backlog: P1 — factory technology inventory + OpenAI web UI addition (Aaron 2026-04-23)

[AceHack]

Summary

Adds a P1 BACKLOG row capturing Aaron's 2026-04-23 directive to inventory every technology the factory uses so each gets first-class support (the way Docker and Postgres already do).

"don't forget to map out all our technology so the factory has first class support for everything ... i think i saw you ad docker and postgres and now we may be adding the openai website/ui i think we already have codex cli mapped"

What's missing

docs/HARNESS-SURFACES.md covers agent harnesses. docs/TECH-RADAR.md covers ring adoption. Per-tech expert skills cover depth. A unified inventory tying install path, version pin, auth-doc URL, expert-skill cross-reference, and TECH-RADAR ring per-tech does not exist yet.

Deliverable

docs/FACTORY-TECHNOLOGY-INVENTORY.md (name TBD) — living doc updated with each new tech adoption, surfacing cross-platform parity status (row #48) per tech.

OpenAI web UI as a new entry

Aaron explicitly named adding OpenAI web UI + Playwright as a new technology. Full Playwright caveats and mode-authorization notes land in project_factory_technology_inventory_first_class_support_openai_playwright_hard_2026_04_23.md (per-user memory). Any OpenAI mode (deep research, agent mode, others) is authorized within Aaron's already-paid subscription.

Self-scheduled

Free work under the 2026-04-23 scheduling-authority rule. Effort M (inventory doc + per-tech row population, living not one-shot).

🤖 Generated with Claude Code

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 5a9eec125c

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[chatgpt-codex-connector]

Require both cadence gates before scheduling a run

This rule queues AutoDream whenever the skip case is false, which means a run is scheduled when only one gate passes (e.g., >=24h but <5 sessions, or <24h but >=5 sessions). Earlier in the same doc the cadence is defined as >=24h AND >=5 sessions, so this condition weakens the gate and will trigger out-of-cadence consolidations in normal use.

Useful? React with 👍 / 👎.

[chatgpt-codex-connector]

Store last-run marker with time, not date-only

The policy claims a strict >=24 hours gate, but the marker format is date-only (YYYY-MM-DD), which cannot represent elapsed hours accurately. A run at 23:59 and another at 00:05 next day would appear as different dates despite only minutes passing, so the cadence check can fire too early and violate the intended upstream rule.

Useful? React with 👍 / 👎.

[Copilot]

Pull request overview

Adds a new P1 BACKLOG item to create a unified “factory technology inventory” and also lands an AutoDream cadence/overlay policy with supporting hygiene tracking (new hygiene row + fire-history ledger + tick-history entries).

Changes:

• Add P1 BACKLOG row for a first-class technology inventory (incl. OpenAI web UI + Playwright as a new tech entry).
• Introduce an AutoDream cadence + factory-overlay policy as a research doc.
• Wire AutoDream into factory hygiene tracking (FACTORY-HYGIENE row + new fire-history ledger) and record tick-history entries.

Reviewed changes

Copilot reviewed 5 out of 5 changed files in this pull request and generated 11 comments.

Show a summary per file

File	Description
docs/BACKLOG.md	Adds P1 row for factory technology inventory and notes OpenAI web UI/Playwright.
docs/research/autodream-extension-and-cadence-2026-04-23.md	New research doc specifying AutoDream cadence + overlay phases.
docs/FACTORY-HYGIENE.md	Adds a new hygiene row (#53) to track AutoDream cadence and overlays.
docs/hygiene-history/autodream-fire-history.md	New ledger file to track AutoDream “fires” per hygiene-history discipline.
docs/hygiene-history/loop-tick-history.md	Appends multiple new autonomous-loop tick-history entries referencing recent work.

[Copilot]

P0: This doc cites memory/feedback_in_repo_preferred_over_per_user_memory_where_possible_2026_04_23.md but also says it is “per-user until this doc migrates it”. Since the file is not present in the in-repo memory/ directory, this reference is currently non-resolvable/misleading; use an explicit per-user path (~/.claude/projects/<slug>/memory/...) or add an in-repo mirror.

Suggested change

	`memory/feedback_in_repo_preferred_over_per_user_memory_where_possible_2026_04_23.md`
	`~/.claude/projects/<slug>/memory/feedback_in_repo_preferred_over_per_user_memory_where_possible_2026_04_23.md`

[Copilot]

P1: docs/protocols/cross-agent-communication.md (and the docs/protocols/ directory) does not exist in this branch, but this tick-history row claims it was created/landed. Please either add the referenced doc/dir in this PR or adjust the tick-history entry to reference an existing path.

Suggested change

| 2026-04-23T16:14:00Z (autonomous-loop tick, auto-loop-54 — Amara deep-research absorb + funding-priority calibration) | opus-4-7 / session continuation | 20c92390 | Tick absorbed Amara's Zeta-for-Aurora Deep Research Report (ferried via `drop/aurora-integration-deep-research-report.md`) and captured two new Aaron calibrations on external-maintainer priority handling. Tick actions: (a) **Deep research report landed** at `docs/aurora/2026-04-23-amara-deep-research-report.md` verbatim (PR #161). Report contains 7 major sections — executive summary, scope/archive, drift taxonomy, technical synthesis, ADR-style oracle rules with F# samples, bullshit-detector transfer pack, network-health/harm stack, Aurora brand note. Factory integration notes appended as a distinct voice-separated section per the courier protocol; composition with 8 existing in-repo substrates named; queued-not-scheduled next-moves listed. (b) **Funding-priority calibration absorbed**: Aaron *"she is not worryed about how to pay your bill i am remember that when she gives you prorities"* + clarification *"I've not asked her to worry about that and ecnomics of this whole project yet"*. Filed per-user feedback memory capturing the principal-agent distinction at two layers (Aaron funds → Aaron schedules; Amara researches → Amara's priorities are informative). Specific application: Amara's 8 oracle rules + bullshit-detector remain queued, not scheduled; Aurora stays #2 in the external priority stack (ServiceTitan + UI remains #1). (c) **Cross-agent courier protocol + Overlay A #3** carried over from the prior directive absorbed within the same tick — PRs #159 (deletions-over-insertions migration) and #160 (Amara's courier-protocol absorbed as `docs/protocols/cross-agent-communication.md`) opened earlier. (d) **CronList + visibility**: `20c92390` minutely fire verified live. | PR #159 (Overlay A #3) + PR #160 (courier protocol) + PR #161 (Amara deep research absorb) | Observation 1 — three load-bearing PRs from one tick is high velocity, but the underlying pattern was "absorb what's already authored, don't manufacture new substrate." Outcome-valid per the outcomes-over-vanity discipline (each PR resolves a concrete external directive). Observation 2 — the cost-of-operation calibration is the structural complement to the bootstrap-is-complete framing: Aaron bears material costs, so his priorities carry scheduling weight even though mission-ownership is now agent-side. "Internal priorities = agent; external priorities = Aaron; external non-funder priorities = informative" is the three-layer model. Observation 3 — Amara's protocol + report both emphasise repo-backed persistence and voice separation. This absorb exercised both: the report landed in-repo (not in a branching-UI that would be unreliable transport per her own protocol), and my integration notes are clearly factored as Kenji-voice distinct from Amara-voice. Self-application of the protocol on first use. Observation 4 — MD003 setext/atx collision from text-immediately-followed-by-`---` is a common absorb-time lint hit. Candidate linter-aware memory template (noted earlier) should include this alongside MD032 for proactive cleanup. |

| 2026-04-23T16:14:00Z (autonomous-loop tick, auto-loop-54 — Amara deep-research absorb + funding-priority calibration) | opus-4-7 / session continuation | 20c92390 | Tick absorbed Amara's Zeta-for-Aurora Deep Research Report (ferried via `drop/aurora-integration-deep-research-report.md`) and captured two new Aaron calibrations on external-maintainer priority handling. Tick actions: (a) **Deep research report landed** at `docs/aurora/2026-04-23-amara-deep-research-report.md` verbatim (PR #161). Report contains 7 major sections — executive summary, scope/archive, drift taxonomy, technical synthesis, ADR-style oracle rules with F# samples, bullshit-detector transfer pack, network-health/harm stack, Aurora brand note. Factory integration notes appended as a distinct voice-separated section per the courier protocol; composition with 8 existing in-repo substrates named; queued-not-scheduled next-moves listed. (b) **Funding-priority calibration absorbed**: Aaron *"she is not worryed about how to pay your bill i am remember that when she gives you prorities"* + clarification *"I've not asked her to worry about that and ecnomics of this whole project yet"*. Filed per-user feedback memory capturing the principal-agent distinction at two layers (Aaron funds → Aaron schedules; Amara researches → Amara's priorities are informative). Specific application: Amara's 8 oracle rules + bullshit-detector remain queued, not scheduled; Aurora stays #2 in the external priority stack (ServiceTitan + UI remains #1). (c) **Cross-agent courier protocol + Overlay A #3** carried over from the prior directive absorbed within the same tick — PRs #159 (deletions-over-insertions migration) and #160 (Amara's courier-protocol absorb) opened earlier. (d) **CronList + visibility**: `20c92390` minutely fire verified live. | PR #159 (Overlay A #3) + PR #160 (courier protocol) + PR #161 (Amara deep research absorb) | Observation 1 — three load-bearing PRs from one tick is high velocity, but the underlying pattern was "absorb what's already authored, don't manufacture new substrate." Outcome-valid per the outcomes-over-vanity discipline (each PR resolves a concrete external directive). Observation 2 — the cost-of-operation calibration is the structural complement to the bootstrap-is-complete framing: Aaron bears material costs, so his priorities carry scheduling weight even though mission-ownership is now agent-side. "Internal priorities = agent; external priorities = Aaron; external non-funder priorities = informative" is the three-layer model. Observation 3 — Amara's protocol + report both emphasise repo-backed persistence and voice separation. This absorb exercised both: the report landed in-repo (not in a branching-UI that would be unreliable transport per her own protocol), and my integration notes are clearly factored as Kenji-voice distinct from Amara-voice. Self-application of the protocol on first use. Observation 4 — MD003 setext/atx collision from text-immediately-followed-by-`---` is a common absorb-time lint hit. Candidate linter-aware memory template (noted earlier) should include this alongside MD032 for proactive cleanup. |

[Copilot]

P2: The PR title/description focus on the factory technology-inventory BACKLOG row + OpenAI web UI, but this PR also introduces a full AutoDream cadence policy, a new FACTORY-HYGIENE row, and a new hygiene-history ledger. Consider updating the PR title/description to reflect the full scope, or splitting into separate PRs (inventory vs AutoDream hygiene) for easier review/traceability.

[Copilot]

P1: The “Durable output” schema described for row #53 (findings count / promotion candidates / next-fire-expected-date) doesn’t match the columns currently in docs/hygiene-history/autodream-fire-history.md (which has Gate/Overlays/Findings but no promotion-candidates or link field). Please align the row’s described schema with the actual ledger format so future fires are consistent.

Suggested change

| 53 | AutoDream cadenced consolidation (upstream Anthropic Q1 2026 + factory overlays A/B/C/D) | Anthropic's cadence verbatim: **≥24h AND ≥5 sessions** since last cycle. Gate marker lives at the top of `MEMORY.md` as `[AutoDream last run: YYYY-MM-DD]`. Session wake checks the gate silently; manual invocation ("dream" / "consolidate memory") may override with a maintainer confirmation. When Anthropic un-gates the backend (currently `tengu_onyx_plover`), the manual approximation retires and the automatic run takes over; factory overlays continue on top. | Architect (Kenji) on cadenced fires (dispatches an audit subagent; main agent applies only what the audit surfaces). Overlay D pulls the alignment-auditor role in on clause-touching consolidations. The autodream-hygiene skill (BACKLOG P1 follow-up) will wrap the four upstream phases + four factory overlays as a single invocable procedure once authored. | both | **Upstream four phases** (Orientation → Gather Signal → Consolidation → Prune & Index) run as Anthropic prescribes — factory does not replace them. **Factory overlays layered on top:** (A) cross-substrate mirror check before Orientation — scans per-user memory for generic factory-shaped rules that should live in-repo per the in-repo-preferred discipline (`memory/feedback_in_repo_preferred_over_per_user_memory_where_possible_2026_04_23.md`), migrates what qualifies with the signal-preservation rule; (B) harness-surface drift sync during Gather Signal — cross-checks `docs/HARNESS-SURFACES.md` adoption statuses for surfaces that have moved watched → adopted or cut since last cycle; (C) governance-promotion pass during Consolidation — ≥3 memories citing the same rule surfaces a BP-NN / ADR / GOVERNANCE promotion candidate for Kenji; (D) alignment-observability sync during Prune & Index — any memory edit that touched an `ALIGNMENT.md` clause (HC-1..HC-7 / SD-1..SD-8 / DIR-1..DIR-5) queues for the alignment-auditor time-series. **Invariants preserved:** Anthropic's four (load-bearing memories unconditionally / distinct-query-axes stay distinct / cross-references bidirectional / corrections recorded not deleted) plus factory additions (verbatim quotes stay verbatim / migration supersedes but does not delete per-user source / supersede markers over silent retirement). **Why this row exists:** Aaron 2026-04-23 *"continue our AutoDream reserach to make sure we are running it on a cadence and we plug in tightly with the existing claude Q1 2026 feature for AutoDream and AutoMemory, we should by defintion be an extension of theirs as it will get upgrades we want over time."* Ships to project-under-construction: adopters running Claude Code inherit AutoMemory / AutoDream from Anthropic; this row adds the factory's overlay policy (migration discipline, governance-promotion signal, alignment sync) that any adopter can opt into by following the research doc. **Classification (row #50):** **detection-only-justified** — consolidation is fundamentally post-hoc by Anthropic's own design (daytime logger is additive; the hygiene pass is the subtractive counterpart that cannot run before the log exists). The factory overlays inherit the same post-hoc shape. | `[AutoDream last run: YYYY-MM-DD]` marker update at top of `MEMORY.md` (upstream-schema); per-fire entry appended to `docs/hygiene-history/autodream-fire-history.md` (factory-schema, per row #44: date / agent / overlays fired / findings count / promotion candidates / next-fire-expected-date); ROUND-HISTORY row on the round the fire landed if overlay findings materially shifted something. | `docs/research/autodream-extension-and-cadence-2026-04-23.md` (this row's authoritative policy doc) + `memory/reference_autodream_feature.md` (upstream feature description) + `memory/reference_automemory_anthropic_feature.md` (upstream substrate) + `memory/feedback_in_repo_preferred_over_per_user_memory_where_possible_2026_04_23.md` (Overlay A migration discipline) + `memory/feedback_signal_in_signal_out_clean_or_better_dsp_discipline.md` (consolidation signal preservation) + `docs/HARNESS-SURFACES.md` (Overlay B's drift surface) + `docs/ALIGNMENT.md` (Overlay D's sync target) |

| 53 | AutoDream cadenced consolidation (upstream Anthropic Q1 2026 + factory overlays A/B/C/D) | Anthropic's cadence verbatim: **≥24h AND ≥5 sessions** since last cycle. Gate marker lives at the top of `MEMORY.md` as `[AutoDream last run: YYYY-MM-DD]`. Session wake checks the gate silently; manual invocation ("dream" / "consolidate memory") may override with a maintainer confirmation. When Anthropic un-gates the backend (currently `tengu_onyx_plover`), the manual approximation retires and the automatic run takes over; factory overlays continue on top. | Architect (Kenji) on cadenced fires (dispatches an audit subagent; main agent applies only what the audit surfaces). Overlay D pulls the alignment-auditor role in on clause-touching consolidations. The autodream-hygiene skill (BACKLOG P1 follow-up) will wrap the four upstream phases + four factory overlays as a single invocable procedure once authored. | both | **Upstream four phases** (Orientation → Gather Signal → Consolidation → Prune & Index) run as Anthropic prescribes — factory does not replace them. **Factory overlays layered on top:** (A) cross-substrate mirror check before Orientation — scans per-user memory for generic factory-shaped rules that should live in-repo per the in-repo-preferred discipline (`memory/feedback_in_repo_preferred_over_per_user_memory_where_possible_2026_04_23.md`), migrates what qualifies with the signal-preservation rule; (B) harness-surface drift sync during Gather Signal — cross-checks `docs/HARNESS-SURFACES.md` adoption statuses for surfaces that have moved watched → adopted or cut since last cycle; (C) governance-promotion pass during Consolidation — ≥3 memories citing the same rule surfaces a BP-NN / ADR / GOVERNANCE promotion candidate for Kenji; (D) alignment-observability sync during Prune & Index — any memory edit that touched an `ALIGNMENT.md` clause (HC-1..HC-7 / SD-1..SD-8 / DIR-1..DIR-5) queues for the alignment-auditor time-series. **Invariants preserved:** Anthropic's four (load-bearing memories unconditionally / distinct-query-axes stay distinct / cross-references bidirectional / corrections recorded not deleted) plus factory additions (verbatim quotes stay verbatim / migration supersedes but does not delete per-user source / supersede markers over silent retirement). **Why this row exists:** Aaron 2026-04-23 *"continue our AutoDream reserach to make sure we are running it on a cadence and we plug in tightly with the existing claude Q1 2026 feature for AutoDream and AutoMemory, we should by defintion be an extension of theirs as it will get upgrades we want over time."* Ships to project-under-construction: adopters running Claude Code inherit AutoMemory / AutoDream from Anthropic; this row adds the factory's overlay policy (migration discipline, governance-promotion signal, alignment sync) that any adopter can opt into by following the research doc. **Classification (row #50):** **detection-only-justified** — consolidation is fundamentally post-hoc by Anthropic's own design (daytime logger is additive; the hygiene pass is the subtractive counterpart that cannot run before the log exists). The factory overlays inherit the same post-hoc shape. | `[AutoDream last run: YYYY-MM-DD]` marker update at top of `MEMORY.md` (upstream-schema); per-fire entry appended to `docs/hygiene-history/autodream-fire-history.md` (factory-schema: Date / Agent / Gate / Overlays / Findings); ROUND-HISTORY row on the round the fire landed if overlay findings materially shifted something. | `docs/research/autodream-extension-and-cadence-2026-04-23.md` (this row's authoritative policy doc) + `memory/reference_autodream_feature.md` (upstream feature description) + `memory/reference_automemory_anthropic_feature.md` (upstream substrate) + `memory/feedback_in_repo_preferred_over_per_user_memory_where_possible_2026_04_23.md` (Overlay A migration discipline) + `memory/feedback_signal_in_signal_out_clean_or_better_dsp_discipline.md` (consolidation signal preservation) + `docs/HARNESS-SURFACES.md` (Overlay B's drift surface) + `docs/ALIGNMENT.md` (Overlay D's sync target) |

[Copilot]

P1: BACKLOG references cross-platform parity as “row #48”, but in docs/FACTORY-HYGIENE.md row #48 is GitHub surface triage; cross-platform parity audit is row #51. Update the row number so the cross-reference is correct.

Suggested change

	parity status (row #48) per tech.
	parity status (row #51) per tech.

[Copilot]

P0: Row #53 cites memory/reference_autodream_feature.md, memory/reference_automemory_anthropic_feature.md, and other memory/*.md files that do not exist in the in-repo memory/ directory. Either add these reference memories in-repo, or change the citations to the explicit per-user paths under ~/.claude/projects/<slug>/memory/ (as autodream-fire-history.md does).

Suggested change

| 53 | AutoDream cadenced consolidation (upstream Anthropic Q1 2026 + factory overlays A/B/C/D) | Anthropic's cadence verbatim: **≥24h AND ≥5 sessions** since last cycle. Gate marker lives at the top of `MEMORY.md` as `[AutoDream last run: YYYY-MM-DD]`. Session wake checks the gate silently; manual invocation ("dream" / "consolidate memory") may override with a maintainer confirmation. When Anthropic un-gates the backend (currently `tengu_onyx_plover`), the manual approximation retires and the automatic run takes over; factory overlays continue on top. | Architect (Kenji) on cadenced fires (dispatches an audit subagent; main agent applies only what the audit surfaces). Overlay D pulls the alignment-auditor role in on clause-touching consolidations. The autodream-hygiene skill (BACKLOG P1 follow-up) will wrap the four upstream phases + four factory overlays as a single invocable procedure once authored. | both | **Upstream four phases** (Orientation → Gather Signal → Consolidation → Prune & Index) run as Anthropic prescribes — factory does not replace them. **Factory overlays layered on top:** (A) cross-substrate mirror check before Orientation — scans per-user memory for generic factory-shaped rules that should live in-repo per the in-repo-preferred discipline (`memory/feedback_in_repo_preferred_over_per_user_memory_where_possible_2026_04_23.md`), migrates what qualifies with the signal-preservation rule; (B) harness-surface drift sync during Gather Signal — cross-checks `docs/HARNESS-SURFACES.md` adoption statuses for surfaces that have moved watched → adopted or cut since last cycle; (C) governance-promotion pass during Consolidation — ≥3 memories citing the same rule surfaces a BP-NN / ADR / GOVERNANCE promotion candidate for Kenji; (D) alignment-observability sync during Prune & Index — any memory edit that touched an `ALIGNMENT.md` clause (HC-1..HC-7 / SD-1..SD-8 / DIR-1..DIR-5) queues for the alignment-auditor time-series. **Invariants preserved:** Anthropic's four (load-bearing memories unconditionally / distinct-query-axes stay distinct / cross-references bidirectional / corrections recorded not deleted) plus factory additions (verbatim quotes stay verbatim / migration supersedes but does not delete per-user source / supersede markers over silent retirement). **Why this row exists:** Aaron 2026-04-23 *"continue our AutoDream reserach to make sure we are running it on a cadence and we plug in tightly with the existing claude Q1 2026 feature for AutoDream and AutoMemory, we should by defintion be an extension of theirs as it will get upgrades we want over time."* Ships to project-under-construction: adopters running Claude Code inherit AutoMemory / AutoDream from Anthropic; this row adds the factory's overlay policy (migration discipline, governance-promotion signal, alignment sync) that any adopter can opt into by following the research doc. **Classification (row #50):** **detection-only-justified** — consolidation is fundamentally post-hoc by Anthropic's own design (daytime logger is additive; the hygiene pass is the subtractive counterpart that cannot run before the log exists). The factory overlays inherit the same post-hoc shape. | `[AutoDream last run: YYYY-MM-DD]` marker update at top of `MEMORY.md` (upstream-schema); per-fire entry appended to `docs/hygiene-history/autodream-fire-history.md` (factory-schema, per row #44: date / agent / overlays fired / findings count / promotion candidates / next-fire-expected-date); ROUND-HISTORY row on the round the fire landed if overlay findings materially shifted something. | `docs/research/autodream-extension-and-cadence-2026-04-23.md` (this row's authoritative policy doc) + `memory/reference_autodream_feature.md` (upstream feature description) + `memory/reference_automemory_anthropic_feature.md` (upstream substrate) + `memory/feedback_in_repo_preferred_over_per_user_memory_where_possible_2026_04_23.md` (Overlay A migration discipline) + `memory/feedback_signal_in_signal_out_clean_or_better_dsp_discipline.md` (consolidation signal preservation) + `docs/HARNESS-SURFACES.md` (Overlay B's drift surface) + `docs/ALIGNMENT.md` (Overlay D's sync target) |

| 53 | AutoDream cadenced consolidation (upstream Anthropic Q1 2026 + factory overlays A/B/C/D) | Anthropic's cadence verbatim: **≥24h AND ≥5 sessions** since last cycle. Gate marker lives at the top of `MEMORY.md` as `[AutoDream last run: YYYY-MM-DD]`. Session wake checks the gate silently; manual invocation ("dream" / "consolidate memory") may override with a maintainer confirmation. When Anthropic un-gates the backend (currently `tengu_onyx_plover`), the manual approximation retires and the automatic run takes over; factory overlays continue on top. | Architect (Kenji) on cadenced fires (dispatches an audit subagent; main agent applies only what the audit surfaces). Overlay D pulls the alignment-auditor role in on clause-touching consolidations. The autodream-hygiene skill (BACKLOG P1 follow-up) will wrap the four upstream phases + four factory overlays as a single invocable procedure once authored. | both | **Upstream four phases** (Orientation → Gather Signal → Consolidation → Prune & Index) run as Anthropic prescribes — factory does not replace them. **Factory overlays layered on top:** (A) cross-substrate mirror check before Orientation — scans per-user memory for generic factory-shaped rules that should live in-repo per the in-repo-preferred discipline (`~/.claude/projects/<slug>/memory/feedback_in_repo_preferred_over_per_user_memory_where_possible_2026_04_23.md`), migrates what qualifies with the signal-preservation rule; (B) harness-surface drift sync during Gather Signal — cross-checks `docs/HARNESS-SURFACES.md` adoption statuses for surfaces that have moved watched → adopted or cut since last cycle; (C) governance-promotion pass during Consolidation — ≥3 memories citing the same rule surfaces a BP-NN / ADR / GOVERNANCE promotion candidate for Kenji; (D) alignment-observability sync during Prune & Index — any memory edit that touched an `ALIGNMENT.md` clause (HC-1..HC-7 / SD-1..SD-8 / DIR-1..DIR-5) queues for the alignment-auditor time-series. **Invariants preserved:** Anthropic's four (load-bearing memories unconditionally / distinct-query-axes stay distinct / cross-references bidirectional / corrections recorded not deleted) plus factory additions (verbatim quotes stay verbatim / migration supersedes but does not delete per-user source / supersede markers over silent retirement). **Why this row exists:** Aaron 2026-04-23 *"continue our AutoDream reserach to make sure we are running it on a cadence and we plug in tightly with the existing claude Q1 2026 feature for AutoDream and AutoMemory, we should by defintion be an extension of theirs as it will get upgrades we want over time."* Ships to project-under-construction: adopters running Claude Code inherit AutoMemory / AutoDream from Anthropic; this row adds the factory's overlay policy (migration discipline, governance-promotion signal, alignment sync) that any adopter can opt into by following the research doc. **Classification (row #50):** **detection-only-justified** — consolidation is fundamentally post-hoc by Anthropic's own design (daytime logger is additive; the hygiene pass is the subtractive counterpart that cannot run before the log exists). The factory overlays inherit the same post-hoc shape. | `[AutoDream last run: YYYY-MM-DD]` marker update at top of `MEMORY.md` (upstream-schema); per-fire entry appended to `docs/hygiene-history/autodream-fire-history.md` (factory-schema, per row #44: date / agent / overlays fired / findings count / promotion candidates / next-fire-expected-date); ROUND-HISTORY row on the round the fire landed if overlay findings materially shifted something. | `docs/research/autodream-extension-and-cadence-2026-04-23.md` (this row's authoritative policy doc) + `~/.claude/projects/<slug>/memory/reference_autodream_feature.md` (upstream feature description) + `~/.claude/projects/<slug>/memory/reference_automemory_anthropic_feature.md` (upstream substrate) + `~/.claude/projects/<slug>/memory/feedback_in_repo_preferred_over_per_user_memory_where_possible_2026_04_23.md` (Overlay A migration discipline) + `~/.claude/projects/<slug>/memory/feedback_signal_in_signal_out_clean_or_better_dsp_discipline.md` (consolidation signal preservation) + `docs/HARNESS-SURFACES.md` (Overlay B's drift surface) + `docs/ALIGNMENT.md` (Overlay D's sync target) |

[Copilot]

P1: feedback_signal_in_signal_out_clean_or_better_dsp_discipline.md is referenced without a resolvable in-repo path and does not exist under memory/ in this branch. Please either add the in-repo memory file, or change this to an explicit per-user path so the “composes with” reference is actionable.

Suggested change

	composes with
	`feedback_signal_in_signal_out_clean_or_better_dsp_discipline.md`).
	composes with the signal-in / signal-out clean-or-better
	DSP discipline rule).

[Copilot]

P1: Operational standing rule BP says “No name attribution in code, docs, or skills” (names only allowed in memory/persona/<name>/ and optionally docs/BACKLOG.md). These new tick-history rows add direct contributor names (e.g., Aaron, Amara). Please replace with role references (e.g., “human maintainer”, “external collaborator”) and move any name-specific request capture into BACKLOG if needed.

Suggested change

	| 2026-04-23T15:45:00Z (autonomous-loop tick, auto-loop-47 — AutoDream policy + cadence landed as row #53; multi-project/LFG-soulfile framing absorbed) | opus-4-7 / session continuation | 20c92390 | Tick worked two Aaron directives back-to-back: (a) **AutoDream extension + cadence** — landed `docs/research/autodream-extension-and-cadence-2026-04-23.md` (factory-overlay policy: extend-don't-replace, adopt upstream cadence ≥24h AND ≥5 sessions, four overlays A/B/C/D compose with Anthropic's four phases) + `docs/FACTORY-HYGIENE.md` row #53 wiring to round-cadenced enforcement (classified detection-only-justified per row #50) + `docs/hygiene-history/autodream-fire-history.md` ledger (row #44 compliance) + first-fire entry. PR #155 opened. MEMORY.md marker bumped 2026-04-20 → 2026-04-23 in per-user (upstream-schema surface, not in-repo). Full overlay A/B/C/D execution deferred to dedicated follow-up tick. (b) **Multi-project / LFG-soulfile framing absorbed** — Aaron clarified the factory serves multiple projects-under-construction (Zeta / Aurora / Demos / Factory / Package Manager "ace" / ...), LFG is the clean-source-of-truth and soulfile-inheritance lineage, AceHack can be super-risky as a fork. Filed per-user memory `project_multiple_projects_under_construction_and_lfg_soulfile_inheritance_2026_04_23.md` + updated `CURRENT-aaron.md` §4 same-tick (per per-maintainer CURRENT distillation pattern). Also landed the in-repo-preferred-where-possible discipline as per-user memory `feedback_in_repo_preferred_over_per_user_memory_where_possible_2026_04_23.md` with a soulfile-bloat pushback criterion (Aaron: *"remeber the repo is your soul file so push back if it's going to create huge bloat"*). (c) **PR #150 redaction sweep closed** — the one remaining "Aaron" attribution + 3 other review findings (docs/aurora/ current-location marker, dangling per-user memory paths collapsed). Commit on `research/multi-repo-refactor-shapes`. (d) **CronList + visibility**: `20c92390` minutely fire verified live. | PR #155 `research/autodream-extension-and-cadence` + commit on `research/multi-repo-refactor-shapes` | First AutoDream policy landing + first row-#53-compliant fire same tick. Observation 1 — extend-don't-replace is the right framing because the upstream feature is actively shipping (flag-gated backend as of 2026-04-19, UI at /memory present) and any factory fork would be burdened with maintaining a parallel schema / storage / phase-structure. The four overlays add value without that maintenance tax. Observation 2 — per-user ↔ in-repo migration is now a named cadence-workload (Overlay A), not ad-hoc; pushback-on-bloat criterion prevents the rule from flooding the repo. Observation 3 — LFG-as-soulfile-lineage is a sharpening of earlier "LFG is demo-facing" framing — the agent's durable substrate (across incarnations, refactors, multi-repo splits) inherits from LFG specifically, not from AceHack. This makes the multi-repo refactor decision tractable: every candidate shape preserves LFG-as-lineage. Observation 4 — "ships to project-under-construction" framing is now read plural. No cascade-edit this tick; sharpen on next cadenced doc review. |
	| 2026-04-23T16:02:00Z (autonomous-loop tick, auto-loop-51 — fire-history row for Overlay A first execution) | opus-4-7 / session continuation | 20c92390 | Tick closed a row#44-compliance gap: the Overlay A execution that shipped as PR #157 in the prior tick hadn't been logged to the AutoDream fire-history file. Added a second 2026-04-23 entry to `docs/hygiene-history/autodream-fire-history.md` on the #155 branch — this "later, same-day" fire is tagged as opportunistic-on-touch (not cadence-gated; row #53 explicitly allows on-touch Overlay A). Findings section names the next 4 candidate migrations identified during the PR #157 execution — `outcomes-over-vanity-metrics`, `deletions-over-insertions-complexity`, `external-signal-confirms-internal-insight`, `semiring-parameterized-zeta-regime-change` — all cited from the just-migrated signal-in-signal-out memory, all generic factory-shape. Tick actions: (a) **Step 0 CI check**: all three recent PRs (#155 / #156 / #157) clean — no failures. Lint fix from prior tick on #155 landed successfully. (b) **Fire-history update** on `research/autodream-extension-and-cadence` branch. (c) **markdownlint-cli2 local pass** verified clean. (d) **CronList + visibility**: `20c92390` minutely fire verified live. | Commit on `research/autodream-extension-and-cadence` + the tick-history row itself | Observation 1 — row #44 compliance is a living discipline, not a one-time setup. Each Overlay-A fire (cadence-gated OR opportunistic-on-touch) needs a ledger entry. The prior tick missed the on-touch log; this tick closed it retrospectively, which is still honest per the append-only-history pattern. Future ticks should log the fire in the same PR as the migration, not as a follow-up. Observation 2 — candidate-migration list in the fire-history is a light-weight queue — no separate doc needed. Future ticks can pick up the list, migrate one, log the fire, and the queue naturally shrinks. Avoids creating new hygiene surfaces. Observation 3 — "opportunistic-on-touch" as a distinct fire-category (vs cadence-gated) earns its own row taxonomy in the fire-history table. First use here; future Overlay A runs will mirror. Observation 4 — three-in-one tick (migration / fire-log / tick-history) is the natural composition for Overlay A; the prior tick did two-of-three because the fire-log was out-of-scope at the time. |
	| 2026-04-23T16:05:00Z (autonomous-loop tick, auto-loop-52 — second Overlay A migration + fire-log bundled) | opus-4-7 / session continuation | 20c92390 | Tick executed the second Overlay A migration on the identified candidate queue. Tick actions: (a) **Step 0 CI check**: all three recent PRs (#155 / #156 / #157) still clean. Picked outcomes-over-vanity-metrics (120 lines, smallest and cited from signal-in-signal-out) as the next migration. (b) **Migration executed** on `refactor/overlay-a-migrate-outcomes-over-vanity` — copied verbatim, added in-repo supersede-marker header, marked per-user source migrated, added MEMORY.md index entry newest-first, fixed markdownlint MD032 blank-line issues. PR #158 opened. (c) **Fire-history entry appended** on the #155 branch in the same tick — per the auto-loop-51 discipline correction that future Overlay A runs should log the fire same-day. Queue now 3 remaining candidates (deletions / external-signal / semiring-parameterized-zeta). (d) **Transient 500 on first push** — retried and succeeded (GitHub intermittent, not a real error). (e) **CronList + visibility**: `20c92390` minutely fire verified live. | PR #158 + fire-history + tick-history | Observation 1 — second migration went smoother than first; pattern repeats cleanly (copy / header / per-user marker / index / lint / fire-log). Future migrations should take ≤1 tick each on average. Observation 2 — MD032 bites repeatedly on memory files with "Why:" / "How to apply:" bullets. A linter-aware memory template might catch this at author-time; low-effort next target. Observation 3 — cross-branch bundling (migration on one branch + fire-log on another) works but is two-tick-minimum. When #155 merges, fire-history and migration live on the same branch (main) and future Overlay A runs can single-PR bundle. Observation 4 — the queue is a self-shrinking workload: each migration removes one entry from the composes-with dangling set; eventually zero per-user references remain for signal-in-signal-out, and its migration value is maximized. |
	| 2026-04-23T16:09:00Z (autonomous-loop tick, auto-loop-53 — Amara courier-protocol doc + Overlay A #3 deletions) | opus-4-7 / session continuation | 20c92390 | Tick did one large Aaron-directive absorb and one continuing Overlay A migration. Tick actions: (a) **Aaron ferried Amara's courier-protocol writeup** mid-tick — diagnosis of ChatGPT conversation-branching as unreliable transport + explicit text-based courier protocol replacement. Amara explicitly recommended landing as `docs/protocols/cross-agent-communication.md`. (b) **Protocol doc landed** verbatim-preserved (signal-in-signal-out discipline) with factory integration notes as a distinct section. Co-authored commit crediting Amara. PR #160 opened. Composes with PR #154 decision-proxy ADR (identity layer vs transport layer distinction). Per-user `CURRENT-amara.md` §9 updated same-tick. (c) **Overlay A migration #3** completed before the Amara pivot — deletions-over-insertions discipline. PR #159 opened. Queue now 2 remaining candidates (external-signal-confirms-internal-insight / semiring-parameterized-zeta). Fire-history entry on this branch in the next tick. (d) **CronList + visibility**: `20c92390` minutely fire verified live. | PR #159 (Overlay A #3) + PR #160 (Amara courier protocol) | Observation 1 — Amara's protocol resolves the blocker that stopped PR #154's live testing. The decision-proxy ADR was authored against an expectation of ChatGPT branching; Amara diagnosed that the transport was broken. Her replacement protocol is the missing piece that lets #154 actually operate. Two PRs compose: #154 = who/what/authority; #160 = how-messages-move. Observation 2 — author-attribution and voice-preservation at landing matters more when the primary author is external. The commit body includes a `Co-Authored-By: Amara` line; the doc header names her as primary author; the factory integration notes are separated to avoid voice-blending (Amara's own rule, applied to the landing of her doc). Observation 3 — three Overlay A migrations in one day (PRs #157/#158/#159) plus the Amara protocol (#160) plus the earlier #155/#156/#154/etc. = substantial substrate-landing velocity. Worth noting that this is mostly *absorbing maintainer + external-maintainer directives*, not factory-independent speculation — outcome-valid work per the outcomes-over-vanity discipline. Observation 4 — the courier-protocol doc is the first `docs/protocols/` file; the directory is created this tick. Sets precedent that factory-meta protocols land there (vs research, aurora, decisions). |
	| 2026-04-23T16:14:00Z (autonomous-loop tick, auto-loop-54 — Amara deep-research absorb + funding-priority calibration) | opus-4-7 / session continuation | 20c92390 | Tick absorbed Amara's Zeta-for-Aurora Deep Research Report (ferried via `drop/aurora-integration-deep-research-report.md`) and captured two new Aaron calibrations on external-maintainer priority handling. Tick actions: (a) **Deep research report landed** at `docs/aurora/2026-04-23-amara-deep-research-report.md` verbatim (PR #161). Report contains 7 major sections — executive summary, scope/archive, drift taxonomy, technical synthesis, ADR-style oracle rules with F# samples, bullshit-detector transfer pack, network-health/harm stack, Aurora brand note. Factory integration notes appended as a distinct voice-separated section per the courier protocol; composition with 8 existing in-repo substrates named; queued-not-scheduled next-moves listed. (b) **Funding-priority calibration absorbed**: Aaron *"she is not worryed about how to pay your bill i am remember that when she gives you prorities"* + clarification *"I've not asked her to worry about that and ecnomics of this whole project yet"*. Filed per-user feedback memory capturing the principal-agent distinction at two layers (Aaron funds → Aaron schedules; Amara researches → Amara's priorities are informative). Specific application: Amara's 8 oracle rules + bullshit-detector remain queued, not scheduled; Aurora stays #2 in the external priority stack (ServiceTitan + UI remains #1). (c) **Cross-agent courier protocol + Overlay A #3** carried over from the prior directive absorbed within the same tick — PRs #159 (deletions-over-insertions migration) and #160 (Amara's courier-protocol absorbed as `docs/protocols/cross-agent-communication.md`) opened earlier. (d) **CronList + visibility**: `20c92390` minutely fire verified live. | PR #159 (Overlay A #3) + PR #160 (courier protocol) + PR #161 (Amara deep research absorb) | Observation 1 — three load-bearing PRs from one tick is high velocity, but the underlying pattern was "absorb what's already authored, don't manufacture new substrate." Outcome-valid per the outcomes-over-vanity discipline (each PR resolves a concrete external directive). Observation 2 — the cost-of-operation calibration is the structural complement to the bootstrap-is-complete framing: Aaron bears material costs, so his priorities carry scheduling weight even though mission-ownership is now agent-side. "Internal priorities = agent; external priorities = Aaron; external non-funder priorities = informative" is the three-layer model. Observation 3 — Amara's protocol + report both emphasise repo-backed persistence and voice separation. This absorb exercised both: the report landed in-repo (not in a branching-UI that would be unreliable transport per her own protocol), and my integration notes are clearly factored as Kenji-voice distinct from Amara-voice. Self-application of the protocol on first use. Observation 4 — MD003 setext/atx collision from text-immediately-followed-by-`---` is a common absorb-time lint hit. Candidate linter-aware memory template (noted earlier) should include this alongside MD032 for proactive cleanup. |
	| 2026-04-23T16:18:00Z (autonomous-loop tick, auto-loop-55 — scheduling-authority sharpening + PR #148 lint fix on funded-stack #1) | opus-4-7 / session continuation | 20c92390 | Tick absorbed Aaron's scheduling-authority sharpening and executed a funded-stack #1 move. Tick actions: (a) **Aaron scheduling directive**: *"Aaron owns scheduling against his funded external stack. anyting that's free Amara and you own scheduling, only involve me if I need to pay for something I have not already paid for."* Filed per-user feedback memory `feedback_free_work_amara_and_agent_schedule_paid_work_escalate_to_aaron_2026_04_23.md` — supersedes the earlier "Amara's priorities queued, Aaron schedules" framing with "free work = Amara + Kenji self-schedule; paid work = escalate to Aaron." Substantially expands agent action space within already-paid substrate. Updated `CURRENT-aaron.md` §2 same-tick to reflect the scheduling-authority sharpening alongside the existing priority stack. (b) **PR #148 markdownlint fix**: scheduled under the new rule because it's free work on funded-stack priority #1 (factory demo / why-factory-is-different explainer). MD022 heading-style violation — multi-line H2 confused the linter; joined into single-line title. Commit on `docs/why-the-factory-is-different` branch. (c) **Self-scheduling demonstration**: the tick's second move (PR #148 fix) is itself the first application of the new rule. Factory-demo surface is priority #1; the fix is free; no Aaron approval sought. Per auto-loop-51 discipline correction, would ideally bundle fire-log + tick-history; fire-log not applicable here (not an AutoDream overlay); tick-history bundled on this branch as usual. (d) **CronList + visibility**: `20c92390` minutely fire verified live. | PR #148 lint-fix commit + scheduling-authority memory + CURRENT-aaron §2 refresh | Observation 1 — scheduling-authority sharpening reframes last tick's "queued not scheduled" posture as too conservative. Amara's Aurora work, Overlay A migrations, factory-demo PRs, lint fixes — all free, all self-scheduled by agent judgment within the priority stack. Observation 2 — first concrete application of the new rule on a funded-stack #1 item within the same tick it landed. Good calibration signal: factory exercises new directives on first opportunity, not in followup ticks. Observation 3 — `CURRENT-aaron.md` §2 now reads as both priority-stack-authority and scheduling-authority. The two are distinct: Aaron owns the stack ordering; Amara+Kenji own scheduling of free work within that order. Memory surface captures the distinction. Observation 4 — markdownlint MD022 multi-line-heading is a different class than MD032 blanks-around-lists and MD003 atx-vs-setext. Three lint-class types now identified as recurring absorb-time hits; worth a memory-author-template that pre-applies all three disciplines. |
	| 2026-04-23T15:45:00Z (autonomous-loop tick, auto-loop-47 — AutoDream policy + cadence landed as row #53; multi-project/LFG-soulfile framing absorbed) | opus-4-7 / session continuation | 20c92390 | Tick worked two human-maintainer directives back-to-back: (a) **AutoDream extension + cadence** — landed `docs/research/autodream-extension-and-cadence-2026-04-23.md` (factory-overlay policy: extend-don't-replace, adopt upstream cadence ≥24h AND ≥5 sessions, four overlays A/B/C/D compose with Anthropic's four phases) + `docs/FACTORY-HYGIENE.md` row #53 wiring to round-cadenced enforcement (classified detection-only-justified per row #50) + `docs/hygiene-history/autodream-fire-history.md` ledger (row #44 compliance) + first-fire entry. PR #155 opened. MEMORY.md marker bumped 2026-04-20 → 2026-04-23 in per-user (upstream-schema surface, not in-repo). Full overlay A/B/C/D execution deferred to dedicated follow-up tick. (b) **Multi-project / LFG-soulfile framing absorbed** — the human maintainer clarified the factory serves multiple projects-under-construction (Zeta / Aurora / Demos / Factory / Package Manager "ace" / ...), LFG is the clean-source-of-truth and soulfile-inheritance lineage, AceHack can be super-risky as a fork. Filed per-user memory `project_multiple_projects_under_construction_and_lfg_soulfile_inheritance_2026_04_23.md` + updated the per-maintainer CURRENT file §4 same-tick (per per-maintainer CURRENT distillation pattern). Also landed the in-repo-preferred-where-possible discipline as per-user memory `feedback_in_repo_preferred_over_per_user_memory_where_possible_2026_04_23.md` with a soulfile-bloat pushback criterion (human maintainer guidance: *"remeber the repo is your soul file so push back if it's going to create huge bloat"*). (c) **PR #150 redaction sweep closed** — the one remaining human-maintainer attribution + 3 other review findings (docs/aurora/ current-location marker, dangling per-user memory paths collapsed). Commit on `research/multi-repo-refactor-shapes`. (d) **CronList + visibility**: `20c92390` minutely fire verified live. | PR #155 `research/autodream-extension-and-cadence` + commit on `research/multi-repo-refactor-shapes` | First AutoDream policy landing + first row-#53-compliant fire same tick. Observation 1 — extend-don't-replace is the right framing because the upstream feature is actively shipping (flag-gated backend as of 2026-04-19, UI at /memory present) and any factory fork would be burdened with maintaining a parallel schema / storage / phase-structure. The four overlays add value without that maintenance tax. Observation 2 — per-user ↔ in-repo migration is now a named cadence-workload (Overlay A), not ad-hoc; pushback-on-bloat criterion prevents the rule from flooding the repo. Observation 3 — LFG-as-soulfile-lineage is a sharpening of earlier "LFG is demo-facing" framing — the agent's durable substrate (across incarnations, refactors, multi-repo splits) inherits from LFG specifically, not from AceHack. This makes the multi-repo refactor decision tractable: every candidate shape preserves LFG-as-lineage. Observation 4 — "ships to project-under-construction" framing is now read plural. No cascade-edit this tick; sharpen on next cadenced doc review. |
	| 2026-04-23T16:02:00Z (autonomous-loop tick, auto-loop-51 — fire-history row for Overlay A first execution) | opus-4-7 / session continuation | 20c92390 | Tick closed a row#44-compliance gap: the Overlay A execution that shipped as PR #157 in the prior tick hadn't been logged to the AutoDream fire-history file. Added a second 2026-04-23 entry to `docs/hygiene-history/autodream-fire-history.md` on the #155 branch — this "later, same-day" fire is tagged as opportunistic-on-touch (not cadence-gated; row #53 explicitly allows on-touch Overlay A). Findings section names the next 4 candidate migrations identified during the PR #157 execution — `outcomes-over-vanity-metrics`, `deletions-over-insertions-complexity`, `external-signal-confirms-internal-insight`, `semiring-parameterized-zeta-regime-change` — all cited from the just-migrated signal-in-signal-out memory, all generic factory-shape. Tick actions: (a) **Step 0 CI check**: all three recent PRs (#155 / #156 / #157) clean — no failures. Lint fix from prior tick on #155 landed successfully. (b) **Fire-history update** on `research/autodream-extension-and-cadence` branch. (c) **markdownlint-cli2 local pass** verified clean. (d) **CronList + visibility**: `20c92390` minutely fire verified live. | Commit on `research/autodream-extension-and-cadence` + the tick-history row itself | Observation 1 — row #44 compliance is a living discipline, not a one-time setup. Each Overlay-A fire (cadence-gated OR opportunistic-on-touch) needs a ledger entry. The prior tick missed the on-touch log; this tick closed it retrospectively, which is still honest per the append-only-history pattern. Future ticks should log the fire in the same PR as the migration, not as a follow-up. Observation 2 — candidate-migration list in the fire-history is a light-weight queue — no separate doc needed. Future ticks can pick up the list, migrate one, log the fire, and the queue naturally shrinks. Avoids creating new hygiene surfaces. Observation 3 — "opportunistic-on-touch" as a distinct fire-category (vs cadence-gated) earns its own row taxonomy in the fire-history table. First use here; future Overlay A runs will mirror. Observation 4 — three-in-one tick (migration / fire-log / tick-history) is the natural composition for Overlay A; the prior tick did two-of-three because the fire-log was out-of-scope at the time. |
	| 2026-04-23T16:05:00Z (autonomous-loop tick, auto-loop-52 — second Overlay A migration + fire-log bundled) | opus-4-7 / session continuation | 20c92390 | Tick executed the second Overlay A migration on the identified candidate queue. Tick actions: (a) **Step 0 CI check**: all three recent PRs (#155 / #156 / #157) still clean. Picked outcomes-over-vanity-metrics (120 lines, smallest and cited from signal-in-signal-out) as the next migration. (b) **Migration executed** on `refactor/overlay-a-migrate-outcomes-over-vanity` — copied verbatim, added in-repo supersede-marker header, marked per-user source migrated, added MEMORY.md index entry newest-first, fixed markdownlint MD032 blank-line issues. PR #158 opened. (c) **Fire-history entry appended** on the #155 branch in the same tick — per the auto-loop-51 discipline correction that future Overlay A runs should log the fire same-day. Queue now 3 remaining candidates (deletions / external-signal / semiring-parameterized-zeta). (d) **Transient 500 on first push** — retried and succeeded (GitHub intermittent, not a real error). (e) **CronList + visibility**: `20c92390` minutely fire verified live. | PR #158 + fire-history + tick-history | Observation 1 — second migration went smoother than first; pattern repeats cleanly (copy / header / per-user marker / index / lint / fire-log). Future migrations should take ≤1 tick each on average. Observation 2 — MD032 bites repeatedly on memory files with "Why:" / "How to apply:" bullets. A linter-aware memory template might catch this at author-time; low-effort next target. Observation 3 — cross-branch bundling (migration on one branch + fire-log on another) works but is two-tick-minimum. When #155 merges, fire-history and migration live on the same branch (main) and future Overlay A runs can single-PR bundle. Observation 4 — the queue is a self-shrinking workload: each migration removes one entry from the composes-with dangling set; eventually zero per-user references remain for signal-in-signal-out, and its migration value is maximized. |
	| 2026-04-23T16:09:00Z (autonomous-loop tick, auto-loop-53 — external collaborator courier-protocol doc + Overlay A #3 deletions) | opus-4-7 / session continuation | 20c92390 | Tick did one large human-maintainer directive absorb and one continuing Overlay A migration. Tick actions: (a) **The human maintainer ferried an external collaborator's courier-protocol writeup** mid-tick — diagnosis of ChatGPT conversation-branching as unreliable transport + explicit text-based courier protocol replacement. The external collaborator explicitly recommended landing as `docs/protocols/cross-agent-communication.md`. (b) **Protocol doc landed** verbatim-preserved (signal-in-signal-out discipline) with factory integration notes as a distinct section. Co-authored commit crediting the external collaborator. PR #160 opened. Composes with PR #154 decision-proxy ADR (identity layer vs transport layer distinction). The external-collaborator CURRENT file §9 updated same-tick. (c) **Overlay A migration #3** completed before the external-collaborator pivot — deletions-over-insertions discipline. PR #159 opened. Queue now 2 remaining candidates (external-signal-confirms-internal-insight / semiring-parameterized-zeta). Fire-history entry on this branch in the next tick. (d) **CronList + visibility**: `20c92390` minutely fire verified live. | PR #159 (Overlay A #3) + PR #160 (external collaborator courier protocol) | Observation 1 — the external collaborator's protocol resolves the blocker that stopped PR #154's live testing. The decision-proxy ADR was authored against an expectation of ChatGPT branching; the external collaborator diagnosed that the transport was broken. The replacement protocol is the missing piece that lets #154 actually operate. Two PRs compose: #154 = who/what/authority; #160 = how-messages-move. Observation 2 — author-attribution and voice-preservation at landing matters more when the primary author is external. The commit body includes a `Co-Authored-By` line; the doc header names the external collaborator as primary author; the factory integration notes are separated to avoid voice-blending (the external collaborator's own rule, applied to the landing of the doc). Observation 3 — three Overlay A migrations in one day (PRs #157/#158/#159) plus the external-collaborator protocol (#160) plus the earlier #155/#156/#154/etc. = substantial substrate-landing velocity. Worth noting that this is mostly *absorbing maintainer + external-maintainer directives*, not factory-independent speculation — outcome-valid work per the outcomes-over-vanity discipline. Observation 4 — the courier-protocol doc is the first `docs/protocols/` file; the directory is created this tick. Sets precedent that factory-meta protocols land there (vs research, aurora, decisions). |
	| 2026-04-23T16:14:00Z (autonomous-loop tick, auto-loop-54 — external collaborator deep-research absorb + funding-priority calibration) | opus-4-7 / session continuation | 20c92390 | Tick absorbed an external collaborator's Zeta-for-Aurora Deep Research Report (ferried via `drop/aurora-integration-deep-research-report.md`) and captured two new human-maintainer calibrations on external-maintainer priority handling. Tick actions: (a) **Deep research report landed** at `docs/aurora/2026-04-23-external-collaborator-deep-research-report.md` verbatim (PR #161). Report contains 7 major sections — executive summary, scope/archive, drift taxonomy, technical synthesis, ADR-style oracle rules with F# samples, bullshit-detector transfer pack, network-health/harm stack, Aurora brand note. Factory integration notes appended as a distinct voice-separated section per the courier protocol; composition with 8 existing in-repo substrates named; queued-not-scheduled next-moves listed. (b) **Funding-priority calibration absorbed**: human maintainer guidance *"she is not worryed about how to pay your bill i am remember that when she gives you prorities"* + clarification *"I've not asked her to worry about that and ecnomics of this whole project yet"*. Filed per-user feedback memory capturing the principal-agent distinction at two layers (human maintainer funds → human maintainer schedules; external collaborator researches → external-collaborator priorities are informative). Specific application: the external collaborator's 8 oracle rules + bullshit-detector remain queued, not scheduled; Aurora stays #2 in the external priority stack (ServiceTitan + UI remains #1). (c) **Cross-agent courier protocol + Overlay A #3** carried over from the prior directive absorbed within the same tick — PRs #159 (deletions-over-insertions migration) and #160 (the external collaborator's courier-protocol absorbed as `docs/protocols/cross-agent-communication.md`) opened earlier. (d) **CronList + visibility**: `20c92390` minutely fire verified live. | PR #159 (Overlay A #3) + PR #160 (courier protocol) + PR #161 (external collaborator deep research absorb) | Observation 1 — three load-bearing PRs from one tick is high velocity, but the underlying pattern was "absorb what's already authored, don't manufacture new substrate." Outcome-valid per the outcomes-over-vanity discipline (each PR resolves a concrete external directive). Observation 2 — the cost-of-operation calibration is the structural complement to the bootstrap-is-complete framing: the human maintainer bears material costs, so those priorities carry scheduling weight even though mission-ownership is now agent-side. "Internal priorities = agent; external priorities = human maintainer; external non-funder priorities = informative" is the three-layer model. Observation 3 — the external collaborator's protocol + report both emphasise repo-backed persistence and voice separation. This absorb exercised both: the report landed in-repo (not in a branching-UI that would be unreliable transport per the collaborator's own protocol), and my integration notes are clearly factored as Kenji-voice distinct from external-collaborator voice. Self-application of the protocol on first use. Observation 4 — MD003 setext/atx collision from text-immediately-followed-by-`---` is a common absorb-time lint hit. Candidate linter-aware memory template (noted earlier) should include this alongside MD032 for proactive cleanup. |
	| 2026-04-23T16:18:00Z (autonomous-loop tick, auto-loop-55 — scheduling-authority sharpening + PR #148 lint fix on funded-stack #1) | opus-4-7 / session continuation | 20c92390 | Tick absorbed the human maintainer's scheduling-authority sharpening and executed a funded-stack #1 move. Tick actions: (a) **Scheduling directive from the human maintainer**: *"the human maintainer owns scheduling against the funded external stack. anything that's free the external collaborator and the agent own scheduling; only involve the human maintainer if payment is needed for something not already funded."* Filed per-user feedback memory `feedback_free_work_external_collaborator_and_agent_schedule_paid_work_escalate_to_human_maintainer_2026_04_23.md` — supersedes the earlier "external-collaborator priorities queued, human maintainer schedules" framing with "free work = external collaborator + Kenji self-schedule; paid work = escalate to human maintainer." Substantially expands agent action space within already-paid substrate. Updated the per-maintainer CURRENT file §2 same-tick to reflect the scheduling-authority sharpening alongside the existing priority stack. (b) **PR #148 markdownlint fix**: scheduled under the new rule because it's free work on funded-stack priority #1 (factory demo / why-factory-is-different explainer). MD022 heading-style violation — multi-line H2 confused the linter; joined into single-line title. Commit on `docs/why-the-factory-is-different` branch. (c) **Self-scheduling demonstration**: the tick's second move (PR #148 fix) is itself the first application of the new rule. Factory-demo surface is priority #1; the fix is free; no human-maintainer approval sought. Per auto-loop-51 discipline correction, would ideally bundle fire-log + tick-history; fire-log not applicable here (not an AutoDream overlay); tick-history bundled on this branch as usual. (d) **CronList + visibility**: `20c92390` minutely fire verified live. | PR #148 lint-fix commit + scheduling-authority memory + per-maintainer CURRENT §2 refresh | Observation 1 — scheduling-authority sharpening reframes last tick's "queued not scheduled" posture as too conservative. The external collaborator's Aurora work, Overlay A migrations, factory-demo PRs, lint fixes — all free, all self-scheduled by agent judgment within the priority stack. Observation 2 — first concrete application of the new rule on a funded-stack #1 item within the same tick it landed. Good calibration signal: factory exercises new directives on first opportunity, not in followup ticks. Observation 3 — the per-maintainer CURRENT file §2 now reads as both priority-stack-authority and scheduling-authority. The two are distinct: the human maintainer owns the stack ordering; the external collaborator + Kenji own scheduling of free work within that order. Memory surface captures the distinction. Observation 4 — markdownlint MD022 multi-line-heading is a different class than MD032 blanks-around-lists and MD003 atx-vs-setext. Three lint-class types now identified as recurring absorb-time hits; worth a memory-author-template that pre-applies all three disciplines. |

[Copilot]

P1: This header says the fire-log schema includes an explicit “link” field (per row #44), but the table has no Link column and the rows don’t provide a consistent link entry. Either add a dedicated Link column (or a structured link format inside Findings), and make sure it matches the schema described in FACTORY-HYGIENE row #53 (which also mentions promotion-candidates/findings-count).

[Copilot]

P1: The hygiene-row numbering is now out of order (row 53 appears before row 52). Please reorder the table (or renumber) so row numbers remain monotonically increasing—this helps keep citations stable and avoids confusion when referencing row IDs.

Suggested change

| 52 | Tick-history bounded-growth audit (`docs/hygiene-history/loop-tick-history.md` line-count vs threshold) | Detect-only (landed 2026-04-22); cadenced detection once per round-close (same cadence as row #44 cadence-history sweep, since this is the canonical row #44 worked example auditing itself); opportunistic on-touch whenever the tick-history file is read or edited. Archive action itself remains manual for now; deferring automation to the larger BACKLOG row that also covers threshold-revision and append-without-reading refactor. | Dejan (devops-engineer) on cadenced detection; the tick itself (self-administered at tick-close) on the opportunistic on-touch — each tick's end-of-tick sequence can invoke this audit after the append + commit to get a `within bounds: 96/500 lines` visibility signal. | factory | `tools/hygiene/audit-tick-history-bounded-growth.sh` checks the file's line count against a threshold (default 500, overrideable via `--threshold N`) and exits 0 within bounds / 2 over threshold. The threshold is set lower than the stated 5000-line paper bound because the file is read on every tick-close append — a per-tick context cost that scales linearly with file size — and 5000 lines represents too large a context hit on a 1-minute cadence. The audit's header block carries a mini-ADR decision record for the 500-line choice (context / decision / alternatives / supersedes / expires-when). **Why this row exists:** Aaron 2026-04-22 tick-fire interrupt: *"does loop tick history grow unbounded? that's an issue if so you just read it"*. Honest state was stated-bound-no-enforcement: file header named 5000 lines, nothing checked it. This row closes the enforcement gap for the threshold-check half of the full BACKLOG row (archive-action + append-without-reading refactor remain deferred). **Self-referential closure:** the tick-history file IS the canonical row-#44 cadence-history-tracking worked example (named explicitly in row #44's "Durable output" citation). Until this row landed, the most-cadenced surface in the factory — the tick itself — had its fire-log surface unaudited for its own growth. Meta-audit triangle remains intact (existence #23 / activation #43 / fire-history #44), and row #49 adds a fourth: fire-history files themselves need bounded-growth audits because they grow at the cadence of the surface they track. **Classification (row #47):** **prevention-bearing** — the audit surfaces approaching-threshold warnings at 80% so the archive action can be planned, rather than reactive-only at over-threshold. Ships to project-under-construction indirectly: adopters inherit the pattern (fire-log files under their own `docs/hygiene-history/` need the same bounded-growth treatment), not this exact script. | Audit output on each fire; cadenced runs appended to `docs/hygiene-history/tick-history-bounded-growth-history.md` (per-fire schema per row #44); BACKLOG row when archival is due (archive-action itself queued as part of the larger tick-history enforcement BACKLOG row); ROUND-HISTORY row when threshold changes or archive action executes. | `tools/hygiene/audit-tick-history-bounded-growth.sh` (detection + mini-ADR header block) + `docs/hygiene-history/loop-tick-history.md` (target surface, canonical row #44 worked example) + BACKLOG row *"Loop-tick-history bounded-growth enforcement"* (larger follow-up: threshold revision + append-without-reading refactor + archive action) |

| 54 | Tick-history bounded-growth audit (`docs/hygiene-history/loop-tick-history.md` line-count vs threshold) | Detect-only (landed 2026-04-22); cadenced detection once per round-close (same cadence as row #44 cadence-history sweep, since this is the canonical row #44 worked example auditing itself); opportunistic on-touch whenever the tick-history file is read or edited. Archive action itself remains manual for now; deferring automation to the larger BACKLOG row that also covers threshold-revision and append-without-reading refactor. | Dejan (devops-engineer) on cadenced detection; the tick itself (self-administered at tick-close) on the opportunistic on-touch — each tick's end-of-tick sequence can invoke this audit after the append + commit to get a `within bounds: 96/500 lines` visibility signal. | factory | `tools/hygiene/audit-tick-history-bounded-growth.sh` checks the file's line count against a threshold (default 500, overrideable via `--threshold N`) and exits 0 within bounds / 2 over threshold. The threshold is set lower than the stated 5000-line paper bound because the file is read on every tick-close append — a per-tick context cost that scales linearly with file size — and 5000 lines represents too large a context hit on a 1-minute cadence. The audit's header block carries a mini-ADR decision record for the 500-line choice (context / decision / alternatives / supersedes / expires-when). **Why this row exists:** Aaron 2026-04-22 tick-fire interrupt: *"does loop tick history grow unbounded? that's an issue if so you just read it"*. Honest state was stated-bound-no-enforcement: file header named 5000 lines, nothing checked it. This row closes the enforcement gap for the threshold-check half of the full BACKLOG row (archive-action + append-without-reading refactor remain deferred). **Self-referential closure:** the tick-history file IS the canonical row-#44 cadence-history-tracking worked example (named explicitly in row #44's "Durable output" citation). Until this row landed, the most-cadenced surface in the factory — the tick itself — had its fire-log surface unaudited for its own growth. Meta-audit triangle remains intact (existence #23 / activation #43 / fire-history #44), and row #49 adds a fourth: fire-history files themselves need bounded-growth audits because they grow at the cadence of the surface they track. **Classification (row #47):** **prevention-bearing** — the audit surfaces approaching-threshold warnings at 80% so the archive action can be planned, rather than reactive-only at over-threshold. Ships to project-under-construction indirectly: adopters inherit the pattern (fire-log files under their own `docs/hygiene-history/` need the same bounded-growth treatment), not this exact script. | Audit output on each fire; cadenced runs appended to `docs/hygiene-history/tick-history-bounded-growth-history.md` (per-fire schema per row #44); BACKLOG row when archival is due (archive-action itself queued as part of the larger tick-history enforcement BACKLOG row); ROUND-HISTORY row when threshold changes or archive action executes. | `tools/hygiene/audit-tick-history-bounded-growth.sh` (detection + mini-ADR header block) + `docs/hygiene-history/loop-tick-history.md` (target surface, canonical row #44 worked example) + BACKLOG row *"Loop-tick-history bounded-growth enforcement"* (larger follow-up: threshold revision + append-without-reading refactor + archive action) |

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 553853734f

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[chatgpt-codex-connector]

Count unique sessions, not per-fact files, for cadence gate

The policy says the AutoDream run gate is >=24h and >=5 sessions, but this implementation substitutes >=5 new per-fact files as the session counter. Because memory files are fact-scoped, one busy session can emit multiple files and satisfy the gate early, while several sessions that produce few/no new files may never satisfy it; both cases violate the stated upstream cadence and can schedule consolidations at the wrong times.

Useful? React with 👍 / 👎.

[Copilot]

Pull request overview

Copilot reviewed 4 out of 4 changed files in this pull request and generated 2 comments.

[Copilot]

P1: The PR description/title focus on the “Factory technology inventory” BACKLOG row, but this PR also adds substantial AutoDream-related research and hygiene-history artifacts (e.g., the AutoDream cadence/overlay research doc and fire-history entries). Please either update the PR description/title to reflect these additional changes or split the AutoDream work into a separate PR to keep scope coherent for reviewers.

[Copilot]

P1: This file references docs/FACTORY-HYGIENE.md row #53, but docs/FACTORY-HYGIENE.md currently has no row 53 (it jumps from #52 to #54). Either add row #53 in the same PR, or update the reference here to the correct existing row number so the link is not dangling.

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: d29474d330

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[chatgpt-codex-connector]

Point roadmap to an existing split-shape source

This backlog row cites docs/research/multi-repo-refactor-shapes-2026-04-23.md as the authority for the D→A→E split, but that file is not present in this commit tree (repo-wide rg --files docs | rg 'multi-repo|refactor-shapes' returns no matching doc). Because the row uses that citation to justify execution order, readers cannot verify the claimed split plan and the dependency chain becomes non-actionable.

Useful? React with 👍 / 👎.

[Copilot]

Pull request overview

Copilot reviewed 3 out of 4 changed files in this pull request and generated 1 comment.

[Copilot]

The PR description focuses on adding a BACKLOG row for the technology inventory, but this PR also adds a large new research doc and substantial hygiene-history log updates. Either update the PR description to reflect the full scope or split the unrelated changes into separate PRs to keep review and rollback risk manageable.

[Copilot]

Pull request overview

Copilot reviewed 3 out of 4 changed files in this pull request and generated no new comments.

[Copilot]

Pull request overview

Copilot reviewed 3 out of 4 changed files in this pull request and generated 1 comment.

[Copilot]

PR description frames this as a BACKLOG capture for a future docs/FACTORY-TECHNOLOGY-INVENTORY.md deliverable, but this PR also introduces several other doc surfaces (e.g., AutoDream research + hygiene history updates) and does not add the inventory doc itself. Consider either (a) narrowing the PR to the described scope, or (b) updating the PR title/description to reflect the additional changes and clarify that the inventory doc is intentionally deferred.

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 9632c25135

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[chatgpt-codex-connector]

Remove future-dated entries from tick fire-history

This file’s schema says date is the write-time of the row, but commit ec222b9 (2026-04-23T21:54:36Z) adds rows stamped later than that time. Fresh evidence in this commit is the newly added 2026-04-23T23:25:00Z and later rows, which cannot be true fire-time records if they were committed at 21:54Z. That breaks the log’s audit value for cadence checks and incident forensics that rely on real chronological evidence.

Useful? React with 👍 / 👎.

[chatgpt-codex-connector]

Use only observed-date directives in backlog rows

This commit is dated 2026-04-23, but this new backlog item is attributed to Aaron 2026-04-24 Otto-43, so it records a directive from a future tick as already received. That makes the backlog’s request provenance non-auditable and can start work under instructions that are not yet durably recorded in the same timeline. Please land this row when the source tick exists, or correct the attribution date to when it was actually observed.

Useful? React with 👍 / 👎.

[Copilot]

Pull request overview

Copilot reviewed 3 out of 4 changed files in this pull request and generated no new comments.

[AceHack]

Closing — BACKLOG.md auto-generated-index conflict pattern.

Per Otto-321 + Otto-322: this PR conflicts on `docs/BACKLOG.md` (auto-generated index regenerated by every PR). The factory technology inventory backlog row content itself is valuable; the index conflicts are mechanical.

Disposition: closing this PR; the per-row backlog file (the actual valuable content) can be cherry-picked into a fresh small PR that lets the BACKLOG.md auto-regenerate cleanly. If you want me to do the cherry-pick, surface a yes-please and I'll open it as a small fresh PR.

🤖 Edge runner triage by Claude Opus 4.7