rules(rate-limit-tier): REST PR-creation fallback under Pure-git tier (PR #4105 anchor) by AceHack · Pull Request #4107 · Lucent-Financial-Group/Zeta

AceHack · 2026-05-17T22:06:40Z

Adds a sub-section to refresh-world-model-poll-pr-gate.md under "Pure-git tick pattern (empirical)" documenting REST POST /repos/.../pulls as a fallback when GraphQL is exhausted.

Empirical anchor: PR #4105 opened via REST at 2026-05-17T21:54Z when GraphQL was 0/5000 (28 min from reset). REST core was at 4838 at the time — separate budget.

Caveats documented:

gh pr merge --auto is GraphQL-only (no REST equivalent for enablePullRequestAutoMerge); PR opened via REST sits without auto-merge until post-reset tick.
gh pr comment is GraphQL; REST equivalent is POST /repos/.../issues/N/comments.
resolveReviewThread is GraphQL-only.
REST PR-creation does NOT bypass branch protection.
JSON body must use HEREDOC + temp file; inline shell-quoted JSON is fragile.

The fallback applies when a substantive landing is ready but you want the PR visible BEFORE the reset window so reviewers can pick it up immediately. Without auto-merge arming, the next post-reset tick must explicitly arm it.

This PR itself was also opened via the REST endpoint — recursively-self-documenting the pattern.

Co-Authored-By: Claude noreply@anthropic.com

… (PR #4105 empirical anchor) Adds a sub-section to refresh-world-model-poll-pr-gate.md under "Pure-git tick pattern (empirical)" documenting that `gh pr create` uses GraphQL but the REST POST /repos/.../pulls endpoint works during Pure-git tier (REST budget is separate from GraphQL budget). Empirical anchor: PR #4105 opened via REST at 2026-05-17T21:54Z when GraphQL was 0/5000 (28 min from reset). REST core was at 4838 at the time. Caveats documented: - gh pr merge --auto is GraphQL-only (no REST equivalent for enablePullRequestAutoMerge); PR opened via REST sits without auto-merge until post-reset tick. - gh pr comment is GraphQL; REST equivalent is POST /repos/.../issues/N/comments. - resolveReviewThread is GraphQL-only. - REST PR-creation does NOT bypass branch protection. - JSON body must use HEREDOC + temp file; inline shell-quoted JSON is fragile. The fallback applies when a substantive landing is ready but you want the PR visible BEFORE the reset window so reviewers can pick it up immediately. Without auto-merge arming, the next post-reset tick must explicitly arm it. Co-Authored-By: Claude <noreply@anthropic.com>

Copilot

Pull request overview

Documentation-only addition to the Pure-git tier rule, recording a REST-based PR-creation fallback when the GraphQL budget is exhausted, with an empirical anchor (PR #4105) and explicit caveats about features (auto-merge, comments, review-thread resolution) that remain GraphQL-only.

Changes:

Adds a new "REST PR-creation fallback under Pure-git tier" sub-section with a HEREDOC+gh api recipe.
Documents the GraphQL-only caveats (gh pr merge --auto, gh pr comment, resolveReviewThread) and that branch protection still applies.
Anchors the pattern to the 2026-05-17T21:54Z PR #4105 instance.

… claim + duplicate-merge + clean-cycle count Three reviewer findings addressed: 1. **Codex P2 (line 330)** — "Align cadence claim with timeline": Original claim said "~2 pre-empts per ~30-min window"; table showed 4 pre-empts (cycles 3, 5, 6, 7). Corrected to "~3-4 Otto-initiated pre-empts per window, the 4th typically being the forced-#6 meta-fallback." 2. **Codex P2 (line 340)** — "Fix duplicate merge event for #4104": Cycle 3 listed PR #4104 as "merged" but it was OPENED + auto-armed in cycle 3 and didn't actually MERGE until cycle 4 (when CI cleared). Restated cycle 3 as "opened + auto-armed" and clarified cycle 4 as the merge event. 3. **Copilot (line 345)** — "Reconcile first ~4 clean pre-empts with cycle 2 = no concrete artifact": The "first ~4 cycles" wording over-counted. Cycle 2 had no pre-empt (no named dep, no escalation, no artifact); cycles 1 + 4 were external counter-reset-via-merge events, not Otto-initiated pre-empts. Restated to count only Otto-initiated pre-empts (3 clean before saturation + 1 forced-#6 = 4 total). Added a "Note on terminology" sub-section distinguishing: - Otto-initiated pre-empt (Otto produces a concrete artifact in response to brief-ack pressure) - Counter-reset-via-merge (external auto-merge firing resets the counter but doesn't count toward pre-empt cadence) Composes with the Codex finding's underlying concern: the rule must distinguish "discipline-bounded Otto behavior" from "external state changes" when measuring cadence. Without that distinction, the cadence claim conflated the two and over-stated the pre-empt budget. Bonus row added to timeline: cycle 8 (22:20Z) — PR #4107 merged via REST PUT /pulls/N/merge bypass when GraphQL was still exhausted. This is the post-forced-#6 substantive close of the window. Co-Authored-By: Claude <noreply@anthropic.com>

…self-documenting) (#4110) * rules(holding): pre-empt-substrate-pool-saturation anchor — single GraphQL-reset window cadence (2026-05-17T21:29Z-22:13Z, forced-#6 at end) Fifth empirical anchor for holding-without-named-dependency-is- standing-by-failure.md. Observed pattern: cycling brief-ack chains under sustained GraphQL exhaustion produce a natural cadence of roughly 2 substantive pre-empts per ~30-min GraphQL reset window before pre-empt-substrate-pool saturates. Session timeline: 7 cycles across ~44 min; first ~4 cycles produced clean pre-empts; cycles 5-6 were forced into REST-only operation by GraphQL exhaustion; cycle 7 reached forced-#6 because the substrate pool of non-fabricated improvements had saturated. Operational lesson: pre-empt-at-#5 is NOT infinitely repeatable within a single rate-limit window. The 06:02Z anchor demonstrated 10 cycles without forced-#6, but those were spread across 2h 27min with multiple resets between cycles (each reset refreshing the substrate-discovery context). When the window is shorter (~30 min) AND no major external state changes occur, the natural cadence is ~2 pre-empts before saturation. Forced-#6 is then NOT a failure of pre-empt discipline; it's substrate-honest acknowledgment that the pool is exhausted for THIS window. Riding cleanly to #6 and applying the meta-fallback is the discipline WORKING. THIS commit is itself the forced-#6 meta-fallback firing, recursively-self-documenting. Composes with refresh-world-model-poll-pr-gate.md (REST PR-creation fallback enabled cycles 5-6 productivity; without it those cycles would have deferred). Co-Authored-By: Claude <noreply@anthropic.com> * fix(rule-anchor/4110): address Codex P2 + Copilot findings on cadence claim + duplicate-merge + clean-cycle count Three reviewer findings addressed: 1. **Codex P2 (line 330)** — "Align cadence claim with timeline": Original claim said "~2 pre-empts per ~30-min window"; table showed 4 pre-empts (cycles 3, 5, 6, 7). Corrected to "~3-4 Otto-initiated pre-empts per window, the 4th typically being the forced-#6 meta-fallback." 2. **Codex P2 (line 340)** — "Fix duplicate merge event for #4104": Cycle 3 listed PR #4104 as "merged" but it was OPENED + auto-armed in cycle 3 and didn't actually MERGE until cycle 4 (when CI cleared). Restated cycle 3 as "opened + auto-armed" and clarified cycle 4 as the merge event. 3. **Copilot (line 345)** — "Reconcile first ~4 clean pre-empts with cycle 2 = no concrete artifact": The "first ~4 cycles" wording over-counted. Cycle 2 had no pre-empt (no named dep, no escalation, no artifact); cycles 1 + 4 were external counter-reset-via-merge events, not Otto-initiated pre-empts. Restated to count only Otto-initiated pre-empts (3 clean before saturation + 1 forced-#6 = 4 total). Added a "Note on terminology" sub-section distinguishing: - Otto-initiated pre-empt (Otto produces a concrete artifact in response to brief-ack pressure) - Counter-reset-via-merge (external auto-merge firing resets the counter but doesn't count toward pre-empt cadence) Composes with the Codex finding's underlying concern: the rule must distinguish "discipline-bounded Otto behavior" from "external state changes" when measuring cadence. Without that distinction, the cadence claim conflated the two and over-stated the pre-empt budget. Bonus row added to timeline: cycle 8 (22:20Z) — PR #4107 merged via REST PUT /pulls/N/merge bypass when GraphQL was still exhausted. This is the post-forced-#6 substantive close of the window. Co-Authored-By: Claude <noreply@anthropic.com> * fix(rule-anchor/4110): address Codex P2 line-355 cadence-baseline inconsistency Codex caught a remaining inconsistency in the "Composes with" paragraph: the rest of the new anchor consistently uses "3-4 pre-empts" but line 355's compose paragraph still said "natural-cadence-of-2-pre-empts." That created conflicting operational guidance inside the same section. Fixed: paragraph now reads "The 3-4-Otto-initiated-pre-empts cadence observed here is conditional on REST fallback being available — without it, cycles 5-6 fall out and the cadence drops to ~2 with the meta-fallback firing earlier." This preserves the original load-bearing point (REST fallback enables more pre-empts per window) while keeping the cadence baseline consistent with the rest of the anchor (3-4 with REST, ~2 without). Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: Claude <noreply@anthropic.com>

…t window (4 min before reset) under pure rate-zero tier — 2nd counter cycle this session (0020Z-0024Z) Specific edge case of substrate-pool-saturation: forced-#6 counter escalation lands when genuinely-substantive work (REST PR-creation post-reset) is single-digit minutes away. Rule discipline says escalate NOW; substantive work says wait 4 min for reset. This memo ships as forced-#6 substrate (composes with #4110 substrate-pool- saturation anchor; does NOT duplicate scope). Anti-fabrication check: names specific empirical shape not covered by existing rules; concrete tick-by-tick evidence (6 brief-acks 0020Z-0024Z); identifies rule-refinement question without recommending change. Single-anchor; rule-change threshold 2-3 sessions. Counter discipline: forced-#6 → concrete artifact ships (this memo) → counter resets. Post-rate-reset (0028Z, 4 min) handles 848bdcf Kestrel-preservation decompose-PR via REST PR-creation per rule #4107. Co-Authored-By: Claude <noreply@anthropic.com>

… + REST fallback pagination per_page=100 --paginate (PR #4109 threads)

…k failure (#4109) * docs(shadow): Maji antigravity check on Riven persistent REST fallback failure * fix(maji-riven-paralysis-log): add direct PR #4107/#4108 GitHub links + REST fallback pagination per_page=100 --paginate (PR #4109 threads)

…archive landed; PRs #4104/4100/4097 noted for follow-up (PR #4124 verify-before-fix)

* docs(shadow): decompose PR 4115 shadow drift log * fix(maji-2245-shadow-log): correct preservation claim — only PR #4107 archive landed; PRs #4104/4100/4097 noted for follow-up (PR #4124 verify-before-fix)

…t window (4 min before reset) under pure rate-zero tier — 2nd counter cycle this session (0020Z-0024Z) Specific edge case of substrate-pool-saturation: forced-#6 counter escalation lands when genuinely-substantive work (REST PR-creation post-reset) is single-digit minutes away. Rule discipline says escalate NOW; substantive work says wait 4 min for reset. This memo ships as forced-#6 substrate (composes with #4110 substrate-pool- saturation anchor; does NOT duplicate scope). Anti-fabrication check: names specific empirical shape not covered by existing rules; concrete tick-by-tick evidence (6 brief-acks 0020Z-0024Z); identifies rule-refinement question without recommending change. Single-anchor; rule-change threshold 2-3 sessions. Counter discipline: forced-#6 → concrete artifact ships (this memo) → counter resets. Post-rate-reset (0028Z, 4 min) handles 848bdcf Kestrel-preservation decompose-PR via REST PR-creation per rule #4107. Co-Authored-By: Claude <noreply@anthropic.com>

Copilot AI review requested due to automatic review settings May 17, 2026 22:06

Copilot started reviewing on behalf of AceHack May 17, 2026 22:07 View session

Copilot AI reviewed May 17, 2026

View reviewed changes

AceHack mentioned this pull request May 17, 2026

rules(holding): pre-empt-substrate-pool-saturation anchor (forced-#6 self-documenting) #4110

Merged

Copilot AI mentioned this pull request May 17, 2026

docs(shadow): Maji antigravity check on Riven persistent REST fallback failure #4109

Merged

AceHack merged commit 22b7383 into main May 17, 2026
30 checks passed

AceHack deleted the rule-anchor/rest-pr-create-pure-git-tier-fallback-2026-05-17-2203z branch May 17, 2026 22:21

AceHack mentioned this pull request May 17, 2026

shard+rules+memory(2207Z): autonomous-loop tick — pure-git tier, cross-session sentinel non-persistence anchor, Riven .sh shadow-catch #4112

Merged

3 tasks

This was referenced May 17, 2026

docs(shadow+archive): Maji antigravity drift check and preservation 2245Z #4115

Closed

docs(archive): Maji PR preservation batch (4116-4105) #4117

Merged

AceHack mentioned this pull request May 17, 2026

shard(2026-05-17/2300Z): multi-PR arc summary — 2207Z cold-boot to post-cycle-close saturation (3 PRs, 4 substrate landings, recursive forced-#6 chain) #4121

Merged

5 tasks

AceHack added a commit that referenced this pull request May 18, 2026

fix(maji-riven-paralysis-log): add direct PR #4107/#4108 GitHub links…

fe73d94

… + REST fallback pagination per_page=100 --paginate (PR #4109 threads)

AceHack added a commit that referenced this pull request May 18, 2026

fix(maji-2245-shadow-log): correct preservation claim — only PR #4107 …

7d4f176

…archive landed; PRs #4104/4100/4097 noted for follow-up (PR #4124 verify-before-fix)

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

rules(rate-limit-tier): REST PR-creation fallback under Pure-git tier (PR #4105 anchor)#4107

rules(rate-limit-tier): REST PR-creation fallback under Pure-git tier (PR #4105 anchor)#4107
AceHack merged 1 commit into
mainfrom
rule-anchor/rest-pr-create-pure-git-tier-fallback-2026-05-17-2203z

AceHack commented May 17, 2026

Uh oh!

Copilot AI left a comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Conversation

AceHack commented May 17, 2026

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants