339 Commits

Include renames

Author	SHA1	Message	Date
Nick	43ef8e43e7	feat(research): RP8 — QUALIFY executor + gate, narrowed semantics (closes #271) ... - _execute_qualify: deterministic-first — 13 implementation-readiness checks (design explicit, interfaces concrete, authority boundaries, data flow, sequence, invariants, tests, acceptance, failure modes, rollback, adversarial mitigations included, falsification tests included, blocking unknowns absent) run BEFORE any MiMo call - MiMo semantic judgment ONLY when deterministic checks pass: judge whether a coder could implement without guessing — not re-research, not re-litigating the design (ADVERSARIAL owns epistemics) - Verdict assembly: deterministic failures → REFINE_SYNTHESIS without a model call; worker verdicts constrained to PROCEED/REFINE_SYNTHESIS; informal reopen attempts downgraded to REFINE_SYNTHESIS; formal reopen requires the four justification fields (gate-enforced) - Malformed worker verdicts treated as REFINE_SYNTHESIS (fail-safe) - 9 new tests; suite 174 pass, ruff clean	2026-09-09 01:25:56 +01:00
Nick	b0b9c3165c	fix(research): RP7 gate — mitigation representation is substantive, not verbatim ... Real-run finding from #161: the worker integrated all 10 adversarial mitigations into its design language (60-100% key-concept overlap in structural fields) but did not quote the mitigation sentences verbatim. Literal substring matching tested copy-paste, not design coverage. The gate now measures keyword-overlap coverage (≥50% of non-stopword key concepts) across invariants/interfaces/data_flow/tests/acceptance. Verified: 10/10 mitigations represented, 7 kill-tests converted to 13 invariants, 11-step implementation sequence → GATE PASSED (e584bbf895b3), tree at QUALIFY.	2026-09-09 01:22:13 +01:00
Nick	a0e0b02449	feat(research): RP7 — SYNTHESIS executor + gate (closes #270) ... - _execute_synthesis: deterministic readiness invariant enforced BEFORE the MiMo call (no cognition on untrustworthy foundations); bounded prompt carries survivors, rejected candidates + reasons, required mitigations, and kill-tests as ACCEPTED CONSTRAINTS - Worker produces build instructions: selected_design, why-this-design-won, rejected_alternatives, components_affected, authority_boundaries, interfaces, data_flow, implementation_sequence, invariants, tests_required, acceptance_criteria, failure_modes, rollback, deliberately_excluded - Gate (_validate_synthesis): all core fields present (design, sequence, interfaces, acceptance, rollback); every falsification test converted into an invariant; every required mitigation represented STRUCTURALLY (invariants/interfaces/data_flow/tests/acceptance — prose mention in the design summary is not representation); rejected-candidate resurrection forbidden (id scan across design + components) - Artifact carries provenance: adversarial_disposition, carried_mitigations, carried_falsification_tests, carried_survivors — the literal-handoff input shows exactly which constraints the design was built under - 8 new tests; suite 165 pass, ruff clean	2026-09-09 01:14:11 +01:00
Nick	a553fb1363	feat(research): adversarial-gated refinement + narrowed QUALIFY (pipeline correction 2026-09-09) ... ADVERSARIAL owns epistemic refinement. QUALIFY owns implementation-readiness. - ADVERSARIAL_DISPOSITIONS enum: SURVIVES / SURVIVES_WITH_MITIGATIONS / EVIDENCE_DEFICIENT / APPLICABILITY_DEFICIENT / INNOVATION_WARRANTED / NO_VIABLE_CANDIDATE. Only SURVIVES* unlock SYNTHESIS; every other disposition routes targeted refinement to the earliest repairable stage (EVIDENCE_DEFICIENT/NO_VIABLE_CANDIDATE → OUTWARD, APPLICABILITY_DEFICIENT → APPLICABILITY, INNOVATION_WARRANTED → INNOVATION) - advance() REQUIRES a valid adversarial disposition — an adversarial pass without a disposition cannot unlock anything - synthesis_readiness() deterministic invariant (§7): disposition unlocks AND ≥1 surviving candidate AND mitigations represented (for SURVIVES_WITH_MITIGATIONS) AND blocking unknowns = 0 - Falsification tests + required mitigations are first-class capsule fields — they reach SYNTHESIS as mandatory inputs, not optional prose (§5) - QUALIFY narrowed (§8–10): outcomes PROCEED / REFINE_SYNTHESIS (routes to SYNTHESIS only) / REOPEN_EARLIER_STAGE (exceptional; requires reason, return_to, new_blocking_fact, why_previous_gate_could_not_reasonably_ have_caught_it). Generic MORE_RESEARCH removed as a QUALIFY outcome. - Fake worker + all chain tests updated to the disposition/outcome contract Acceptance §18: 18/18 PASS (test_adversarial_gated_refinement.py). 148 tests pass, ruff clean.	2026-09-09 01:03:13 +01:00
Nick	bac9f583f9	fix(research): RP6 gate — normalize worker dimension naming, accept dedicated falsification_tests ... Real-run findings from #161: worker emits snake_case dimensions (weak_assumptions, Rune_constraint_violations) — gate now normalizes snake/kebab to spaces before matching. Falsification may be satisfied either as an attack dimension or as dedicated falsification_tests (kill-tests) — the worker produced 2 concrete kill-tests (e.g. FT1: run harness with embedding backend unreachable; any unlabeled mode switch voids validation). Verified: 16 attacks, 6 survivors, 1 rejection (memory-adapter-protocol — duplicate authority vs memory_selector.py source registry), 2 external checks, 25 repo-verification tool calls → GATE PASSED (3827446e701a), tree at SYNTHESIS.	2026-09-09 00:47:03 +01:00
Nick	fb70092fed	feat(research): RP6 — ADVERSARIAL executor + gate (closes #269) ... - _execute_adversarial: one bounded MiMo red-team pass on the leading APPLICABILITY candidates; targeted external checks permitted with receipts - Dossier: surviving/rejected candidates, attacks (dimension+finding+evidence+ severity), critical assumptions, required mitigations, research gaps, falsification tests - Gate (_validate_adversarial): rubber-stamp fails (zero attacks); all seven attack dimensions must be addressed; every leading candidate must be attacked at least once; a fatal attack on a surviving candidate requires an explicit rebuttal - File channel accepted whenever stdout parse yields nothing (established worker pattern); stage-ordering guard (no APPLICABILITY → STAGE_FAILED) - 7 new tests; suite 130 pass, ruff clean	2026-09-09 00:37:59 +01:00
Nick	3b41e06303	fix(research): RP4 — prefer worker dossier file whenever stdout parse yields no candidates ... Prose-only stdout with a valid applicability.json on disk previously produced an empty artifact stub (gate-fail with misleading 'no candidates' error). Now: stdout JSON parsed first; if no candidates, the dossier file channel is checked. Structured artifact remains the authority. Verified on real #161 run: 9 candidates + repo-verified receipts → GATE PASSED (f477543dc8c9), route STANDARD_SOLUTION_SUFFICIENT → ADVERSARIAL (INNOVATION skipped on merit).	2026-09-09 00:30:44 +01:00
Nick	81aef725e0	feat(research): RP4 — APPLICABILITY executor + gate (closes #267) ... - _execute_applicability: one bounded MiMo pass consuming ISSUE+INWARD+OUTWARD artifacts; bounded inputs (source/claim ids, not prose); structured dossier written by worker to applicability.json — file channel accepted (structured artifact is the authority), stdout JSON also parsed - Gate (_validate_applicability): route must be STANDARD_SOLUTION_SUFFICIENT or INNOVATION_WARRANTED; candidates must use canonical classifications; viable candidates (DIRECTLY_APPLICABLE/APPLICABLE_WITH_ADAPTATION/ PROMISING_FOR_INNOVATION) require integration_point AND evidence ids; source_ids must resolve to accepted OUTWARD sources (no fabricated citations) - Route decision drives conditional INNOVATION routing at advance() - Stage-ordering guard: no OUTWARD artifact → STAGE_FAILED without MiMo call - 6 new tests; suite 123 pass, ruff clean	2026-09-09 00:21:46 +01:00
Nick	5b92068899	fix(research): RP3 — accept worker-written dossier file as artifact channel ... The structured artifact IS the authority (§5); stdout text is just one delivery channel. When the relay collects no stdout texts but the worker wrote a valid dossier to the stage artifact file, the executor normalizes it into the canonical unified structure (_normalize_outward_artifact) and gates it the same way. Gate semantics unchanged: ≥2 sources, real read receipts required, tool receipts required. Verified against the real #161 OUTWARD run: worker dossier (16 sources, 4 read with 22 claims, 4 contradictions, 8 limitations) + relay receipts extracted from the live events file (4 queries, 4 reads, 22 tools) → GATE PASSED, tree advanced to APPLICABILITY. Artifact hash bc57c4600880.	2026-09-09 00:16:02 +01:00
Nick	416df5c08f	fix(research): RP3 OUTWARD evidence chain — real read receipts, unified gate reads nested artifact ... - ResearchEventRelay captures per-event tool receipts (QUERY / SOURCE_READ / TOOL / TOOL_FAILED with url + timestamp) — the QUERY→SOURCE→READ→CLAIM chain now has real provenance, not just counts - OUTWARD artifact embeds tool_receipts; sources carry read_receipt flag — a source counts as read only if the relay captured a real fetch - _validate_outward fixed to read the unified (discovery/reading) artifact structure — previous validator read top-level keys that never existed, so any real run would have gate-failed; now also enforces ≥1 actually-read source and non-empty tool receipts (search snippets alone ≠ evidence) 125 tests pass, ruff clean.	2026-09-09 00:07:12 +01:00
Nick	26eef8e3d3	feat(research): RP2/#265 — runner-placement enforcement + code classification manifest ... THE HEAVY RUNNER IS THE DESKTOP PC, NOT THE PI. - scripts/runner_evidence.py: runtime execution evidence capture (hostname, runner identity from env, labels, execution class, stage, process id, issue, research process id, timestamp) — identity captured at runtime, never inferred from configuration alone - Deterministic placement gate (validate_placement): desktop-heavy stage executed on Pi → PLACEMENT_REJECTED; hostname checked too (cannot hide the Pi behind a desktop runner name); missing evidence fields rejected; unverified runners rejected (no silent fallback); pi-lightweight forge operations (metadata, labels, eligibility) explicitly allowed - Placement gate wired into StageExecutor.execute(): every stage result embeds runner_evidence; Pi execution fails the tree and cannot count as acceptance - docs/RESEARCH_CODE_CLASSIFICATION.md: aggressive detection, conservative classification (CURRENT/SUPERSEDED/COMPATIBILITY/TEST_FIXTURE/ UNKNOWN_PURPOSE); NO deletion in #265 — retirement is RP11 after RP10 proof; run_full_research() self-walk + --watch poll classified SUPERSEDED; tui-restart-pending marked SUPERSEDED CANDIDATE (verify before removal) Acceptance: canonical order PASS; conditional INNOVATION PASS; ISSUE deterministic PASS; earliest-stage refinement PASS; heavy-runner requirement encoded PASS; Pi rejection PASS; runtime identity/hostname/labels captured PASS; stage/run/process identity PASS; Gitea stage authority preserved (one-stage executor unchanged) PASS; no self-walking production loop in the canonical path PASS; no premature retirement PASS. 125 tests pass, ruff clean. Pre-existing henxels digest env failure unchanged.	2026-09-09 00:02:16 +01:00
Nick	54e6967d79	feat(research): conditional INNOVATION routing — INNOVATION is never ceremonial ... Semantic correction per RP2 review (2026-09-09): - APPLICABILITY artifact carries a route decision: STANDARD_SOLUTION_SUFFICIENT → ADVERSARIAL (INNOVATION skipped) INNOVATION_WARRANTED → INNOVATION → ADVERSARIAL - Default when artifact is silent: skip INNOVATION (do not manufacture novelty) - Invalid route values rejected; NO_INNOVATION_WARRANTED is a valid success - ISSUE gate strictly deterministic: needs_mimo hardwired False (compat shim, marked REMOVE AFTER), ambiguity recorded as signal for downstream stages - Contract compiler uses canonical stage names only (no retired names in required/skipped fields); INNOVATION included only when warranted - Refinement may route around INNOVATION (innovation → INNOVATION; mechanism weakness → ADVERSARIAL directly) Acceptance (all PASS): canonical order retained; INNOVATION conditional; APPLICABILITY→ADVERSARIAL bypass; APPLICABILITY→INNOVATION route; NO_INNOVATION_WARRANTED valid; ISSUE deterministic/no-MiMo; earliest- affected-stage refinement; no blind mandatory walk. 112 tests pass, ruff clean.	2026-09-08 23:59:31 +01:00
Nick	8551cd723d	feat(research): RP2 — canonical stage model (ISSUE→INWARD→OUTWARD→APPLICABILITY→INNOVATION→ADVERSARIAL→SYNTHESIS→QUALIFY) ... Canonical handoff 2026-09-08 (epic #257, children #264-#277): - ISSUE (deterministic issue-quality gate) replaces DEFINE as stage 0 — the Gitea issue is the authoritative definition; no cognitive DEFINE stage - APPLICABILITY added after OUTWARD with canonical candidate classifications - INNOVATION precedes ADVERSARIAL (canonical order per §1) - OUTWARD unified (OR1 preserved): discovery+reading are artifact subsections - RETIRED_STAGES declared: DEFINE/OUTWARD_DISCOVERY/OUTWARD_READING cannot be advanced or dispatched through the canonical path (RETIRED_STAGE status) - more_research → targeted refinement routing to EARLIEST deficient stage; external unknowns route to unified OUTWARD, never the retired split stages - fake worker, integration/boundary/reliability tests rewritten for canonical chain; legacy-state tree at a retired stage raises on advance - new prompt templates: issue.md, applicability.md (with MUST NOT contracts) Tests: 104 passed. Ruff clean. Pre-existing henxels digest failure unchanged (missing henxels.contract module in env, fails identically on clean tree). closes #264 (RP1 stage model); runner-placement enforcement (RP2/#265) next	2026-09-08 23:50:10 +01:00
Nick	9d1e0da8e5	feat(research): OR1 — unify OUTWARD_DISCOVERY+OUTWARD_READING into OUTWARD ... One coherent MiMo external-research pass. Discovery and reading remain visible as subsections inside the artifact, not separate top-level stages. Artifact has discovery and reading subsections. Event relay streams both.	2026-09-08 23:17:51 +01:00
Nick	83ea89c1ba	feat(research): OUTWARD_DISCOVERY executor — real MiMo discovery with structured artifact ... - _execute_outward_discovery: compiles stage-scoped prompt from tree state, invokes MiMo locally with live event relay, extracts URLs from research text, builds OutwardDiscoveryArtifact (queries + sources + coverage + selection) - _validate_outward_discovery: fast gate (≥2 sources, unique IDs, valid URLs, coverage) - Boundary test updated: OUTWARD_DISCOVERY reaches the MiMo invocation boundary (subprocess mocked in unit tests, real MiMo in acceptance) BUILD ONE COGNITIVE STAGE. PROVE ONE COGNITIVE STAGE. THEN REPEAT.	2026-09-08 22:31:16 +01:00
Nick	d4a4222fcd	feat(research): stage-trigger boundary executor — one event = one stage, idempotency guard, no self-walking ... Per RUNE_RESEARCH_STAGE_TRIGGER_BOUNDARY_ACCEPTANCE_PROMPT: - Each stage is a separate ResearchStageReady event - The executor runs exactly one stage per invocation - Duplicate events are acknowledged as DUPLICATE (no second execution) - Gitea independently authorizes the next stage - Rune does NOT self-advance through the methodology - DEFINE is deterministic, INWARD is deterministic context builder - OUTWARD_DISCOVERY returns NOT_IMPLEMENTED (proves the boundary) 7 boundary tests green.	2026-09-08 22:10:20 +01:00
Nick	1c11984701	fix(research): gitea_api double-read bug — r.read() consumed body, second call returned empty	2026-09-08 21:30:20 +01:00
Nick	5a9825fa7f	fix(research): DEFINE and INWARD use deterministic paths — MiMo only for bounded semantic inspection	2026-09-08 21:23:40 +01:00
Nick	efc895bd30	feat(research): R1-R2 deterministic DEFINE + INWARD context builder ... DEFINE: deterministic contract compilation from Gitea issue. No MiMo unless ambiguous. Classifies question type, extracts sub-questions, produces required-stage plan with skip reasons. INWARD context builder: deterministic. Matches issue keywords against umbrella manifest and source/test files. Produces bounded candidate context. MiMo only invoked for semantic inspection of the bounded candidates, not broad agent wandering. METHODOLOGY STAGE ≠ MANDATORY LLM CALL.	2026-09-08 21:18:42 +01:00
Nick	8c3be8303d	feat(research): local research execution backend — corrected execution model ... Gitea triggers and ratifies cognition. Rune/MiMo performs cognition. The TUI shows the live process. The backend runs LOCALLY on nick's machine (not in Gitea Actions): - receives stage-ready events (polls Gitea for research-pending issues) - compiles stage prompts from the ResearchTaskTree - invokes mimo LOCALLY (subprocess — not Gitea Actions) - streams events to the TUI via the event relay - validates artifacts with stage-specific gates - records results in Gitea - advances to the next stage Gitea Actions becomes a TRIGGER, not a WORKER.	2026-09-08 20:34:03 +01:00
Nick	bfee4fa270	debug(research): add events count + stderr capture to stage executor	2026-09-08 19:35:51 +01:00
Nick	7653c28346	feat(research): stage-specific validation gate before advance — OUTWARD requires ≥2 URLs, INWARD requires ≥2 code paths, INNOVATION requires evidence derivation. Gate failure does NOT advance (retry semantics). The structured artifact IS the authority, not prose.	2026-09-08 19:18:36 +01:00
Nick	03e994ebb3	feat(research): RSC0-9 core — idempotency guard, live event relay, per-stage executor, stage-scoped prompts, MORE_RESEARCH targeting, durable state persistence ... - research-dispatcher.yml: label event → API query → stage dispatch (automatic) - research_event_relay.py: live event relay (QueryIssued/SourceRead/ToolFailed etc.) - research_task_tree.py: process lock (idempotency), round sync from persisted state - research_prompt_compiler.py: dynamic stage-scoped prompts from tree state - run_research_stage.py: one-stage executor + tree persistence to master - fake_worker.py: deterministic 8-stage integration harness (15 tests green) - Pipeline extension guide committed 15 relevant pipeline tests passed. Proven: 8-stage chain, MORE_RESEARCH targeted branch, cross-workspace persistence, evidence handoff.	2026-09-08 18:24:18 +01:00
Nick	baf97b568a	fix(research): round number synced from persisted state on load — tree.round was a Python attribute not synced from state['round']	2026-09-08 17:34:21 +01:00
Nick	8dbdd4516f	debug: tree persist check logging	2026-09-08 16:26:23 +01:00
Nick	55cfccb82c	fix(research): task tree persisted to master after each stage + loaded from master on fresh workspace — Gitea owns durable state (RSC1 doctrine)	2026-09-08 15:54:28 +01:00
Nick	8f48f8a2e4	fix(research): create output directory before writing events file	2026-09-08 15:28:40 +01:00
Nick	82888ee8ab	feat(research): RSC1-3 — ResearchTaskTree (canonical state), dynamic stage prompt compiler, bounded one-stage executor ... RSC1: ResearchTaskTree tracks issue+round+stage+completed+artifacts+blocking_unknowns. Persists to task_tree.json per issue. advance/fail/more_research/capsule/get_prior_artifacts. RSC2: compile_research_prompt(tree, stage) builds a task-specific prompt from the stage template + process capsule + prior artifacts + blocking unknowns. RSC3: run_research_stage.py executes ONE MiMo invocation for ONE stage. Compiles prompt → invokes mimo → extracts text → advances tree → returns next stage. The workflow dispatches per-stage (Gitea event model IS the scheduler).	2026-09-08 14:51:51 +01:00
Nick	b6d1a08750	feat(research): R1-R5 — event-driven coordinator, stage-scoped methodology, OUTWARD router, structured artifact gate, MORE_RESEARCH immediate re-dispatch ... R1: disposition routing wired into the research stage workflow — PROCEED lets research-clear fire, MORE_RESEARCH dispatches round+1 immediately (no sweep wait). The workflow completion IS the event. R2: 8 stage-scoped prompt templates (DEFINE through QUALIFY) — each gets a narrow prompt, frozen prior artifacts, explicit MUST NOT constraints. R3: research_router.py — classifies questions (academic/software/web), routes to OpenAlex/SemanticScholar/arXiv/GitHub/DuckDuckGo, doctrine queries include limitations/alternatives/failures. R4: structured artifact validated in the stage workflow before commit — receipt + URLs + code paths + disposition all checked. R5: MORE_RESEARCH dispatches round+1 from the workflow (no sweep wait); blocking unknowns passed to the next round. R0 red reproduction recorded: foreground slept 300s×N while child mimo worker was productive (18.6% CPU, 547MB, 8min CPU). Anti-pattern confirmed.	2026-09-08 12:31:53 +01:00
Nick	b2a43a3a92	feat(research): dispatcher workflow + structured artifact gate (P0 dispatch reliability + P0.4 artifact validation) ... - research-dispatcher.yml: triggers on issues.labeled, checks label via API (deterministic), dispatches research-stage via workflow_dispatch (proven). Fixes the label-event payload quirk that silently skipped API-applied labels. - research-stage-headless.yml: dispatch-only trigger (dispatcher handles label events); structured artifact generation from mimo events (receipt + URLs + code paths + disposition) validated by research_artifact.py before commit. - The prose comment stays as human-readable rendering; the ARTIFACT is the gate authority (Nick: replace prose-regex authority with structured artifact validation).	2026-09-08 11:26:30 +01:00
Nick	a8cebea264	feat(research): MORE_RESEARCH re-dispatch semantics (P0.6) — sweep keeps MORE_RESEARCH rounds eligible (re-dispatch when label lost); PROCEED rounds are done. Disposition routing documented in stage workflow	2026-09-08 07:12:34 +01:00
Nick	7f050a13df	feat(research): structured research artifact schema + causal validation (P0.4, red-first) ... Per the Forge Cognitive Research Loop handoff §8/§9/§11/§12: - OUTWARD valid only with real discovery (≥2 sources, url+tool+learned each, ≥1 query recorded) - INNOVATION candidates must derive_from prior claims; ≥1 from OUTWARD unless exempt - SYNTHESIS must cite evidence_used; MORE_RESEARCH requires named blocking_unknowns - dispositions: PROCEED | MORE_RESEARCH (nothing else) 10 red-first tests frozen green.	2026-09-08 07:08:06 +01:00
Nick	ab2c567ea4	fix(robot): classify gate on BOTH update paths (conflict-first + behind-base) — code-path touch always waits for fresh CI; docs-only carries. Closes the #208 slip (merge on stale required-checks)	2026-09-08 05:54:37 +01:00
Nick	61f1ca63e8	feat(robot): conflict-first policy — staleness resolved immediately on mergeable=False (before any wait), 409 conflicts skip with reason; carry-forward race closed by re-verifying mergeable post-update (Nick policy: merges resolve in ~1min, then sleep)	2026-09-08 05:49:55 +01:00
conductor	c9d7c1ccef	Merge branch 'master' into umbrella-pipeline	2026-09-08 03:34:19 +01:00
Nick	540f30b553	feat(pipeline): streamline — direct-commit version bumps, robot transient retry, extension guide (Nick policy, 2026-09-08) ... ## Bumps are bookkeeping, not reviewable code auto-version now commits the 5 version surfaces DIRECTLY to master via the contents API — no bump branch, no bump PR, no bump CI wave, no staleness cascade, no concurrent-bump race (230/231 proved it). In-memory gate: all 5 surfaces must agree on the new version BEFORE any commit (TUI footer renders rune.__version__ at call time — the displayed version IS __init__.py). Commit messages carry the provenance link to the earning PR. ## Robot: transient 405 'Please try again later' retried (3x backoff) Forge mergeability recompute was failing the robot on every merge burst — transient is 'not ready', not a refusal. Fail-loud applies to refusals and to exhausted retries (both paths tested). ## Future-proofing: docs/pipeline-extension-guide.md Placement decision tree (merge-deciding → required-checks; work → narrowest event; bookkeeping → direct commit), event-delivery quirk table (every entry learned by a live failure), per-type checklists, the three invariants. Registry links it. Any future agent reads the guide BEFORE adding a process.	2026-09-08 03:22:35 +01:00
Nick	333d645dbe	fix(scripts): __main__ passes sys.argv[1:] — python strips the script name; CI invocation contract restored	2026-09-08 02:46:26 +01:00
Nick	ae8c23a981	feat(release): bump fast lane + provenance record (Nick's policy, 2026-09-08) ... Version bumps are version-string changes; the full pipeline is the wrong tool. Per Nick: - provenance: bump PR body now RECORDS the PR that earned the promotion (Earned by: #N — title, with link) — the promotion has a paper trail - light gate: bump PRs skip the 7 heavy jobs (head-ref if); required-checks runs scripts/check_version_surfaces.py instead — proves all five version surfaces agree (__init__ canonical, rune_tui header, canary literal, pyproject wheel, README badge) so the TUI footer will render the new version (VersionLabel reads rune.__version__ at call time) - red-first: 7 tests for the surface gate; full suite 877+84	2026-09-08 02:26:59 +01:00
Nick	229bad13bd	feat(robot): carry-forward policy — checks re-run only on contributed-code change (Nick's policy, 2026-09-08) ... Behind-base self-heal previously forced a full CI re-run even when the update's tree diff touched no code path — redundant by construction (identical code-path trees cannot produce different test outcomes). - merge_robot emits UPDATED protocol line after self-heal - scripts/carry_forward_check.py classifies the tested-head→new-head tree diff: CARRY_FORWARD (docs-only) vs RERUN_REQUIRED (any code-path touch) - workflow consumes it: CARRY_FORWARD republishes the required-checks aggregate citing tree identity; RERUN_REQUIRED waits for CI as today - policy recorded: first pass = full pipeline; base movement with unchanged code paths = carry; bugs/mistakes = new commits = full re-run Red-first: 2 new tests (classification + companion script contract).	2026-09-08 02:06:34 +01:00
Nick	0d04ea0aba	merge master (behind-base — the loop's own sound)	2026-09-08 01:33:16 +01:00
Nick	3f7ffb91ca	merge master (registry fix)	2026-09-08 01:20:01 +01:00
Nick	e637b676b3	fix(robot): self-heal behind-base PRs — update via API and retry merge; 409 conflict skips with reason (red-first) ... THE INEFFICIENCY (Nick): every master movement staled every other open PR; the robot SKIPPED them; a human worktree dance updated branches by hand; CI re-ran; the next auto-bump staled everything again. Loop documented across the whole session (round-1/round-2 'behind-base update' commits). Fix: the robot performs POST /pulls/{n}/update itself on 405-behind, then retries the merge. Skips only genuine conflicts (409). The forge heals its own staleness — no agent, no human. - test_behind_base_pr_is_updated_then_rechecked (new contract) - test_update_conflict_409_skips_not_fails - test_behind_base_405_self_heals_then_merges (supersedes old skip contract) - suite: 13 robot tests green	2026-09-08 01:09:42 +01:00
Nick	e4e81cfa6e	merge master (resolve: master reviewed state wins; spec-gate branch copy already wired ROBOT_TOKEN)	2026-09-08 01:03:57 +01:00
Nick	3a18534516	merge master (resolve: master's auto-version evolution wins — semver extraction is the newer reviewed state; #192 convergence machinery on this branch supersedes via its own PR review)	2026-09-08 00:58:18 +01:00
conductor	d67c535227	Merge branch 'master' into bugfix-contract	2026-09-08 00:57:19 +01:00
Nick	fa689c77e9	feat(pipeline): generic agent-stage runner — transport with tool receipts, locks, restart safety (P0.2, red-first) ... scripts/run_agent_stage.py per the Forge Cognitive Research Loop handoff: - ONE runner for all cognitive stages (research/planning/review) — not a family of per-stage scripts - tool receipts derived from STRUCTURED events (type:tool parts), never model self-report; OUTWARD validity = >=2 completed search/fetch calls across >=2 distinct web domains - idempotency key issue+stage+round; TTL locks (crashed stage -> stale lock expires -> redispatch safe) - fail loud: mimo crash, schema violation, missing receipt all return 1 - event schema verified live against runner mimo 0.1.13 (type:text/part.text — the spec-gate's parser had the wrong shape; fixed here) - canary evidence (T8): no native search tool on runner mimo; discovery works via webfetch of search-engine HTML + fetched pages (2 domains, real content, honest self-report of the fallback)	2026-09-08 00:40:18 +01:00
Nick	037c47f604	merge master (behind-base)	2026-09-08 00:17:21 +01:00
Nick	3065d11384	fix(release): auto-version resurrected — semver logic extracted to scripts/semver_bump.py; YAML-parse-death from #190 discharge (red-first) ... Root cause of missing version bumps since 2026-09-06 15:01: #190 pasted inline python into a double-quoted YAML scalar (unescaped quotes, column-0 lines) making auto-version.yml UNPARSEABLE. Gitea rejects the workflow wholesale — dispatch 500, pull_request:closed triggers never fire. Six merges tonight + all merges since #190: zero bumps. - scripts/semver_bump.py: testable next_version() (0.x semver conventions) - workflow repaired, parses clean - version-behind-tag now a LOUD ::warning anomaly (#192), never silent skip - NEW GATE: tests/test_semver_bump.py validates ALL workflow files parse — the missing lint that let this rot silently (7 workflows covered)	2026-09-07 23:23:24 +01:00
Nick	db14f66bc0	feat(pipeline): research structuralization — dispatched headless research stage + idempotent backlog sweep (#204 second slice) ... Nick's critique structuralized (2026-09-07): - 'is research being done or already done?' → sweep detects existing 4-phase rounds (INWARD/OUTWARD/INNOVATION/SYNTHESIS comments) and SKIPS those issues; never re-researches completed work - research must CALL the LLM → research-stage-headless.yml dispatches headless mimo on research-pending label events (spec-gate runner pattern, verified) - filed as a research FILE per issue → research/issue-<n>-research.md merged to master via auto-PR; comment carries the markers research-clear keys on - 4 phases → SYNTHESIS ends in ordered build instructions = implementer's prompt - TUI callback seam → prompt externalized to governed prompts/research-round.md (placeholders substituted at runtime; L3/TUI owns it via reviewed diffs later) - failsafe: sweep dry-run by default; --apply explicit; red-first tests (10) Also: spec-gate-headless.yml copied to master stream with ROBOT_TOKEN wired (same reserved-secret bug the robot had — GITEA_TOKEN is the read-only auto token).	2026-09-07 23:05:17 +01:00
Nick	e0ca302bc1	merge master (behind-base update, round 2)	2026-09-07 22:45:39 +01:00