Add safe CSV artifact preview to job detail UI

Adds a Preview action next to eligible partial/final CSV artifacts on
the job detail page. Reads at most 64 KiB and 30 rows via a coordinator-
owned blob open, verifying job ownership and the same downloadable rule
as the existing download proxy so an artifact ID from another job is
never disclosed. Non-CSV and malformed/empty content fail safely with a
sanitized message instead of being rendered as text; all cell values go
through html/template escaping.

STATUS.md

@@ -32,8 +32,8 @@ Docker PostgreSQL stack on 2026-07-23.
 | CTX-04 Worker registry and HTTP API | Implemented | Registration, claim, heartbeat, result, failure, and status endpoints. |
 | CTX-05 Artifact storage | Implemented | Coordinator-owned inputs/results, checksum verification, and upload flow. |
 | CTX-06 Python Worker live-contract alignment | Implemented | Worker completed a real uploaded shard via HTTP on 2026-07-23. |
-| CTX-07 Distributed workload protocol | Implemented | Versioned Python contract models, registry, strict plan validation, and deterministic reduction ordering are in `scimesh/distributed/`. The concrete molecular planner/reducer remains CTX-08/09. |
+| CTX-07 Distributed workload protocol | Implemented | Versioned Python contract models, registry, strict plan validation, and deterministic reduction ordering are in `scimesh/distributed/`. |
-| CTX-08 Distributed similarity-search | Not started | Local reference exists. |
+| CTX-08 Distributed similarity-search | Implemented (scientific layer) | Python planner resolves `query_id` once, creates deterministic shard plans, worker adapter emits exact partial top-k CSVs/metrics, and reducer matches the local reference. Coordinator persistence/orchestration remains CTX-09. |
 | CTX-09 Reducer and final-result API | Not started | Depends on CTX-07 and CTX-08. |
 | CTX-10 Distributed similarity-graph | Not started | Local reference exists. |
 | CTX-11 Dashboard/operator view | Implemented (diagnostic scope) | Protected local view: job/task/worker status, validated similarity-search upload, diagnostic partial-artifact download, and bounded polling. Final-result reduction remains CTX-09. |
@@ -41,20 +41,22 @@ Docker PostgreSQL stack on 2026-07-23.
 
 ## Next recommended assignment
 
-Assign **CTX-08** to the workload role: implement the molecular
+Assign **CTX-09** to the coordinator role: materialize planned shards,
-`similarity-search` planner and worker adapter on top of the accepted CTX-07
+persist them transactionally, invoke the registered reducer once, and expose a
-contract.
+durable final artifact.
 
 ## Known constraints
 
-- The CTX-07 protocol is implemented, but no concrete molecular planner or
+- The Python `similarity-search` planner/reducer is implemented, but the Go
-  reducer is registered yet; the operator UI labels `partial_result` files as
+  coordinator does not yet invoke it or persist its final artifact. The
-  diagnostic and cannot present them as final output.
+  operator UI labels `partial_result` files as diagnostic and cannot present
+  them as final output.
   Use the local `scimesh` CLI for complete workload results.
 - The worker/coordinator flow currently accepts both underscore API workload
   names and hyphenated CLI names while the contract is consolidated.
-- A real-stack worker test uses a small `query_smiles` shard. Resolving a
+- A real-stack worker test uses a small `query_smiles` shard. The Python
-  `query_id` once and sharing it across shards belongs to CTX-07.
+  planner resolves `query_id` once and shares `query_smiles`; connecting that
+  planner to uploaded coordinator jobs belongs to CTX-09.
 - The coordinator accepts uploaded distributed jobs only for
   `similarity-search` with `query_smiles`. It rejects `similarity-graph` until
   CTX-10 supplies cross-shard pair planning.

coordinator/cmd/coordinator/main.go

@@ -82,6 +82,7 @@ func run() error {
 		DownloadArtifact: usecase.NewDownloadArtifact(artifactRepo, blobStore),
 		GetTaskInput:     usecase.NewGetTaskInput(taskRepo, artifactRepo, blobStore),
 		Dashboard:        usecase.NewDashboard(uiReadRepo),
+		PreviewArtifact:  usecase.NewPreviewArtifact(uiReadRepo, blobStore),
 	}
 
 	// Background reapers are tracked so shutdown can wait for them. Without this

coordinator/internal/transport/http/server.go

@@ -29,6 +29,7 @@ type UseCases struct {
 	DownloadArtifact *usecase.DownloadArtifact
 	GetTaskInput     *usecase.GetTaskInput
 	Dashboard        *usecase.Dashboard
+	PreviewArtifact  *usecase.PreviewArtifact
 }
 
 type Server struct {
@@ -82,6 +83,7 @@ func (s *Server) Handler(token string, uiToken ...string) http.Handler {
 		ui.HandleFunc("POST /ui/api/jobs/{job_id}/cancel", s.handleCancelJob)
 		ui.HandleFunc("POST /ui/api/jobs/upload", s.handleUploadDataset)
 		ui.HandleFunc("GET /ui/jobs/{job_id}/artifacts/{artifact_id}", s.handleUIArtifactDownload)
+		ui.HandleFunc("GET /ui/jobs/{job_id}/artifacts/{artifact_id}/preview", s.handleUIArtifactPreview)
 		mux.Handle("/ui", chain(ui, withRequestID, withAccessLog(s.log), withBasicAuth(uiToken[0]), withSameOrigin))
 		mux.Handle("/ui/", chain(ui, withRequestID, withAccessLog(s.log), withBasicAuth(uiToken[0]), withSameOrigin))
 	} else {

coordinator/internal/transport/http/server_test.go

@@ -42,6 +42,7 @@ func newEnvWithUIToken(t *testing.T, ready func(context.Context) error, configur
 	clk := memstore.NewClock(time.Date(2026, 7, 21, 12, 0, 0, 0, time.UTC))
 	tx := memstore.Tx{}
 	lease := 2 * time.Minute
+	uiRead := memstore.NewUIReadRepo(jobs, tasks, work, arts)
 
 	uc := coordhttp.UseCases{
 		RegisterWorker:   usecase.NewRegisterWorker(work, clk),
@@ -56,7 +57,8 @@ func newEnvWithUIToken(t *testing.T, ready func(context.Context) error, configur
 		UploadArtifact:   usecase.NewUploadArtifact(tasks, arts, blobs, tx, clk),
 		DownloadArtifact: usecase.NewDownloadArtifact(arts, blobs),
 		GetTaskInput:     usecase.NewGetTaskInput(tasks, arts, blobs),
-		Dashboard:        usecase.NewDashboard(memstore.NewUIReadRepo(jobs, tasks, work, arts)),
+		Dashboard:        usecase.NewDashboard(uiRead),
+		PreviewArtifact:  usecase.NewPreviewArtifact(uiRead, blobs),
 	}
 	worker, err := uc.RegisterWorker.Execute(context.Background(), usecase.RegisterWorkerInput{
 		Name: "test-worker", Capabilities: []string{"w", "similarity-search"},
@@ -287,6 +289,134 @@ func TestUIArtifactDownloadRejectsAnotherJobsArtifact(t *testing.T) {
 	}
 }
 
+func TestUIArtifactPreviewRequiresAuth(t *testing.T) {
+	e := newEnv(t, healthy)
+	code, job := e.do(t, "POST", "/jobs", `{"workload":"w","input_uri":"s3://in","chunks":[{"chunk_index":0,"input_uri":"s3://c","input_sha256":"sha"}]}`)
+	if code != http.StatusCreated {
+		t.Fatalf("create: %d", code)
+	}
+	_, claim := e.do(t, "POST", "/tasks/claim", `{"worker_id":"w1","capabilities":["w"]}`)
+	artifactID := e.putArtifact(t, claim["task_id"].(string), "w1", int(claim["attempt"].(float64)), "a,b\n1,2\n")
+
+	req, _ := http.NewRequestWithContext(context.Background(), "GET",
+		e.ts.URL+"/ui/jobs/"+job["id"].(string)+"/artifacts/"+artifactID+"/preview", nil)
+	resp, err := http.DefaultClient.Do(req)
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer resp.Body.Close()
+	if resp.StatusCode != http.StatusUnauthorized {
+		t.Errorf("unauthenticated preview = %d, want 401", resp.StatusCode)
+	}
+}
+
+func TestUIArtifactPreviewRendersEscapedCSVRows(t *testing.T) {
+	e := newEnv(t, healthy)
+	code, job := e.do(t, "POST", "/jobs", `{"workload":"w","input_uri":"s3://in","chunks":[{"chunk_index":0,"input_uri":"s3://c","input_sha256":"sha"}]}`)
+	if code != http.StatusCreated {
+		t.Fatalf("create: %d", code)
+	}
+	_, claim := e.do(t, "POST", "/tasks/claim", `{"worker_id":"w1","capabilities":["w"]}`)
+	csv := "chembl_id,note\nCHEMBL1,<script>alert(1)</script>\n"
+	artifactID := e.putArtifact(t, claim["task_id"].(string), "w1", int(claim["attempt"].(float64)), csv)
+
+	req, _ := http.NewRequestWithContext(context.Background(), "GET",
+		e.ts.URL+"/ui/jobs/"+job["id"].(string)+"/artifacts/"+artifactID+"/preview", nil)
+	req.SetBasicAuth("operator", uiToken)
+	resp, err := http.DefaultClient.Do(req)
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer resp.Body.Close()
+	if resp.StatusCode != http.StatusOK {
+		t.Fatalf("preview: %d", resp.StatusCode)
+	}
+	body, _ := io.ReadAll(resp.Body)
+	if strings.Contains(string(body), "<script>alert(1)</script>") {
+		t.Error("preview must escape HTML-like CSV values, found raw <script> tag")
+	}
+	if !strings.Contains(string(body), "&lt;script&gt;") {
+		t.Errorf("expected escaped script tag in preview body: %s", body)
+	}
+	if !strings.Contains(string(body), "CHEMBL1") {
+		t.Error("preview missing expected cell value")
+	}
+}
+
+func TestUIArtifactPreviewRejectsAnotherJobsArtifact(t *testing.T) {
+	e := newEnv(t, healthy)
+	code, _ := e.do(t, "POST", "/jobs", `{"workload":"w","input_uri":"s3://in","chunks":[{"chunk_index":0,"input_uri":"s3://c","input_sha256":"sha"}]}`)
+	if code != http.StatusCreated {
+		t.Fatalf("first job: %d", code)
+	}
+	_, claim := e.do(t, "POST", "/tasks/claim", `{"worker_id":"w1","capabilities":["w"]}`)
+	artifactID := e.putArtifact(t, claim["task_id"].(string), "w1", int(claim["attempt"].(float64)), "a,b\n1,2\n")
+	code, second := e.do(t, "POST", "/jobs", `{"workload":"w","input_uri":"s3://in","chunks":[{"chunk_index":0,"input_uri":"s3://c","input_sha256":"sha"}]}`)
+	if code != http.StatusCreated {
+		t.Fatalf("second job: %d", code)
+	}
+	req, _ := http.NewRequestWithContext(context.Background(), "GET",
+		e.ts.URL+"/ui/jobs/"+second["id"].(string)+"/artifacts/"+artifactID+"/preview", nil)
+	req.SetBasicAuth("operator", uiToken)
+	resp, err := http.DefaultClient.Do(req)
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer resp.Body.Close()
+	if resp.StatusCode != http.StatusNotFound {
+		t.Errorf("cross-job preview = %d, want 404", resp.StatusCode)
+	}
+}
+
+func TestUIArtifactPreviewIsFriendlyForNonCSV(t *testing.T) {
+	e := newEnv(t, healthy)
+	code, job := e.do(t, "POST", "/jobs", `{"workload":"w","input_uri":"s3://in","chunks":[{"chunk_index":0,"input_uri":"s3://c","input_sha256":"sha"}]}`)
+	if code != http.StatusCreated {
+		t.Fatalf("create: %d", code)
+	}
+	_, claim := e.do(t, "POST", "/tasks/claim", `{"worker_id":"w1","capabilities":["w"]}`)
+	taskID := claim["task_id"].(string)
+	attempt := int(claim["attempt"].(float64))
+
+	req, _ := http.NewRequestWithContext(context.Background(), "PUT",
+		e.ts.URL+"/tasks/"+taskID+"/artifacts/notes.bin", strings.NewReader("\x00\x01binary garbage"))
+	req.Header.Set("Authorization", "Bearer "+token)
+	req.Header.Set("Content-Type", "application/octet-stream")
+	req.Header.Set("X-Worker-ID", e.workerID)
+	req.Header.Set("X-Task-Attempt", strconv.Itoa(attempt))
+	putResp, err := http.DefaultClient.Do(req)
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer putResp.Body.Close()
+	if putResp.StatusCode != http.StatusOK {
+		t.Fatalf("put non-csv artifact: %d", putResp.StatusCode)
+	}
+	var m map[string]any
+	b, _ := io.ReadAll(putResp.Body)
+	_ = json.Unmarshal(b, &m)
+	artifactID := m["artifact_id"].(string)
+
+	previewReq, _ := http.NewRequestWithContext(context.Background(), "GET",
+		e.ts.URL+"/ui/jobs/"+job["id"].(string)+"/artifacts/"+artifactID+"/preview", nil)
+	previewReq.SetBasicAuth("operator", uiToken)
+	resp, err := http.DefaultClient.Do(previewReq)
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer resp.Body.Close()
+	if resp.StatusCode != http.StatusOK {
+		t.Fatalf("preview status: %d", resp.StatusCode)
+	}
+	body, _ := io.ReadAll(resp.Body)
+	if strings.Contains(string(body), "binary garbage") {
+		t.Error("non-CSV bytes must not be rendered as text")
+	}
+	if !strings.Contains(string(body), "not a CSV file") {
+		t.Errorf("expected a friendly non-CSV explanation, got: %s", body)
+	}
+}
+
 func TestHealthUnavailableWhenDBDown(t *testing.T) {
 	e := newEnv(t, func(context.Context) error { return context.DeadlineExceeded })
 	resp := e.get(t, "/health")

coordinator/internal/transport/http/templates/artifact-preview.html

@@ -0,0 +1,31 @@
+{{define "artifact-preview.html"}}
+<!doctype html>
+<html lang="en">
+<head>
+  <meta charset="utf-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1">
+  <title>SciMesh artifact preview</title>
+  <style>
+    :root{color:#172033;background:#f6f8fc;font:16px/1.5 system-ui,sans-serif}body{margin:0}.page{max-width:1180px;margin:auto;padding:32px 20px 56px}a{color:#174ecf}.back{text-decoration:none}h1{margin:18px 0 4px;font-size:1.6rem;word-break:break-word}.muted{color:#68758b}.notice{margin:16px 0;padding:15px 17px;border:1px solid #f2cb72;border-radius:10px;background:#fff8e6}.table-wrap{overflow-x:auto;border:1px solid #dfe5f0;border-radius:10px;background:#fff;margin-top:16px}table{width:100%;border-collapse:collapse}td,th{padding:10px 12px;border-bottom:1px solid #e8ecf4;text-align:left;vertical-align:top;white-space:pre-wrap;word-break:break-word}th{color:#50617d;font-size:.78rem;text-transform:uppercase;letter-spacing:.06em;background:#f6f8fc}tr:last-child td{border:0}.empty{padding:24px;text-align:center;color:#68758b}
+  </style>
+</head>
+<body>
+  <main class="page">
+    <a class="back" href="/ui/jobs/{{.JobID}}">← Back to job</a>
+    <h1>Preview: {{.Filename}}</h1>
+    <p class="muted">Diagnostic preview only — a partial shard result, not a final molecular-search answer. At most {{.RowLimit}} rows and {{.ByteLimit}} bytes are read from storage.</p>
+    {{if not .Previewable}}
+      <div class="notice">{{.Reason}}</div>
+    {{else}}
+      {{if .Truncated}}<div class="notice">Truncated: showing at most the first {{.RowLimit}} rows or {{.ByteLimit}} bytes of this artifact. Download it for the full contents.</div>{{end}}
+      <div class="table-wrap">
+        <table>
+          <tr>{{range .Headers}}<th>{{.}}</th>{{end}}</tr>
+          {{range .Rows}}<tr>{{range .}}<td>{{.}}</td>{{end}}</tr>{{else}}<tr><td class="empty" colspan="99">No data rows.</td></tr>{{end}}
+        </table>
+      </div>
+    {{end}}
+  </main>
+</body>
+</html>
+{{end}}

coordinator/internal/transport/http/templates/job.html

@@ -17,7 +17,7 @@
     <h2>Shard tasks</h2><p class="muted">If a task fails, its code and message appear here. Refresh the page to update the detailed rows.</p>
     <div class="table-wrap"><table><tr><th>Shard</th><th>State</th><th>Attempt</th><th>Worker / lease</th><th>Error</th></tr>{{range .Tasks}}<tr><td>#{{.ChunkIndex}}</td><td><span class="status status-{{statusClass .Status}}">{{statusLabel .Status}}</span></td><td>{{.Attempt}} / {{.MaxAttempts}}</td><td>{{if .LeaseOwner}}<code>{{.LeaseOwner}}</code>{{if .LeaseExpiresAt}}<br><small>until {{time .LeaseExpiresAt}}</small>{{end}}{{else}}<span class="muted">—</span>{{end}}</td><td class="error">{{if .ErrorCode}}<strong>{{taskErrorLabel .ErrorCode}}</strong><br><small>{{taskErrorHint .ErrorCode}}</small>{{else}}<span class="muted">—</span>{{end}}</td></tr>{{else}}<tr><td colspan="5" class="empty">No tasks have appeared yet.</td></tr>{{end}}</table></div>
     <h2>Coordinator artifacts</h2>
-    <div class="table-wrap"><table><tr><th>Type</th><th>File</th><th>Size</th><th>Integrity check</th><th></th></tr>{{range .Artifacts}}<tr><td>{{if .Diagnostic}}<strong>Partial result</strong><br><small>diagnostic</small>{{else}}{{.Kind}}{{end}}</td><td>{{.Filename}}</td><td>{{bytes .SizeBytes}}</td><td><code>{{.SHA256}}</code></td><td>{{if .Downloadable}}<a class="download" href="/ui/jobs/{{$.ID}}/artifacts/{{.ID}}">Download CSV</a>{{else}}<span class="muted">Unavailable</span>{{end}}</td></tr>{{else}}<tr><td colspan="5" class="empty">No artifacts yet. The worker uploads a CSV after it completes a shard.</td></tr>{{end}}</table></div>
+    <div class="table-wrap"><table><tr><th>Type</th><th>File</th><th>Size</th><th>Integrity check</th><th></th></tr>{{range .Artifacts}}<tr><td>{{if .Diagnostic}}<strong>Partial result</strong><br><small>diagnostic</small>{{else}}{{.Kind}}{{end}}</td><td>{{.Filename}}</td><td>{{bytes .SizeBytes}}</td><td><code>{{.SHA256}}</code></td><td>{{if .Downloadable}}<a class="download" href="/ui/jobs/{{$.ID}}/artifacts/{{.ID}}">Download CSV</a> <a class="download" href="/ui/jobs/{{$.ID}}/artifacts/{{.ID}}/preview">Preview</a>{{else}}<span class="muted">Unavailable</span>{{end}}</td></tr>{{else}}<tr><td colspan="5" class="empty">No artifacts yet. The worker uploads a CSV after it completes a shard.</td></tr>{{end}}</table></div>
   </main>
   <script>
     const id={{printf "%q" .ID}},state={pending:['Waiting for a worker','waiting','Waiting for an available worker with the required capability.'],leased:['Assigned to a worker','active','A worker has claimed the task and should begin processing shortly.'],running:['Running','active','A worker is reading a shard, calculating fingerprints, and uploading its result through the coordinator.'],completed:['Tasks complete','success','Every shard task is complete. Files below are still partial results.'],failed:['Needs attention','danger','One or more shard tasks failed. Open the task list below for details.'],cancelled:['Stopped','waiting','The operator stopped this job. No new shards can be claimed.']};

coordinator/internal/transport/http/ui.go

@@ -279,3 +279,26 @@ func (s *Server) handleUIArtifactDownload(w http.ResponseWriter, r *http.Request
 	w.Header().Set("X-Checksum-SHA256", art.SHA256)
 	_, _ = io.Copy(w, body)
 }
+
+// handleUIArtifactPreview renders a bounded, job-scoped CSV preview. The use
+// case enforces the same ownership and downloadable rule as the download
+// proxy above; nothing here trusts the artifact ID beyond that check.
+func (s *Server) handleUIArtifactPreview(w http.ResponseWriter, r *http.Request) {
+	jobID, ok := s.uiJobID(w, r)
+	if !ok {
+		return
+	}
+	artifactID, err := uuid.Parse(r.PathValue("artifact_id"))
+	if err != nil {
+		s.writeError(w, r, domain.ErrInvalidInput)
+		return
+	}
+	ctx, cancel := s.reqCtx(r)
+	defer cancel()
+	view, err := s.uc.PreviewArtifact.Execute(ctx, jobID, artifactID)
+	if err != nil {
+		s.writeError(w, r, err)
+		return
+	}
+	s.renderUI(w, "artifact-preview.html", view)
+}

coordinator/internal/usecase/preview.go

@@ -0,0 +1,150 @@
+package usecase
+
+import (
+	"context"
+	"encoding/csv"
+	"errors"
+	"io"
+	"strings"
+
+	"github.com/google/uuid"
+
+	"github.com/emil28092005/SciMesh/coordinator/internal/domain"
+)
+
+// previewMaxRows and previewMaxBytes bound how much of an artifact the
+// diagnostic preview ever reads or renders: a partial shard CSV can be large,
+// and this is a diagnostic aid, not a viewer for the full file.
+const (
+	previewMaxRows  = 30
+	previewMaxBytes = 64 * 1024
+)
+
+// ArtifactPreviewView is what the UI renders for a diagnostic CSV preview. It
+// never carries a storage path, database error, or worker-local detail.
+type ArtifactPreviewView struct {
+	JobID       string
+	ArtifactID  string
+	Filename    string
+	Previewable bool
+	Reason      string
+	Headers     []string
+	Rows        [][]string
+	Truncated   bool
+	RowLimit    int
+	ByteLimit   int64
+}
+
+// PreviewArtifact renders at most the first previewMaxRows rows of a CSV
+// artifact, reading at most previewMaxBytes from storage. It reuses the same
+// job-scoped, downloadable-artifact rule as the download proxy so an artifact
+// ID from another job is never previewable.
+type PreviewArtifact struct {
+	read  UIReadRepository
+	blobs BlobStore
+}
+
+func NewPreviewArtifact(read UIReadRepository, blobs BlobStore) *PreviewArtifact {
+	return &PreviewArtifact{read: read, blobs: blobs}
+}
+
+func (p *PreviewArtifact) Execute(ctx context.Context, jobID, artifactID uuid.UUID) (ArtifactPreviewView, error) {
+	job, err := p.read.GetJob(ctx, jobID)
+	if err != nil {
+		return ArtifactPreviewView{}, err
+	}
+	tasks, err := p.read.ListTasksByJob(ctx, jobID)
+	if err != nil {
+		return ArtifactPreviewView{}, err
+	}
+	// Same status derivation the dashboard uses, so a final artifact previews
+	// exactly when it would also be offered for download.
+	status := jobCard(*job, tasks).Status
+
+	artifacts, err := p.read.ListArtifactsByJob(ctx, jobID)
+	if err != nil {
+		return ArtifactPreviewView{}, err
+	}
+	var art *domain.Artifact
+	for i := range artifacts {
+		if artifacts[i].ID == artifactID {
+			art = &artifacts[i]
+			break
+		}
+	}
+	if art == nil {
+		return ArtifactPreviewView{}, domain.ErrArtifactNotFound
+	}
+	downloadable := art.Kind == domain.ArtifactPartialResult ||
+		(art.Kind == domain.ArtifactFinalResult && status == string(domain.JobCompleted))
+	if !downloadable {
+		return ArtifactPreviewView{}, domain.ErrArtifactNotFound
+	}
+
+	view := ArtifactPreviewView{
+		JobID:      jobID.String(),
+		ArtifactID: art.ID.String(),
+		Filename:   art.Filename,
+		RowLimit:   previewMaxRows,
+		ByteLimit:  previewMaxBytes,
+	}
+	if !isCSVArtifact(art) {
+		view.Reason = "This artifact is not a CSV file, so it cannot be shown as text here. Download it instead."
+		return view, nil
+	}
+	if art.SizeBytes == 0 {
+		view.Reason = "This artifact is empty."
+		return view, nil
+	}
+
+	rc, err := p.blobs.Open(ctx, art.StorageKey)
+	if err != nil {
+		return ArtifactPreviewView{}, err
+	}
+	defer func() { _ = rc.Close() }()
+
+	// LimitedReader caps the bytes read from storage regardless of how many
+	// rows are found within that window — the artifact is never loaded whole.
+	limited := &io.LimitedReader{R: rc, N: previewMaxBytes}
+	reader := csv.NewReader(limited)
+	reader.FieldsPerRecord = -1 // a byte-limited cut mid-row must not look like a schema error
+
+	header, err := reader.Read()
+	if err != nil {
+		view.Reason = "This artifact could not be read as CSV."
+		return view, nil
+	}
+	view.Headers = append([]string(nil), header...)
+
+	rows := make([][]string, 0, previewMaxRows)
+	for len(rows) < previewMaxRows {
+		record, err := reader.Read()
+		if err != nil {
+			if !errors.Is(err, io.EOF) {
+				// Malformed content further into the stream: keep what parsed
+				// cleanly and say the preview stopped early.
+				view.Truncated = true
+			}
+			break
+		}
+		rows = append(rows, append([]string(nil), record...))
+	}
+	view.Rows = rows
+
+	if art.SizeBytes > previewMaxBytes {
+		view.Truncated = true
+	} else if len(rows) == previewMaxRows {
+		if _, err := reader.Read(); err == nil {
+			view.Truncated = true
+		}
+	}
+	view.Previewable = true
+	return view, nil
+}
+
+func isCSVArtifact(a *domain.Artifact) bool {
+	if a.ContentType == "text/csv" {
+		return true
+	}
+	return strings.HasSuffix(strings.ToLower(a.Filename), ".csv")
+}

coordinator/internal/usecase/preview_test.go

@@ -0,0 +1,226 @@
+package usecase_test
+
+import (
+	"context"
+	"errors"
+	"strconv"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/google/uuid"
+
+	"github.com/emil28092005/SciMesh/coordinator/internal/domain"
+	"github.com/emil28092005/SciMesh/coordinator/internal/memstore"
+	"github.com/emil28092005/SciMesh/coordinator/internal/usecase"
+)
+
+func newPreviewHarness() (*usecase.PreviewArtifact, *memstore.JobRepo, *memstore.TaskRepo, *memstore.ArtifactRepo, *memstore.BlobStore) {
+	jobs := memstore.NewJobRepo()
+	tasks := memstore.NewTaskRepo()
+	work := memstore.NewWorkerRepo()
+	arts := memstore.NewArtifactRepo()
+	blobs := memstore.NewBlobStore()
+	read := memstore.NewUIReadRepo(jobs, tasks, work, arts)
+	return usecase.NewPreviewArtifact(read, blobs), jobs, tasks, arts, blobs
+}
+
+func mustInsertJob(t *testing.T, jobs *memstore.JobRepo, status domain.JobStatus) uuid.UUID {
+	t.Helper()
+	job := &domain.Job{ID: uuid.New(), Workload: "similarity-search", Status: status, CreatedAt: time.Now()}
+	if err := jobs.Insert(context.Background(), job); err != nil {
+		t.Fatalf("insert job: %v", err)
+	}
+	return job.ID
+}
+
+func mustCompleteJob(t *testing.T, jobs *memstore.JobRepo, tasks *memstore.TaskRepo) uuid.UUID {
+	t.Helper()
+	jobID := mustInsertJob(t, jobs, domain.JobRunning)
+	task := &domain.Task{
+		ID: uuid.New(), JobID: jobID, ChunkIndex: 0, Workload: "similarity-search",
+		Status: domain.TaskCompleted, MaxAttempts: 3, CreatedAt: time.Now(),
+	}
+	if err := tasks.InsertBatch(context.Background(), []*domain.Task{task}); err != nil {
+		t.Fatalf("insert task: %v", err)
+	}
+	return jobID
+}
+
+func mustInsertArtifact(t *testing.T, arts *memstore.ArtifactRepo, blobs *memstore.BlobStore,
+	jobID uuid.UUID, kind domain.ArtifactKind, filename, contentType, body string) uuid.UUID {
+	t.Helper()
+	id := uuid.New()
+	sha, size, err := blobs.Put(context.Background(), id.String(), strings.NewReader(body))
+	if err != nil {
+		t.Fatalf("put blob: %v", err)
+	}
+	art := &domain.Artifact{
+		ID: id, JobID: jobID, Kind: kind, Filename: filename,
+		StorageKey: id.String(), ContentType: contentType,
+		SizeBytes: size, SHA256: sha, CreatedAt: time.Now(),
+	}
+	if err := arts.Insert(context.Background(), art); err != nil {
+		t.Fatalf("insert artifact: %v", err)
+	}
+	return id
+}
+
+func TestPreviewArtifactRendersCSVRows(t *testing.T) {
+	preview, jobs, _, arts, blobs := newPreviewHarness()
+	jobID := mustInsertJob(t, jobs, domain.JobRunning)
+	artID := mustInsertArtifact(t, arts, blobs, jobID, domain.ArtifactPartialResult, "result.csv", "text/csv",
+		"chembl_id,score\nCHEMBL1,0.9\nCHEMBL2,0.8\n")
+
+	view, err := preview.Execute(context.Background(), jobID, artID)
+	if err != nil {
+		t.Fatalf("Execute: %v", err)
+	}
+	if !view.Previewable {
+		t.Fatalf("expected previewable, reason=%q", view.Reason)
+	}
+	if view.Truncated {
+		t.Error("small CSV should not be truncated")
+	}
+	if len(view.Headers) != 2 || view.Headers[0] != "chembl_id" {
+		t.Errorf("headers = %v", view.Headers)
+	}
+	if len(view.Rows) != 2 || view.Rows[0][0] != "CHEMBL1" {
+		t.Errorf("rows = %v", view.Rows)
+	}
+}
+
+func TestPreviewArtifactTruncatesAt30Rows(t *testing.T) {
+	preview, jobs, _, arts, blobs := newPreviewHarness()
+	jobID := mustInsertJob(t, jobs, domain.JobRunning)
+
+	var sb strings.Builder
+	sb.WriteString("id,value\n")
+	for i := 0; i < 40; i++ {
+		sb.WriteString("R" + strconv.Itoa(i) + ",v\n")
+	}
+	artID := mustInsertArtifact(t, arts, blobs, jobID, domain.ArtifactPartialResult, "result.csv", "text/csv", sb.String())
+
+	view, err := preview.Execute(context.Background(), jobID, artID)
+	if err != nil {
+		t.Fatalf("Execute: %v", err)
+	}
+	if len(view.Rows) != 30 {
+		t.Fatalf("rows = %d, want 30", len(view.Rows))
+	}
+	if !view.Truncated {
+		t.Error("expected truncated for more than 30 data rows")
+	}
+}
+
+func TestPreviewArtifactTruncatesAt64KiB(t *testing.T) {
+	preview, jobs, _, arts, blobs := newPreviewHarness()
+	jobID := mustInsertJob(t, jobs, domain.JobRunning)
+
+	var sb strings.Builder
+	sb.WriteString("id,value\n")
+	row := "row," + strings.Repeat("x", 200) + "\n"
+	for sb.Len() < 70*1024 {
+		sb.WriteString(row)
+	}
+	artID := mustInsertArtifact(t, arts, blobs, jobID, domain.ArtifactPartialResult, "result.csv", "text/csv", sb.String())
+
+	view, err := preview.Execute(context.Background(), jobID, artID)
+	if err != nil {
+		t.Fatalf("Execute: %v", err)
+	}
+	if !view.Truncated {
+		t.Error("expected truncated for an artifact bigger than 64KiB")
+	}
+	if len(view.Rows) > 30 {
+		t.Errorf("rows = %d, want <= 30", len(view.Rows))
+	}
+}
+
+func TestPreviewArtifactRejectsNonCSV(t *testing.T) {
+	preview, jobs, _, arts, blobs := newPreviewHarness()
+	jobID := mustInsertJob(t, jobs, domain.JobRunning)
+	artID := mustInsertArtifact(t, arts, blobs, jobID, domain.ArtifactPartialResult,
+		"shard-0.tsv", "text/tab-separated-values", "chembl_id\tcanonical_smiles\nCHEMBL1\tCCO\n")
+
+	view, err := preview.Execute(context.Background(), jobID, artID)
+	if err != nil {
+		t.Fatalf("Execute: %v", err)
+	}
+	if view.Previewable {
+		t.Error("non-CSV artifact must not be previewable as text")
+	}
+	if view.Reason == "" {
+		t.Error("expected a friendly reason")
+	}
+}
+
+func TestPreviewArtifactFailsSafelyOnEmptyArtifact(t *testing.T) {
+	preview, jobs, _, arts, blobs := newPreviewHarness()
+	jobID := mustInsertJob(t, jobs, domain.JobRunning)
+	artID := mustInsertArtifact(t, arts, blobs, jobID, domain.ArtifactPartialResult, "result.csv", "text/csv", "")
+
+	view, err := preview.Execute(context.Background(), jobID, artID)
+	if err != nil {
+		t.Fatalf("Execute: %v", err)
+	}
+	if view.Previewable {
+		t.Error("empty artifact must not be previewable")
+	}
+	if view.Reason == "" {
+		t.Error("expected a friendly reason")
+	}
+}
+
+func TestPreviewArtifactFailsSafelyOnMalformedCSV(t *testing.T) {
+	preview, jobs, _, arts, blobs := newPreviewHarness()
+	jobID := mustInsertJob(t, jobs, domain.JobRunning)
+	// An unterminated quote makes even the header row unparsable.
+	artID := mustInsertArtifact(t, arts, blobs, jobID, domain.ArtifactPartialResult, "result.csv", "text/csv", `"unterminated`)
+
+	view, err := preview.Execute(context.Background(), jobID, artID)
+	if err != nil {
+		t.Fatalf("Execute: %v", err)
+	}
+	if view.Previewable {
+		t.Error("malformed CSV must not be previewable")
+	}
+	if view.Reason == "" {
+		t.Error("expected a friendly reason")
+	}
+}
+
+func TestPreviewArtifactRejectsCrossJobArtifact(t *testing.T) {
+	preview, jobs, _, arts, blobs := newPreviewHarness()
+	jobA := mustInsertJob(t, jobs, domain.JobRunning)
+	jobB := mustInsertJob(t, jobs, domain.JobRunning)
+	artID := mustInsertArtifact(t, arts, blobs, jobA, domain.ArtifactPartialResult, "result.csv", "text/csv", "a,b\n1,2\n")
+
+	if _, err := preview.Execute(context.Background(), jobB, artID); !errors.Is(err, domain.ErrArtifactNotFound) {
+		t.Fatalf("err = %v, want ErrArtifactNotFound", err)
+	}
+}
+
+func TestPreviewArtifactRejectsUncompletedFinalResult(t *testing.T) {
+	preview, jobs, _, arts, blobs := newPreviewHarness()
+	jobID := mustInsertJob(t, jobs, domain.JobRunning)
+	artID := mustInsertArtifact(t, arts, blobs, jobID, domain.ArtifactFinalResult, "final.csv", "text/csv", "a,b\n1,2\n")
+
+	if _, err := preview.Execute(context.Background(), jobID, artID); !errors.Is(err, domain.ErrArtifactNotFound) {
+		t.Fatalf("err = %v, want ErrArtifactNotFound", err)
+	}
+}
+
+func TestPreviewArtifactAllowsFinalResultOnceJobIsCompleted(t *testing.T) {
+	preview, jobs, tasks, arts, blobs := newPreviewHarness()
+	jobID := mustCompleteJob(t, jobs, tasks)
+	artID := mustInsertArtifact(t, arts, blobs, jobID, domain.ArtifactFinalResult, "final.csv", "text/csv", "a,b\n1,2\n")
+
+	view, err := preview.Execute(context.Background(), jobID, artID)
+	if err != nil {
+		t.Fatalf("Execute: %v", err)
+	}
+	if !view.Previewable {
+		t.Fatalf("expected previewable, reason=%q", view.Reason)
+	}
+}

docs/ctx-07-distributed-workload-protocol.md

@@ -4,9 +4,11 @@
 
 This document is the implementation contract for CTX-07. Its generic protocol,
 registry, strict JSON models, and deterministic reduction ordering are
-implemented in `scimesh/distributed/`. It does not implement a molecular
+implemented in `scimesh/distributed/`. CTX-08 implements the molecular
-planner, reducer, API endpoint, database migration, or final artifact. Until
+similarity-search planner, worker adapter, and pure reducer on top of it. This
-CTX-08 and CTX-09 are complete, shard CSVs remain diagnostic partial results.
+document does not implement a coordinator API endpoint, database migration, or
+durable final artifact. Until CTX-09 is complete, shard CSVs remain diagnostic
+partial results.
 
 The protocol gives local scientific workloads a coordinator-independent way to
 validate a job, plan artifact-backed tasks, and later reduce completed outputs.
@@ -154,7 +156,10 @@ rank,chembl_id,canonical_smiles,similarity
 ```
 
 - `rank` is one-based local rank.
-- `similarity` uses the local CLI's six-decimal formatting.
+- `similarity` uses a round-trip decimal representation of the computed float
+  (for Python, `repr(similarity)`). This preserves exact cross-shard ranking;
+  the reducer writes the user-facing final CSV with the local CLI's six-decimal
+  display formatting.
 - Rows are sorted by `(-similarity, chembl_id, canonical_smiles)` for
   `threshold_direction=greater`, or `(similarity, chembl_id,
   canonical_smiles)` for `less`.
@@ -203,7 +208,7 @@ multiplicity. Reduction is independent of worker completion order and uses
 
 ## Deferred work
 
-CTX-08 implements the similarity-search planner, runner adapter, reducer, and
+CTX-09 materializes the planned shard files as coordinator artifacts, invokes
-comparison against the local CLI. CTX-09 persists the final artifact and job
+the registered reducer once, and persists its final artifact/job state. CTX-10
-state. CTX-10 defines graph-specific triangular block plans; it must not reuse
+defines graph-specific triangular block plans; it must not reuse the search
-the search shard scheme without its pair-coverage invariants.
+shard scheme without its pair-coverage invariants.

docs/worker-daemon-task.md

@@ -122,7 +122,10 @@ Content-Type: application/json
   },
   "metrics": {
     "elapsed_seconds": 12.4,
-    "processed_rows": 10000
+    "scanned_rows": 10000,
+    "valid_molecules": 9876,
+    "invalid_smiles": 124,
+    "matches_emitted": 20
   }
 }
 ```
@@ -189,8 +192,11 @@ class Runner(Protocol):
         """Run one task and return output artifacts plus safe metrics."""
 ```
 
-`SciMeshRunner` should map `workload` and validated parameters to the existing
+`SciMeshRunner` maps an allowlisted workload and validated parameters to the
-SciMesh CLI. For example, a `similarity-search` task invokes:
+local SciMesh reference functions. A planned `similarity-search` task contains
+a resolved `query_smiles` (never `query_id`) and writes one exact local top-k
+partial CSV plus the metrics above. Legacy single-shard tasks may still use the
+CLI compatibility path:
 
 ```text
 scimesh similarity-search <local-input> --query-id ... --output <task-dir>/result.csv

scimesh/distributed/__init__.py

@@ -12,17 +12,25 @@ from .models import (
     FinalResult,
     PlannedTask,
 )
-from .registry import DistributedWorkloadRegistry, PlanningService, WorkloadDescription
+from .registry import (
+    DistributedWorkloadRegistry,
+    PlanningService,
+    WorkloadDescription,
+    default_distributed_registry,
+)
+from .similarity_search import SimilaritySearchDistributedWorkload
 from .workload import DistributedWorkload
 
 __all__ = [
     "ArtifactReference",
     "CompletedPartial",
+    "default_distributed_registry",
     "DistributedPlan",
     "DistributedWorkload",
     "DistributedWorkloadRegistry",
     "FinalResult",
     "PlannedTask",
     "PlanningService",
+    "SimilaritySearchDistributedWorkload",
     "WorkloadDescription",
 ]

scimesh/distributed/registry.py

@@ -50,7 +50,8 @@ class PlanningService:
 
     It writes neither jobs nor artifacts.  A Go coordinator bridge can therefore
     validate and produce a plan before opening its own all-or-nothing persistence
-    transaction; CTX-08/09 will implement that concrete bridge and reducers.
+    transaction; CTX-09 will implement that concrete bridge and durable result
+    orchestration.
     """
 
     def __init__(self, registry: DistributedWorkloadRegistry) -> None:
@@ -94,3 +95,14 @@ class PlanningService:
         if not isinstance(result, FinalResult):
             raise ValueError("distributed reducer must return a FinalResult")
         return result
+
+
+def default_distributed_registry() -> DistributedWorkloadRegistry:
+    """Return the currently supported distributed scientific workloads."""
+    # Delayed import keeps the generic registry independent of concrete RDKit
+    # workloads and avoids making the contract layer import application setup.
+    from .similarity_search import SimilaritySearchDistributedWorkload
+
+    registry = DistributedWorkloadRegistry()
+    registry.register(SimilaritySearchDistributedWorkload())
+    return registry

scimesh/distributed/similarity_search.py

@@ -0,0 +1,380 @@
+"""Distributed planning and reduction for exact molecular similarity search."""
+
+from __future__ import annotations
+
+import csv
+import hashlib
+import heapq
+import math
+from pathlib import Path
+from typing import Any, Iterator, Mapping, Sequence
+from uuid import UUID, uuid5
+
+from rdkit import Chem
+
+from scimesh.chemistry.dataset import MoleculeRecord, find_molecule_by_id, parse_smiles
+from scimesh.chemistry.fingerprints import FP_RADIUS, FP_SIZE
+from scimesh.workloads.similarity_search import (
+    SimilarityMatch,
+    _HeapEntry,
+    search_similar,
+    write_search_results,
+)
+
+from .models import ArtifactReference, CompletedPartial, DistributedPlan, FinalResult, PlannedTask
+
+
+_TSV_CONTENT_TYPE = "text/tab-separated-values"
+_CSV_CONTENT_TYPE = "text/csv"
+_SEARCH_COLUMNS = ("rank", "chembl_id", "canonical_smiles", "similarity")
+_REQUIRED_COLUMNS = {"chembl_id", "canonical_smiles"}
+
+
+def write_similarity_search_partial(output_path: Path, matches: Sequence[SimilarityMatch]) -> None:
+    """Write a worker partial with a round-trip score, not display rounding.
+
+    The public final CSV continues to use the local CLI's six-decimal display.
+    A reducer needs the full binary float representation to rank candidates
+    from separate shards exactly as the single-process reference does.
+    """
+    output_path.parent.mkdir(parents=True, exist_ok=True)
+    with output_path.open("w", encoding="utf-8", newline="") as destination:
+        writer = csv.DictWriter(destination, fieldnames=_SEARCH_COLUMNS)
+        writer.writeheader()
+        for rank, match in enumerate(matches, start=1):
+            writer.writerow({
+                "rank": rank,
+                "chembl_id": match.molecule_id,
+                "canonical_smiles": match.smiles,
+                "similarity": repr(match.similarity),
+            })
+
+
+class SimilaritySearchDistributedWorkload:
+    """Planner/reducer for exact global top-k Tanimoto similarity search."""
+
+    name = "similarity-search"
+    description = "Exact top-k molecular similarity search over deterministic TSV shards."
+
+    def validate_job(self, parameters: Mapping[str, object]) -> None:
+        allowed = {
+            "query_id", "query_smiles", "top_k", "threshold",
+            "threshold_direction", "max_rows", "progress_every",
+        }
+        unknown = set(parameters) - allowed
+        if unknown:
+            raise ValueError(f"unsupported similarity-search parameters: {', '.join(sorted(unknown))}")
+        query_id = parameters.get("query_id")
+        query_smiles = parameters.get("query_smiles")
+        if (query_id is None) == (query_smiles is None):
+            raise ValueError("exactly one of query_id or query_smiles is required")
+        if query_id is not None:
+            self._string(query_id, "query_id")
+        if query_smiles is not None:
+            self._string(query_smiles, "query_smiles")
+        self._positive_int(parameters.get("top_k", 20), "top_k")
+        if "max_rows" in parameters:
+            self._positive_int(parameters["max_rows"], "max_rows")
+        if "progress_every" in parameters:
+            self._nonnegative_int(parameters["progress_every"], "progress_every")
+        if "threshold" in parameters:
+            self._unit_interval(parameters["threshold"], "threshold")
+        if "threshold_direction" in parameters and parameters["threshold_direction"] not in {"greater", "less"}:
+            raise ValueError("threshold_direction must be 'greater' or 'less'")
+
+    def plan(
+        self,
+        input_path: Path,
+        input_artifact_id: str,
+        parameters: Mapping[str, object],
+        shard_rows: int,
+        workspace: Path,
+    ) -> DistributedPlan:
+        self.validate_job(parameters)
+        if not input_path.is_file():
+            raise ValueError("input_path must be a readable dataset file")
+        if isinstance(shard_rows, bool) or not isinstance(shard_rows, int) or shard_rows < 1:
+            raise ValueError("shard_rows must be a positive integer")
+        try:
+            input_id = UUID(input_artifact_id)
+        except ValueError as error:
+            raise ValueError("input_artifact_id must be a UUID") from error
+
+        query_smiles, query_source = self._resolve_query(input_path, parameters)
+        resolved = self._resolved_parameters(parameters, query_smiles, query_source)
+        workspace.mkdir(parents=True, exist_ok=True)
+        shard_paths: list[Path] = []
+        try:
+            shard_paths = self._write_shards(input_path, workspace, shard_rows, resolved.get("max_rows"))
+            tasks = tuple(
+                PlannedTask(
+                    chunk_index=index,
+                    input_artifact=ArtifactReference(
+                        artifact_id=str(uuid5(input_id, f"scimesh:similarity-search:shard:{index}")),
+                        sha256=_sha256_file(path),
+                        content_type=_TSV_CONTENT_TYPE,
+                    ),
+                    parameters=self._task_parameters(resolved),
+                )
+                for index, path in enumerate(shard_paths)
+            )
+        except Exception:
+            for path in shard_paths:
+                path.unlink(missing_ok=True)
+            raise
+        return DistributedPlan(self.name, resolved, tasks)
+
+    def reduce(
+        self,
+        partial_results: Sequence[CompletedPartial],
+        parameters: Mapping[str, object],
+        workspace: Path,
+    ) -> FinalResult:
+        """Merge materialized partial CSVs into one deterministic final CSV.
+
+        The coordinator bridge materializes each downloaded artifact at
+        ``workspace / artifact_id`` before it calls this method. Those local
+        paths are an ephemeral bridge detail, never present in the plan or task
+        payload. CTX-09 owns the durable final-artifact upload and job state.
+        """
+        if not partial_results:
+            raise ValueError("at least one partial result is required")
+        resolved = self._validate_resolved_parameters(parameters)
+        top_k = resolved["top_k"]
+        direction = resolved["threshold_direction"]
+        heap: list[_HeapEntry] = []
+
+        ordered_partials = tuple(sorted(partial_results, key=lambda partial: partial.chunk_index))
+        indexes = [partial.chunk_index for partial in ordered_partials]
+        if len(indexes) != len(set(indexes)):
+            raise ValueError("partial results must have unique chunk_index values")
+        for partial in ordered_partials:
+            path = workspace / partial.artifact.artifact_id
+            if not path.is_file():
+                raise ValueError("materialized partial result is missing")
+            if _sha256_file(path) != partial.artifact.sha256:
+                raise ValueError("materialized partial result checksum does not match its artifact reference")
+            for match in self._read_partial(path, direction):
+                rank_key = match.sort_key(direction)
+                entry = _HeapEntry(match, rank_key)
+                if len(heap) < top_k:
+                    heapq.heappush(heap, entry)
+                elif rank_key < heap[0].rank_key:
+                    heapq.heapreplace(heap, entry)
+
+        matches = sorted((entry.match for entry in heap), key=lambda match: match.sort_key(direction))
+        output = workspace / "result.csv"
+        write_search_results(output, matches)
+        final_id = uuid5(
+            UUID(ordered_partials[0].artifact.artifact_id),
+            "scimesh:similarity-search:final:" + ",".join(
+                partial.artifact.artifact_id for partial in ordered_partials
+            ),
+        )
+        return FinalResult(
+            ArtifactReference(str(final_id), _sha256_file(output), _CSV_CONTENT_TYPE),
+            {"matches_emitted": len(matches), "partial_count": len(ordered_partials)},
+        )
+
+    def _resolve_query(
+        self, input_path: Path, parameters: Mapping[str, object]
+    ) -> tuple[str, dict[str, str]]:
+        query_id = parameters.get("query_id")
+        if isinstance(query_id, str):
+            record = find_molecule_by_id(input_path, query_id)
+            return Chem.MolToSmiles(record.molecule, canonical=True), {"kind": "chembl_id", "value": query_id}
+        supplied = parameters["query_smiles"]
+        assert isinstance(supplied, str)  # checked by validate_job
+        molecule = parse_smiles(supplied)
+        if molecule is None:
+            raise ValueError("query_smiles is invalid")
+        return Chem.MolToSmiles(molecule, canonical=True), {"kind": "smiles", "value": supplied}
+
+    def _resolved_parameters(
+        self, parameters: Mapping[str, object], query_smiles: str, query_source: Mapping[str, str]
+    ) -> dict[str, object]:
+        resolved: dict[str, object] = {
+            "query_smiles": query_smiles,
+            "query_source": dict(query_source),
+            "top_k": self._positive_int(parameters.get("top_k", 20), "top_k"),
+            "threshold_direction": parameters.get("threshold_direction", "greater"),
+            "fingerprint": {"algorithm": "morgan", "radius": FP_RADIUS, "fp_size": FP_SIZE},
+        }
+        if "threshold" in parameters:
+            resolved["threshold"] = self._unit_interval(parameters["threshold"], "threshold")
+        if "max_rows" in parameters:
+            resolved["max_rows"] = self._positive_int(parameters["max_rows"], "max_rows")
+        if "progress_every" in parameters:
+            resolved["progress_every"] = self._nonnegative_int(parameters["progress_every"], "progress_every")
+        return resolved
+
+    def _validate_resolved_parameters(self, parameters: Mapping[str, object]) -> dict[str, object]:
+        query_smiles = self._string(parameters.get("query_smiles"), "query_smiles")
+        if parse_smiles(query_smiles) is None:
+            raise ValueError("query_smiles is invalid")
+        resolved = self._resolved_parameters(
+            parameters,
+            Chem.MolToSmiles(parse_smiles(query_smiles), canonical=True),
+            {"kind": "resolved", "value": query_smiles},
+        )
+        # A reducer receives immutable plan metadata, whose query source and
+        # fixed fingerprint are observational context rather than worker input.
+        if "fingerprint" in parameters:
+            fingerprint = parameters["fingerprint"]
+            if fingerprint != {"algorithm": "morgan", "radius": FP_RADIUS, "fp_size": FP_SIZE}:
+                raise ValueError("resolved fingerprint does not match SciMesh defaults")
+        return resolved
+
+    @staticmethod
+    def _task_parameters(resolved: Mapping[str, object]) -> dict[str, object]:
+        # max_rows is applied before sharding. Passing it to each task would
+        # silently scan N rows per shard instead of the requested global prefix.
+        return {
+            key: value for key, value in resolved.items()
+            if key in {"query_smiles", "top_k", "threshold", "threshold_direction", "progress_every"}
+        }
+
+    def _write_shards(
+        self, input_path: Path, workspace: Path, shard_rows: int, max_rows: object
+    ) -> list[Path]:
+        limit = int(max_rows) if isinstance(max_rows, int) else None
+        paths: list[Path] = []
+        current: Path | None = None
+        destination = None
+        rows_in_shard = 0
+        seen_rows = 0
+        try:
+            with input_path.open("r", encoding="utf-8", newline="") as source:
+                reader = csv.DictReader(source, delimiter="\t")
+                fieldnames = reader.fieldnames or []
+                if not _REQUIRED_COLUMNS.issubset(set(fieldnames)):
+                    missing = sorted(_REQUIRED_COLUMNS - set(fieldnames))
+                    raise ValueError(f"dataset is missing required columns: {', '.join(missing)}")
+                for row in reader:
+                    if limit is not None and seen_rows >= limit:
+                        break
+                    if destination is None or rows_in_shard == shard_rows:
+                        if destination is not None:
+                            destination.close()
+                        current = workspace / f"shard-{len(paths)}.tsv"
+                        destination = current.open("w", encoding="utf-8", newline="")
+                        writer = csv.DictWriter(destination, fieldnames=fieldnames, delimiter="\t", lineterminator="\n")
+                        writer.writeheader()
+                        paths.append(current)
+                        rows_in_shard = 0
+                    writer.writerow(row)
+                    rows_in_shard += 1
+                    seen_rows += 1
+        finally:
+            if destination is not None:
+                destination.close()
+        if not paths:
+            raise ValueError("dataset has no data rows")
+        return paths
+
+    @staticmethod
+    def _read_partial(path: Path, direction: object) -> Iterator[SimilarityMatch]:
+        if not path.is_file():
+            raise ValueError("materialized partial result is missing")
+        if direction not in {"greater", "less"}:
+            raise ValueError("threshold_direction must be 'greater' or 'less'")
+        previous_key: tuple[float, str, str] | None = None
+        with path.open("r", encoding="utf-8", newline="") as source:
+            reader = csv.DictReader(source)
+            if tuple(reader.fieldnames or ()) != _SEARCH_COLUMNS:
+                raise ValueError("partial result has an invalid CSV header")
+            for expected_rank, row in enumerate(reader, start=1):
+                if set(row) != set(_SEARCH_COLUMNS) or row["rank"] != str(expected_rank):
+                    raise ValueError("partial result has an invalid rank")
+                try:
+                    similarity = float(row["similarity"])
+                except (TypeError, ValueError) as error:
+                    raise ValueError("partial result has an invalid similarity") from error
+                if not math.isfinite(similarity) or not 0 <= similarity <= 1:
+                    raise ValueError("partial result has an invalid similarity")
+                match = SimilarityMatch(similarity, row["chembl_id"], row["canonical_smiles"])
+                key = match.sort_key(direction)
+                if previous_key is not None and key < previous_key:
+                    raise ValueError("partial result is not sorted deterministically")
+                previous_key = key
+                yield match
+
+    @staticmethod
+    def _string(value: object, name: str) -> str:
+        if not isinstance(value, str) or not value.strip() or len(value) > 200:
+            raise ValueError(f"{name} must be a non-empty string")
+        return value
+
+    @staticmethod
+    def _positive_int(value: object, name: str) -> int:
+        if isinstance(value, bool) or not isinstance(value, int) or value < 1:
+            raise ValueError(f"{name} must be a positive integer")
+        return value
+
+    @staticmethod
+    def _nonnegative_int(value: object, name: str) -> int:
+        if isinstance(value, bool) or not isinstance(value, int) or value < 0:
+            raise ValueError(f"{name} must be a non-negative integer")
+        return value
+
+    @staticmethod
+    def _unit_interval(value: object, name: str) -> float:
+        if isinstance(value, bool) or not isinstance(value, (int, float)) or not math.isfinite(value) or not 0 <= value <= 1:
+            raise ValueError(f"{name} must be a number between 0 and 1")
+        return float(value)
+
+
+def run_similarity_search_shard(
+    input_path: Path, parameters: Mapping[str, object], output_path: Path
+) -> dict[str, int]:
+    """Run one planned shard using the local reference implementation.
+
+    This is the worker adapter used by CTX-08. It deliberately accepts only
+    resolved ``query_smiles``: resolving an identifier independently in each
+    shard would make the distributed search scientifically invalid.
+    """
+    allowed = {"query_smiles", "top_k", "threshold", "threshold_direction", "progress_every"}
+    unknown = set(parameters) - allowed
+    if unknown:
+        raise ValueError(f"unsupported similarity-search parameters: {', '.join(sorted(unknown))}")
+    query_smiles = parameters.get("query_smiles")
+    if not isinstance(query_smiles, str) or not query_smiles.strip():
+        raise ValueError("query_smiles is required for a distributed shard")
+    molecule = parse_smiles(query_smiles)
+    if molecule is None:
+        raise ValueError("query_smiles is invalid")
+    top_k = SimilaritySearchDistributedWorkload._positive_int(parameters.get("top_k", 20), "top_k")
+    threshold = None
+    if "threshold" in parameters:
+        threshold = SimilaritySearchDistributedWorkload._unit_interval(parameters["threshold"], "threshold")
+    direction = parameters.get("threshold_direction", "greater")
+    if direction not in {"greater", "less"}:
+        raise ValueError("threshold_direction must be 'greater' or 'less'")
+    progress_every = 0
+    if "progress_every" in parameters:
+        progress_every = SimilaritySearchDistributedWorkload._nonnegative_int(
+            parameters["progress_every"], "progress_every"
+        )
+    result = search_similar(
+        input_path,
+        MoleculeRecord("query", query_smiles, molecule),
+        top_k=top_k,
+        progress_every=progress_every,
+        threshold=threshold,
+        threshold_direction=direction,
+    )
+    write_similarity_search_partial(output_path, result.matches)
+    return {
+        "scanned_rows": result.stats.scanned,
+        "valid_molecules": result.stats.valid,
+        "invalid_smiles": result.stats.invalid,
+        "matches_emitted": len(result.matches),
+    }
+
+
+def _sha256_file(path: Path) -> str:
+    digest = hashlib.sha256()
+    with path.open("rb") as source:
+        for block in iter(lambda: source.read(1024 * 1024), b""):
+            digest.update(block)
+    return digest.hexdigest()

scimesh/worker/daemon.py

@@ -9,6 +9,7 @@ from pathlib import Path
 import random
 import re
 import shutil
+import subprocess
 import threading
 import time
 from datetime import datetime, timezone
@@ -202,12 +203,23 @@ class WorkerDaemon:
     def _report_failure(self, task: ClaimedTask, error: Exception) -> None:
         message = self._sanitize_error_message(error)
         try:
-            self.coordinator.fail(task, {"worker_id": self._worker_id(), "attempt": task.attempt, "error_code": type(error).__name__, "error_message": message})
+            self.coordinator.fail(task, {
+                "worker_id": self._worker_id(),
+                "attempt": task.attempt,
+                "error_code": type(error).__name__,
+                "error_message": message,
+                "retryable": self._is_retryable(error),
+            })
         except CoordinatorTransientError:
             raise
         except Exception:
             self._log("failed", task, error_type="FailureReportError")
 
+    @staticmethod
+    def _is_retryable(error: Exception) -> bool:
+        """Retry transient worker/transport failures, never invalid scientific input."""
+        return not isinstance(error, (ValueError, FileNotFoundError, subprocess.CalledProcessError))
+
     def _sanitize_error_message(self, error: Exception) -> str:
         """Keep coordinator-visible failures useful without exposing local paths."""
         message = str(error).replace(str(self.config.work_dir), "<worker-dir>")

scimesh/worker/runners.py

@@ -7,6 +7,8 @@ import subprocess
 import sys
 from typing import Protocol
 
+from scimesh.distributed.similarity_search import run_similarity_search_shard
+
 from .models import ClaimedTask, ProducedArtifact, RunResult
 
 
@@ -34,6 +36,12 @@ class SciMeshRunner:
             query_id, query_smiles = params.get("query_id"), params.get("query_smiles")
             if (query_id is None) == (query_smiles is None):
                 raise ValueError("exactly one of query_id or query_smiles is required")
+            if query_smiles is not None and "max_rows" not in params:
+                metrics = run_similarity_search_shard(input_path, params, output_path)
+                return RunResult((ProducedArtifact(output_path, "text/csv"),), metrics)
+            # Legacy URI jobs may still use query_id or an explicitly task-local
+            # max_rows value. CTX-08 plans never create those payloads; retain
+            # CLI execution only for backwards compatibility at this boundary.
             top_k = self._positive_int(params, "top_k", default=20)
             command += ["--query-id", self._string(params, "query_id")] if query_id is not None else ["--query-smiles", self._string(params, "query_smiles")]
             command += ["--top-k", str(top_k)]

tests/test_distributed_similarity_search.py

@@ -0,0 +1,184 @@
+"""Scientific reference tests for the CTX-08 distributed search workload."""
+
+from __future__ import annotations
+
+import csv
+import hashlib
+from pathlib import Path
+from uuid import NAMESPACE_URL, uuid5
+
+import pytest
+
+from scimesh.chemistry.dataset import find_molecule_by_id
+from scimesh.distributed import (
+    ArtifactReference,
+    CompletedPartial,
+    PlanningService,
+    default_distributed_registry,
+)
+from scimesh.distributed.registry import DistributedWorkloadRegistry
+from scimesh.distributed.similarity_search import (
+    SimilaritySearchDistributedWorkload,
+    run_similarity_search_shard,
+    write_similarity_search_partial,
+)
+from scimesh.workloads.similarity_search import search_similar, write_search_results
+
+
+def make_dataset(path: Path) -> None:
+    path.write_text(
+        "chembl_id\tcanonical_smiles\textra\n"
+        "CHEMBL_QUERY\tCCO\tquery\n"
+        "CHEMBL_A\tCCCO\ta\n"
+        "CHEMBL_B\tCCCC\tb\n"
+        "CHEMBL_INVALID\tnot-a-smiles\tbad\n"
+        "CHEMBL_DUPLICATE\tCCO\tduplicate\n"
+        "CHEMBL_C\tCCN\tc\n",
+        encoding="utf-8",
+    )
+
+
+def planner() -> tuple[PlanningService, SimilaritySearchDistributedWorkload]:
+    workload = SimilaritySearchDistributedWorkload()
+    registry = DistributedWorkloadRegistry()
+    registry.register(workload)
+    return PlanningService(registry), workload
+
+
+def test_default_registry_exposes_only_supported_distributed_search() -> None:
+    assert [item.name for item in default_distributed_registry().descriptions()] == ["similarity-search"]
+
+
+def checksum(path: Path) -> str:
+    return hashlib.sha256(path.read_bytes()).hexdigest()
+
+
+def test_query_id_is_resolved_once_before_deterministic_shards(
+    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
+) -> None:
+    dataset = tmp_path / "chembl.tsv"
+    workspace = tmp_path / "workspace"
+    make_dataset(dataset)
+    service, _ = planner()
+    calls = 0
+    real_find = find_molecule_by_id
+
+    def count_find(path: Path, query_id: str) -> MoleculeRecord:
+        nonlocal calls
+        calls += 1
+        return real_find(path, query_id)
+
+    monkeypatch.setattr("scimesh.distributed.similarity_search.find_molecule_by_id", count_find)
+    input_id = str(uuid5(NAMESPACE_URL, "dataset"))
+    plan = service.plan(
+        "similarity-search", dataset, input_id,
+        {"query_id": "CHEMBL_QUERY", "top_k": 3, "max_rows": 5, "progress_every": 0},
+        2, workspace,
+    )
+
+    assert calls == 1
+    assert plan.resolved_parameters["query_smiles"] == "CCO"
+    assert plan.resolved_parameters["query_source"] == {"kind": "chembl_id", "value": "CHEMBL_QUERY"}
+    assert [task.chunk_index for task in plan.tasks] == [0, 1, 2]
+    assert all("query_id" not in task.parameters for task in plan.tasks)
+    assert all("max_rows" not in task.parameters for task in plan.tasks)
+    assert all(task.parameters["query_smiles"] == "CCO" for task in plan.tasks)
+    assert [
+        sum(1 for _ in path.open(encoding="utf-8")) - 1
+        for path in sorted(workspace.glob("shard-*.tsv"))
+    ] == [2, 2, 1]
+
+
+def test_distributed_reduction_matches_single_process_reference(tmp_path: Path) -> None:
+    dataset = tmp_path / "chembl.tsv"
+    workspace = tmp_path / "workspace"
+    make_dataset(dataset)
+    service, workload = planner()
+    plan = service.plan(
+        "similarity-search", dataset, str(uuid5(NAMESPACE_URL, "dataset")),
+        {"query_smiles": "CCO", "top_k": 3, "threshold": 0.0}, 2, workspace,
+    )
+
+    partials: list[CompletedPartial] = []
+    # Worker two finishes the latter shards first. Worker one loses its first
+    # attempt for shard zero, then retries it last. The reducer must remain
+    # independent of both completion and retry order.
+    for task in reversed(plan.tasks):
+        shard = workspace / f"shard-{task.chunk_index}.tsv"
+        temporary_partial = workspace / f"worker-output-{task.chunk_index}.csv"
+        metrics = run_similarity_search_shard(shard, task.parameters, temporary_partial)
+        partial_id = str(uuid5(NAMESPACE_URL, f"partial:{task.chunk_index}"))
+        partials.append(
+            CompletedPartial(
+                task.chunk_index,
+                ArtifactReference(
+                    partial_id, checksum(temporary_partial), "text/csv",
+                ),
+                metrics,
+            )
+        )
+        # The reducer materializes result files under their own coordinator IDs,
+        # not shard input IDs. Keep this fixture faithful to that boundary.
+        temporary_partial.rename(workspace / partial_id)
+
+    final = workload.reduce(tuple(partials), plan.resolved_parameters, workspace)
+    reference = tmp_path / "reference.csv"
+    query_record = find_molecule_by_id(dataset, "CHEMBL_QUERY")
+    write_search_results(reference, search_similar(dataset, query_record, top_k=3, threshold=0.0).matches)
+
+    assert (workspace / "result.csv").read_bytes() == reference.read_bytes()
+    assert final.metrics == {"matches_emitted": 3, "partial_count": 3}
+    rows = list(csv.DictReader((workspace / "result.csv").open(encoding="utf-8")))
+    assert {row["chembl_id"] for row in rows}.isdisjoint({"CHEMBL_QUERY", "CHEMBL_DUPLICATE"})
+
+
+def test_reducer_rejects_unsorted_or_invalid_partial_csv(tmp_path: Path) -> None:
+    workspace = tmp_path / "workspace"
+    workspace.mkdir()
+    workload = SimilaritySearchDistributedWorkload()
+    artifact_id = str(uuid5(NAMESPACE_URL, "bad"))
+    partial_path = workspace / artifact_id
+    partial_path.write_text(
+        "rank,chembl_id,canonical_smiles,similarity\n1,A,CC,0.1\n2,B,CCC,0.9\n",
+        encoding="utf-8",
+    )
+    artifact = ArtifactReference(artifact_id, checksum(partial_path), "text/csv")
+
+    with pytest.raises(ValueError, match="not sorted"):
+        workload.reduce(
+            (CompletedPartial(0, artifact, {"scanned_rows": 2}),),
+            {"query_smiles": "CCO", "top_k": 2, "threshold_direction": "greater", "fingerprint": {"algorithm": "morgan", "radius": 2, "fp_size": 2048}},
+            workspace,
+        )
+
+
+def test_partial_csv_preserves_exact_scores_for_global_ranking(tmp_path: Path) -> None:
+    partial = tmp_path / "partial.csv"
+    # Both values look identical in a six-decimal final CSV. The exact value
+    # must survive shard transport so the global reducer can still rank them.
+    from scimesh.workloads.similarity_search import SimilarityMatch
+
+    write_similarity_search_partial(
+        partial,
+        [SimilarityMatch(0.50000049, "A", "CC"), SimilarityMatch(0.50000048, "B", "CCC")],
+    )
+    values = list(csv.DictReader(partial.open(encoding="utf-8")))
+    assert values[0]["similarity"] == repr(0.50000049)
+    assert values[1]["similarity"] == repr(0.50000048)
+
+
+def test_planner_rejects_fingerprint_override_and_invalid_query(tmp_path: Path) -> None:
+    dataset = tmp_path / "chembl.tsv"
+    make_dataset(dataset)
+    service, _ = planner()
+
+    with pytest.raises(ValueError, match="unsupported similarity-search parameters"):
+        service.plan(
+            "similarity-search", dataset, str(uuid5(NAMESPACE_URL, "dataset")),
+            {"query_smiles": "CCO", "fingerprint": {"radius": 1}}, 2, tmp_path / "workspace",
+        )
+    with pytest.raises(ValueError, match="query_smiles is invalid"):
+        service.plan(
+            "similarity-search", dataset, str(uuid5(NAMESPACE_URL, "dataset")),
+            {"query_smiles": "invalid"}, 2, tmp_path / "workspace",
+        )

tests/test_worker_daemon.py

@@ -106,6 +106,90 @@ def test_claims_runs_uploads_and_submits_csv(tmp_path: Path) -> None:
     }
 
 
+def test_worker_executes_a_resolved_similarity_search_shard(tmp_path: Path) -> None:
+    content = b"chembl_id\tcanonical_smiles\nQUERY\tCCO\nMATCH\tCCCO\nINVALID\tnot-a-smiles\n"
+    task = make_task(content)
+    task = ClaimedTask(
+        task.task_id, task.attempt, task.lease_expires_at, task.workload, task.input,
+        {"query_smiles": "CCO", "top_k": 5, "progress_every": 0},
+    )
+    worker, coordinator, artifacts, _, _ = daemon(tmp_path, task, content)
+    worker.runner = SciMeshRunner()
+
+    assert worker.run_once() == RunOnceOutcome(claimed=True, completed=True)
+    output = artifacts.uploaded[0][2].read_text(encoding="utf-8")
+    assert output.startswith("rank,chembl_id,canonical_smiles,similarity\n")
+    metrics = coordinator.submissions[0]["metrics"]
+    assert metrics["scanned_rows"] == 3
+    assert metrics["valid_molecules"] == 2
+    assert metrics["invalid_smiles"] == 1
+    assert metrics["matches_emitted"] == 1
+    assert isinstance(metrics["elapsed_seconds"], float)
+
+
+def test_two_workers_complete_resolved_shards_after_one_retry(tmp_path: Path) -> None:
+    content = b"chembl_id\tcanonical_smiles\nQUERY\tCCO\nMATCH\tCCCO\n"
+    first = make_task(content)
+    first = ClaimedTask(
+        "retry-task", 1, first.lease_expires_at, "similarity-search", first.input,
+        {"query_smiles": "CCO", "top_k": 5},
+    )
+    second = ClaimedTask(
+        "other-task", 1, first.lease_expires_at, "similarity-search", first.input,
+        {"query_smiles": "CCO", "top_k": 5},
+    )
+
+    class RetryCoordinator(FakeCoordinator):
+        def __init__(self) -> None:
+            super().__init__(None)
+            self.queue = [first, second]
+            self.claimants: list[str] = []
+
+        def claim(self, worker_id: str, capabilities: tuple[str, ...]) -> ClaimedTask | None:
+            self.claimants.append(worker_id)
+            return self.queue.pop(0) if self.queue else None
+
+        def fail(self, task: ClaimedTask, payload: dict) -> None:
+            self.failures.append(payload)
+            if task.task_id == "retry-task" and task.attempt == 1 and payload["retryable"]:
+                self.queue.append(
+                    ClaimedTask(
+                        task.task_id, 2, task.lease_expires_at, task.workload, task.input,
+                        task.parameters,
+                    )
+                )
+
+    class FailFirstAttempt:
+        def __init__(self) -> None:
+            self.calls = 0
+            self.delegate = SciMeshRunner()
+
+        def run(self, task: ClaimedTask, task_dir: Path) -> RunResult:
+            self.calls += 1
+            if self.calls == 1:
+                raise RuntimeError("simulated retryable shard failure")
+            return self.delegate.run(task, task_dir)
+
+    coordinator = RetryCoordinator()
+    artifacts = FakeArtifacts(content)
+    worker_a = WorkerDaemon(
+        WorkerConfig("https://example.test", "worker-a", tmp_path / "worker-a"),
+        coordinator, artifacts, FailFirstAttempt(),
+    )
+    worker_b = WorkerDaemon(
+        WorkerConfig("https://example.test", "worker-b", tmp_path / "worker-b"),
+        coordinator, artifacts, SciMeshRunner(),
+    )
+
+    assert worker_a.run_once() == RunOnceOutcome(claimed=True, completed=False)
+    assert worker_b.run_once() == RunOnceOutcome(claimed=True, completed=True)
+    assert worker_a.run_once() == RunOnceOutcome(claimed=True, completed=True)
+    assert coordinator.claimants == ["worker-a", "worker-b", "worker-a"]
+    assert len(coordinator.failures) == 1
+    assert coordinator.failures[0]["retryable"] is True
+    assert len(coordinator.submissions) == 2
+
+
 def test_no_task_does_not_create_directory(tmp_path: Path) -> None:
     worker, _, _, runner, config = daemon(tmp_path, None, b"")
     assert worker.run_once() == RunOnceOutcome(claimed=False, completed=False)
@@ -161,6 +245,7 @@ def test_interrupting_an_active_task_reports_a_sanitized_failure(tmp_path: Path)
             "attempt": 1,
             "error_code": "InterruptedError",
             "error_message": "worker interrupted by operator",
+            "retryable": True,
         }
     ]
 
@@ -234,6 +319,7 @@ def test_bad_checksum_reports_failure_without_running(tmp_path: Path) -> None:
     assert worker.run_once() == RunOnceOutcome(claimed=True, completed=False)
     assert runner.calls == 0
     assert coordinator.failures[0]["error_code"] == "ValueError"
+    assert coordinator.failures[0]["retryable"] is False
     assert not coordinator.submissions
 
 
@@ -356,30 +442,35 @@ def test_runner_maps_graph_and_smiles_search_parameters(tmp_path: Path, monkeypa
     runner = SciMeshRunner()
     graph = ClaimedTask("graph", 1, "2026-07-30T00:00:00Z", "similarity-graph", InputArtifact("https://example/input", "x"), {"threshold": 0.2, "threshold_direction": "less", "block_size": 42, "max_rows": 7, "progress_every": 0})
     search = ClaimedTask("search", 1, "2026-07-30T00:00:00Z", "similarity-search", InputArtifact("https://example/input", "x"), {"query_smiles": "CCO", "top_k": 3})
+    search_dir = tmp_path / "search"
+    search_dir.mkdir()
+    (search_dir / "input").write_text(
+        "chembl_id\tcanonical_smiles\nA\tCCO\nB\tCCCO\n", encoding="utf-8"
+    )
     runner.run(graph, tmp_path / "graph")
-    runner.run(search, tmp_path / "search")
+    result = runner.run(search, search_dir)
     assert "--threshold-direction" in commands[0] and "less" in commands[0]
     assert "--block-size" in commands[0] and "42" in commands[0]
     assert "--max-rows" in commands[0] and "7" in commands[0]
-    assert "--query-smiles" in commands[1] and "CCO" in commands[1]
+    assert len(commands) == 1
+    assert result.metrics == {
+        "scanned_rows": 2, "valid_molecules": 2, "invalid_smiles": 0, "matches_emitted": 1,
+    }
 
 
 def test_runner_accepts_coordinator_workload_names(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
-    commands: list[list[str]] = []
+    task_dir = tmp_path / "search"
-
+    task_dir.mkdir()
-    def fake_run(command: list[str], **_: object) -> None:
+    (task_dir / "input").write_text(
-        commands.append(command)
+        "chembl_id\tcanonical_smiles\nA\tCCO\nB\tCCCO\n", encoding="utf-8"
-        output = Path(command[command.index("--output") + 1])
+    )
-        output.parent.mkdir(parents=True, exist_ok=True)
-        output.write_text("a,b\\n", encoding="utf-8")
-
-    monkeypatch.setattr("scimesh.worker.runners.subprocess.run", fake_run)
     task = ClaimedTask(
         "search", 1, "2026-07-30T00:00:00Z", "similarity_search",
         InputArtifact("https://example/input", "a" * 64), {"query_smiles": "CCO"},
     )
-    SciMeshRunner().run(task, tmp_path / "search")
+    result = SciMeshRunner().run(task, task_dir)
-    assert commands[0][3] == "similarity-search"
+    assert result.metrics["matches_emitted"] == 1
+    assert (task_dir / "result.csv").is_file()
 
 
 def test_claimed_task_rejects_path_traversal_and_invalid_metadata() -> None:
@@ -457,21 +548,15 @@ def test_relative_work_dir_is_normalized_for_runner_subprocesses(
 
     task_dir = config.work_dir / "task" / "1"
     task_dir.mkdir(parents=True)
-    (task_dir / "input").write_text("fixture", encoding="utf-8")
+    (task_dir / "input").write_text(
-    command: list[str] = []
+        "chembl_id\tcanonical_smiles\nA\tCCO\nB\tCCCO\n", encoding="utf-8"
-
+    )
-    def fake_run(args: list[str], **_: object) -> None:
-        command.extend(args)
-        output = Path(args[args.index("--output") + 1])
-        output.write_text("id,score\n", encoding="utf-8")
-
-    monkeypatch.setattr("scimesh.worker.runners.subprocess.run", fake_run)
     task = ClaimedTask(
         "task", 1, "2026-07-30T00:00:00Z", "similarity-search",
         InputArtifact("https://example.test/input", "a" * 64), {"query_smiles": "CCO"},
     )
     SciMeshRunner().run(task, task_dir)
-    assert command[4] == str(task_dir / "input")
+    assert (task_dir / "result.csv").is_file()
 
 
 def test_worker_registration_sets_returned_identity(tmp_path: Path) -> None: