Apply B1+B2+B3+B4 from 2026-04-30 cross-lineage scrum

Cross-lineage scrum (Opus 4.7 / Kimi K2.6 / Qwen3-coder via chatd's
/v1/chat) on the harness's first 4 commits surfaced 5 real bugs;
this commit lands the 4 inside the LLM/validator stack. B5 (scanner
skip-list semantics) ships separately as it changes scan behavior
on every target repo.

B1 (Kimi BLOCK + Opus WARN convergent) — internal/validators:
evidencePresent had two flaws: (1) cursor advanced on match in the
trim-line fallback, breaking same-line repeated matches AND skipping
not-yet-considered lines so out-of-order evidence spuriously failed;
(2) strings.Contains on a single `}` trim-matched any closing brace
in the file, defeating the "evidence quotes real text" contract.
Fix: trivial-evidence guard FIRST (reject anything <4 non-whitespace
chars) + per-line search no longer advances a cursor. New regression
test TestEvidencePresent_RejectsTrivialMatches covers `}`, `{`, `)`,
empty, and out-of-order multi-line evidence (which now passes —
order isn't part of the contract).

B2 (Kimi WARN + Opus WARN convergent) — internal/pipeline:
WriteJSON error for rejected-findings.json was swallowed with
`if err == nil`, so a write failure left the validation phase
reporting status="ok" while the audit trail vanished. Mirror the
validated-findings branch: surface the error in
validatePhase.Errors + bump status to degraded + ExitCode=66.

B3 (Kimi BLOCK + Opus BLOCK convergent) — internal/llm/ollama.go:
HealthCheck.basic_prompt_ok was set to true on ANY non-empty
response, so a model emitting `<think>...` traces or apologies
passed silently. Now requires the response to contain "OK"
(uppercase, substring). Substring rather than equality lets minor
whitespace/punctuation variations through (some models add a
trailing period). Errors now record what the model actually said
when it fails the check.

B4 (Opus BLOCK only — same class as today's chatd Anthropic-temp
fix) — internal/llm/ollama.go: chatBody had `if opts.Temperature != 0`
which silently dropped Temperature=0 from the request, so HealthCheck
+ Reviewer (both pass Temperature=0 expecting determinism) actually
ran at Ollama's ~0.8 default. Always forward Temperature now. The
two callers always set explicit values, so "0 means 0" is correct;
if a future caller wants Ollama's default they'll switch
CompleteOptions.Temperature to *float64 like chatd did this morning.

Verified end-to-end: insecure-repo + --enable-llm still produces 25
confirmed findings (16 static + 9 LLM), 0 rejected. Validator unit
tests: 11 pass (added TestEvidencePresent_RejectsTrivialMatches).

Same-day-as-shipping scrum, same-day-as-shipping fixes. The
convergent-≥2 gate caught 3 of these; the 4th was Opus-only but
verified by reading the code (same idiom as today's chatd bug).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

internal/pipeline/pipeline.go

@@ -174,9 +174,18 @@ func RunRepo(ctx context.Context, in Inputs) (*Result, error) {
 		validatePhase.OutputHash = sha
 	}
 	if len(valOut.Rejected) > 0 {
-		// Rejected file is informational, not gate-blocking — the
-		// audit trail belongs in version control.
-		if _, err := reporters.WriteJSON(filepath.Join(in.OutputDir, "rejected-findings.json"), valOut); err == nil {
+		// Scrum fix B2 (Kimi WARN + Opus WARN, 2026-04-30): surface
+		// write errors into validatePhase.Errors. Pre-fix the error
+		// was swallowed (`if _, err := ...; err == nil`), which broke
+		// the receipts-honesty contract — phase status said "ok" while
+		// the rejected-findings audit trail silently vanished.
+		if _, err := reporters.WriteJSON(filepath.Join(in.OutputDir, "rejected-findings.json"), valOut); err != nil {
+			validatePhase.Status = "degraded"
+			validatePhase.Errors = append(validatePhase.Errors, "rejected-findings.json: "+err.Error())
+			if res.ExitCode == 0 {
+				res.ExitCode = 66
+			}
+		} else {
 			validatePhase.OutputFiles = append(validatePhase.OutputFiles, "rejected-findings.json")
 			res.OutputFiles = append(res.OutputFiles, "rejected-findings.json")
 		}