", "brain_classify", "brain_graph", "brain_context",
"session_log", "session_log",
}, names) }, names)
// brain_index is auto-called after every brain_write, so surfacing it as
// a caller verb is cognitive load with no decision behind it (ADR-0012
// rule 4, #78). The capability stays reachable — see the admin test below.
assert.NotContains(t, names, "brain_index")
}
func TestBrainIndexStaysCallableForAdminUseAfterDeSurfacing(t *testing.T) {
// De-surfacing hides the verb from the model-facing list; it must not
// remove the operation. A maintenance caller still needs to rebuild a
// Map of Content by hand.
srv := mcp.NewServer(t.TempDir(), nil, nil, nil)
req := httptest.NewRequest(http.MethodPost, "/mcp", body(t, map[string]any{
"jsonrpc": "2.0", "id": 3, "method": "tools/call",
"params": map[string]any{"name": "brain_index", "arguments": map[string]any{}},
}))
rr := httptest.NewRecorder()
srv.ServeHTTP(rr, req)
require.Equal(t, http.StatusOK, rr.Code)
var resp map[string]any
require.NoError(t, json.Unmarshal(rr.Body.Bytes(), &resp))
assert.NotContains(t, resp, "error", "brain_index must still dispatch: %v", resp["error"])
} }
func TestServerNotificationGetsNoBody(t *testing.T) { func TestServerNotificationGetsNoBody(t *testing.T) {
+9 -12
View File
@@ -8,10 +8,8 @@ import (
"path/filepath" "path/filepath"
"sort" "sort"
"strings" "strings"
"time"
"github.com/mathiasbq/hyperguild/ingestion/internal/search" "github.com/mathiasbq/hyperguild/ingestion/internal/search"
"github.com/mathiasbq/hyperguild/ingestion/internal/textutil"
) )
// brainContextArgs is the input shape of brain_context. project_root is // brainContextArgs is the input shape of brain_context. project_root is
@@ -157,21 +155,17 @@ func (s *Server) brainContext(ctx context.Context, args json.RawMessage) (json.R
entries = entries[:limit] entries = entries[:limit]
} }
out := map[string]any{"entries": entries} return json.Marshal(map[string]any{"entries": entries})
// The queue nudge rides along with a call the session already makes, so
// noticing an aging note costs nobody a decision to go looking (#82).
// Advisory only, and absent entirely when there is nothing to say.
if n := pendingNudge(s.brainDir, time.Now(), pendingNudgeThreshold); n != nil {
out["pending_review"] = n
}
return json.Marshal(out)
} }
// truncateExcerpt clamps an already-stripped excerpt to maxLen characters // truncateExcerpt clamps an already-stripped excerpt to maxLen characters
// without re-running the frontmatter parser. The ellipsis suffix matches // without re-running the frontmatter parser. The ellipsis suffix matches
// the convention used in search.excerpt. // the convention used in search.excerpt.
func truncateExcerpt(s string, maxLen int) string { func truncateExcerpt(s string, maxLen int) string {
return textutil.Truncate(s, maxLen) if len(s) <= maxLen {
return s
}
return s[:maxLen] + "…"
} }
// readExcerpt loads a doc relative to brainDir, strips its frontmatter, // readExcerpt loads a doc relative to brainDir, strips its frontmatter,
@@ -191,7 +185,10 @@ func readExcerpt(brainDir, relPath string, maxLen int) string {
if len(parts) == 3 { if len(parts) == 3 {
body = strings.TrimSpace(parts[2]) body = strings.TrimSpace(parts[2])
} }
return textutil.Truncate(body, maxLen) if len(body) > maxLen {
return body[:maxLen] + "…"
}
return body
} }
// max1 returns the maximum of n and 1, used to guard against divide-by-zero // max1 returns the maximum of n and 1, used to guard against divide-by-zero
+4 -2
View File
@@ -12,7 +12,6 @@ import (
"strings" "strings"
"github.com/mathiasbq/hyperguild/ingestion/internal/brain" "github.com/mathiasbq/hyperguild/ingestion/internal/brain"
"github.com/mathiasbq/hyperguild/ingestion/internal/textutil"
"github.com/mathiasbq/hyperguild/ingestion/internal/vectorstore" "github.com/mathiasbq/hyperguild/ingestion/internal/vectorstore"
) )
@@ -428,5 +427,8 @@ func excerpt(content string, maxLen int) string {
if len(parts) == 3 { if len(parts) == 3 {
body = strings.TrimSpace(parts[2]) body = strings.TrimSpace(parts[2])
} }
return textutil.Truncate(body, maxLen) if len(body) > maxLen {
return body[:maxLen] + "…"
}
return body
} }
@@ -1,75 +0,0 @@
// Package startupretry retries a startup dependency that may not be serving
// yet, instead of exiting on its first failure.
//
// It exists for the cold-boot ordering race (#83): on a cluster restart the
// ingestion pod can reach OIDC discovery before dex is answering, gets a 502
// from ingress, and dies — after having already connected postgres, backfilled
// the graph and ingested session batches, all of which the restart redoes.
// Nothing is misconfigured in that scenario; the pod simply started first.
//
// The budget is bounded on purpose. Retrying forever would turn a genuine
// misconfiguration (wrong issuer URL, bad audience) into a process that looks
// healthy and never serves, which is harder to diagnose than a crash loop.
package startupretry
import (
"context"
"fmt"
"time"
)
// Policy bounds the retry: at most Attempts calls, with the delay doubling
// from Base and capped at Max.
type Policy struct {
Attempts int // total calls, including the first; < 1 means 1
Base time.Duration // delay before the second attempt
Max time.Duration // ceiling for the doubling delay
}
// Do calls fn until it succeeds, the attempt budget is spent, or ctx ends.
//
// The returned error wraps the last failure, so callers keep the diagnosis
// they would have had without the retry.
func Do[T any](ctx context.Context, p Policy, fn func(context.Context) (T, error)) (T, error) {
var zero T
attempts := p.Attempts
if attempts < 1 {
attempts = 1
}
delay := p.Base
var lastErr error
for i := range attempts {
if err := ctx.Err(); err != nil {
return zero, fmt.Errorf("startupretry: %w", err)
}
v, err := fn(ctx)
if err == nil {
return v, nil
}
lastErr = err
if i == attempts-1 {
break
}
if delay <= 0 {
delay = time.Second
}
if p.Max > 0 && delay > p.Max {
delay = p.Max
}
select {
case <-ctx.Done():
return zero, fmt.Errorf("startupretry: %w", ctx.Err())
case <-time.After(delay):
}
delay *= 2
}
return zero, fmt.Errorf("startupretry: gave up after %d attempts: %w", attempts, lastErr)
}
@@ -1,144 +0,0 @@
// ingestion/internal/startupretry/startupretry_test.go
package startupretry
import (
"context"
"errors"
"testing"
"time"
)
func fastPolicy(attempts int) Policy {
return Policy{Attempts: attempts, Base: time.Millisecond, Max: 2 * time.Millisecond}
}
func TestDo_ReturnsImmediatelyOnFirstSuccess(t *testing.T) {
calls := 0
got, err := Do(context.Background(), fastPolicy(5), func(context.Context) (string, error) {
calls++
return "ready", nil
})
if err != nil {
t.Fatalf("Do: %v", err)
}
if got != "ready" {
t.Errorf("got %q, want %q", got, "ready")
}
if calls != 1 {
t.Errorf("calls = %d, want 1", calls)
}
}
func TestDo_SurvivesTransientFailuresThenSucceeds(t *testing.T) {
// The observed cold-boot race: dex is not serving yet, ingress answers
// 502 for the first few attempts, then discovery works.
calls := 0
got, err := Do(context.Background(), fastPolicy(5), func(context.Context) (string, error) {
calls++
if calls < 4 {
return "", errors.New("oidc discovery: status 502")
}
return "ready", nil
})
if err != nil {
t.Fatalf("Do returned %v — a transient 502 must not be fatal", err)
}
if got != "ready" {
t.Errorf("got %q, want %q", got, "ready")
}
if calls != 4 {
t.Errorf("calls = %d, want 4", calls)
}
}
func TestDo_GivesUpAfterTheAttemptBudgetAndReportsTheLastError(t *testing.T) {
// A genuinely broken issuer must still fail — retrying forever would turn
// a config error into a silent hang, which is worse than crash-looping.
last := errors.New("oidc discovery: status 404")
calls := 0
_, err := Do(context.Background(), fastPolicy(3), func(context.Context) (string, error) {
calls++
return "", last
})
if !errors.Is(err, last) {
t.Fatalf("err = %v, want it to wrap the last failure", err)
}
if calls != 3 {
t.Errorf("calls = %d, want 3 (the attempt budget)", calls)
}
}
func TestDo_StopsPromptlyWhenTheContextIsCancelled(t *testing.T) {
ctx, cancel := context.WithCancel(context.Background())
calls := 0
done := make(chan struct{})
var err error
go func() {
defer close(done)
_, err = Do(ctx, Policy{Attempts: 100, Base: 50 * time.Millisecond, Max: time.Second},
func(context.Context) (string, error) {
calls++
if calls == 1 {
cancel()
}
return "", errors.New("still down")
})
}()
select {
case <-done:
case <-time.After(2 * time.Second):
t.Fatal("Do did not return after context cancellation")
}
if !errors.Is(err, context.Canceled) {
t.Errorf("err = %v, want context.Canceled", err)
}
}
func TestDo_BacksOffAndIsCappedByMax(t *testing.T) {
var delays []time.Duration
p := Policy{Attempts: 5, Base: 10 * time.Millisecond, Max: 25 * time.Millisecond}
last := time.Now()
_, _ = Do(context.Background(), p, func(context.Context) (string, error) {
now := time.Now()
delays = append(delays, now.Sub(last))
last = now
return "", errors.New("down")
})
// delays[0] is the first call (no wait); the rest are the sleeps.
if len(delays) != 5 {
t.Fatalf("attempts = %d, want 5", len(delays))
}
if delays[1] >= delays[2] {
t.Errorf("backoff is not growing: %v then %v", delays[1], delays[2])
}
for i, d := range delays[1:] {
if d > 2*p.Max {
t.Errorf("delay %d = %v, exceeds the Max cap %v with slack", i+1, d, p.Max)
}
}
}
func TestPolicy_ZeroValueStillMakesOneAttempt(t *testing.T) {
// A caller that forgets to configure the policy must not silently get a
// no-op that returns a nil validator and a nil error.
calls := 0
_, err := Do(context.Background(), Policy{}, func(context.Context) (string, error) {
calls++
return "", errors.New("down")
})
if calls != 1 {
t.Errorf("calls = %d, want 1", calls)
}
if err == nil {
t.Error("err = nil, want the failure surfaced")
}
}
-45
View File
@@ -1,45 +0,0 @@
// Package textutil holds small text helpers shared across the ingestion
// service.
package textutil
import "unicode/utf8"
// Ellipsis marks a value that was cut short.
const Ellipsis = "…"
// Truncate shortens s to at most limit CHARACTERS, appending an ellipsis when
// anything was dropped.
//
// It exists because four call sites did `s[:limit] + "…"` (#93). Both halves
// of that are byte operations: len() counts bytes and a slice cuts bytes, so
// on Swedish text — where å ä ö are two bytes and an em dash is three — the
// cut lands mid-character and leaves an orphaned lead byte. The result is
// invalid UTF-8.
//
// That failed loudly in exactly one place, wiki/index.md, which is written
// raw to disk and then rejected by every strict decoder. The other three fed
// MCP responses, where encoding/json silently substitutes U+FFFD — so those
// had been quietly eating the last character of truncated excerpts with no
// error anywhere.
//
// The marker is appended only when content was actually dropped: an ellipsis
// on complete text is a lie about the content.
func Truncate(s string, limit int) string {
if limit <= 0 {
return ""
}
if utf8.RuneCountInString(s) <= limit {
return s
}
// Walk runes rather than converting to []rune: the input can be a whole
// note body, and this runs on the read path.
count := 0
for i := range s {
if count == limit {
return s[:i] + Ellipsis
}
count++
}
return s + Ellipsis
}
@@ -1,66 +0,0 @@
// ingestion/internal/textutil/truncate_test.go
package textutil_test
import (
"strings"
"testing"
"unicode/utf8"
"github.com/mathiasbq/hyperguild/ingestion/internal/textutil"
)
func TestTruncate_ShortStringsAreUntouched(t *testing.T) {
for _, s := range []string{"", "kort", "räv", "a — b"} {
if got := textutil.Truncate(s, 100); got != s {
t.Errorf("Truncate(%q, 100) = %q, want it unchanged", s, got)
}
}
}
func TestTruncate_NeverCutsInsideACharacter(t *testing.T) {
// The property, not an example: whatever the limit, the result must be
// valid UTF-8. Byte-slicing Swedish text (å ä ö) or an em dash produces
// an orphaned lead byte, which is what corrupted wiki/index.md (#93).
s := strings.Repeat("räv — ål — ökäd ", 20)
for limit := 0; limit <= len(s)+5; limit++ {
got := textutil.Truncate(s, limit)
if !utf8.ValidString(got) {
t.Fatalf("Truncate(s, %d) produced invalid UTF-8: %q", limit, got)
}
}
}
func TestTruncate_CountsCharactersNotBytes(t *testing.T) {
// "räv" is 4 bytes, 3 runes. A byte-based limit of 3 would cut inside the
// "ä"; a rune-based one returns it whole.
if got := textutil.Truncate("räv", 3); got != "räv" {
t.Errorf("Truncate(\"räv\", 3) = %q, want the whole word", got)
}
got := textutil.Truncate("räven springer", 5)
if utf8.RuneCountInString(got) != 6 { // 5 runes + the ellipsis
t.Errorf("Truncate(...) = %q, want 5 runes plus the marker", got)
}
if !strings.HasSuffix(got, "…") {
t.Errorf("Truncate(...) = %q, want it marked as truncated", got)
}
}
func TestTruncate_MarksOnlyWhenSomethingWasDropped(t *testing.T) {
// An ellipsis on text that was not cut is a lie about the content.
if got := textutil.Truncate("räv", 10); strings.HasSuffix(got, "…") {
t.Errorf("Truncate(%q, 10) = %q, want no truncation marker", "räv", got)
}
if got := textutil.Truncate("räv", 3); strings.HasSuffix(got, "…") {
t.Errorf("exact-length input must not be marked: %q", got)
}
}
func TestTruncate_NonPositiveLimitYieldsNothingRatherThanPanicking(t *testing.T) {
for _, limit := range []int{0, -1, -100} {
if got := textutil.Truncate("räven", limit); got != "" {
t.Errorf("Truncate(_, %d) = %q, want empty", limit, got)
}
}
}
+4 -3
View File
@@ -6,8 +6,6 @@ import (
"os" "os"
"path/filepath" "path/filepath"
"strings" "strings"
"github.com/mathiasbq/hyperguild/ingestion/internal/textutil"
) )
// RebuildIndex writes brain/wiki/index.md from the current wiki contents. // RebuildIndex writes brain/wiki/index.md from the current wiki contents.
@@ -64,7 +62,10 @@ func pageFirstSentence(brainDir string, e Entry) string {
if line == "" || strings.HasPrefix(line, "#") { if line == "" || strings.HasPrefix(line, "#") {
continue continue
} }
return textutil.Truncate(line, 100) if len(line) > 100 {
return line[:100] + "…"
}
return line
} }
return "" return ""
} }
+3
View File
@@ -0,0 +1,3 @@
{
"$schema": "https://docs.renovatebot.com/renovate-schema.json"
}