Gap fixes: pattern fallback, narrative citations, call_log plumbing

Closing trust-breaks surfaced in the strategic audit.

A — MEMORY chip renders even when sparse:
Previously rendered nothing when no trait crossed threshold, which
recruiters would read as "system has no signal." Now explicitly
says "memory is sparse for this role+geo — no trait crossed
threshold" or "no similar past playbooks yet — first fill of this
kind will seed it." Honest when it doesn't know.

B — Removed /intelligence/learn dead endpoint:
Legacy CSV-writer path that destructively re-wrote
successful_playbooks. /log and /log_failure replace it cleanly.
Leaving dead code confuses future maintainers.

C — Narrative tooltips on Endorsed chips:
Hovering the green "Endorsed · N playbooks" chip now fetches
the worker's past operations from successful_playbooks_live and
shows a story: "Maria — past endorsements: • Welder x2 in
Toledo (2026-04-15), • Welder x1 in Toledo (2026-04-18)..."
Falls back to honest "narrative unavailable" if the seed
didn't land in SQL.

D — call_log infrastructure in worker modal:
New "Recent Contact" section queries call_log JOIN candidates by
name. Surfaces last 3 call entries with timestamp, recruiter,
disposition, duration. When empty (which is today's reality —
candidates table only has 1000 rows vs call_log's higher IDs),
shows an honest message about the data gap and what real ATS
integration would unlock.

Honest call: D ships infrastructure. Actual utility depends on
aligning candidate IDs between the candidates table and
call_log — current synthetic data doesn't cross-ref cleanly.
When real ATS data lands, this section becomes the
"system knows who we called yesterday" feature the recruiter
needs.

Deferred (would require a dedicated session):
- Rate awareness (needs worker pay_rate + contract bill_rate)
- Push / background daemon (Slack/SMS/email integration)
- Confidence calibration (needs a probabilistic ranking layer)

mcp-server/index.ts

@@ -1391,15 +1391,11 @@ tr:hover{background:#111827}
           }
         }
 
-        // Intelligence: Log a search → selection as a learned pattern
-        if (url.pathname === "/intelligence/learn" && req.method === "POST") {
-          const b = await json();
-          const csv = `timestamp,operation,approach,result,context\n"${new Date().toISOString()}","search: ${(b.query||"").replace(/"/g,'""')}","${(b.filters||"").replace(/"/g,'""')}","selected: ${(b.worker_name||"").replace(/"/g,'""')} (${b.worker_id||""})","role=${b.worker_role||""} state=${b.worker_state||""} city=${b.worker_city||""}"`;
-          const form = new FormData();
-          form.append("file", new Blob([csv], { type: "text/csv" }), "playbook.csv");
-          await fetch(`${BASE}/ingest/file?name=successful_playbooks`, { method: "POST", body: form });
-          return ok({ learned: true, pattern: `"${b.query}" → ${b.worker_name}` });
-        }
+        // Removed 2026-04-20: /intelligence/learn was a legacy CSV writer
+        // that destructively re-wrote successful_playbooks. /log and
+        // /log_failure replace it cleanly via /vectors/playbook_memory/seed
+        // and /mark_failed. Keeping the endpoint would only mislead
+        // future callers — dead code rots.
 
         // Intelligence: Activity feed — what the system has learned
         if (url.pathname === "/intelligence/activity" && req.method === "POST") {