.gitea/workflows/pipeline-gate.yml

@@ -176,7 +176,8 @@ jobs:
             const issue = context.payload.issue;
             if (!issue) { core.info('no issue in payload'); return; }
             const comment = context.payload.comment?.body || '';
-            // Require all 4 phase headers to be present (case-insensitive)
+
+            // --- Phase header detection (case-insensitive) ---
             const hasInward = /\bINWARD\b/i.test(comment);
             const hasOutward = /\bOUTWARD\b/i.test(comment);
             const hasInnovation = /\bINNOVATION\b/i.test(comment);
@@ -185,12 +186,194 @@ jobs:
               core.info(`research-clear: comment on #${issue.number} missing phases (inward=${hasInward} outward=${hasOutward} innovation=${hasInnovation} synthesis=${hasSynthesis}) — skip`);
               return;
             }
-            const labels = (issue.labels || []).map(l => l.name);
-            if (!labels.includes('research-pending')) {
+
+            // --- Evidence enforcement (per phase, section-scoped) ---
+            // Split the comment into phase sections on the phase headers.
+            function section(phase) {
+              const re = new RegExp(`\\b${phase}\\b[\\s\\S]*?(?=\\b(?:INWARD|OUTWARD|INNOVATION|SYNTHESIS)\\b|$)`, 'i');
+              const m = comment.match(re);
+              return m ? m[0] : '';
+            }
+            const forgeHost = context.payload.repository?.html_url ? new URL(context.payload.repository.html_url).host : '';
+            const externalUrlRe = /https?:\/\/[^\s)\]>]+/gi;
+            const codePathRe = /(?:^|\s)(?:src|tests|scripts|docs|\.gitea)\/[\w./-]+/gi;
+            const plansPathRe = /(?:^|\s)plans\/[\w./-]+/gi;
+
+            function uniqueExternalUrls(text) {
+              const found = text.match(externalUrlRe) || [];
+              const uniq = new Map(); // normalized key -> original URL (fetchable)
+              for (const u of found) {
+                try {
+                  const parsed = new URL(u);
+                  if (parsed.host && parsed.host !== forgeHost) {
+                    const key = parsed.host + parsed.pathname;
+                    if (!uniq.has(key)) uniq.set(key, u);
+                  }
+                } catch (e) { /* skip malformed */ }
+              }
+              return uniq;
+            }
+            function codeCitations(text) {
+              return new Set((text.match(codePathRe) || []).map(s => s.trim()));
+            }
+
+            const inwardSec = section('INWARD');
+            const outwardSec = section('OUTWARD');
+            const innovationSec = section('INNOVATION');
+            const synthesisSec = section('SYNTHESIS');
+            const tailSec = innovationSec + '\n' + synthesisSec;
+
+            const inwardCites = codeCitations(inwardSec);
+            const outwardUrls = uniqueExternalUrls(outwardSec);
+            const tailUrls = uniqueExternalUrls(tailSec);
+            const tailPlans = (tailSec.match(plansPathRe) || []).length;
+
+            const missing = [];
+            if (inwardCites.size < 2) missing.push(`- **INWARD**: needs ≥2 codebase citations (paths like src/..., tests/..., .gitea/...) — found ${inwardCites.size}.`);
+            if (outwardUrls.size < 2) missing.push(`- **OUTWARD**: needs ≥2 UNIQUE external source URLs (not this forge) — found ${outwardUrls.size}. Research must pull real sources to learn from so later stages build on evidence.`);
+            if (tailUrls.size < 1 && tailPlans < 1) missing.push(`- **INNOVATION/SYNTHESIS**: needs ≥1 source URL reference or a plans/ artifact path tying synthesis back to evidence.`);
+
+            // --- INNOVATION must be source-tied: ≥1 external URL from OUTWARD
+            // re-referenced (proving candidates derive from pulled sources, not invention).
+            const innovationUrlKeys = [...uniqueExternalUrls(innovationSec).keys()];
+            const tiedToOutward = innovationUrlKeys.filter(k => outwardUrls.has(k));
+            if (outwardUrls.size >= 2 && tiedToOutward.length < 1) {
+              missing.push(`- **INNOVATION**: candidate approaches must derive from OUTWARD sources — re-reference ≥1 of the OUTWARD source URLs here and say what it contributed. Found 0 source-tied candidates.`);
+            }
+
+            // --- SYNTHESIS qualification gate: the synthesis must (a) declare its
+            // evidence sufficiency, (b) judge feasibility REALISTICALLY (mechanism +
+            // assumptions + failure modes), and (c) either commit to a plan artifact
+            // or honestly bounce to MORE RESEARCH. Evidence-insufficient synthesis
+            // MUST declare MORE RESEARCH — bluffing through fails the gate.
+            const SYNTH_REJECTS = [];
+            const suffMarker = /\bevidence[^\n]{0,40}(suffic|adequat|insuffic)|insufficient evidence|evidence gap/i;
+            const hasSufficiency = suffMarker.test(synthesisSec);
+            const moreResearch = /\bMORE[- ]RESEARCH\b/i.test(synthesisSec);
+            const hasPlanArtifact = /(?:^|\s)plans\/[\w./-]+/.test(synthesisSec);
+            if (moreResearch) {
+              // Honest loop-back path: open questions REQUIRED, feasibility verdict
+              // explicitly NOT required — a substantiated MORE-RESEARCH is the honest
+              // outcome; demanding feasibility prose would teach padding.
+              const openQs = (synthesisSec.match(/\?\s*$/gm) || []).length + (synthesisSec.match(/\bopen question|\bunknown|\bunresolved/gi) || []).length;
+              if (openQs < 1) {
+                SYNTH_REJECTS.push(`- **MORE-RESEARCH declared but unsubstantiated**: name the specific open questions/unknowns that require more research (at least one '?', 'open question', or 'unknown').`);
+              }
+              if (!hasSufficiency) {
+                SYNTH_REJECTS.push(`- **MORE-RESEARCH qualification**: state what evidence you have, what is missing, and why the gap blocks a design decision (evidence-sufficiency statement).`);
+              }
+            } else {
+              // Proceed-to-plan path: full qualification — sufficiency + feasibility + kill test.
+              if (!hasSufficiency) {
+                SYNTH_REJECTS.push(`- **SYNTHESIS qualification**: no evidence-sufficiency statement. State explicitly whether OUTWARD evidence is sufficient to design from, and why (e.g. 'Evidence sufficient: <2-3 sources converge on the mechanism>' or 'Evidence insufficient: <what specifically is missing>').`);
+              }
+              const feasMarker = /\bfeasib|\bwon'?t work\b|\bwill work\b|\brisk\b|\bfailure mode\b|\bassumption\b|\brealistic/i;
+              const hasFeasibility = feasMarker.test(synthesisSec);
+              if (!hasFeasibility) {
+                SYNTH_REJECTS.push(`- **SYNTHESIS qualification**: no feasibility judgement. State the working mechanism, the load-bearing assumptions, and the failure modes — and judge realistically whether the synthesis WILL WORK. Optimism is not evidence.`);
+              }
+              // Kill test: a feasibility claim must name its cheapest disproof.
+              // The plan must carry it as an early frozen test — prose is not a prediction.
+              const hasKillTest = /\bkill test\b|\bdisprov|\bfalsif/i.test(synthesisSec);
+              if (hasFeasibility && !hasKillTest) {
+                SYNTH_REJECTS.push(`- **SYNTHESIS kill test**: name the cheapest observation that would DISPROVE the feasibility claim (a 'kill test:' line). For workflow-only changes the protected CI run may be the kill test — say so explicitly. A claim with no disproof is not a claim.`);
+              }
+              if (!hasPlanArtifact) {
+                SYNTH_REJECTS.push(`- **SYNTHESIS disposition**: must reference a concrete plans/ artifact (ready to implement) or declare **MORE-RESEARCH** with the specific open questions. Neither found.`);
+              }
+            }
+
+            // --- Trail of use: each OUTWARD source must carry an inline annotation
+            // (what was learned from it) on the same line — the verifiable trail.
+            const annotated = [...outwardUrls.entries()].filter(([, url]) => {
+              const line = outwardSec.split('\n').find(l => l.includes(url));
+              if (!line) return false;
+              const prose = line.replace(externalUrlRe, '').replace(/[-*`>\[\]()]/g, '').trim();
+              return prose.length >= 15;
+            });
+            if (outwardUrls.size >= 2 && annotated.length < 2) {
+              missing.push(`- **OUTWARD trail**: each source needs an inline note of what it taught (URL + ≥15 chars of what was learned, same line) — ${annotated.length}/${outwardUrls.size} annotated. A bare URL list is not a research trail.`);
+            }
+
+            // --- Live verification: fetch up to 5 sources; dead/hallucinated links fail.
+            // 2xx/3xx = real; 403/405/406/429 = real-but-bot-blocked (count as verified);
+            // 404/410/DNS/timeout (after 1 retry) = dead.
+            const toVerify = [...outwardUrls.values()].slice(0, 5);
+            const dead = [];
+            for (const u of toVerify) {
+              let ok = false;
+              for (let attempt = 0; attempt < 2 && !ok; attempt++) {
+                try {
+                  const ctl = new AbortController();
+                  const t = setTimeout(() => ctl.abort(), 8000);
+                  const r = await fetch(u, { redirect: 'follow', signal: ctl.signal, headers: { 'User-Agent': 'rune-research-gate/1.0 (source verification)' } });
+                  clearTimeout(t);
+                  ok = (r.status < 400) || [403, 405, 406, 429].includes(r.status);
+                  if (!ok && [404, 410].includes(r.status)) break; // definitively dead, no retry
+                } catch (e) {
+                  clearTimeout(t);
+                  if (attempt === 1) { /* second failure — stays dead */ }
+                }
+              }
+              if (!ok) dead.push(u);
+            }
+            if (dead.length > 0) {
+              missing.push(`- **OUTWARD verification**: source(s) failed live fetch: ${dead.join(', ')} — dead or unreachable links cannot serve as research evidence.`);
+            }
+
+            const labels0 = (issue.labels || []).map(l => l.name);
+            if (!labels0.includes('research-pending')) {
               core.info(`research-clear: #${issue.number} has no research-pending label — skip`);
               return;
             }
-            // Clear research-pending, add ready
+
+            if (missing.length > 0) {
+              await github.rest.issues.createComment({
+                owner: context.repo.owner, repo: context.repo.repo,
+                issue_number: issue.number,
+                body: `🚫 **Research round REJECTED — evidence gate.** All 4 phase headers present, but the evidence floor is not met:\n\n${missing.join('\n')}\n\nresearch-pending stays. Post the missing evidence (real sources fetched, real paths read) and the gate will re-run on your next comment.`,
+              });
+              core.info(`research-clear: evidence gate rejected #${issue.number}: ${missing.length} gap(s)`);
+              return;
+            }
+
+            // --- Honest loop-back: synthesis declared MORE-RESEARCH with substantiated
+            // open questions and all evidence floors met. This is a SUCCESS for honesty:
+            // research-pending stays, the named unknowns drive the next research pass.
+            // Bound: after 2 prior loop-backs on this issue, escalate to the owner
+            // instead of cycling silently — infinite MORE-RESEARCH is dithering.
+            if (moreResearch) {
+              let priorLoopBacks = 0;
+              try {
+                const comments = await github.rest.issues.listComments({
+                  owner: context.repo.owner, repo: context.repo.repo,
+                  issue_number: issue.number, per_page: 100,
+                });
+                priorLoopBacks = comments.data.filter(c => (c.body || '').includes('honest loop-back accepted')).length;
+              } catch (e) { core.info('loop-back count fetch failed: ' + (e && e.message)); }
+              if (priorLoopBacks >= 2) {
+                await github.rest.issues.createComment({
+                  owner: context.repo.owner, repo: context.repo.repo,
+                  issue_number: issue.number,
+                  body: `⏸️ **Loop-back bound reached (${priorLoopBacks} prior MORE-RESEARCH cycles).** The synthesis again declares MORE-RESEARCH with substantiated open questions. Escalating to the owner rather than cycling silently: this issue needs a human decision — narrow the scope, accept a design under uncertainty, or split the unknowns into their own research issues.`,
+                });
+                await github.rest.issues.addLabels({
+                  owner: context.repo.owner, repo: context.repo.repo,
+                  issue_number: issue.number, labels: ['blocked'],
+                }).catch(e => { if (e.status !== 404) throw e; });
+                core.info(`research-clear: loop-back bound reached on #${issue.number} — escalated with blocked label.`);
+                return;
+              }
+              await github.rest.issues.createComment({
+                owner: context.repo.owner, repo: context.repo.repo,
+                issue_number: issue.number,
+                body: `🔁 **Synthesis not ready — honest loop-back accepted (cycle ${priorLoopBacks + 1}).** Evidence floors met (INWARD citations: ${inwardCites.size}, OUTWARD sources: ${outwardUrls.size}, trail annotated: ${annotated.length}, live-verified: ${outwardUrls.size - dead.length}), but the synthesis itself declares MORE-RESEARCH with substantiated open questions.\n\nresearch-pending stays. Next round must resolve the named unknowns — a later synthesis must either produce a plans/ artifact or identify NEW unknowns. Bound: 2 loop-backs, then escalation.`,
+              });
+              core.info(`research-clear: honest MORE-RESEARCH loop-back on #${issue.number} (cycle ${priorLoopBacks + 1}) — research-pending retained.`);
+              return;
+            }
+
+            // Clear research-pending, add in-progress
             try {
               await github.rest.issues.removeLabel({
                 owner: context.repo.owner, repo: context.repo.repo,
@@ -204,9 +387,9 @@ jobs:
             await github.rest.issues.createComment({
               owner: context.repo.owner, repo: context.repo.repo,
               issue_number: issue.number,
-              body: `🔬 **Research round verified** — all 4 phases (INWARD / OUTWARD / INNOVATION / SYNTHESIS) detected in Rune's research. research-pending cleared.\n\n▶️ **in-progress applied** — Rune is now working on this issue. The pipeline will notify at each transition.`,
+              body: `🔬 **Research round verified — synthesis qualified.** 4 phases + evidence floor met (INWARD citations: ${inwardCites.size}, OUTWARD sources: ${outwardUrls.size}, trail annotated: ${annotated.length}, live-fetch verified: ${outwardUrls.size - dead.length}); synthesis declared evidence ${hasSufficiency ? 'sufficiency statement ✓' : '✓'} + feasibility judgement ✓ and committed to a plans/ artifact.\n\n▶️ **in-progress applied** — Rune is now working on this issue. The pipeline will notify at each transition.`,
             });
-            core.info(`research-clear: #${issue.number} research verified, label cleared.`);
+            core.info(`research-clear: #${issue.number} research verified with evidence, label cleared.`);
 
   # INCOMPLETE CATCHER: detect branches with commits but no PR, belonging to
   # in-progress issues — auto-create draft PR with incomplete label + ledger.

plans/2026-09-07-research-gate-evidence.md

@@ -0,0 +1,31 @@
+# Research-gate evidence enforcement (pipeline hardening) — Plan
+
+> **Contract:** controller-authored (controller-sized change), independent review gate + protected CI still apply. Conventional commit referencing the tranche epic #147 (§3.4-adjacent gate integrity). No deviation without plan-tail record.
+
+## Goal
+
+Nick's directive: research rounds must actually PULL sources so downstream stages work on evidence. Today `research-clear` clears on four regex keywords — a round of pure improvisation clears identically to a genuine one (observed this session). The gate must verify EVIDENCE per phase.
+
+## Change (single job edit: `.gitea/workflows/pipeline-gate.yml` research-clear)
+
+Split the comment body into phase sections (on the phase headers). Require:
+- **INWARD:** ≥2 codebase citations matching `(src|tests|scripts|docs|.gitea)/...` path pattern (evidence the code was actually read).
+- **OUTWARD:** ≥2 UNIQUE external http(s) URLs, excluding the forge's own host (self-references are not external sources) — evidence sources were actually pulled.
+- **INNOVATION + SYNTHESIS:** ≥1 total URL reference OR a `plans/` path mention (the synthesis must tie back to sources or a concrete plan artifact).
+- Missing evidence → the job posts a comment naming exactly what's missing (per phase), research-pending STAYS, no label transition. Existing success path unchanged otherwise.
+
+## Non-goals
+
+- No LLM judging in CI (anti-complexity; regex evidence floor only).
+- No change to gate/teach jobs; no new labels.
+
+## Tasks
+
+1. Edit research-clear script: section splitter + evidence counters + rejection comment. Verify YAML parses; henxels exit 0; all canaries green (unchanged src → suite untouched but CI will run it on PR anyway).
+2. Commit `feat(pipeline): research gate requires evidence (sources in OUTWARD, citations in INWARD) (#147)`; push; PR; protected merge.
+
+## Acceptance
+
+- A sourceless OUTWARD no longer clears the gate (rejection comment received).
+- An evidenced round (URLs + citations) clears as before.
+- Verified live: the next tranche research round (posted with general-3's pulled sources) passes the new gate.