Merge bugfix/rule-paths-absolute into develop

This commit is contained in:
bchanot committed 2026-10-31 14:50:59 +01:00
commit 5e8f4e51c5
8 files changed
+49 -10

No files matched your search

+1
View File
@@ -675,3 +675,4 @@ rules:
## 2026-10-31 ## 2026-10-31
- Phase 4a per-repo pass: 12 repos upgraded to v2 on chore/memory-v2 (game headings demoted, trucks bullet Indexes dropped + BLK-001 resolved, robin BLK-013/015 closures kept); BLK-038 found (upgrade cemented prose false-closed) → /bugfix 2dae528, 3 lenses + confirmation, verifier CONFORME 6/6, security PASS, real-data replay oracle over 13 repos; game/zq redone with user statuses. LRN-244, LRN-245. faunosteo prepared off-repo (V1-2 active). - Phase 4a per-repo pass: 12 repos upgraded to v2 on chore/memory-v2 (game headings demoted, trucks bullet Indexes dropped + BLK-001 resolved, robin BLK-013/015 closures kept); BLK-038 found (upgrade cemented prose false-closed) → /bugfix 2dae528, 3 lenses + confirmation, verifier CONFORME 6/6, security PASS, real-data replay oracle over 13 repos; game/zq redone with user statuses. LRN-244, LRN-245. faunosteo prepared off-repo (V1-2 active).
- Step 2 suites: /hotfix 40a993c (absolute ~/.claude/rules paths in interviewer + guardrails) + 7899670 (analyzer memory field dropped), security PASS x2. Measured design hook: 59 fires, 0 web-building Reads (no once-per-session). Probe: Bash sed -n loads path rules like Read. Census blind spots: 0 real citations.
+7 -5
View File
@@ -46,12 +46,14 @@ Shared rules for every phase:
- [x] **Phase 1, native context diet: no mod** (redesigned 2026-10-24, shrunk 2026-10-25: one carrier per section, existing files first) - [x] **Phase 1, native context diet: no mod** (redesigned 2026-10-24, shrunk 2026-10-25: one carrier per section, existing files first)
- Done 2026-10-29 on feature/context-diet (4bbb3c5..789a2b2): BDR-130, BDR-131, LRN-238..241, EVAL-053. `/context` 30.5k → 26.2k (own −2.8k). Verifier CONFORME 21/21, security PASS. Contract `.claude/tasks/contracts/2026-10-28-context-diet-1944.md` § PROOF. - Done 2026-10-29 on feature/context-diet (4bbb3c5..789a2b2): BDR-130, BDR-131, LRN-238..241, EVAL-053. `/context` 30.5k → 26.2k (own −2.8k). Verifier CONFORME 21/21, security PASS. Contract `.claude/tasks/contracts/2026-10-28-context-diet-1944.md` § PROOF.
- [ ] User step: delete the auto-memory leftovers by hand (`~/.claude/projects/-home-bchanot-Documents-{faunosteo,jeux-deploy,robin-petier}/memory/`); doctor warns until then. - [ ] User step: delete the auto-memory leftovers by hand (`~/.claude/projects/-home-bchanot-Documents-{faunosteo,jeux-deploy,robin-petier}/memory/`); doctor warns until then.
- [ ] Remove the dead `memory: project` field from agents/analyzer.md (auto memory off drops it, LRN-240). - [x] Remove the dead `memory: project` field from agents/analyzer.md (/hotfix 7899670, 2026-10-31).
- [ ] Deferred (gate 2026-10-29): "Skill routing" lines → our skills' `description:` (phase 3 bullet said phase 1 cleanup). - [ ] Deferred (gate 2026-10-29): "Skill routing" lines → our skills' `description:` (phase 3 bullet said phase 1 cleanup).
- [ ] Census blind spots: nested `lib/<dir>/x.md § Y`, templates/ and .claude/rules/ outside doctrine-citers. - [ ] Census blind spots: nested `lib/<dir>/x.md § Y`, templates/ and .claude/rules/ outside doctrine-citers. Measured 2026-10-31: 0 real citations in all three today (preventive).
- [ ] Measure the design hook's "Read … first" re-Read cost (instructions-loaded log) before adding "once per session". - [x] Measure the design hook's "Read … first" re-Read cost (2026-10-31, transcripts since 789a2b2): 59 hook fires, 0 Read-tool reads of web-building.md, 8 Bash mentions (repo maintenance). Re-read cost ≈ 0 → no "once per session" needed.
- [ ] Probe: path rules seen injected after a Bash `sed -n` read (final review M8): confirm Read-only semantics before a later phase relies on it. - [ ] Design hook false positives: the pointer is almost never followed, and it fires on non-design prompts (fired on the 2026-10-30 phase 4a memory-work prompt). Decide: tighten the trigger, or drop the hook now that web-building.md loads by path. User call, nothing coded.
- [ ] Minor: relative `rules/supabase.md` paths in interviewer.md / guardrails SKILL.md beside absolute ones; agent description losses ("dispatcher applies", "no dispatch", gate-in-dispatcher; security-auditor names no dispatcher). - [x] Probe Bash `sed -n` (2026-10-31, two `claude -p --model haiku` runs here, mods/model-router/.claude-plugin/plugin.json): Bash `sed -n` AND Read both log `path_glob_match` mods.md with that trigger file. Path rules load after a Bash read too; not isolated whether the harness or the rtk rewrite triggers it.
- [x] Minor: relative rule paths in interviewer.md / guardrails SKILL.md → `~/.claude/rules/` (/hotfix 40a993c).
- [ ] Agent description losses: user pick 2026-10-31 = restore "(dispatcher applies)" on geo-analyzer + seo-analyzer only; the rest closed (bodies keep it).
- [x] robin_petier `chore/memory-lan-server` (BDR-075): merged 2026-10-29 (6877443). - [x] robin_petier `chore/memory-lan-server` (BDR-075): merged 2026-10-29 (6877443).
- Facts 2026-10-24 (scratchpad pathtest, memtest): a `paths:` rule loads on Read of a matching file, NOT on Write of a new file; `"autoMemoryEnabled": false` removes the auto-memory system section; classic SessionStart / UserPromptSubmit hooks inject additionalContext; instruction files reload on compaction natively. `hooks/design-toolchain-reminder.sh` fired 2,131 times (16 to 210 per day); `brainstorming` is vendored and gitignored (.gitignore:78), an edit there does not persist. - Facts 2026-10-24 (scratchpad pathtest, memtest): a `paths:` rule loads on Read of a matching file, NOT on Write of a new file; `"autoMemoryEnabled": false` removes the auto-memory system section; classic SessionStart / UserPromptSubmit hooks inject additionalContext; instruction files reload on compaction natively. `hooks/design-toolchain-reminder.sh` fired 2,131 times (16 to 210 per day); `brainstorming` is vendored and gitignored (.gitignore:78), an edit there does not persist.
- Section → carrier: - Section → carrier:
@@ -0,0 +1,17 @@
# CONTRACT — analyzer-memory-field
## REQUEST (verbatim — IMMUTABLE)
Remove the dead `memory: project` field from agents/analyzer.md (auto memory off drops it, LRN-240).
## CLARIFICATIONS
none (hotfix autofill)
## ACCEPTANCE CRITERIA
1. Symptom gone: agents/analyzer.md frontmatter has no `memory:` line; the other frontmatter keys are unchanged.
CHECK: cd /home/bchanot/Documents/claude && ! sed -n '1,/^---$/{p}' agents/analyzer.md | sed -n '2,$p' | grep -q '^memory:' && [ "$(sed -n '2,6p' agents/analyzer.md | cut -d: -f1 | tr '\n' ' ')" = "name description tools model effort " ] && echo FIELD-OK
EXPECT: FIELD-OK
EVIDENCE: pending
2. Build/tests green: agent frontmatter suites pass.
## FILE SCOPE
- agents/analyzer.md
@@ -0,0 +1,18 @@
# CONTRACT — rule-paths-absolute
## REQUEST (verbatim — IMMUTABLE)
Two relative rule paths beside absolute ones: agents/interviewer.md:27 and skills/guardrails/SKILL.md:10-11 cite `rules/secure-by-default.md`, `rules/supabase.md`, `rules/cloud-functions.md`, `rules/a11y.md` while the same files use `~/.claude/lib/…` absolute paths; a reader in a project repo resolves `rules/` against that project. Make them `~/.claude/rules/<name>.md` (TODO phase 1 minor).
## CLARIFICATIONS
none (hotfix autofill)
## ACCEPTANCE CRITERIA
1. Symptom gone: no bare `rules/<name>.md` path left in the two files; each now reads `~/.claude/rules/<name>.md`.
CHECK: cd /home/bchanot/Documents/claude && ! grep -nE '(^|[^/~.a-z])rules/[a-z0-9-]+\.md' agents/interviewer.md skills/guardrails/SKILL.md && grep -q '~/.claude/rules/supabase.md' agents/interviewer.md && grep -q '~/.claude/rules/supabase.md' skills/guardrails/SKILL.md && echo PATHS-OK
EXPECT: PATHS-OK
EVIDENCE: pending
2. Build/tests green: `make test` suites touching these files (routing, citers) pass.
## FILE SCOPE
- agents/interviewer.md
- skills/guardrails/SKILL.md
+1
View File
@@ -51,6 +51,7 @@ Format follows [Keep a Changelog](https://keepachangelog.com/) and this project
- The five `effort-low` … `effort-max` skills, `lib/effort-pins.txt`, `lib/effort-pins.sh` and `lib/model-check.sh`, with their tests and the effort-pin re-apply steps of `install-plugins.sh` and `update-all.sh`. The model-router rows replace them. A typed `/effort-<level>` no longer exists: use `ultrathink` or `/route effort=max`. Breaking: the next release is 3.0.0. - The five `effort-low` … `effort-max` skills, `lib/effort-pins.txt`, `lib/effort-pins.sh` and `lib/model-check.sh`, with their tests and the effort-pin re-apply steps of `install-plugins.sh` and `update-all.sh`. The model-router rows replace them. A typed `/effort-<level>` no longer exists: use `ultrathink` or `/route effort=max`. Breaking: the next release is 3.0.0.
### Fixed ### Fixed
- `/guardrails` and the interviewer cite the secure-by-default, Supabase, cloud-function and a11y rules by their absolute `~/.claude/rules/<name>.md` path; run from a project repo, the bare `rules/<name>.md` path resolved against that project and missed the rule files.
- `/reconcile` no longer reports a v2 blocker as open because a status word appears in its title or prose (BLK-032..034). - `/reconcile` no longer reports a v2 blocker as open because a status word appears in its title or prose (BLK-032..034).
- model-router probes the model main is about to run on, moved to or kept (the session's own model included), before routing main to it: with a model out of usage credits, every new session and hold lapse used to route main there, or keep it there, and lose the turn to a 429. That model is tried once with a small completion bounded to 8 s; a timeout or error marks it down (reason `probe`) and the decision is taken again once. A model that answered is not probed again until marked down (kept across `/clear`). `"probe": false` in `~/.claude/model-router.json` turns it off; `/route show` prints `probe:`. When a lower model stands in for its tier's held head, the phase's own effort goes one notch up (reflect xhigh, plan max, orchestrate high on Opus); explicit and floor efforts are never raised. Tests: `mods/model-router/hooks/register.test.ts`. - model-router probes the model main is about to run on, moved to or kept (the session's own model included), before routing main to it: with a model out of usage credits, every new session and hold lapse used to route main there, or keep it there, and lose the turn to a 429. That model is tried once with a small completion bounded to 8 s; a timeout or error marks it down (reason `probe`) and the decision is taken again once. A model that answered is not probed again until marked down (kept across `/clear`). `"probe": false` in `~/.claude/model-router.json` turns it off; `/route show` prints `probe:`. When a lower model stands in for its tier's held head, the phase's own effort goes one notch up (reflect xhigh, plan max, orchestrate high on Opus); explicit and floor efforts are never raised. Tests: `mods/model-router/hooks/register.test.ts`.
- model-router residuals of waves 1-4 (2026-10-11): the kill switch fails closed (a `~/.claude/model-router.json` present but unreadable at first load, or an `enabled` that is not a boolean, turns the router off and says so; `/route reload` answers `config unreadable; previous config kept` instead of `config reloaded`); a prompt rule whose pattern nests quantifiers (`(a+)+$`) is dropped; a config file that is not a regular file reads as failed; every log of a caught error prints its kind and code only, never the message (a JSON parse error quotes the file); rejected table keys are masked in logs and model alias keys must be short printable names; `__proto__`, `constructor` and `prototype` are never read or written as keys; the agent offers map is capped like the descriptions; a `models` alias added without a `fallback` list is ranked at the end of the default chain (the upgrade gates now apply to it); a dated or variant id maps to its table id only at a `-` boundary (`claude-sonnet-5-50` no longer reads as sonnet); the status refresh and the main-decision log on the step path can no longer unroute a step; the route tool's failure answer says the route may be partly applied. `lib/tests/mods.test.sh` proves `claude plugin test` exists from its usage line (an unknown subcommand exits 0), `doctor.sh` bounds `claude plugin list --json` to 60 s, `update-all.sh` skips `@skills-dir` mods. Kit 428 → 431. - model-router residuals of waves 1-4 (2026-10-11): the kill switch fails closed (a `~/.claude/model-router.json` present but unreadable at first load, or an `enabled` that is not a boolean, turns the router off and says so; `/route reload` answers `config unreadable; previous config kept` instead of `config reloaded`); a prompt rule whose pattern nests quantifiers (`(a+)+$`) is dropped; a config file that is not a regular file reads as failed; every log of a caught error prints its kind and code only, never the message (a JSON parse error quotes the file); rejected table keys are masked in logs and model alias keys must be short printable names; `__proto__`, `constructor` and `prototype` are never read or written as keys; the agent offers map is capped like the descriptions; a `models` alias added without a `fallback` list is ranked at the end of the default chain (the upgrade gates now apply to it); a dated or variant id maps to its table id only at a `-` boundary (`claude-sonnet-5-50` no longer reads as sonnet); the status refresh and the main-decision log on the step path can no longer unroute a step; the route tool's failure answer says the route may be partly applied. `lib/tests/mods.test.sh` proves `claude plugin test` exists from its usage line (an unknown subcommand exits 0), `doctor.sh` bounds `claude plugin list --json` to 60 s, `update-all.sh` skips `@skills-dir` mods. Kit 428 → 431.
-1
View File
@@ -4,7 +4,6 @@ description: Analyze code, codebase, or problem before any modification. Produce
tools: Read, Grep, Glob, Bash tools: Read, Grep, Glob, Bash
model: opus model: opus
effort: xhigh effort: xhigh
memory: project
--- ---
# ANALYZER # ANALYZER
+1 -1
View File
@@ -24,7 +24,7 @@ Gather context. Produce complete PROJECT BRIEF as single source of truth.
| "I don't know / you decide" | Propose ONE concrete default + why, ask yes/no | Take the default, mark `(assumed)`, list in OPEN DECISIONS | | "I don't know / you decide" | Propose ONE concrete default + why, ask yes/no | Take the default, mark `(assumed)`, list in OPEN DECISIONS |
| Contradictory answers (e.g. embedded runtime + managed cloud DB) | Name the contradiction, ask which side wins | Put BOTH options in OPEN DECISIONS; do not silently pick one | | Contradictory answers (e.g. embedded runtime + managed cloud DB) | Name the contradiction, ask which side wins | Put BOTH options in OPEN DECISIONS; do not silently pick one |
| Language not stated (new project / from scratch / whole-project rewrite) | Propose Rust + why (`~/.claude/lib/architecture-defaults.md` § Default language); name the contraindication if another language fits better (browser frontend, mandated platform, missing ecosystem) | Rust, marked `(assumed)`, listed in OPEN DECISIONS | | Language not stated (new project / from scratch / whole-project rewrite) | Propose Rust + why (`~/.claude/lib/architecture-defaults.md` § Default language); name the contraindication if another language fits better (browser frontend, mandated platform, missing ecosystem) | Rust, marked `(assumed)`, listed in OPEN DECISIONS |
| Project has an API, a database, messaging, cloud functions or a UI | Apply `rules/secure-by-default.md` (Supabase and cloud-function detail: `rules/supabase.md`, `rules/cloud-functions.md`): note under QUALITY which of the six guardrail domains apply, and whether the accessibility baseline (`rules/a11y.md`) applies, and list each dashboard-only item (spend cap, WAF, budget alert) in OPEN DECISIONS as manual | A domain applies and nothing is planned: list it in OPEN DECISIONS, never drop it silently | | Project has an API, a database, messaging, cloud functions or a UI | Apply `~/.claude/rules/secure-by-default.md` (Supabase and cloud-function detail: `~/.claude/rules/supabase.md`, `~/.claude/rules/cloud-functions.md`): note under QUALITY which of the six guardrail domains apply, and whether the accessibility baseline (`~/.claude/rules/a11y.md`) applies, and list each dashboard-only item (spend cap, WAF, budget alert) in OPEN DECISIONS as manual | A domain applies and nothing is planned: list it in OPEN DECISIONS, never drop it silently |
| Partial answer to the block | Re-ask ONLY the missing items in the follow-up round | Missing fields → `none stated` + OPEN DECISIONS entry | | Partial answer to the block | Re-ask ONLY the missing items in the follow-up round | Missing fields → `none stated` + OPEN DECISIONS entry |
| Feature list balloons (>10) | Keep the 10 the user ranks first as V1 | Overflow goes to OUT OF SCOPE with a `(deferred by budget)` tag | | Feature list balloons (>10) | Keep the 10 the user ranks first as V1 | Overflow goes to OUT OF SCOPE with a `(deferred by budget)` tag |
+4 -3
View File
@@ -7,9 +7,10 @@ argument-hint: '[project path] [--domain api,hosting,supabase,messaging,function
# /guardrails # /guardrails
Checks a project against `rules/secure-by-default.md` (domains 4 and 6 in Checks a project against `~/.claude/rules/secure-by-default.md` (domains
full: `rules/supabase.md`, `rules/cloud-functions.md`), then fixes what the 4 and 6 in full: `~/.claude/rules/supabase.md`,
user accepts and proves each fix. A scanner reads the tree as data and finds `~/.claude/rules/cloud-functions.md`), then fixes what the user accepts
and proves each fix. A scanner reads the tree as data and finds
what text can prove. This skill judges the hits, covers what text cannot what text can prove. This skill judges the hits, covers what text cannot
prove, lists what only a dashboard can set and, on request, probes a running prove, lists what only a dashboard can set and, on request, probes a running
target the user owns. It then proposes fixes, applies the accepted ones and target the user owns. It then proposes fixes, applies the accepted ones and