Files
hyperguild/ingestion/internal/mcp/tools_capture.go
mathias 055af368cd
CI / Lint / Test / Vet (push) Successful in 29s
CI / Mirror to GitHub (push) Skipped
feat(mcp): brain_read + brain_edit, contained to the sync source (brain#4) (#96)
brain_read returns a note verbatim; brain_edit is str_replace with an
exactly-once match, operating on the tree brain-sync commits from.

An adversarial design review before implementation changed three things:

1. Governance files are not in the model-facing tool. Brain content is
   ingested from the outside world and reaches a model's context, and that
   model would hold the editor — one poisoned page could rewrite the
   CLAUDE.md a .dispatch-allow agent later loads as instructions. And
   brain-sync merges with --strategy-option=ours, so the live tree beats a
   human's corrective push on the conflicting lines. CLAUDE.md now goes
   through brain_edit_root: de-surfaced from tools/list and gated on the
   local static principal. The scopes are disjoint — the privileged door
   has the smaller reach.

2. Reads needed the same allowlist, and brain_get already lacked it: it
   returned verbatim session transcripts under archive/ by path. A test
   proved the exposure live before the fix.

3. Canonicalise before allowlisting — knowledge/../.git/hooks/post-commit
   would otherwise reach a hook that brain-sync executes in a pod holding
   the Gitea push credentials.

Plus overlapping match counting, UTF-8 validation both ways, refusal while
git is mid-operation, flock with the read inside the lock, atomic
same-dir rename, and reindex only when frontmatter is touched.

Refs brain#4.

Co-authored-by: Mathias <mthbqv@gmail.com>
2026-08-18 18:14:05 +00:00

102 lines
4.1 KiB
Go

package mcp
import (
"context"
"encoding/json"
"fmt"
"github.com/mathiasbq/hyperguild/ingestion/internal/capturehttp"
)
// principalKey is the context key under which the authenticated principal
// (re-derived in ServeHTTP) is stashed for the capture tool.
type principalKeyT struct{}
var principalKey principalKeyT
type principalInfo struct {
principal string
viaStatic bool
}
func withPrincipal(ctx context.Context, principal string, viaStatic bool) context.Context {
return context.WithValue(ctx, principalKey, principalInfo{principal: principal, viaStatic: viaStatic})
}
// captureToolDescriptor is the tools/list entry for the capture relay.
// Appended only when WithCapture has wired the tool.
func captureToolDescriptor() map[string]any {
str := func(d string) map[string]any { return map[string]any{"type": "string", "description": d} }
insightItem := map[string]any{
"type": "object",
"properties": map[string]any{
"text": str("the insight body"), "wing": str("brain wing"),
"hall": str("brain hall (facts/decisions/failures/hypotheses/sources)"),
"supersede_slug": str("optional: slug of a prior note to revise in place instead of creating"),
},
"required": []string{"text", "wing", "hall"},
}
ticketItem := map[string]any{
"type": "object",
"properties": map[string]any{
"repo": str("gitea repo (owner is always mathias)"), "action": str("create|close|comment"),
"number": map[string]any{"type": "integer", "description": "issue number (close/comment)"},
"title": str("issue title (create)"), "body": str("issue/comment body"),
},
"required": []string{"repo", "action"},
}
schema := map[string]any{
"type": "object",
"properties": map[string]any{
"context": map[string]any{
"type": "object",
"properties": map[string]any{
"harness": str("descriptive harness label (telemetry only, never a gate input)"),
"session_ref": str("optional session reference"), "fidelity": str("live-capture|transcript-parse|agent-runlog"),
"actor": str("acting user/agent"), "classification": str("caller-declared sensitivity: public|internal|confidential"),
},
},
"insights": map[string]any{"type": "array", "items": insightItem},
"tickets": map[string]any{"type": "array", "items": ticketItem},
"dry_run": map[string]any{"type": "boolean", "description": "validate + return the would-be receipt, write nothing"},
},
}
b, _ := json.Marshal(schema)
return map[string]any{
"name": "capture",
"description": "Persist a session's value uniformly: insights → brain (write or supersede), action items → Gitea tickets. The relay door for MCP-native harnesses. Origin is server-derived from your authenticated identity; confidential captures through a us-nexus surface are refused (I1). Returns a partial-aware receipt.",
"inputSchema": json.RawMessage(b),
}
}
// brainCapture is the MCP capture tool: the #55 relay for MCP-native
// harnesses. It re-uses the same CaptureService, principal-derivation, and
// origin resolver as POST /capture — only the transport differs. It holds
// no state and retains nothing beyond the I5 audit record.
func (s *Server) brainCapture(ctx context.Context, args json.RawMessage) (json.RawMessage, error) {
if s.capture == nil {
return nil, fmt.Errorf("capture tool not configured")
}
info, ok := ctx.Value(principalKey).(principalInfo)
if !ok || info.principal == "" {
// No authenticated principal ⇒ cannot derive origin ⇒ cannot gate.
return nil, fmt.Errorf("capture requires an authenticated principal")
}
in, err := capturehttp.DecodeRequest(args)
if err != nil {
return nil, fmt.Errorf("invalid capture request: %w", err)
}
// Principal and origin are server-derived — never taken from the body.
in.Context.Principal = info.principal
in.Context.Origin = s.capture.resolver.Resolve(info.principal, info.viaStatic)
rec, err := s.capture.svc.Capture(ctx, in)
if err != nil {
// Surface I1/I5 refusals and validation failures verbatim; errors.Is
// markers (ErrSovereigntyRefused / ErrAuditUnavailable) ride in the message.
return nil, err
}
return json.Marshal(rec)
}