Compare commits

...
Author SHA1 Message Date
mathiasandClaude Opus 4.8 5288554338 fix(gitea): WriteFile creates via POST, updates via PUT (real contents API)
CI / Lint / Test / Vet (pull_request) Successful in 13s
CI / Mirror to GitHub (pull_request) Has been skipped
A live token-scope probe against mathias/ai-sessions revealed gitea's
contents API uses POST to create and PUT (sha required) to update — the
first impl always PUT'd, so creating a new summary 422'd "[SHA]: Required".
The httptest mock had the same wrong assumption. Pick the method by
whether the file exists (GET sha). Token confirmed contents:write
(push:true) by the probe.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 17:22:37 +02:00
mathiasandClaude Opus 4.8 2368564523 fix(capture): wire ai-sessions SummaryWriter into the relay (#66)
CI / Lint / Test / Vet (pull_request) Successful in 13s
CI / Mirror to GitHub (pull_request) Has been skipped
The deployed CaptureService was constructed with a nil SummaryWriter, so
a capture carrying a summary block returned the partial-failure
"no summary writer configured" (surfaced in the 2026-06-23 claude.ai
dogfood). The Gitea client already reaches mathias/* over BRAIN_GITEA_TOKEN
and now implements SummaryWriter, so inject it (type-asserted from the
tracker) — no new credential, no manifest change. Session summaries now
write to mathias/ai-sessions at summaries/<harness>/<YYYY-MM>/...

Reuses the existing token deliberately; assumes it carries contents:write
scope on ai-sessions (it already does issue writes for the tracker). If
the token is issue-scoped only, the live write 422s — a token-scope widen,
not a code fix.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 10:47:00 +02:00
mathiasandClaude Opus 4.8 0e28b2125b feat(gitea): WriteFile contents-API upsert — satisfies SummaryWriter (#66)
Adds Client.WriteFile (Gitea contents API) so the Gitea client also
implements capture.SummaryWriter. Upserts: a GET resolves the current
blob sha so an existing file is updated (the richer-fidelity-supersedes
rule for re-captured sessions) rather than 422'd. Owner stays the fixed
const; token only in the Authorization header (no leak — regression
tested). Refactors the HTTP path into a shared request() helper so the
contents flow can branch on 404 without it being an error.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 10:47:00 +02:00
mathiasandClaude Opus 4.8 06e21c019e docs(capture): as-built implementation report for the #49 epic
CI / Lint / Test / Vet (push) Successful in 12s
CI / Mirror to GitHub (push) Successful in 4s
Records what shipped (v0.11.0): architecture, sub-issue→PR map, I1–I5
compliance, the operational env reference, test coverage, and the
deferred follow-ups. Companion to specs/capture-bdd-spec.md (the design
contract) for onboarding + future audit.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 07:41:24 +02:00
mathias 76514215f4 Merge pull request 'feat: capture relay — MCP capture tool for non-library harnesses (#55, capture 49f)' (#61) from feat/capture-mcp-relay into main
CI / Lint / Test / Vet (push) Successful in 12s
CI / Mirror to GitHub (push) Has been skipped
2026-06-23 05:26:55 +00:00
mathiasandClaude Opus 4.8 7cf5bc221d feat(mcp): capture relay tool — MCP door for non-library harnesses (#55)
CI / Lint / Test / Vet (pull_request) Successful in 13s
CI / Mirror to GitHub (pull_request) Has been skipped
Adds the `capture` MCP tool: the #55 relay for harnesses that cannot run
the use-case in-process (claude.ai Chat/Cowork/Design, Crush, Pi, LLM
Council). They reach it through the existing /mcp OAuth connector.

- Thin: forwards to the SAME CaptureService as POST /capture; holds no
  state and retains nothing beyond the I5 audit record. The containment
  properties accepted in infra security-baseline (I2 ledger) hold by
  construction.
- Per-principal: ServeHTTP re-derives the caller's principal from the
  Bearer header (the chassis middleware gates but discards it) and stashes
  it in context; the tool resolves the trust-zone origin from it. A
  caller-asserted harness/origin in the body is ignored — origin is
  server-derived, so the I1 confidential refusal still fires for us-nexus
  callers (claude.ai), and sovereign-allowlisted JWT principals pass.
- Registered only when WithCapture is wired (all three sites: tools(),
  handleCall, package doc); main wires REST + MCP from the same service,
  resolver, and credentials.

Tests: listed-only-when-wired, forwards-via-static-principal,
confidential-via-us-nexus-refused, confidential-via-sovereign-allowed,
unauthenticated-rejected, caller-cannot-forge-origin.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 00:21:11 +02:00
mathiasandClaude Opus 4.8 f78a5474a5 refactor(capturehttp): export Authenticate + DecodeRequest for reuse (#55)
Lifts the Bearer principal-derivation and the request→CaptureInput decode
out of the REST handler into exported package funcs, so the MCP capture
tool (#55 relay) reuses the exact same auth precedence and wire shape —
one implementation, not two. No behaviour change to POST /capture.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 00:21:11 +02:00
mathias c307b72bd5 Merge pull request 'feat: I5 audit path + classification-aware degradation (#54, capture 49e)' (#60) from feat/capture-audit-degradation into main
CI / Lint / Test / Vet (push) Successful in 13s
CI / Mirror to GitHub (push) Successful in 4s
2026-06-22 21:57:52 +00:00
9 changed files with 633 additions and 43 deletions
+13 -4
View File
@@ -410,13 +410,22 @@ func main() {
os.Exit(1) os.Exit(1)
} }
auditSink := buildAuditSink(ctx, brainDir, logger) auditSink := buildAuditSink(ctx, brainDir, logger)
// The Gitea client also satisfies SummaryWriter (#66): session
// summaries are written to mathias/ai-sessions over the same API
// token. nil only if a future tracker impl lacks file writes.
summaryWriter, _ := tracker.(capture.SummaryWriter)
captureSvc := capture.NewService( captureSvc := capture.NewService(
mcpSrv.BrainStore(), tracker, nil, classCfg, auditSink) mcpSrv.BrainStore(), tracker, summaryWriter, classCfg, auditSink)
sovereign := splitList(os.Getenv("BRAIN_CAPTURE_SOVEREIGN_PRINCIPALS")) sovereign := splitList(os.Getenv("BRAIN_CAPTURE_SOVEREIGN_PRINCIPALS"))
captureH := capturehttp.New(captureSvc, jwtValidator, mcpToken, "local-cli", resolver := capturehttp.NewOriginResolver(sovereign)
capturehttp.NewOriginResolver(sovereign)) captureH := capturehttp.New(captureSvc, jwtValidator, mcpToken, "local-cli", resolver)
mux.Handle("POST /capture", captureH) mux.Handle("POST /capture", captureH)
logger.Info("capture endpoint enabled", "sovereign_principals", len(sovereign)) // Same use-case behind the MCP `capture` tool (#55 relay) so MCP-native
// harnesses (claude.ai, Crush, Pi, LLM Council) reach capture through
// the existing /mcp OAuth connector. mcpSrv is already wrapped above;
// WithCapture mutates the same instance, so the tool appears live.
mcpSrv.WithCapture(captureSvc, jwtValidator, mcpToken, "local-cli", resolver)
logger.Info("capture enabled (REST + MCP tool)", "sovereign_principals", len(sovereign))
} else { } else {
logger.Info("capture endpoint disabled (BRAIN_GITEA_TOKEN unset)") logger.Info("capture endpoint disabled (BRAIN_GITEA_TOKEN unset)")
} }
+31 -14
View File
@@ -11,6 +11,7 @@ import (
"crypto/subtle" "crypto/subtle"
"encoding/json" "encoding/json"
"errors" "errors"
"io"
"net/http" "net/http"
"strings" "strings"
@@ -90,19 +91,22 @@ type summaryBody struct {
// ServeHTTP authenticates, derives origin, runs the use-case, and maps the // ServeHTTP authenticates, derives origin, runs the use-case, and maps the
// result to an HTTP status. // result to an HTTP status.
func (h *Handler) ServeHTTP(w http.ResponseWriter, r *http.Request) { func (h *Handler) ServeHTTP(w http.ResponseWriter, r *http.Request) {
principal, viaStatic, ok := h.authenticate(r) principal, viaStatic, ok := Authenticate(r, h.staticToken, h.staticPrincipal, h.validator)
if !ok { if !ok {
http.Error(w, "unauthorized", http.StatusUnauthorized) http.Error(w, "unauthorized", http.StatusUnauthorized)
return return
} }
var req request body, err := io.ReadAll(r.Body)
if err := json.NewDecoder(r.Body).Decode(&req); err != nil { if err != nil {
writeJSON(w, http.StatusBadRequest, map[string]string{"error": "read body"})
return
}
in, err := DecodeRequest(body)
if err != nil {
writeJSON(w, http.StatusBadRequest, map[string]string{"error": "invalid JSON"}) writeJSON(w, http.StatusBadRequest, map[string]string{"error": "invalid JSON"})
return return
} }
in := req.toInput()
// Principal and origin are server-derived — overwrite anything the // Principal and origin are server-derived — overwrite anything the
// caller may have tried to put in the body. // caller may have tried to put in the body.
in.Context.Principal = principal in.Context.Principal = principal
@@ -125,26 +129,39 @@ func (h *Handler) ServeHTTP(w http.ResponseWriter, r *http.Request) {
writeJSON(w, statusFor(rec), rec) writeJSON(w, statusFor(rec), rec)
} }
// authenticate mirrors the chassis Bearer precedence (static wins, then // Authenticate mirrors the chassis Bearer precedence (static token wins,
// JWT) but returns the resolved principal and whether the static path was // then Dex JWT) and returns the resolved principal plus whether the static
// taken — the chassis middleware hides both, and capture needs them to // path was taken — the chassis middleware hides both, and capture (REST or
// derive the origin. // MCP) needs them to derive the trust-zone origin. ok is false when no
func (h *Handler) authenticate(r *http.Request) (principal string, viaStatic, ok bool) { // credential matched.
func Authenticate(r *http.Request, staticToken, staticPrincipal string, validator Validator) (principal string, viaStatic, ok bool) {
raw, found := strings.CutPrefix(r.Header.Get("Authorization"), "Bearer ") raw, found := strings.CutPrefix(r.Header.Get("Authorization"), "Bearer ")
if !found || raw == "" { if !found || raw == "" {
return "", false, false return "", false, false
} }
if h.staticToken != "" && subtle.ConstantTimeCompare([]byte(raw), []byte(h.staticToken)) == 1 { if staticToken != "" && subtle.ConstantTimeCompare([]byte(raw), []byte(staticToken)) == 1 {
return h.staticPrincipal, true, true return staticPrincipal, true, true
} }
if h.validator != nil { if validator != nil {
if sub, err := h.validator.Validate(r.Context(), raw); err == nil && sub != "" { if sub, err := validator.Validate(r.Context(), raw); err == nil && sub != "" {
return sub, false, true return sub, false, true
} }
} }
return "", false, false return "", false, false
} }
// DecodeRequest parses a capture request body into a CaptureInput. Shared
// by the REST adapter and the MCP capture tool so the wire shape has one
// definition. Principal and Origin are NOT set here — the caller sets them
// from the authenticated identity.
func DecodeRequest(data []byte) (capture.CaptureInput, error) {
var b request
if err := json.Unmarshal(data, &b); err != nil {
return capture.CaptureInput{}, err
}
return b.toInput(), nil
}
func (b request) toInput() capture.CaptureInput { func (b request) toInput() capture.CaptureInput {
in := capture.CaptureInput{ in := capture.CaptureInput{
Context: capture.CaptureContext{ Context: capture.CaptureContext{
+91 -22
View File
@@ -12,6 +12,7 @@ package gitea
import ( import (
"bytes" "bytes"
"context" "context"
"encoding/base64"
"encoding/json" "encoding/json"
"fmt" "fmt"
"io" "io"
@@ -93,37 +94,105 @@ func (c *Client) CloseIssue(ctx context.Context, repo string, number int, commen
return capture.IssueRef{Repo: repo, Number: number, URL: out.HTMLURL}, nil return capture.IssueRef{Repo: repo, Number: number, URL: out.HTMLURL}, nil
} }
// do performs a JSON request against the Gitea API and decodes the // WriteFile creates or updates a file in repo at path via the Gitea
// response into out. Errors carry the status and a truncated body for // contents API — the SummaryWriter port (#66). It upserts: a GET resolves
// diagnosis but never the token. // the current blob sha (if any) so an existing file is updated rather than
func (c *Client) do(ctx context.Context, method, path string, payload any, out *issueResponse) error { // rejected (the richer-fidelity-supersedes rule for re-captured sessions).
reqBody, err := json.Marshal(payload) // Owner is the fixed const, like every other call.
if err != nil { func (c *Client) WriteFile(ctx context.Context, repo, path, content string) error {
return fmt.Errorf("marshal request: %w", err) cpath := fmt.Sprintf("/api/v1/repos/%s/%s/contents/%s", owner, repo, path)
} sha, err := c.fileSHA(ctx, cpath)
req, err := http.NewRequestWithContext(ctx, method, c.baseURL+path, bytes.NewReader(reqBody))
if err != nil { if err != nil {
return err return err
} }
req.Header.Set("Content-Type", "application/json") payload := map[string]any{
req.Header.Set("Accept", "application/json") "message": "capture: " + path,
// Gitea's token scheme. Held here only; never logged. "content": base64.StdEncoding.EncodeToString([]byte(content)),
req.Header.Set("Authorization", "token "+c.token) }
// Gitea contents API: POST creates a new file, PUT updates an existing
resp, err := c.http.Do(req) // one (PUT requires the current sha). Pick by whether the file exists.
method := http.MethodPost
if sha != "" {
method = http.MethodPut
payload["sha"] = sha
}
status, body, err := c.request(ctx, method, cpath, payload)
if err != nil { if err != nil {
return fmt.Errorf("gitea %s %s: %w", method, path, err) return err
}
if status < 200 || status >= 300 {
return fmt.Errorf("gitea %s %s: status %d: %s", method, cpath, status, strings.TrimSpace(string(body)))
}
return nil
} }
defer func() { _ = resp.Body.Close() }()
respBody, _ := io.ReadAll(io.LimitReader(resp.Body, 4096)) // fileSHA returns the current blob sha for a contents path, or "" when the
if resp.StatusCode < 200 || resp.StatusCode >= 300 { // file does not exist (404). Any other non-2xx is an error.
return fmt.Errorf("gitea %s %s: status %d: %s", method, path, resp.StatusCode, strings.TrimSpace(string(respBody))) func (c *Client) fileSHA(ctx context.Context, cpath string) (string, error) {
status, body, err := c.request(ctx, http.MethodGet, cpath, nil)
if err != nil {
return "", err
} }
if out != nil && len(respBody) > 0 { if status == http.StatusNotFound {
if err := json.Unmarshal(respBody, out); err != nil { return "", nil
}
if status < 200 || status >= 300 {
return "", fmt.Errorf("gitea GET %s: status %d: %s", cpath, status, strings.TrimSpace(string(body)))
}
var meta struct {
SHA string `json:"sha"`
}
if err := json.Unmarshal(body, &meta); err != nil {
return "", fmt.Errorf("gitea GET %s: decode: %w", cpath, err)
}
return meta.SHA, nil
}
// do performs a JSON request against the Gitea API and decodes a 2xx
// response into out. Errors carry the status and a truncated body for
// diagnosis but never the token.
func (c *Client) do(ctx context.Context, method, path string, payload any, out *issueResponse) error {
status, body, err := c.request(ctx, method, path, payload)
if err != nil {
return err
}
if status < 200 || status >= 300 {
return fmt.Errorf("gitea %s %s: status %d: %s", method, path, status, strings.TrimSpace(string(body)))
}
if out != nil && len(body) > 0 {
if err := json.Unmarshal(body, out); err != nil {
return fmt.Errorf("gitea %s %s: decode response: %w", method, path, err) return fmt.Errorf("gitea %s %s: decode response: %w", method, path, err)
} }
} }
return nil return nil
} }
// request is the shared HTTP path: marshals an optional JSON payload,
// attaches auth (token only ever in the header), and returns the status +
// body so callers can branch on status (e.g. 404) without it being an
// error. Never logs the token.
func (c *Client) request(ctx context.Context, method, path string, payload any) (int, []byte, error) {
var reader io.Reader
if payload != nil {
reqBody, err := json.Marshal(payload)
if err != nil {
return 0, nil, fmt.Errorf("marshal request: %w", err)
}
reader = bytes.NewReader(reqBody)
}
req, err := http.NewRequestWithContext(ctx, method, c.baseURL+path, reader)
if err != nil {
return 0, nil, err
}
req.Header.Set("Content-Type", "application/json")
req.Header.Set("Accept", "application/json")
req.Header.Set("Authorization", "token "+c.token)
resp, err := c.http.Do(req)
if err != nil {
return 0, nil, fmt.Errorf("gitea %s %s: %w", method, path, err)
}
defer func() { _ = resp.Body.Close() }()
body, _ := io.ReadAll(io.LimitReader(resp.Body, 8192))
return resp.StatusCode, body, nil
}
+66
View File
@@ -115,3 +115,69 @@ func TestErrorPathDoesNotLeakToken(t *testing.T) {
assert.NotContains(t, err.Error(), testToken, "token must never appear in an error message") assert.NotContains(t, err.Error(), testToken, "token must never appear in an error message")
assert.Contains(t, err.Error(), "500") assert.Contains(t, err.Error(), "500")
} }
func TestWriteFileCreatesNewFile(t *testing.T) {
var getPath, postPath, postBody string
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
switch r.Method {
case http.MethodGet:
getPath = r.URL.Path
w.WriteHeader(http.StatusNotFound) // file does not exist yet
case http.MethodPost: // gitea contents API: POST = create
postPath = r.URL.Path
b, _ := io.ReadAll(r.Body)
postBody = string(b)
w.WriteHeader(http.StatusCreated)
_ = json.NewEncoder(w).Encode(map[string]any{"content": map[string]any{"html_url": "https://git/x"}})
default:
t.Errorf("create must POST, got %s", r.Method)
}
}))
defer srv.Close()
err := gitea.New(srv.URL, testToken).WriteFile(context.Background(),
"ai-sessions", "summaries/claude-code/2026-06/2026-06-23-x-abcd1234.md", "# Summary\n\nbody\n")
require.NoError(t, err)
assert.Equal(t, "/api/v1/repos/mathias/ai-sessions/contents/summaries/claude-code/2026-06/2026-06-23-x-abcd1234.md", getPath)
assert.Equal(t, getPath, postPath)
// base64 of the content, no sha on create.
assert.Contains(t, postBody, "IyBTdW1tYXJ5") // base64("# Summary")
assert.NotContains(t, postBody, `"sha"`)
}
func TestWriteFileUpdatesExisting(t *testing.T) {
var putBody string
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
switch r.Method {
case http.MethodGet:
w.WriteHeader(http.StatusOK)
_ = json.NewEncoder(w).Encode(map[string]any{"sha": "deadbeef"})
case http.MethodPut:
b, _ := io.ReadAll(r.Body)
putBody = string(b)
w.WriteHeader(http.StatusOK)
_ = json.NewEncoder(w).Encode(map[string]any{"content": map[string]any{"html_url": "https://git/x"}})
}
}))
defer srv.Close()
err := gitea.New(srv.URL, testToken).WriteFile(context.Background(), "ai-sessions", "p/x.md", "new")
require.NoError(t, err)
assert.Contains(t, putBody, `"sha":"deadbeef"`, "existing file → update with sha")
}
func TestWriteFileErrorNoTokenLeak(t *testing.T) {
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if r.Method == http.MethodGet {
w.WriteHeader(http.StatusNotFound)
return
}
w.WriteHeader(http.StatusUnprocessableEntity)
_, _ = w.Write([]byte("bad"))
}))
defer srv.Close()
err := gitea.New(srv.URL, testToken).WriteFile(context.Background(), "ai-sessions", "p/x.md", "x")
require.Error(t, err)
assert.NotContains(t, err.Error(), testToken)
assert.Contains(t, err.Error(), "422")
}
+8 -1
View File
@@ -38,7 +38,7 @@ func (s *Server) tools() []map[string]any {
return b return b
} }
return []map[string]any{ tools := []map[string]any{
{ {
"name": "brain_query", "name": "brain_query",
"description": "BM25 full-text search across brain/knowledge/ and brain/wiki/ markdown files. Optionally scope by wing (topic domain) and hall (memory type).", "description": "BM25 full-text search across brain/knowledge/ and brain/wiki/ markdown files. Optionally scope by wing (topic domain) and hall (memory type).",
@@ -171,6 +171,13 @@ func (s *Server) tools() []map[string]any {
}), }),
}, },
} }
// The capture relay tool (#55) is advertised only when wired via
// WithCapture — MCP-native harnesses (claude.ai, Crush, Pi, LLM Council)
// reach capture through it.
if s.capture != nil {
tools = append(tools, captureToolDescriptor())
}
return tools
} }
type brainQueryArgs struct { type brainQueryArgs struct {
+53 -2
View File
@@ -1,7 +1,8 @@
// 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_index, brain_tunnel, brain_ingest, brain_ingest_raw, // brain_index, brain_tunnel, brain_ingest, brain_ingest_raw,
// brain_answer, brain_classify, brain_graph, brain_context, session_log. // brain_answer, brain_classify, brain_graph, brain_context, session_log,
// and capture (the #55 relay tool, registered only when WithCapture is set).
package mcp package mcp
import ( import (
@@ -12,6 +13,7 @@ import (
"github.com/mathiasbq/hyperguild/ingestion/internal/brainstore" "github.com/mathiasbq/hyperguild/ingestion/internal/brainstore"
"github.com/mathiasbq/hyperguild/ingestion/internal/capture" "github.com/mathiasbq/hyperguild/ingestion/internal/capture"
"github.com/mathiasbq/hyperguild/ingestion/internal/capturehttp"
"github.com/mathiasbq/hyperguild/ingestion/internal/graphstore" "github.com/mathiasbq/hyperguild/ingestion/internal/graphstore"
"github.com/mathiasbq/hyperguild/ingestion/internal/graphsync" "github.com/mathiasbq/hyperguild/ingestion/internal/graphsync"
"github.com/mathiasbq/hyperguild/ingestion/internal/pipeline" "github.com/mathiasbq/hyperguild/ingestion/internal/pipeline"
@@ -50,6 +52,19 @@ type Server struct {
graph graphsync.Store // nil = brain_graph and GraphRAG augmentation disabled graph graphsync.Store // nil = brain_graph and GraphRAG augmentation disabled
store *brainstore.Store // shared brain write/update/get impl (also used by capture) store *brainstore.Store // shared brain write/update/get impl (also used by capture)
tracker capture.IssueTracker // nil = no Gitea ticket integration; wired for capture (#53) tracker capture.IssueTracker // nil = no Gitea ticket integration; wired for capture (#53)
capture *captureDeps // nil = capture MCP tool disabled (#55 relay)
}
// captureDeps holds what the MCP `capture` tool (the #55 relay door for
// MCP-native harnesses like claude.ai) needs: the use-case, the auth bits
// to re-derive the caller's principal from the Bearer header (the chassis
// middleware gates but discards the principal), and the origin resolver.
type captureDeps struct {
svc *capture.Service
validator capturehttp.Validator
staticToken string
staticPrincipal string
resolver capturehttp.OriginResolver
} }
// NewServer constructs a Server bound to brainDir. pipelineCfg supplies the // NewServer constructs a Server bound to brainDir. pipelineCfg supplies the
@@ -123,6 +138,29 @@ func (s *Server) BrainStore() *brainstore.Store {
return s.store return s.store
} }
// WithCapture enables the MCP `capture` tool (#55) — the relay door for
// MCP-native harnesses (claude.ai, Crush, Pi, LLM Council) that cannot run
// the use-case in-process. It forwards to the same CaptureService as
// POST /capture, deriving the caller's principal + origin from the same
// auth credentials that gate /mcp. nil svc leaves the tool unregistered.
func (s *Server) WithCapture(svc *capture.Service, validator capturehttp.Validator, staticToken, staticPrincipal string, resolver capturehttp.OriginResolver) *Server {
if svc == nil {
s.capture = nil
return s
}
if staticPrincipal == "" {
staticPrincipal = "local-cli"
}
s.capture = &captureDeps{
svc: svc,
validator: validator,
staticToken: staticToken,
staticPrincipal: staticPrincipal,
resolver: resolver,
}
return s
}
func (s *Server) ServeHTTP(w http.ResponseWriter, r *http.Request) { func (s *Server) ServeHTTP(w http.ResponseWriter, r *http.Request) {
// MCP streamable HTTP: GET establishes the SSE stream for server-to-client events. // MCP streamable HTTP: GET establishes the SSE stream for server-to-client events.
if r.Method == http.MethodGet { if r.Method == http.MethodGet {
@@ -172,7 +210,18 @@ func (s *Server) ServeHTTP(w http.ResponseWriter, r *http.Request) {
rpcErr = &rpcError{Code: -32602, Message: "invalid params"} rpcErr = &rpcError{Code: -32602, Message: "invalid params"}
break break
} }
out, err := s.handleCall(r.Context(), p.Name, p.Arguments) // Re-derive the authenticated principal from the Bearer header so
// the capture tool can compute the trust-zone origin. The request
// is already gated by BearerMiddleware; this only recovers the
// identity that middleware discards.
ctx := r.Context()
if s.capture != nil {
if principal, viaStatic, ok := capturehttp.Authenticate(
r, s.capture.staticToken, s.capture.staticPrincipal, s.capture.validator); ok {
ctx = withPrincipal(ctx, principal, viaStatic)
}
}
out, err := s.handleCall(ctx, p.Name, p.Arguments)
if err != nil { if err != nil {
rpcErr = &rpcError{Code: -32000, Message: err.Error()} rpcErr = &rpcError{Code: -32000, Message: err.Error()}
break break
@@ -214,6 +263,8 @@ func (s *Server) handleCall(ctx context.Context, name string, args json.RawMessa
return s.brainUpdate(ctx, args) return s.brainUpdate(ctx, args)
case "brain_get": case "brain_get":
return s.brainGet(ctx, args) return s.brainGet(ctx, args)
case "capture":
return s.brainCapture(ctx, args)
case "brain_index": case "brain_index":
return s.brainIndex(ctx, args) return s.brainIndex(ctx, args)
case "brain_tunnel": case "brain_tunnel":
+105
View File
@@ -0,0 +1,105 @@
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},
"summary": map[string]any{"type": "object", "properties": map[string]any{
"title": str("summary title"), "body": str("summary body"),
"repos_touched": map[string]any{"type": "array", "items": map[string]any{"type": "string"}},
}},
"dry_run": map[string]any{"type": "boolean", "description": "validate + return the would-be receipt, write nothing"},
},
}
b, _ := json.Marshal(schema)
return map[string]any{
"name": "capture",
"description": "Persist a session's value uniformly: insights → brain (write or supersede), action items → Gitea tickets, optional summary → ai-sessions. The relay door for MCP-native harnesses. Origin is server-derived from your authenticated identity; confidential captures through a us-nexus surface are refused (I1). Returns a partial-aware receipt.",
"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)
}
@@ -0,0 +1,150 @@
package mcp_test
import (
"bytes"
"context"
"encoding/json"
"errors"
"net/http"
"net/http/httptest"
"os"
"path/filepath"
"testing"
"github.com/mathiasbq/hyperguild/ingestion/internal/audit"
"github.com/mathiasbq/hyperguild/ingestion/internal/brainstore"
"github.com/mathiasbq/hyperguild/ingestion/internal/capture"
"github.com/mathiasbq/hyperguild/ingestion/internal/capturehttp"
"github.com/mathiasbq/hyperguild/ingestion/internal/classification"
"github.com/mathiasbq/hyperguild/ingestion/internal/mcp"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
const capStaticTok = "cap-static-tok"
type capFakeTracker struct{}
func (capFakeTracker) CreateIssue(context.Context, string, string, string) (capture.IssueRef, error) {
return capture.IssueRef{Repo: "hyperguild", Number: 1, URL: "https://git/1"}, nil
}
func (capFakeTracker) CloseIssue(context.Context, string, int, string) (capture.IssueRef, error) {
return capture.IssueRef{}, nil
}
func (capFakeTracker) CommentIssue(context.Context, string, int, string) (capture.IssueRef, error) {
return capture.IssueRef{}, nil
}
type capFakeValidator struct {
subject string
err error
}
func (v capFakeValidator) Validate(context.Context, string) (string, error) {
return v.subject, v.err
}
func captureServer(t *testing.T, validator capturehttp.Validator, sovereign []string) (*mcp.Server, string) {
t.Helper()
brainDir := t.TempDir()
cfg, err := classification.Load(brainDir)
require.NoError(t, err)
svc := capture.NewService(brainstore.New(brainDir), capFakeTracker{}, nil, cfg, audit.NewSlogSink(nil))
srv := mcp.NewServer(brainDir, nil, nil, nil)
srv.WithCapture(svc, validator, capStaticTok, "local-cli", capturehttp.NewOriginResolver(sovereign))
return srv, brainDir
}
func captureCall(t *testing.T, srv http.Handler, authz string, args map[string]any) map[string]any {
t.Helper()
body, _ := json.Marshal(map[string]any{
"jsonrpc": "2.0", "id": 1, "method": "tools/call",
"params": map[string]any{"name": "capture", "arguments": args},
})
req := httptest.NewRequest(http.MethodPost, "/mcp", bytes.NewReader(body))
if authz != "" {
req.Header.Set("Authorization", authz)
}
rr := httptest.NewRecorder()
srv.ServeHTTP(rr, req)
var resp map[string]any
require.NoError(t, json.Unmarshal(rr.Body.Bytes(), &resp))
return resp
}
func TestCaptureToolListedWhenWired(t *testing.T) {
srv, _ := captureServer(t, nil, nil)
body, _ := json.Marshal(map[string]any{"jsonrpc": "2.0", "id": 1, "method": "tools/list"})
req := httptest.NewRequest(http.MethodPost, "/mcp", bytes.NewReader(body))
rr := httptest.NewRecorder()
srv.ServeHTTP(rr, req)
assert.Contains(t, rr.Body.String(), `"capture"`)
}
func TestCaptureToolNotListedByDefault(t *testing.T) {
srv := mcp.NewServer(t.TempDir(), nil, nil, nil) // no WithCapture
body, _ := json.Marshal(map[string]any{"jsonrpc": "2.0", "id": 1, "method": "tools/list"})
req := httptest.NewRequest(http.MethodPost, "/mcp", bytes.NewReader(body))
rr := httptest.NewRecorder()
srv.ServeHTTP(rr, req)
assert.NotContains(t, rr.Body.String(), `"capture"`)
}
func TestCaptureToolForwardsViaStaticPrincipal(t *testing.T) {
srv, brainDir := captureServer(t, nil, nil)
resp := captureCall(t, srv, "Bearer "+capStaticTok, map[string]any{
"context": map[string]any{"harness": "claude-code", "actor": "mathias", "classification": "internal"},
"insights": []map[string]any{{"text": "a fact", "wing": "hyperguild", "hall": "facts"}},
"tickets": []map[string]any{{"repo": "hyperguild", "action": "create", "title": "t"}},
})
require.Nil(t, resp["error"], "got error: %v", resp["error"])
text := resp["result"].(map[string]any)["content"].([]any)[0].(map[string]any)["text"].(string)
var rec capture.CaptureReceipt
require.NoError(t, json.Unmarshal([]byte(text), &rec))
assert.True(t, rec.Insights[0].OK)
assert.True(t, rec.Tickets[0].OK)
// Forwarded to the real brain store.
_, statErr := os.Stat(filepath.Join(brainDir, "wiki/hyperguild/facts"))
require.NoError(t, statErr)
}
func TestCaptureToolRefusesConfidentialViaUSNexus(t *testing.T) {
// JWT principal not in the sovereign allowlist ⇒ us-nexus origin.
srv, _ := captureServer(t, capFakeValidator{subject: "claudeai-oauth"}, nil)
resp := captureCall(t, srv, "Bearer jwt-token", map[string]any{
"context": map[string]any{"harness": "claudeai-chat", "actor": "mathias", "classification": "confidential"},
"insights": []map[string]any{{"text": "secret", "wing": "client-seb", "hall": "facts"}},
})
require.NotNil(t, resp["error"])
assert.Contains(t, resp["error"].(map[string]any)["message"].(string), "sovereignty")
}
func TestCaptureToolAllowsConfidentialViaSovereignJWT(t *testing.T) {
srv, _ := captureServer(t, capFakeValidator{subject: "koala-cli"}, []string{"koala-cli"})
resp := captureCall(t, srv, "Bearer jwt-token", map[string]any{
"context": map[string]any{"harness": "claude-code", "actor": "mathias", "classification": "confidential"},
"insights": []map[string]any{{"text": "secret", "wing": "client-seb", "hall": "facts"}},
})
assert.Nil(t, resp["error"], "sovereign JWT principal should be allowed: %v", resp["error"])
}
func TestCaptureToolRejectsUnauthenticated(t *testing.T) {
srv, _ := captureServer(t, capFakeValidator{err: errors.New("no jwt")}, nil)
resp := captureCall(t, srv, "", map[string]any{ // no Authorization
"context": map[string]any{"harness": "x", "classification": "internal"},
"insights": []map[string]any{{"text": "a", "wing": "hyperguild", "hall": "facts"}},
})
require.NotNil(t, resp["error"])
assert.Contains(t, resp["error"].(map[string]any)["message"].(string), "authenticated principal")
}
func TestCaptureToolCallerCannotForgeOrigin(t *testing.T) {
// Body asserts sovereign harness, but the us-nexus JWT principal governs.
srv, _ := captureServer(t, capFakeValidator{subject: "claudeai-oauth"}, nil)
resp := captureCall(t, srv, "Bearer jwt", map[string]any{
"context": map[string]any{"harness": "sovereign-soil", "classification": "confidential"},
"insights": []map[string]any{{"text": "secret", "wing": "client-seb", "hall": "facts"}},
})
require.NotNil(t, resp["error"])
assert.Contains(t, resp["error"].(map[string]any)["message"].(string), "sovereignty")
}
+116
View File
@@ -0,0 +1,116 @@
# Capture capability — implementation report (as-built)
**Status:** Shipped 2026-06-23, tagged `v0.11.0`. Epic hyperguild #49 (sub-issues #50#55) closed.
**Spec:** `specs/capture-bdd-spec.md` (the design contract this implements).
**Governed by:** `infra/docs/architecture/01-invariants.md` (I1I5) + the I2 acceptance ledger entry in `infra/docs/security-baseline.md`.
This document records what was actually built, where it lives, how it maps to the spec, and what was deferred — for onboarding and future audit. It does not restate the design rationale (see the spec and the linked brain entries).
---
## 1. Outcome
One uniform capture capability — insights → brain, action items → Gitea tickets, optional summary → ai-sessions — reachable identically from every harness:
- **In-process / direct-REST harnesses** (Claude Code CLI, Agentsquad, claude.ai Code, headless): `POST /capture` on the brain server.
- **MCP-native harnesses** (claude.ai Chat/Cowork/Design, Crush, Pi, LLM Council): the `capture` MCP tool, reached over the existing `/mcp` OAuth connector.
Both doors call the **same** `CaptureService`; only the transport and credential assembly differ. The persistence behaviour (validation, classification, I1 gate, orchestration, I5 audit, partial receipt) is written once.
---
## 2. Architecture (as-built)
```
POST /capture (REST) capture MCP tool
capturehttp.Handler mcp.Server.brainCapture
\ /
\ (auth → principal → /
\ origin; decode) /
v v
capture.CaptureService (use-case, pure)
┌───────────────┬───────────────┬──────────────┬───────────────┐
BrainStore IssueTracker SummaryWriter ClassificationPolicy AuditSink
brainstore. gitea.Client (nil today) classification.Config audit.Degrading
Store (REST) Sink / SlogSink
│ │
api.WriteNote/UpdateNote/ReadNote (#45) LokiCentral + FileBuffer
+ wing index + auto-tunnel + graph re-index + NtfyNotifier + Reconcile
```
- **`internal/capture/`** — the use-case + ports + entities. Pure; no I/O. Owns validation (fail-closed), effective-classification resolution (stricter wins), the **I1 sovereignty gate**, best-effort orchestration, the **two-phase I5 audit** (Reserve before writes / Record after), and the partial-aware receipt.
- **`internal/brainstore/`** — concrete `BrainStore` wrapping the #45 `api` primitives + wiki upkeep (wing `_index`, auto-tunnel, graph re-index). The MCP `brain_write`/`brain_update`/`brain_get` handlers were re-pointed at it: one implementation, not two.
- **`internal/classification/`** — `public < internal < confidential` taxonomy + per-wing/repo tags from an optional `classification.yaml`; fail-safe to confidential.
- **`internal/gitea/`** — `IssueTracker` over the Gitea REST API; owner forced to `mathias`; token only in the Authorization header.
- **`internal/capturehttp/`** — the REST adapter + the shared `Authenticate` / `DecodeRequest` / `OriginResolver` (also used by the MCP tool).
- **`internal/audit/`** — `SlogSink` (default) and the `DegradingSink` (loki + durable `FileBuffer` + `NtfyNotifier` + `Reconcile`).
- **`internal/mcp/`** — the `capture` relay tool + principal threading (re-derives the caller's principal from the Bearer header the chassis middleware discards).
---
## 3. Sub-issue → PR map
| Sub | Issue | PR(s) | Delivered |
|-----|-------|-------|-----------|
| 49a | #50 | #56 | classification taxonomy + per-wing/repo tags (fail-safe to confidential) |
| 49b | #51 | #57 | `CaptureService` use-case + ports + entities; `BrainStore` extraction (MCP re-pointed) |
| 49c | #52 | #58 | Gitea `IssueTracker` (owner forced mathias; token never logged) |
| 49d | #53 | #59 | `POST /capture` REST + OAuth2 + I1 sovereignty gate (server-derived origin) |
| 49e | #54 | #60 | I5 audit path + classification-aware degradation (loki + buffer + reconcile) |
| 49f | #55 | #61, infra #151 (ledger), #152 (deploy) | MCP `capture` relay tool + I2 ledger + I3 deploy |
Predecessor: #45 (`brain_update`/`brain_get` verbs, PR #46) — the read-after-write contract capture reuses.
---
## 4. Invariant compliance
| Inv | How satisfied |
|-----|---------------|
| **I1** sovereign containment | Effective classification = stricter(caller-declared, target-derived #50). Origin is **server-derived from the authenticated principal**, never `context.harness`. Confidential + us-nexus origin → refused before any write; refusal audited. Asserted-vs-derived mismatch → security event. |
| **I2** deliberate acceptance | The relay's cross-harness reach is recorded in `infra/docs/security-baseline.md` with six containment properties + Revisit-if, **merged before relay code shipped** (infra #151). |
| **I3** GitOps reconcilability | Env + `gitea-api-token` ExternalSecret under `infra/k3s/apps/supervisor/`, Flux-reconciled; image bumped by CD. No untracked runtime. |
| **I5** auditability | Every capture emits a request-level audit record. Classification-aware degradation: confidential + sink-down → hard-refuse; internal/public + sink-down → durable local buffer + ntfy + reconcile-on-recovery; floor → refuse if nothing can record. |
---
## 5. Operational reference (env)
Set on the `ingestion` deployment (`infra/k3s/apps/supervisor/ingestion-deployment.yaml`):
| Env | Purpose | Notes |
|-----|---------|-------|
| `BRAIN_GITEA_URL` / `BRAIN_GITEA_TOKEN` | enables the `IssueTracker` → gates `/capture` + the MCP tool | token from 1P `DMABE_GITEA_API_TOKEN` via ESO; unset ⇒ capture disabled |
| `BRAIN_LOKI_URL` | activates the `DegradingSink` | unset ⇒ `SlogSink` (audit to stdout → alloy → loki; no refuse/buffer semantics) |
| `BRAIN_NTFY_URL` / `BRAIN_NTFY_TOKEN` | degraded-state alerts | optional |
| `BRAIN_CAPTURE_SOVEREIGN_PRINCIPALS` | JWT subjects treated as sovereign-soil | comma-separated; static-token caller is always sovereign; unknown JWT ⇒ us-nexus (fail safe) |
| `BRAIN_AUDIT_RECONCILE_INTERVAL` | buffer→loki replay tick | default 60s |
The audit buffer lives at `<brain>/.audit-buffer/capture.jsonl` on the brain hostPath (nodeSelector-pinned to koala) — durable across restart without a separate PV.
---
## 6. Tests
67 test functions across the six packages. Coverage maps to the spec's Gherkin: happy path, supersede-not-duplicate, fail-closed validation, partial-failure receipt, dry-run, stricter-classification-wins, I1 confidential-via-us-nexus-refused / via-sovereign-allowed / asserted-label-ignored / caller-cannot-forge-origin, I5 confidential-refuse / internal-buffer / floor-refuse / reconcile / buffer-survives-restart, and the MCP relay tool (forwards, preserves principal, unauth rejected). `task check` green.
---
## 7. Deferred (not in this epic)
Tracked here so they aren't lost; file as issues when picked up:
- **SKILL veneer** — the `close-session` SKILL becomes the claude.ai trigger/harvest layer that calls capture.
- **Per-harness token provisioning** for Crush / Pi / LLM Council (claude.ai is done via the existing `/mcp` connector).
- **Harvest adapters** — transcript-parse vs chat-memory-reconstruct vs agent-runlog, each assembling capture args at its own fidelity.
- **`SummaryWriter` impl** — ai-sessions summary persistence (the port + path logic exist; the concrete writer is nil today, so a request with a summary fails that one item).
---
## 8. Brain learnings
- `wiki/hyperguild/decisions/capture-classification-taxonomy`
- `wiki/hyperguild/decisions/gate-on-server-derived-signals-fail-safe`
- `wiki/hyperguild/decisions/two-phase-reserve-record-audit-gate`
- `wiki/hyperguild/failures/mcp-bearer-middleware-discards-principal`
- `wiki/hyperguild/facts/brain-mcp-embeddings-out-of-band-sync` (from #45, the predecessor)