docs: add UPSTREAM-RHYTHM.md — Zeta's fork-first batched PR cadence by AceHack · Pull Request #2 · AceHack/Zeta

AceHack · 2026-04-21T15:44:42Z

Summary

Adds docs/UPSTREAM-RHYTHM.md, the Zeta-specific project-level
config that the factory-generic fork-pr-workflow skill defers to
for upstream-cadence choice.

The doc encodes Aaron's 2026-04-22 cost-model correction: day-to-day
PRs target AceHack/Zeta:main (free CI), one bulk
AceHack/main → LFG/main sync every ~10 PRs carries the accumulated
work. Previously the agent was opening PRs directly against LFG and
paying LFG Copilot + Actions billing per PR.

What's in the doc

Diagram of the batched rhythm
Why Zeta diverges from industry default (LFG paid surface,
AceHack free, "poor man's setup" framing)
Concrete gh commands for default PR, bulk sync, and forward-sync
Five named exceptions for direct-to-LFG PRs
Threshold tuning guidance (~10 is a suggestion; 5-20 reasonable)
Proposed "bulk-sync cadence monitor" FACTORY-HYGIENE row

Resolves a phantom pointer

memory/feedback_fork_pr_cost_model_prs_land_on_acehack_sync_to_lfg_in_bulk.md
already cited docs/UPSTREAM-RHYTHM.md as an intended target under
"Factory artifacts to update / create". This PR lands that target.

Cost rationale

This PR itself goes to AceHack, not LFG. LFG Copilot + Actions don't
run on it. Per the rhythm the doc describes.

Test plan

Markdown renders cleanly
No broken intra-repo links
Commands shown are valid gh / gh api invocations
AceHack CI green

🤖 Generated with Claude Code

The fork-pr-workflow skill defers the upstream-cadence choice to project-level config. This is Zeta's config: - Default PR target: AceHack/Zeta:main (free CI, free Copilot) - Bulk sync AceHack/main -> LFG/main every ~10 PRs (one PR, not N) - Five named exceptions for direct-to-LFG (security P0, external contributor, Aaron explicit, CI-repair, the bulk-sync PR itself) - Concrete gh commands for each case - Proposed cadence-monitor FACTORY-HYGIENE row Resolves a phantom pointer in memory/feedback_fork_pr_cost_model_prs_land_on_acehack_sync_to_lfg_in_bulk.md which cited docs/UPSTREAM-RHYTHM.md as an intended target. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

…ucent-Financial-Group#93 review) (Lucent-Financial-Group#95) One row appended (row 116) for the auto-loop-6 tick that: - Absorbed the external ChatGPT-substrate companion's pro-mode repo-search report #2 with a five-pattern drift-taxonomy + Aurora-branding memo + independent cross-substrate measurement of this repo. - Landed cross-substrate audit memory with receive / verify / correspond / hold-register-boundary / redirect protocol applied; five-pattern correspondence table mapping companion's drift taxonomy onto factory disciplines (register-boundary, retraction, out-of-scope, witnessable-self-directed-evolution, roommate-register). - Introduced new alignment-trajectory measurable (cross-substrate-report-accuracy-rate, target >90%, current 2/2 data points at 100%). - Addressed PR Lucent-Financial-Group#93 Copilot review two findings (P1 cross-tree path citation + P2 hyphenation mismatch with meta-wins-log canonical spelling) via commit c1a4863 — same soul-file-independence teaching instance the pre-check memory documents. - Refreshed PR Lucent-Financial-Group#93 against advancing main after PR Lucent-Financial-Group#94 merged (048c35c..fead862). Row lands on separate branch off origin/main per tick-commits-on-PR-branch = live-loop class discipline (row 112). Pre-check grep on additions = clean. Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>

…ogged (Lucent-Financial-Group#177) Creates durable append-only log for the cadenced NSA testing protocol declared in the 2026-04-23 "NSA persona is first- class" directive. Closes gap #3 of the Frontier bootstrap readiness roadmap (BACKLOG P0, filed Otto-2). File contents: - Why-this-exists block with directive verbatim - Append-only discipline (same shape as sibling hygiene-history files) - 3 test configurations: baseline / NSA-default / NSA-worktree - 5-prompt test set v1 - Schema: date / test-id / prompt-id / config / model / outcome / gap-found / notes - Outcome definitions: pass / partial / fail - Cadence: every 5-10 autonomous-loop ticks, one prompt per fire - Known substrate-gap patterns running list - First row: NSA-001 (Otto-1 feasibility test, 2026-04-23T18:42:00Z) — partial pass, found Zeta identity but missed Otto because MEMORY.md had no pointer; gap fixed same-tick, pattern recorded Attribution: Otto (loop-agent PM hat) — hat-less-by-default substrate hygiene work. No specialist persona hats worn. Closes gap #3 of 8 in the Frontier readiness roadmap. Remaining: gap #1 (multi-repo split) / #2 (linguistic-seed substrate) / #4 (bootstrap-reference docs) / #5 (factory-vs- Zeta separation) / #6 (persona file portability) / #7 (tick-history scope-mixed) / #8 (hygiene rows untagged). Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>

Lucent-Financial-Group#180) Second file audited in the factory-vs-Zeta separation audit (gap #5). AGENTS.md is the universal onboarding handbook. Overall classification: both (coupled) — mostly factory- generic in shape, with Zeta-library-specific content in 6 areas: 1. Three load-bearing values #2 (Z-set / operator laws) 2. "What we borrow" section (DBSP / Arrow / etc. list) 3. Build and test gate (dotnet commands) 4. Code style (F# / .NET specifics) 5. Inline ZSet / algebra examples (audit on-touch) 6. Pre-v1 Status declaration (project-specific shape) Estimated refactor effort: M (more surgical edits than CLAUDE.md's S, but each isolated). Post-split location: Frontier (authoritative onboarding template); adopters fork + customise example sections. Zeta-specific content extracted to Zeta repo's own CONTRIBUTING.md (or equivalent). Section-by-section breakdown for 15 sections documented. Attribution: Otto (loop-agent PM hat). Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>

…ON LANDED) (Lucent-Financial-Group#194) Creates docs/linguistic-seed/ directory + README.md (220 lines) establishing the substrate shape for gap #2 of the Frontier bootstrap readiness roadmap. Content: - Why-this-exists block with three load-bearing uses: prompt-injection resistance / Soulfile DSL vocabulary / Craft prereq graph root - Minimal-axiom approach (Tarski / Meredith / Robinson Q lineage) - Per-term schema (plain English / mathematical / Lean4 formalisation / grounding point / exclusions / citations) - Prereq DAG growth discipline (no cycles / backwards-chain from current needs) - Initial term candidates (truth / implication / equality / set / function / axiom / definition / retraction) - Composition with prompt-injection bootstrap + Soulfile DSL + Craft prereq graph + Frontier bootstrap Gap #2 status: pending → SKELETON LANDED. Full population (20+ Lean4-formalised terms) = multi-round follow-on. Attribution: Otto (loop-agent PM hat) skeleton; Soraya (formal-verification-expert) on Lean4 cadence when it fires. Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>

…utably (Lucent-Financial-Group#214) Amara's 2026-04-23 ZSet-semantics courier report (absorbed as PR Lucent-Financial-Group#211) called out the `RecursiveSemiNaive` monotone-only boundary as a "must remain explicitly labeled" gap. The code (src/Core/Recursive.fs XML doc WARNING section) and the spec (openspec/specs/retraction- safe-recursion/spec.md § "Requirement: semi-naïve recursion is monotone-only") already document it; this PR adds the *executable* documentation so the boundary cannot silently drift. New file: `tests/Tests.FSharp/Operators/RecursiveSemiNaive. Boundary.Tests.fs` (~170 lines, 2 tests, 0 warnings): Test 1 — `RecursiveSemiNaive matches Recursive on monotone inputs (acyclic DAG)`: encodes spec scenario #1. Compares positive-weight support between `Recursive` and `RecursiveSemiNaive` on a monotone edge seed; they must agree. Test 2 — `RecursiveSemiNaive leaks stale facts after retraction (documented boundary)`: encodes spec scenario #2. Feeds an edge retraction after initial closure and ASSERTS that the derived closure row (1,3) remains with positive weight. **Reading note: the leak test is not a bug being asserted; it is a boundary being recorded.** If a future change ever makes the test fail (i.e., the leak gets fixed), the investigation is documented in the test body — replace combinator with gap-monotone signed-delta variant OR investigate harness masking. Build + test verification: dotnet build tests/Tests.FSharp/Tests.FSharp.fsproj -c Release = 0 Warning(s) + 0 Error(s) in 5.4s dotnet test ... --filter "RecursiveSemiNaiveBoundary" = 2 Passed, 0 Failed Companion register: file registered in Tests.FSharp.fsproj after `Operators/RecursiveCounting.MultiSeed.Tests.fs` per existing section convention. Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>

…(Amara action #2) (Lucent-Financial-Group#223) Amara's 4th ferry (PR Lucent-Financial-Group#221) action item #2: pin Claude model snapshot + loaded memory state + prompt bundle hash so "Claude" is not a moving target across model version shifts (3.5 → 3.7 → 4 → 4.x all have materially different system-prompt bundles + knowledge cutoffs + memory-retention language per archived Drive artifacts). Three-part scaffolding (v0): 1. tools/hygiene/capture-tick-snapshot.sh - Captures mechanically-accessible state: * Claude Code CLI version (`claude --version`) * CLAUDE.md + AGENTS.md + memory/MEMORY.md SHAs * Memory index byte count * Git HEAD + branch + repo * Date UTC * Per-user ~/.claude/CLAUDE.md SHA if present - Outputs YAML (default) or JSON (`--json`) - Agent fills model_snapshot + prompt_bundle_hash from session context (not CLI-accessible today) 2. docs/hygiene-history/session-snapshots.md - Session-level + significant-event pins (not per-tick) - Append-only row format: session_id / captured_utc / event (session-open | mid-session-pin | session-close | compaction) / agent / model / CLI version / git state / files SHAs / notes / prompt_bundle_hash - Seeded with one mid-session-pin for this tick's Otto-70 capture (the session has been running ~70 ticks; actual session-open is earlier and unreachable for pins) 3. docs/hygiene-history/loop-tick-history.md schema extension - New "On snapshot pinning" subsection documenting the relationship: per-tick pins optional + inline in `notes`; session-level pins go in the sidecar file. - Snapshot capture is discipline, not gate — don't slow the autonomous-loop tick-close for every fire. What the snapshot does NOT capture yet: - model_snapshot — known to the agent from session context, not exposed by `claude --version` (which gives CLI version only). Agent fills. - prompt_bundle_hash — no current tool reconstructs the system prompt bundle. Placeholder null until such a tool lands. Amara's Determinize-stage work potentially. - Active permissions / skill set — session-specific; not captured in v0. First run of the tool on this branch surfaced a separate drift: memory/MEMORY.md is at 58842 bytes (~58KB, over the FACTORY-HYGIENE row #11 24976-byte cap). Not fixed in this PR — known-separately tracked drift. Amara Stabilize-stage: 3/3 landed (with this PR). ✓ Action #3 — decision-proxy-evidence schema (PR Lucent-Financial-Group#222) ✓ Action #4 — branch-chat non-canonical framing (PR Lucent-Financial-Group#222) ✓ Action #2 — snapshot pinning scaffolding (this PR) "Deterministic reconciliation" framing (Otto-67 endorsement): snapshot pinning is the mechanism that reconciles "what Claude knew" with "what Claude did" across time — essential for any future audit, tuning, or Amara-style drift analysis. Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>

…ries (8th-ferry candidate #1) (Lucent-Financial-Group#278) Research-grade absorb per Amara 8th-ferry landing plan (PR Lucent-Financial-Group#274). Separates real quantum-sensing literature from software analogy so the latter can borrow carefully without contaminating the former. Key structure: - **Do not operationalize stated as first rule** — this doc MUST NOT be cited as authorisation for Zeta or Aurora "quantum-powered" / "quantum-inspired" claims. 2024 engineering review caps microwave QR at <1 km typical. - **What the physics actually supports**: Lloyd 2008 + Tan Gaussian-state 6 dB error-exponent + 2023 Nature Physics microwave demo + 2024 engineering range-cap review + standard radar R⁻⁴ range equation. Quantum sensing broader and more mature than quantum-radar specifically (NV-centers / magnetometers / atomic clocks are real; radar is speculative). - **5 importable software analogies**: retained reference path (anchor for weak evidence); correlation beats isolation (kNN retrieval not single-source agreement); time-bandwidth product (repeated independent observations over window); decoherence (carrier overlap destroys independence weight); cross-section-is- observability (salience != evidence). - **6-item NOT-imply list**: no quantum-radar claim; no quantum-inspired algebra; no quantum-certified alignment robustness; no Aurora-as-quantum-safety; etc. First-class content, future references must honour. - **Composition table** mapping analogies to existing substrate (SD-9 / DRIFT-TAXONOMY patterns 2 + 5 / citations-as-first-class / alignment-observability / oracle-scoring v0 / BLAKE3 v0). No new mechanisms proposed; analogies slot in as framing. - **Graduation candidates** named with explicit ADR gating: retained-witness correlation metric; salience-vs-evidence PR review diagnostic; decoherence-inspired carrier- downgrade rule. Each needs separate ADR + operational artifact + regression-test before graduating. Scope limits: - Does NOT propose implementation. - Does NOT audit existing Zeta claims against analogy boundaries. - Does NOT commit to quantum-literature tracking cadence. - Does NOT license creative expansion of analogy set (5 is what Amara cited; new literature = new research doc). - Does NOT re-verify primary sources; preserves Amara's scoping discipline verbatim. Self-applies §33 archive-header format — 14th aurora/research doc in a row. Lands within-standing-authority per Otto-82/90/93 calibration — research-grade doc; not account / spending / named-design-review / readiness-signal gated. Closes 8th-ferry candidate #1 of remaining 4 (after TECH-RADAR batch closed #5 Otto-96). Remaining: - #2 Semantic-canonicalization research doc (M; spine) - #3 Provenance-aware bullshit-detector (M) - #4 docs/EVIDENCE-AND-AGREEMENT.md future operational promotion (gated on 1-3) Otto-97 tick primary deliverable.

…correction) (Lucent-Financial-Group#332) Completes the input pipeline for TemporalCoordinationDetection. phaseLockingValue (PR Lucent-Financial-Group#298): PLV expects phases in radians but didn't prescribe how events become phases. This ship fills the gap. 17th graduation under Otto-105 cadence. Addresses Amara 17th-ferry Part 2 correction #5: 'Without phase construction, PLV is just a word.' Surface (2 pure functions): - PhaseExtraction.epochPhase : double -> double[] -> double[] Periodic-epoch phase. φ(t) = 2π · (t mod period) / period. Suited to consensus-protocol events with fixed cadence (slot duration, heartbeat, epoch boundary). - PhaseExtraction.interEventPhase : double[] -> double[] -> double[] Circular phase between consecutive events. For sample t in [t_k, t_{k+1}), phase = 2π · (t - t_k) / (t_{k+1} - t_k). Suited to irregular event-driven streams. Both return double[] of phase values in [0, 2π) radians. Empty output on degenerate inputs (no exception). eventTimes assumed sorted ascending; samples outside the event range get 0 phase (callers filter to interior if they care). Hilbert-transform analytic-signal approach (Amara's Option B) deferred — needs FFT support which Zeta doesn't currently ship. Future graduation when signal-processing substrate lands. Tests (12, all passing): epochPhase: - t=0 → phase 0 - t=period/2 → phase π - wraps cleanly at period boundary - handles negative sample times correctly - returns empty on invalid period (≤0) or empty samples interEventPhase: - empty on <2 events or empty samples - phase 0 at start of first interval - phase π at midpoint - adapts to varying interval lengths (O(log n) binary search for bracketing interval) - returns 0 before first and after last event (edge cases) Composition with phaseLockingValue: - Two nodes with identical epochPhase period → PLV = 1 (synchronized) - Two nodes with same period but constant offset → PLV = 1 (perfect phase locking at non-zero offset is still locking) This composes the full firefly-synchronization detection pipeline end-to-end for event-driven validator streams: validator event times → PhaseExtraction → phaseLockingValue → temporal-coordination-detection signal 5 of 8 Amara 17th-ferry corrections now shipped: #1 λ₁(K₃)=2 ✓ already correct (PR Lucent-Financial-Group#321) #2 modularity relational ✓ already correct (PR Lucent-Financial-Group#324) #3 cohesion/exclusivity/conductance ✓ shipped (PR Lucent-Financial-Group#331) #4 windowed stake covariance ✓ shipped (PR Lucent-Financial-Group#331) #5 event-stream → phase pipeline ✓ THIS SHIP Remaining: #4 robust-z-score composite variant (future); #6 ADR phrasing (already correct); #7 KSK naming (BACKLOG Lucent-Financial-Group#318 awaiting Max coord); #8 SOTA humility (doc-phrasing discipline). Build: 0 Warning / 0 Error. Provenance: - Concept: Aaron firefly-synchronization design - Formalization: Amara 17th-ferry correction #5 with 3-option menu (epoch / Hilbert / circular) - Implementation: Otto (17th graduation; options A + C shipped, Hilbert deferred) Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>

…-ferry §B + §F + corrections #2 #7 #9 (Lucent-Financial-Group#342) Research-grade design doc for the Stage-2 rung of Amara's corrected promotion ladder. Specifies: (a) placement under src/Experimental/CartelLab/ (not src/Core/ — that's Stage 4); (b) MetricVector type with PLV magnitude AND offset split (correction #6); (c) INullModelGenerator interface + Preserves/Avoids table columns; (d) IAttackInjector forward-looking interface (Stage 3); (e) Wilson-interval reporting contract with {successes, trials, lowerBound, upperBound} schema (correction #2 — no more "~95% CI ±5%" handwave); (f) RobustZScoreMode with Hybrid fallback (correction #7 — percentile-rank when MAD < epsilon); (g) explicit artifact-output layout under artifacts/ coordination-risk/ with five files + run-manifest.json (correction #9). 6-stage promotion path (0 doc / 1 ADR / 2.a skeleton / 2.b full null-models + first attack / 3 attack suite / 4 Core/NetworkIntegrity / 5 Aurora-KSK) matches Amara's corrected ladder and Otto-105 cadence. Doc-only change; no code, no tests, no workflow, no BACKLOG tail touch (avoids positional-conflict pattern that cost Lucent-Financial-Group#334 → Lucent-Financial-Group#341 re-file this session). This is the 7th of 10 18th-ferry operationalizations: - #1/#10 test-classification (Lucent-Financial-Group#339) - #2 Wilson-interval design specified (this doc) - #6 PLV phase-offset shipped (Lucent-Financial-Group#340) - #7 MAD=0 Hybrid mode specified (this doc) - #9 artifact layout specified (this doc) - #4 exclusivity already shipped (Lucent-Financial-Group#331) - #5 modularity relational already shipped (Lucent-Financial-Group#324) Remaining: Wilson-interval IMPLEMENTATION (waits on Lucent-Financial-Group#323 + Stage 2.a), MAD=0 Hybrid IMPLEMENTATION (waits on Lucent-Financial-Group#333 + Stage 2.a), conductance-sign doc (waits on Lucent-Financial-Group#331), Stage-2.a skeleton itself. Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>

…ation (Amara 19th #3) (Lucent-Financial-Group#347) * docs: DST accepted-boundaries registry stub + push-with-retry.sh classification (Amara 19th #3) Amara 19th-ferry correction #3 asked for push-with-retry.sh to either (a) document as external-boundary exception with rationale, or (b) convert to investigation-wrapper. Audit finding: the script already implements (a) with high discipline — root-cause investigation block in the header, targeted-5xx-only retries (not blind), exponential backoff, max-attempts cap, per-attempt logging to stderr, full error-text preservation via tee, distinct exit codes for transient-retry-exhausted vs non-transient vs env-error. Amara's concern was based on the doc-level visibility gap, not an implementation gap. This PR closes the gap by: 1. Creating docs/research/dst-accepted-boundaries.md — the accepted-boundaries registry Amara's correction #2 + the DST-compliance-criteria doc (PR Lucent-Financial-Group#346) both require. Schema for entries locked. First entry: push-with-retry.sh with full rationale, investigation summary, retry- discipline breakdown, and revisit triggers. 2. Adding a classification pointer in the script's header comment block: cites the registry + "First classified 2026-04-23, formally registered Otto-168 2026-04-24." Registry research-grade today; promotes to docs/DST-ACCEPTED- BOUNDARIES.md top-level when PR 1 of the 19th-ferry revised roadmap lands (entropy-scanner + ADR). Next migration candidates named: DiskBackingStore stays BLOCKER until PR 5 simulates it (not accepted-boundary — simulation is correct answer there). Future multi-node network I/O stays BLOCKER until PR 8. Composes with PR Lucent-Financial-Group#346 dst-compliance-criteria doc, PR Lucent-Financial-Group#344 19th-ferry absorb, .claude/skills DST guide, existing push-with-retry.sh implementation. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * fix(Lucent-Financial-Group#347): 4 review threads — schema clarify + planned-file xref softening - thread PRRT_kwDOSF9kNM59Wql1 (line 12, P1): self-resolving; docs/research/dst-compliance-criteria.md now exists on main via a later merge; cross-reference is valid, no edit needed. - thread PRRT_kwDOSF9kNM59Wqmv (line 42, P2): schema relaxed from "one of the 12 DST entropy classes" to "one or more of the 12 DST entropy classes, comma- or `+`-separated when a site genuinely crosses multiple (e.g. a network boundary whose only retry policy is itself a distinct entropy source)". Keeps the first entry's combined "external network I/O + retry-on-failure" value accurate — retry-on-failure is a policy IN the network-I/O boundary, not a separate class. - thread PRRT_kwDOSF9kNM59Wqm8 (line 172, P1): same self-resolve as thread 1; docs/research/dst-compliance-criteria.md exists. - thread PRRT_kwDOSF9kNM59WqnP (line 125, P1): DiskBackingStore.fs and ISimulationFs are not in src/; rephrased as forward-looking with explicit "(planned, not yet landed)" parentheticals plus a sentence clarifying this row is a placeholder the scan can compare against once PR 5 of the 19th-ferry roadmap arrives. --------- Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>

The fork-pr-workflow skill defers the upstream-cadence choice to project-level config. This is Zeta's config: - Default PR target: AceHack/Zeta:main (free CI, free Copilot) - Bulk sync AceHack/main -> LFG/main every ~10 PRs (one PR, not N) - Five named exceptions for direct-to-LFG (security P0, external contributor, Aaron explicit, CI-repair, the bulk-sync PR itself) - Concrete gh commands for each case - Proposed cadence-monitor FACTORY-HYGIENE row Resolves a phantom pointer in memory/feedback_fork_pr_cost_model_prs_land_on_acehack_sync_to_lfg_in_bulk.md which cited docs/UPSTREAM-RHYTHM.md as an intended target. Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>

…nt-Financial-Group#139) * docs: add UPSTREAM-RHYTHM.md — Zeta's fork-first batched PR cadence (#2) The fork-pr-workflow skill defers the upstream-cadence choice to project-level config. This is Zeta's config: - Default PR target: AceHack/Zeta:main (free CI, free Copilot) - Bulk sync AceHack/main -> LFG/main every ~10 PRs (one PR, not N) - Five named exceptions for direct-to-LFG (security P0, external contributor, Aaron explicit, CI-repair, the bulk-sync PR itself) - Concrete gh commands for each case - Proposed cadence-monitor FACTORY-HYGIENE row Resolves a phantom pointer in memory/feedback_fork_pr_cost_model_prs_land_on_acehack_sync_to_lfg_in_bulk.md which cited docs/UPSTREAM-RHYTHM.md as an intended target. Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com> * docs: scout LFG-only capabilities; add 6th direct-to-LFG exception; P3 BACKLOG row Aaron 2026-04-22 clarified LFG is not just "paid surface to avoid" but a throttled experimental tier: Copilot Business + Teams plan, all enhancements enabled (internet search, coding agent, etc.). Standing permission to change any LFG setting except the $0 budget cap and personal info. Enterprise upgrade offered if we build a large-enough LFG-only backlog to justify it. Changes: - docs/research/lfg-only-capabilities-scout.md — new scouting doc. Verified Copilot Business plan via gh api; enumerates 10 candidate experiments across Copilot Business, Teams plan, Actions runner classes, and org-level features. Each has a cadence. Declines self-hosted runners and raising the budget cap. - docs/UPSTREAM-RHYTHM.md — adds a 6th direct-to-LFG exception ("LFG-only capability experiment") so these experiments don't fight the batched cost model. - docs/BACKLOG.md — new P3 row "LFG-only experiment track (throttled)" pointing at the scout doc; gated on the 10-item threshold for the Enterprise upgrade conversation. Source memory: memory/feedback_lfg_paid_copilot_teams_throttled_experiments_allowed.md Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * docs: address PR Lucent-Financial-Group#139 review threads — row-number fixes, compare syntax, seeded hygiene-history, IP template cleanup - UPSTREAM-RHYTHM.md: fix compare basehead syntax (Codex P1 — use owner:branch, not owner:repo:branch) - AGENT-GITHUB-SURFACES.md + github-surface-triage SKILL.md: FACTORY-HYGIENE row refs Lucent-Financial-Group#44→Lucent-Financial-Group#47, Lucent-Financial-Group#45→Lucent-Financial-Group#48 - AGENT-ISSUE-WORKFLOW.md: soften "BACKLOG row is open" to "TODO: file a BACKLOG row" - research/lfg-only-capabilities-scout.md: clarify HB-001 is resolved org-migration; merge queue is follow-up - BACKLOG.md: unsplit inline-code spans in P3 LFG row - hygiene-history/{wiki,discussions}-history.md: seed files referenced by Surface 3/4 docs - .github/ISSUE_TEMPLATE/feature_request.md: remove stale GitHub default template (Zeta set covers bug_report/backlog_item/human_ask) Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>

AceHack merged commit 4a28b18 into main Apr 21, 2026

AceHack mentioned this pull request Apr 23, 2026

ci: memory-index duplicate-link lint + FACTORY-HYGIENE #60 (Amara action item #2) #12

Open

3 tasks

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

docs: add UPSTREAM-RHYTHM.md — Zeta's fork-first batched PR cadence#2

docs: add UPSTREAM-RHYTHM.md — Zeta's fork-first batched PR cadence#2
AceHack merged 1 commit intomainfrom
land-upstream-rhythm-doc

AceHack commented Apr 21, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Conversation

AceHack commented Apr 21, 2026

Summary

What's in the doc

Resolves a phantom pointer

Cost rationale

Test plan

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant