Version, authenticate and fully trace ecosystem calls #84

Merged
claude merged 135 commits from overnight/eco-versioned-traces into master 2026-08-01 14:50:26 +02:00
Showing only changes of commit f432eb0b25 - Show all commits
+72 -55
View File
@@ -45,6 +45,12 @@ const mavenRequester = "maven"
// setEcosystemHeaders stamps the version, requester, auth and correlation
// headers common to every outgoing ecosystem request. token may be empty,
// which means the transport itself is trusted (loopback or unix socket).
//
// The correlation ID is read from the context and never minted here. Minting
// one per request sent the far side an ID that existed nowhere on this side,
// and gave a single multi-hop action as many unrelated IDs as it made calls.
// Callers that start an action assign the ID once (handleHexisAct,
// handlePraxisAct, resolveEntityReference) and every hop inherits it.
func setEcosystemHeaders(req *http.Request, ctx context.Context, versionHeader, token string) {
req.Header.Set("Content-Type", "application/json")
req.Header.Set(versionHeader, ecosystemAPIVersion)
@@ -53,13 +59,9 @@ func setEcosystemHeaders(req *http.Request, ctx context.Context, versionHeader,
if token != "" {
req.Header.Set("Authorization", "Bearer "+token)
}
id := correlationIDFromCtx(ctx)
if id == "" {
// A call made outside a traced action still gets an ID, so the far
// side's log line can be matched to this one request.
id = newCorrelationID()
if id := correlationIDFromCtx(ctx); id != "" {
req.Header.Set("X-Correlation-ID", id)
}
req.Header.Set("X-Correlation-ID", id)
}
// ecosystemError is the typed failure every ecosystem client returns, so
@@ -202,16 +204,16 @@ func (c *nexusClient) Resolve(ctx context.Context, query string, types []string)
func (c *nexusClient) Health(ctx context.Context) error {
req, err := http.NewRequestWithContext(ctx, http.MethodGet, c.baseURL+"/health", nil)
if err != nil {
return err
return &ecosystemError{Service: "nexus", Op: "health", Err: err}
}
setEcosystemHeaders(req, ctx, "X-Nexus-Version", c.token)
resp, err := c.httpClient.Do(req)
if err != nil {
return err
return &ecosystemError{Service: "nexus", Op: "health", Err: err}
}
resp.Body.Close()
if resp.StatusCode != 200 {
return fmt.Errorf("nexus health: %s", http.StatusText(resp.StatusCode))
return httpError("nexus", "health", resp.StatusCode)
}
return nil
}
@@ -237,8 +239,11 @@ func (c *praxisClient) withToken(token string) *praxisClient {
return c
}
// getJSON performs a GET and decodes the JSON body into out.
func (c *praxisClient) getJSON(ctx context.Context, path string, out any) error {
// getJSON performs a GET and decodes the JSON body into out. op is the logical
// operation name for errors and traces: the path carries the query string, and
// after entity scoping that means an entity id in every log line built from the
// error, next to a trace that redacts far less than that.
func (c *praxisClient) getJSON(ctx context.Context, op, path string, out any) error {
req, err := http.NewRequestWithContext(ctx, http.MethodGet, c.baseURL+path, nil)
if err != nil {
return err
@@ -246,21 +251,21 @@ func (c *praxisClient) getJSON(ctx context.Context, path string, out any) error
setEcosystemHeaders(req, ctx, "X-Praxis-Version", c.token)
resp, err := c.httpClient.Do(req)
if err != nil {
return &ecosystemError{Service: "praxis", Op: path, Err: err}
return &ecosystemError{Service: "praxis", Op: op, Err: err}
}
defer resp.Body.Close()
if resp.StatusCode != 200 {
return httpError("praxis", path, resp.StatusCode)
return httpError("praxis", op, resp.StatusCode)
}
if err := json.NewDecoder(resp.Body).Decode(out); err != nil {
return &ecosystemError{Service: "praxis", Op: path, Status: resp.StatusCode, Err: err}
return &ecosystemError{Service: "praxis", Op: op, Status: resp.StatusCode, Err: err}
}
return nil
}
func (c *praxisClient) ListAttention(ctx context.Context, limit int) ([]map[string]any, error) {
var out []map[string]any
err := c.getJSON(ctx, fmt.Sprintf("/api/v1/tools/attention?limit=%d", limit), &out)
err := c.getJSON(ctx, "attention", fmt.Sprintf("/api/v1/tools/attention?limit=%d", limit), &out)
return out, err
}
@@ -270,13 +275,14 @@ func (c *praxisClient) ListAttention(ctx context.Context, limit int) ([]map[stri
// instead of filtering the unscoped list client-side.
func (c *praxisClient) ListAttentionForEntity(ctx context.Context, entityID string, limit int) ([]map[string]any, error) {
var out []map[string]any
err := c.getJSON(ctx, fmt.Sprintf("/api/v1/tools/attention?limit=%d&entity_id=%s", limit, url.QueryEscape(entityID)), &out)
err := c.getJSON(ctx, "attention_for_entity",
fmt.Sprintf("/api/v1/tools/attention?limit=%d&entity_id=%s", limit, url.QueryEscape(entityID)), &out)
return out, err
}
func (c *praxisClient) ListChanges(ctx context.Context, limit int) ([]map[string]any, error) {
var out []map[string]any
err := c.getJSON(ctx, fmt.Sprintf("/api/v1/tools/changes?limit=%d", limit), &out)
err := c.getJSON(ctx, "changes", fmt.Sprintf("/api/v1/tools/changes?limit=%d", limit), &out)
return out, err
}
@@ -302,24 +308,32 @@ type praxisItem struct {
// postItemAction posts {"item_id": id} to a Praxis tools lifecycle endpoint
// and decodes the resulting item. Shared by Surface/Acknowledge/Resolve/Ignore.
func (c *praxisClient) postItemAction(ctx context.Context, path, itemID string) (*praxisItem, error) {
body, _ := json.Marshal(map[string]any{"item_id": itemID})
func (c *praxisClient) postItemAction(ctx context.Context, op, path, itemID string) (*praxisItem, error) {
return c.postJSON(ctx, op, path, map[string]any{"item_id": itemID})
}
// postJSON posts a body to a Praxis lifecycle endpoint and decodes the item.
// Every failure is a *ecosystemError, including the transport and decode ones:
// these are the paths that mutate remote state, and the question worth
// answering afterwards is whether the call never left or was refused.
func (c *praxisClient) postJSON(ctx context.Context, op, path string, payload map[string]any) (*praxisItem, error) {
body, _ := json.Marshal(payload)
req, err := http.NewRequestWithContext(ctx, http.MethodPost, c.baseURL+path, bytes.NewReader(body))
if err != nil {
return nil, err
return nil, &ecosystemError{Service: "praxis", Op: op, Err: err}
}
setEcosystemHeaders(req, ctx, "X-Praxis-Version", c.token)
resp, err := c.httpClient.Do(req)
if err != nil {
return nil, err
return nil, &ecosystemError{Service: "praxis", Op: op, Err: err}
}
defer resp.Body.Close()
if resp.StatusCode != 200 {
return nil, httpError("praxis", path, resp.StatusCode)
return nil, httpError("praxis", op, resp.StatusCode)
}
var out praxisItem
if err := json.NewDecoder(resp.Body).Decode(&out); err != nil {
return nil, fmt.Errorf("decode: %w", err)
return nil, &ecosystemError{Service: "praxis", Op: op, Status: resp.StatusCode, Err: err}
}
return &out, nil
}
@@ -328,46 +342,28 @@ func (c *praxisClient) postItemAction(ctx context.Context, path, itemID string)
// ECOSYSTEM-SPEC.md §2.3). Callers that read attention aloud must call this, never
// Acknowledge, so "I mentioned it" stays distinguishable from "you told me you saw it".
func (c *praxisClient) Surface(ctx context.Context, itemID string) (*praxisItem, error) {
return c.postItemAction(ctx, "/api/v1/tools/surface", itemID)
return c.postItemAction(ctx, "surface", "/api/v1/tools/surface", itemID)
}
func (c *praxisClient) Acknowledge(ctx context.Context, itemID string) (*praxisItem, error) {
return c.postItemAction(ctx, "/api/v1/tools/acknowledge", itemID)
return c.postItemAction(ctx, "acknowledge", "/api/v1/tools/acknowledge", itemID)
}
func (c *praxisClient) Resolve(ctx context.Context, itemID string) (*praxisItem, error) {
return c.postItemAction(ctx, "/api/v1/tools/resolve", itemID)
return c.postItemAction(ctx, "resolve", "/api/v1/tools/resolve", itemID)
}
func (c *praxisClient) Ignore(ctx context.Context, itemID string) (*praxisItem, error) {
return c.postItemAction(ctx, "/api/v1/tools/ignore", itemID)
return c.postItemAction(ctx, "ignore", "/api/v1/tools/ignore", itemID)
}
func (c *praxisClient) Pin(ctx context.Context, itemID string, pinned bool) (*praxisItem, error) {
body, _ := json.Marshal(map[string]any{"item_id": itemID, "pinned": pinned})
req, err := http.NewRequestWithContext(ctx, http.MethodPost, c.baseURL+"/api/v1/tools/pin", bytes.NewReader(body))
if err != nil {
return nil, err
}
setEcosystemHeaders(req, ctx, "X-Praxis-Version", c.token)
resp, err := c.httpClient.Do(req)
if err != nil {
return nil, err
}
defer resp.Body.Close()
if resp.StatusCode != 200 {
return nil, httpError("praxis", "pin", resp.StatusCode)
}
var out praxisItem
if err := json.NewDecoder(resp.Body).Decode(&out); err != nil {
return nil, fmt.Errorf("decode: %w", err)
}
return &out, nil
return c.postJSON(ctx, "pin", "/api/v1/tools/pin", map[string]any{"item_id": itemID, "pinned": pinned})
}
func (c *praxisClient) GetItem(ctx context.Context, itemID string) (*praxisItem, error) {
var out praxisItem
err := c.getJSON(ctx, "/api/v1/tools/items/"+itemID, &out)
err := c.getJSON(ctx, "get_item", "/api/v1/tools/items/"+itemID, &out)
if err != nil {
return nil, err
}
@@ -376,7 +372,7 @@ func (c *praxisClient) GetItem(ctx context.Context, itemID string) (*praxisItem,
func (c *praxisClient) Search(ctx context.Context, query string, limit int) ([]praxisItem, error) {
var out []praxisItem
err := c.getJSON(ctx, fmt.Sprintf("/api/v1/tools/search?q=%s&limit=%d", url.QueryEscape(query), limit), &out)
err := c.getJSON(ctx, "search", fmt.Sprintf("/api/v1/tools/search?q=%s&limit=%d", url.QueryEscape(query), limit), &out)
return out, err
}
@@ -400,14 +396,18 @@ func wireEcosystem(cfg *config.Config) *ecosystemWiring {
// Hexis capability service
if cfg.Hexis != nil && cfg.Hexis.URL != "" {
w.hexis = hexisclient.New(cfg.Hexis.URL)
if cfg.Hexis.Token != "" {
// Upstream hexis grew Client.WithToken, but the copy vendored
// here predates it, so the token cannot be sent yet. Say so
// loudly rather than pretending the call is authenticated.
log.Printf("ecosystem: hexis token configured but the vendored hexis client cannot send it — re-vendor github.com/kami/hexis to enable bearer auth")
// Upstream hexis grew Client.WithToken, but the copy vendored here
// predates it, so the token cannot be sent. Hexis is the only one
// of the three that executes anything, and configuring auth on the
// executing service is not a best-effort request: refuse to wire it
// rather than execute unauthenticated for weeks behind one boot-time
// log line.
log.Printf("ecosystem: hexis token configured but the vendored hexis client cannot send it — hexis stays disabled; re-vendor github.com/kami/hexis to enable bearer auth")
} else {
w.hexis = hexisclient.New(cfg.Hexis.URL)
log.Printf("ecosystem: hexis at %s", cfg.Hexis.URL)
}
log.Printf("ecosystem: hexis at %s", cfg.Hexis.URL)
} else {
log.Printf("ecosystem: hexis not configured")
}
@@ -439,7 +439,19 @@ func (w *ecosystemWiring) resolveEntityReference(ctx context.Context, text strin
log.Printf("ecosystem: nexus resolve error: %v", err)
return "", "", nil, err
}
if result.Status == "resolved" && result.Entity != nil {
if result.Status == "resolved" {
// "resolved" with nothing to resolve to is a contract violation, not a
// miss. Treating it as "no such entity" let the caller fall straight
// through to the local executor with his verb intact, which is a
// dependency failure reaching execution.
if result.Entity == nil || result.Entity.ID == "" {
err := &ecosystemError{
Service: "nexus", Op: "resolve", Status: 200,
Err: errors.New("resolved status with no entity"),
}
log.Printf("ecosystem: %v", err)
return "", "", nil, err
}
return result.Entity.ID, result.Entity.DisplayName, nil, nil
}
if result.Status == "ambiguous" {
@@ -459,6 +471,11 @@ func (w *ecosystemWiring) resolveEntityReference(ctx context.Context, text strin
// healthy and genuinely has nothing registered for this entity. Callers must
// not conflate the two: a dependency failure must not silently read as "no
// capabilities" and fall through to unrelated local execution.
//
// The vendored Hexis client stamps a correlation header on Execute only, so
// discovery and execution cannot be joined on the Hexis side. Maven's own
// traces still share one ID for both hops; the gap is on the far side and
// closes when the client is re-vendored.
func (w *ecosystemWiring) discoverCapabilities(ctx context.Context, entityID string) ([]hexisclient.Capability, error) {
if w == nil || w.hexis == nil || entityID == "" {
return nil, nil