CalvinBackup/gstack
1
0 Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-11-05 08:23:59 +01:00
Code Issues Packages Projects Releases Wiki Activity

test: re-pin size, context and carve guards for the GSTA-134 skill diets

Browse Source 
Every pin moves down except office-hours' parity maxSizeRatio (1.1796 ->
1.1921, GStack Minder's call as merge-queue owner): its union grew 1,662 B
because the second-opinion question now sits in the skeleton while the
untouched CODEX_SECOND_OPINION resolver keeps its own copy. design-review
leaves the size allowlist on every host.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
This commit is contained in:
garrytanandcapy-ai[bot] committed 2026-10-28 01:16:07 +00:00
1 parent b0fba22f6c
commit 6087befea2
3 files changed
+17 -32
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

test/fixtures/context-budget.json
Vendored
+3 -3
View File
@@ -18,7 +18,7 @@
"design-consultation": 10513,
"design-html": 8896,
"design-motion": 4724,
"design-review": 30295,
"design-review": 22175,
"design-shotgun": 9318,
"deslop-shared-libs": 3411,
"devex-review": 15303,
@@ -42,7 +42,7 @@
"learn": 2931,
"make-pdf": 5204,
"modernize": 3772,
"office-hours": 19139,
"office-hours": 11467,
"open-gstack-browser": 4872,
"openclaw/skills/gstack-openclaw-ceo-review": 2764,
"openclaw/skills/gstack-openclaw-investigate": 1429,
@@ -50,7 +50,7 @@
"openclaw/skills/gstack-openclaw-retro": 2542,
"pair-agent": 5293,
"plan-ceo-review": 15776,
"plan-design-review": 17262,
"plan-design-review": 14687,
"plan-devex-review": 12215,
"plan-eng-review": 11369,
"plan-tune": 9215,
test/fixtures/skill-md-size-allowlist.json
Vendored
+8 -23
View File
@@ -3,65 +3,50 @@
"limit": 100000,
"pins": {
"agy/gstack-autoplan": 109810,
"agy/gstack-design-review": 123527,
"agy/gstack-plan-design-review": 121890,
"agy/gstack-plan-design-review": 110044,
"agy/gstack-plan-devex-review": 116496,
"agy/gstack-plan-eng-review": 147241,
"agy/gstack-review": 103755,
"claude/design-review": 115449,
"codex/gstack-autoplan": 108553,
"codex/gstack-design-review": 123646,
"codex/gstack-land-and-deploy": 100284,
"codex/gstack-plan-design-review": 122962,
"codex/gstack-plan-design-review": 111116,
"codex/gstack-plan-devex-review": 118004,
"codex/gstack-plan-eng-review": 148406,
"codex/gstack-review": 103278,
"copilot/gstack-autoplan": 109253,
"copilot/gstack-design-review": 123142,
"copilot/gstack-plan-design-review": 122201,
"copilot/gstack-plan-design-review": 110355,
"copilot/gstack-plan-devex-review": 115958,
"copilot/gstack-plan-eng-review": 147406,
"copilot/gstack-review": 103336,
"cursor/gstack-autoplan": 108485,
"cursor/gstack-design-review": 122407,
"cursor/gstack-plan-design-review": 120746,
"cursor/gstack-plan-design-review": 108900,
"cursor/gstack-plan-devex-review": 115228,
"cursor/gstack-plan-eng-review": 145996,
"cursor/gstack-review": 121628,
"factory/gstack-autoplan": 110763,
"factory/gstack-design-review": 124191,
"factory/gstack-land-and-deploy": 100105,
"factory/gstack-plan-design-review": 123521,
"factory/gstack-plan-design-review": 111675,
"factory/gstack-plan-devex-review": 118591,
"factory/gstack-plan-eng-review": 149104,
"factory/gstack-review": 125401,
"gbrain/gstack-autoplan": 108892,
"gbrain/gstack-design-review": 112612,
"gbrain/gstack-plan-design-review": 109503,
"gbrain/gstack-plan-eng-review": 128623,
"hermes/gstack-autoplan": 108982,
"hermes/gstack-design-review": 112719,
"hermes/gstack-plan-design-review": 109612,
"hermes/gstack-plan-eng-review": 128708,
"kiro/gstack-autoplan": 108259,
"kiro/gstack-design-review": 122233,
"kiro/gstack-plan-design-review": 120598,
"kiro/gstack-plan-design-review": 108752,
"kiro/gstack-plan-devex-review": 115080,
"kiro/gstack-plan-eng-review": 145858,
"kiro/gstack-review": 121452,
"openclaw/gstack-autoplan": 108715,
"openclaw/gstack-design-review": 111535,
"openclaw/gstack-plan-design-review": 108472,
"openclaw/gstack-plan-eng-review": 127138,
"opencode/gstack-autoplan": 109234,
"opencode/gstack-design-review": 122992,
"opencode/gstack-plan-design-review": 122033,
"opencode/gstack-plan-design-review": 110187,
"opencode/gstack-plan-devex-review": 115836,
"opencode/gstack-plan-eng-review": 147265,
"opencode/gstack-review": 122250,
"slate/gstack-autoplan": 108372,
"slate/gstack-design-review": 122320,
"slate/gstack-plan-design-review": 120672,
"slate/gstack-plan-design-review": 108826,
"slate/gstack-plan-devex-review": 115154,
"slate/gstack-plan-eng-review": 145927,
"slate/gstack-review": 121540
test/helpers/carve-guards.ts
+6 -6
View File
@@ -245,7 +245,7 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
// tier-2+ skeleton (measured 89,184). Main's v1.64.0.0 adds ~340 B more
// (telemetry --error-message/--failed-step preamble prose, PR #769).
// Budget covers the sum of both waves.
maxSkeletonBytes: 66_644, // GSTA-96 hoist (2026-10-26): lowered from 85_900 by the shared preamble that moved to sections/preamble.md, keeping the pre-hoist headroom of 581 bytes; measured 66,063. Before: Harness-aware outside voice: validated dispatch and provenance. + v1.91.19.0 wave: design --version probe (B4) and verdict-form outside voice (INV-1) on top of v1.91.17.0's round accounting (#3022); measured 80,443 (2026-10-03). + Oct 6 fix wave A3/CEO-12: free text reaches commands only through agent-written mktemp files (mktemp block, write rule, path rebuild and refusal at each posting, prompt and brief site); skeleton measured 84,669 (2026-10-06). + Oct 7 wave B3: the Codex probe runs as a command (select-model capture lines, check-sandbox/probe-model/run-with-timeout subcommands) instead of being sourced; skeleton measured 84,804 (2026-10-07). + Oct 7 wave CEO-28/DX-11: review prompts ask for a severity per finding and design proposals use the proposal gate; skeleton measured 84,863 (2026-10-07). + Oct 7 wave guard (CEO-20): conditional `run_in_background` request plus the background-run recovery at each foreground dispatch site; skeleton measured 84,748 (2026-10-07). Merged with the guard area: measured skeleton 84,945 (2026-10-07). + Honest Work wave merged (W2/W3 gate integrity in review/ship, W4 kernel + DONE line in every tier-2+ skill, W5/W7 in spec/ship): re-measured on the integrated tree (2026-10-10).
maxSkeletonBytes: 56_209, // GSTA-134 skill diet (2026-10-28): lowered from 66_644 to the measured dieted skeleton, 56,209. Before: GSTA-96 hoist (2026-10-26): lowered from 85_900 by the shared preamble that moved to sections/preamble.md, keeping the pre-hoist headroom of 581 bytes; measured 66,063. Before: Harness-aware outside voice: validated dispatch and provenance. + v1.91.19.0 wave: design --version probe (B4) and verdict-form outside voice (INV-1) on top of v1.91.17.0's round accounting (#3022); measured 80,443 (2026-10-03). + Oct 6 fix wave A3/CEO-12: free text reaches commands only through agent-written mktemp files (mktemp block, write rule, path rebuild and refusal at each posting, prompt and brief site); skeleton measured 84,669 (2026-10-06). + Oct 7 wave B3: the Codex probe runs as a command (select-model capture lines, check-sandbox/probe-model/run-with-timeout subcommands) instead of being sourced; skeleton measured 84,804 (2026-10-07). + Oct 7 wave CEO-28/DX-11: review prompts ask for a severity per finding and design proposals use the proposal gate; skeleton measured 84,863 (2026-10-07). + Oct 7 wave guard (CEO-20): conditional `run_in_background` request plus the background-run recovery at each foreground dispatch site; skeleton measured 84,748 (2026-10-07). Merged with the guard area: measured skeleton 84,945 (2026-10-07). + Honest Work wave merged (W2/W3 gate integrity in review/ship, W4 kernel + DONE line in every tier-2+ skill, W5/W7 in spec/ship): re-measured on the integrated tree (2026-10-10).
minUnionBytes: 99_200, // token-reduction Phases 1-2 (v1.69.x branch); measured union 110,293
mustContain: ['design', 'visual'],
maxSizeRatio: 1.12, // D1 1.104 + main's ~0.008
@@ -350,10 +350,10 @@ do not launch the downstream skill or open a browser.`,
// the #538 opt-out + D1 evidence directive — ratio 1.104 measured.
// #2499 project-scope MCP jq in the brain-sync block grew every tier-2+
// skeleton ~1.5KB (entry resolution emitted once per SKILL.md).
maxSkeletonBytes: 80_533, // GSTA-96 hoist (2026-10-26): lowered from 95_900 by the shared preamble that moved to sections/preamble.md, keeping the pre-hoist headroom of 952 bytes; measured 79,581. Before: Office-hours + sketch outside voices include host guards and completion checks. + v1.91.19.0 wave: Q<N> open-question prose form (#2729, approved Q3), DESIGN_READY --version probe (B4), Aside ~/.local/bin fallback (E7), verdict-form outside voice (INV-1), plus v1.91.17.0's round accounting (#3022) merged in; measured 89,684 (2026-10-03). + Oct 6 fix wave A3/CEO-12: free text reaches commands only through agent-written mktemp files (mktemp block, write rule, path rebuild and refusal at each posting, prompt and brief site); skeleton measured 92,590 (2026-10-06). + Oct 7 wave B3: the Codex probe runs as a command (select-model capture lines, check-sandbox/probe-model/run-with-timeout subcommands) instead of being sourced; skeleton measured 92,869 (2026-10-07). + Oct 7 wave CEO-28/DX-11: review prompts ask for a severity per finding and design proposals use the proposal gate; skeleton measured 92,930 (2026-10-07). + Oct 7 wave guard (CEO-20): conditional `run_in_background` request plus the background-run recovery at each foreground dispatch site; skeleton measured 92,756 (2026-10-07). Merged with the guard area: measured skeleton 93,099 (2026-10-07). + fix wave PR D: the Phase 4.5 builder-profile read before the session log (#2801) and the pre-telemetry design-doc check (#1049); measured skeleton 94,877 (2026-10-07). + Honest Work wave merged (W2/W3 gate integrity in review/ship, W4 kernel + DONE line in every tier-2+ skill, W5/W7 in spec/ship): re-measured on the integrated tree (2026-10-10).
maxSkeletonBytes: 43_885, // GSTA-134 skill diet (2026-10-28): lowered from 80_533 to the measured skeleton after the second opinion and visual design moved to sections, 43,885. Before: GSTA-96 hoist (2026-10-26): lowered from 95_900 by the shared preamble that moved to sections/preamble.md, keeping the pre-hoist headroom of 952 bytes; measured 79,581. Before: Office-hours + sketch outside voices include host guards and completion checks. + v1.91.19.0 wave: Q<N> open-question prose form (#2729, approved Q3), DESIGN_READY --version probe (B4), Aside ~/.local/bin fallback (E7), verdict-form outside voice (INV-1), plus v1.91.17.0's round accounting (#3022) merged in; measured 89,684 (2026-10-03). + Oct 6 fix wave A3/CEO-12: free text reaches commands only through agent-written mktemp files (mktemp block, write rule, path rebuild and refusal at each posting, prompt and brief site); skeleton measured 92,590 (2026-10-06). + Oct 7 wave B3: the Codex probe runs as a command (select-model capture lines, check-sandbox/probe-model/run-with-timeout subcommands) instead of being sourced; skeleton measured 92,869 (2026-10-07). + Oct 7 wave CEO-28/DX-11: review prompts ask for a severity per finding and design proposals use the proposal gate; skeleton measured 92,930 (2026-10-07). + Oct 7 wave guard (CEO-20): conditional `run_in_background` request plus the background-run recovery at each foreground dispatch site; skeleton measured 92,756 (2026-10-07). Merged with the guard area: measured skeleton 93,099 (2026-10-07). + fix wave PR D: the Phase 4.5 builder-profile read before the session log (#2801) and the pre-telemetry design-doc check (#1049); measured skeleton 94,877 (2026-10-07). + Honest Work wave merged (W2/W3 gate integrity in review/ship, W4 kernel + DONE line in every tier-2+ skill, W5/W7 in spec/ship): re-measured on the integrated tree (2026-10-10).
minUnionBytes: 115_800, // Phase 4 wave 4; measured union 118,175
mustContain: ['design doc', 'problem statement'],
maxSizeRatio: 1.1796, // + Oct 6 fix wave A3/CEO-12: free text reaches commands only through agent-written mktemp files (mktemp block, write rule, path rebuild and refusal at each posting, prompt and brief site); measured 149,758 / 131,110 = 1.1422 (2026-10-06). + Oct 7 wave B3: the Codex probe runs as a command (select-model capture lines, check-sandbox/probe-model/run-with-timeout subcommands) instead of being sourced; measured 150,037 / 131,110 = 1.1444 (2026-10-07). + Oct 7 wave CEO-28/DX-11: review prompts ask for a severity per finding and design proposals use the proposal gate; measured 150,098 / 131,110 = 1.1448 (2026-10-07). + Oct 7 wave guard (CEO-20): conditional `run_in_background` request plus the background-run recovery at each foreground dispatch site; measured 150,011 / 131,110 = 1.1442 (2026-10-07). Merged with the guard area: measured 150,354 / 131,110 = 1.1468 (2026-10-07). + fix wave PR D: builder-profile read before the session log with Phase 6 using the carried values (#2801), the inline design doc before approval (#879) and the pre-telemetry design-doc check (#1049); measured 153,206 / 131,110 = 1.1685 (2026-10-07). + empty LAST_ASSIGNMENT/LAST_PROJECT guards in the welcome_back and regular greetings (backfilled profiles); measured 153,469 / 131,110 = 1.1705 (2026-10-08). + Honest Work wave merged (W2/W3 gate integrity in review/ship, W4 kernel + DONE line in every tier-2+ skill, W5/W7 in spec/ship): re-measured on the integrated tree (2026-10-10). + GSTA-96 shared-preamble hoist (owner-approved raise, Garry 2026-10-25: "do it"): the union now holds sections/preamble.md, so a fresh invocation reads the pointer plus the shared file and its own copies of shared sections; measured 160,989 / 131,110 = 1.2279 (2026-10-25). Before: 1.18. - GSTA-96 dedupe: the Q<N> open-question form is office-hours' own appended subsection, so its copies of the shared Format and fallback subsections go; measured 154,653 / 131,110 = 1.1796 (2026-10-26), 154,624 = 1.1793 after the main merge. Before: 1.2279.
maxSizeRatio: 1.1921, // GSTA-134 (2026-10-28, raised from 1.1796 by GStack Minder as merge-queue owner): +1,662 B union: second-opinion question moved into the main file while CODEX_SECOND_OPINION keeps its copy; per-run load 73,248→43,885 B; measured 156,286 / 131,110 = 1.19202, rounded up. Before: + Oct 6 fix wave A3/CEO-12: free text reaches commands only through agent-written mktemp files (mktemp block, write rule, path rebuild and refusal at each posting, prompt and brief site); measured 149,758 / 131,110 = 1.1422 (2026-10-06). + Oct 7 wave B3: the Codex probe runs as a command (select-model capture lines, check-sandbox/probe-model/run-with-timeout subcommands) instead of being sourced; measured 150,037 / 131,110 = 1.1444 (2026-10-07). + Oct 7 wave CEO-28/DX-11: review prompts ask for a severity per finding and design proposals use the proposal gate; measured 150,098 / 131,110 = 1.1448 (2026-10-07). + Oct 7 wave guard (CEO-20): conditional `run_in_background` request plus the background-run recovery at each foreground dispatch site; measured 150,011 / 131,110 = 1.1442 (2026-10-07). Merged with the guard area: measured 150,354 / 131,110 = 1.1468 (2026-10-07). + fix wave PR D: builder-profile read before the session log with Phase 6 using the carried values (#2801), the inline design doc before approval (#879) and the pre-telemetry design-doc check (#1049); measured 153,206 / 131,110 = 1.1685 (2026-10-07). + empty LAST_ASSIGNMENT/LAST_PROJECT guards in the welcome_back and regular greetings (backfilled profiles); measured 153,469 / 131,110 = 1.1705 (2026-10-08). + Honest Work wave merged (W2/W3 gate integrity in review/ship, W4 kernel + DONE line in every tier-2+ skill, W5/W7 in spec/ship): re-measured on the integrated tree (2026-10-10). + GSTA-96 shared-preamble hoist (owner-approved raise, Garry 2026-10-25: "do it"): the union now holds sections/preamble.md, so a fresh invocation reads the pointer plus the shared file and its own copies of shared sections; measured 160,989 / 131,110 = 1.2279 (2026-10-25). Before: 1.18. - GSTA-96 dedupe: the Q<N> open-question form is office-hours' own appended subsection, so its copies of the shared Format and fallback subsections go; measured 154,653 / 131,110 = 1.1796 (2026-10-26), 154,624 = 1.1793 after the main merge. Before: 1.2279.
},
'document-release': {
skill: 'document-release',
@@ -751,10 +751,10 @@ do not launch the downstream skill or open a browser.`,
// No section-loading paid case yet: a new periodic case would push the
// periodic census past its 38-slice cap (test/paid-retry-supervision.test.ts).
behavioral: 'none',
maxSkeletonBytes: 115_947, // GSTA-96 hoist merged with v1.91.274.0 (#3507, 2026-10-27): the hoisted skeleton plus main's headroom of 0 bytes; measured 115,947 on the merged tree. Before: measured 137735 on the merged tree with main f27a760 (2026-10-27, #3507); 137767 (2026-10-26; 137773 on 2026-10-25 before the shorter craft-audit trigger): the Section index the external-host carve test requires, its craft-audit row, and the STOP pointer (GSTA-92; Garry 2026-10-25 'Do it' (GSTA-92)).
minUnionBytes: 143_300, // measured union 144802 on the merged tree with main f27a760 (2026-10-27, #3507); 145037 (2026-10-26)
maxSkeletonBytes: 84_869, // GSTA-134 skill diet (2026-10-28): lowered from 115_947 to the measured skeleton after the outside voices and test bootstrap moved to sections, 84,869. Before: GSTA-96 hoist merged with v1.91.274.0 (#3507, 2026-10-27): the hoisted skeleton plus main's headroom of 0 bytes; measured 115,947 on the merged tree. Before: measured 137735 on the merged tree with main f27a760 (2026-10-27, #3507); 137767 (2026-10-26; 137773 on 2026-10-25 before the shorter craft-audit trigger): the Section index the external-host carve test requires, its craft-audit row, and the STOP pointer (GSTA-92; Garry 2026-10-25 'Do it' (GSTA-92)).
minUnionBytes: 136_100, // GSTA-134 skill diet (2026-10-28): measured union 137,602 (lowered from 143_300); before: measured union 144802 on the merged tree with main f27a760 (2026-10-27, #3507); 145037 (2026-10-26)
mustContain: ['AI Slop Detection', 'Fix Loop', 'gstack-design-lint', 'Proof beside each claim', 'holds session data'],
maxSizeRatio: 1.3739, // GSTA-96 hoist merged with v1.91.274.0 (#3507, 2026-10-27): the union now holds sections/preamble.md (the hoist's owner-approved raise, decision A) on top of main's 1.3681; measured 145,410 / 105,842 = 1.3739 on the merged tree. Before: first parity guard for design-review: measured 144802 / 105,842 = 1.3681 on the merged tree with main f27a760 (2026-10-27, #3507: the design lint swap); before that 145082 / 105,842 = 1.3708 (2026-10-25; 145077 after the /ship review fixes, 145068 = 1.3707 after the line-13 reword, 145049 = 1.3705 after the post-merge /ship review, 145037 = 1.3704 after its second pass, 2026-10-26), the skeleton's growth since v1.64.1.0 plus the craft audit (Garry 2026-10-25 'Do it' (GSTA-92)).
maxSizeRatio: 1.3001, // GSTA-134 skill diet (2026-10-28): measured 137,602 / 105,842 = 1.30007, rounded up (lowered from 1.3739). Before: GSTA-96 hoist merged with v1.91.274.0 (#3507, 2026-10-27): the union now holds sections/preamble.md (the hoist's owner-approved raise, decision A) on top of main's 1.3681; measured 145,410 / 105,842 = 1.3739 on the merged tree. Before: first parity guard for design-review: measured 144802 / 105,842 = 1.3681 on the merged tree with main f27a760 (2026-10-27, #3507: the design lint swap); before that 145082 / 105,842 = 1.3708 (2026-10-25; 145077 after the /ship review fixes, 145068 = 1.3707 after the line-13 reword, 145049 = 1.3705 after the post-merge /ship review, 145037 = 1.3704 after its second pass, 2026-10-26), the skeleton's growth since v1.64.1.0 plus the craft audit (Garry 2026-10-25 'Do it' (GSTA-92)).
},
// ── Token-reduction Phase 4 wave 4 (v1.69.x branch): design doctrine carve ──