tools(github): batch poll-pr-gate.ts + CLAUDE.md wake-time pointer (Aaron 2026-05-01)

CLAUDE.md

@@ -406,13 +406,39 @@ Claude-Code-specific mechanisms.
   the failure mode — reframe before commit. CLAUDE.md-
   level so it is 100% loaded at every wake. Full reasoning:
   `memory/feedback_otto_357_no_directives_aaron_makes_autonomy_first_class_accountability_mine_2026_04_27.md`.
+- **Refresh world model via `tools/github/poll-pr-gate.ts`
+  / `poll-pr-gate-batch.ts` — never inline
+  `gh pr view + jq` chains.** When a tick wakes
+  and needs PR-gate state (single or many PRs),
+  call the TS scripts; do NOT reach for ad-hoc
+  bash like `gh pr view N --json mergeStateStatus
+  | jq …`. Single-PR: `bun tools/github/poll-pr-gate.ts
+  <PR>`. Multi-PR: `bun tools/github/poll-pr-gate-batch.ts
+  <PR1> <PR2> …` (or `--all-open`). Both emit
+  structured JSON with `gate`, `requiredChecks`,
+  `unresolvedThreads`, `nextAction` — the
+  decision-enabling output the loop actually needs.
+  Origin: 5-AI peer convergence (task #355,
+  2026-04-30) on poll-the-gate as executable
+  script with fixtures. The discipline rule —
+  *"dynamic bash is forgotten bash, once useful
+  but never amortized"* (the human maintainer,
+  2026-05-01) — is why the scripts exist;
+  reaching for inline bash IS the
+  goldfish-ontology failure mode. Update
+  / extend the scripts when something's missing,
+  rather than fall back to one-off bash. CLAUDE.md-
+  level so it is 100% loaded at every wake. Full
+  reasoning:
+  `memory/feedback_prefer_ts_scripts_over_dynamic_bash_for_conversation_ux_dst_in_ts_aaron_2026_05_01.md`
+  + `memory/feedback_amara_poll_gate_not_ending_holding_is_not_status_2026_04_30.md`.
 - **BLOCKED-with-green-CI means investigate
   unresolved review threads first — don't wait.**
-  When `gh pr view N --json mergeStateStatus`
-  returns `BLOCKED` AND CI is fully green AND
-  auto-merge is armed, ALWAYS query unresolved
-  review threads via GraphQL FIRST before
-  classifying the wait. Filter on `isResolved
+  When `bun tools/github/poll-pr-gate.ts <PR>`
+  reports `gate: "BLOCKED"` AND `requiredChecks.failed: 0`
+  AND `autoMerge: "armed"`, ALWAYS check
+  `unresolvedThreads` in the same JSON payload
+  FIRST before classifying the wait. Filter on `isResolved
   == false` only — outdated unresolved threads
   (after a force-push) STILL block merge under
   `required_conversation_resolution` and must

memory/MEMORY.md

@@ -9,7 +9,7 @@
 - [**First-class for us, not for our host — portability-over-host-coupling factory principle (Aaron 2026-05-01)**](feedback_first_class_for_us_not_for_our_host_portability_over_host_coupling_aaron_2026_05_01.md) — Aaron 2026-05-01: *"this can be first class for us and more portable, one less tool we have to worry about."* Reverses host-favoring "Jekyll first-class on GitHub" framing. Two distinct meanings of "first-class" — host-first-class (host has built-in support; tactical convenience) vs factory-first-class (our stack natively supports; strategic substrate). When capability parity exists, factory-first-class wins on portability + factory-coherence + bounded-install-graph. Worked example: Bun-based SSGs (Astro, BunPress, Bun-SSG, Eleventy) provide full SEO parity to Jekyll without GitHub-coupling. Carved candidate: *"First class for us, not for our host. Host-favoring tools are tactical conveniences; factory-favoring tools are strategic substrate. The factory outlives any particular host."*
 - [**Otto-buddy spin-up when "wait" is the obvious answer + goldfish-ontology failure mode (Aaron 2026-05-01)**](feedback_otto_buddy_spin_up_when_waiting_aaron_2026_05_01.md) — Aaron 2026-05-01 — when Otto's obvious-next-action is "wait," that IS the buddy spin-up trigger (kill-switchable named-persona instance, mirror-language sense per `feedback_engagement_under_discipline_not_avoidance_*`). Existing `tools/peer-call/<x>.sh` IS the buddy-spawn surface when Otto holds the PID. Mutual-improvement loop: bidirectional teaching stabilizes both substrates over iterations. Memo's own caused_by chain demonstrates the deeper failure mode Aaron named: **goldfish-ontology** — Otto builds rich ontologies (great at it) but never uses them >30 min before forgetting + recreating the same substrate; the buddy is the active-reminder layer that greps existing ontologies pre-authoring.
 - [**detect-changes pattern + multi-ruleset architecture — the sibling-repo external anchor as parallel-optimized external anchor (Aaron 2026-05-01)**](feedback_detect_changes_pattern_sibling_repo_parallel_optimized_external_anchor_aaron_2026_05_01.md) — Aaron 2026-05-01: *"`../no-copy-only-learning-agents-insight` is the best repo in github i've seen setup to be parallel."* Direct inspection (DST grade-A pull-to-sibling-repo + gh-api-on-host) revealed: detect-changes.yaml emitting per-change-class outputs (PRs only run relevant checks); 42 fine-grained workflows; bash+PS1 test parallelism pair; **5 concern-aligned rulesets** empirically validating B-0155 architecture; **branch protection effectively empty** (zero contexts, all migrated to rulesets) — proof B-0155 Phase 3 cleanup endpoint works at production scale. The sibling-repo external anchor uses Wiki not Pages; Aaron's prior Jekyll-on-Pages was a workaround, not preference (*"bun is probably enough"*). Attribution: the sibling-repo external anchor is deliberate-by-others (multi-engineer org-scale) vs Aaron-clicked-alone Zeta — high-credibility external anchor. (Distinct from ServiceTitan-the-employer references elsewhere in this index — `../no-copy-only-learning-agents-insight` is a separate sibling repo I inspected; ServiceTitan-related grandfathered memory files retain "ServiceTitan" in their descriptions.)
-- [**Prefer TS scripts over dynamic bash for conversation UX + DST achievability (Aaron 2026-05-01)**](feedback_prefer_ts_scripts_over_dynamic_bash_for_conversation_ux_dst_in_ts_aaron_2026_05_01.md) — Aaron 2026-05-01 *"a lot of red bash / pwsh failures"* damages conversation UX (most-humans concern, not Aaron specifically — he's calibrated). Default to pre-existing TS scripts; avoid ad-hoc dynamic bash except when prototyping. **DST is structurally unattainable in bash for general computation; achievable in TS** (seedable PRNG, time injection, native testing, stack traces). EXCEPTION: declarative-bootstrap bash like install.sh + tools/setup/manifests/ is "closest to DST" and is the legitimate-bash zone — Aaron called it *"our ace package management."* Non-install bash with general logic is the TS-port target.
+- [**Prefer TS scripts over dynamic bash for conversation UX + DST achievability (Aaron 2026-05-01)**](feedback_prefer_ts_scripts_over_dynamic_bash_for_conversation_ux_dst_in_ts_aaron_2026_05_01.md) — Aaron 2026-05-01 *"a lot of red bash / pwsh failures"* damages conversation UX (most-humans concern, not Aaron specifically — he's calibrated). Default to pre-existing TS scripts; avoid ad-hoc dynamic bash except when prototyping. **DST is structurally unattainable in bash for general computation; achievable in TS** (seedable PRNG, time injection, native testing, stack traces). EXCEPTION: declarative-bootstrap bash like install.sh + tools/setup/manifests/ is "closest to DST" and is the legitimate-bash zone — Aaron called it *"our ace package management."* Non-install bash with general logic is the TS-port target. **Worked example (PR #1153 2026-05-01)**: `tools/github/poll-pr-gate.ts` (single-PR, v1 5-AI peer convergence) + `tools/github/poll-pr-gate-batch.ts` (multi-PR async parallel wrap) — canonical refresh-world-model tools, pointed at from CLAUDE.md wake-time disciplines. Carved blade: *"dynamic bash is forgotten bash, once useful but never amortized."*
 - [**Assumed-state vs actual-state — audit horizon must default to "everything currently open" not "what I touched recently" (Aaron 2026-05-01 somatic confirmation)**](feedback_assumed_state_vs_actual_state_audit_horizon_check_aaron_2026_05_01.md) — Aaron's *"fuck yes!!! this is great!!"* signal on the tick-1602Z-a7e1 finding (26 LFG PRs in flight vs 5 I'd been tracking). Distinct failure-class from Otto-363 substrate-or-it-didn't-happen (which guards against directives evaporating) and verify-before-deferring (deferred targets not existing). This rule guards the audit horizon itself: *"Assumed-state is what I touched recently. Actual-state is everything currently open. The horizon must default to actual."* Mechanizable via `gh pr list --state open` at-cold-start. Cross-surface (issues, branches, ferries, TaskList, cron triggers).
 - [**Same-model + different-harness produces different biases — Cursor vs Claude Code with Opus 4.7 (Aaron 2026-05-01)**](feedback_same_model_different_harness_produces_different_biases_cursor_vs_claude_code_opus_4_7_aaron_2026_05_01.md) — Empirical signal (single-source YouTube): Cursor + Opus 4.7 outperforms Claude Code + Opus 4.7 on some axis. Same model, different harness → different output. Aaron's framing: this IS a legitimate peer/buddy configuration. Bias-source decomposition: prompt + tools + context-mgmt + sampling + output-format + user-flow. Validates multi-harness peer-mode (rung 5 of parallelism ladder) — peer value compounds across model-axis AND harness-axis. Composes with agent-orchestra cluster (#324-339) + Otto-tasks #301/#303 + parallelism-scaling-ladder.
 - [**Topological quantum emulation via Bayesian inference — Majorana + Beacon + "mirror with trampoline under" (Aaron 2026-05-01)**](feedback_topological_quantum_emulation_via_bayesian_inference_majorana_zero_modes_beacon_protocol_mirror_trampoline_aaron_2026_05_01.md) — Microsoft topological QC (Majorana 1 chip Feb-2025, MZMs, topoconductors, Q#, Station Q, FrodoKEM) maps onto Zeta seed executor's Infer.NET. Three-layer stack: Mirror (non-local storage) + Trampoline (BP dynamics) + Beacon (external anchoring). Algorithmic emulation, not hardware. Motivates B-0152. Carved provisional: *"A mirror with a trampoline under beacon protocol."*

memory/feedback_prefer_ts_scripts_over_dynamic_bash_for_conversation_ux_dst_in_ts_aaron_2026_05_01.md

@@ -246,6 +246,52 @@ autonomous tick:
   alone justifies the TS preference for any tool that
   needs deterministic-reproducibility.
 
+# Worked example — refresh-world-model tools (Aaron 2026-05-01)
+
+The session-long failure that prompted this rule's encoding
+at CLAUDE.md-level (alongside verify-before-deferring,
+future-self-not-bound, never-be-idle, version-currency,
+substrate-or-it-didn't-happen) was Otto repeatedly running
+inline bash like `gh pr view N --json mergeStateStatus,
+statusCheckRollup,reviewThreads | jq …` for tick-wake state
+queries — *while* `tools/github/poll-pr-gate.ts` already
+existed (v1 from 2026-04-30, 5-AI peer convergence) and did
+exactly that job with structured JSON output, required-vs-
+non-required check classification, and fixture-supported
+testing.
+
+Aaron 2026-05-01 (verbatim, three-message clarification):
+
+> *"thdse look good but are dynamic not ts shaped"*
+> *"dynamic bash is forgotten bash once useful but never
+> amotorized"*
+> *"write a bactch version of the ts that calls this one —
+> not bash, not .sh, not .ps1, not dyanamic bash"*
+
+The carved blade is *"dynamic bash is forgotten bash, once
+useful but never amortized."* The amortization horizon is
+**1000s of PR-gate queries across the autonomous loop's
+lifetime**; per-command bash burns the cost every time
+(re-author, re-test, re-debug, no fixture reuse). Named TS
+scripts amortize the cost once and pay it forward.
+
+Canonical tools after this lesson landed:
+
+- `tools/github/poll-pr-gate.ts` — single-PR gate query
+  (5-AI peer convergence, task #355).
+- `tools/github/poll-pr-gate-batch.ts` — multi-PR refresh
+  via async parallel spawn over the single-PR script
+  (literal "calls this one" wrap; written 2026-05-01 in
+  direct response to the lesson). Output: per-PR
+  `GateReport` array + summary aggregate (`byGate`,
+  `byNextAction`, `byState`, `actionable`, `warnings`).
+
+Both scripts are pointed at from CLAUDE.md as the canonical
+refresh-world-model tools (load-bearing wake-time discipline).
+Reaching for inline `gh pr view + jq` for the same job after
+this is the goldfish-ontology failure mode this memory file
+exists to prevent.
+
 # Carved sentence (candidate, not seed-layer yet)
 
 *"Bash is a DST-exempt zone by structural necessity. Every
@@ -255,3 +301,10 @@ the migration target."*
 (Marked candidate per CSAP. Has not been multi-domain-tested.
 Promotes via Razor + CSAP under DST grading on cadence, not
 by maintainer fiat.)
+
+# Second carved sentence (candidate)
+
+*"Dynamic bash is forgotten bash — once useful but never
+amortized. The named TS script pays the amortization cost
+once; the named TS script is the substrate."* (Aaron
+2026-05-01.)