devrites 3.2.26 → 3.2.27

package/CHANGELOG.md

@@ -2,6 +2,12 @@
 
 All notable changes to DevRites are documented here. The format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/) and DevRites adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). Releases are generated automatically by [semantic-release](https://semantic-release.gitbook.io/) from Conventional Commits on `main`.
 
+## [3.2.27](https://github.com/ViktorsBaikers/DevRites/compare/v3.2.26...v3.2.27) (2026-07-29)
+
+### Fixed
+
+* **rite:** separate recovery causes from symptoms ([c01f516](https://github.com/ViktorsBaikers/DevRites/commit/c01f5164ce349e5caad6ce450cfa6d76c7ce522b))
+
 ## [3.2.26](https://github.com/ViktorsBaikers/DevRites/compare/v3.2.25...v3.2.26) (2026-07-29)
 
 ### Fixed

package/README.md

@@ -25,7 +25,7 @@ final commit, push, and tag, and it requires a typed `GO` confirmation.
 Unattended runs may create local WIP checkpoint commits along the way, but only
 Ship collapses and pushes them.
 
-**Status:** [`v3.2.26`](https://github.com/ViktorsBaikers/DevRites/releases/tag/v3.2.26): see [`CHANGELOG.md`](CHANGELOG.md) for release notes.
+**Status:** [`v3.2.27`](https://github.com/ViktorsBaikers/DevRites/releases/tag/v3.2.27): see [`CHANGELOG.md`](CHANGELOG.md) for release notes.
 
 ## Quick start
 

package/pack/.claude/skills/devrites-debug-recovery/reference/cleanup-and-classify.md

@@ -2,8 +2,10 @@
 
 ## Classify one causal fingerprint
 
-Use one class per normalized root cause. A class changes only when new evidence changes
-the diagnosis:
+Fingerprint the causal diagnosis, never the failing test or symptom. Reuse it while
+plausible. If a discriminating fix proves the cause absent but the symptom remains,
+preserve that diagnosis as a dead end and classify a new fingerprint. Failure alone
+never resets a budget.
 
 - `intent_gap`: desired behavior, scope, policy, or risk choice is unsettled.
 - `spec_gap`: an acceptance outcome or product decision is missing.
@@ -20,11 +22,9 @@ Ask the engine for the canonical owner and action:
 devrites-engine recovery route <class>
 ```
 
-Follow the `recovery-route/v1` result. `humanPause: true` routes an unresolved intent or
-spec choice through Clarify. Technical routes stay agent-owned: repair the implementation
-or proof tool, normalize the environment, or repair the plan without asking permission to
-retry. A credential, external quota, irreversible action, or user-owned process that only
-the human can handle gets an exact human-intervention gate; it is not retry authorization.
+Follow `recovery-route/v1`. `humanPause: true` routes unresolved intent/spec through
+Clarify. Technical routes stay agent-owned. Gate only an exact human credential, quota,
+irreversible action, or user-owned process—never retry authorization.
 
 Record the class with every new failed attempt and green clear:
 

package/pack/.claude/skills/rite-plan/reference/replan-and-repair.md

@@ -33,9 +33,9 @@ errors: `devrites-api-interface`), then split into a backend slice (can land wit
 stub consumer) and a frontend slice (can land against a mock/real contract).
 
 ## unblock
-A `/rite-prove` failure can't be fixed inside the current slice. Capture the blocker in
-`state.md`, decide: route around it (reorder), shrink the slice (reslice), or escalate
-to the user (if it changes scope). Don't loop on the same failing approach.
+An exhausted fingerprint blocks diagnosis, not symptom. Route around/reslice; escalate
+only for scope change. If proof removed that cause but symptom remains, keep the dead
+end and plan a new diagnosis/proof fingerprint. Never clear/reuse old one.
 
 ## Always
 Update `state.md` (phase, next step) and append a dated line to `decisions.md`

package/pack/generated/claude/skills/devrites-debug-recovery/reference/cleanup-and-classify.md

@@ -2,8 +2,10 @@
 
 ## Classify one causal fingerprint
 
-Use one class per normalized root cause. A class changes only when new evidence changes
-the diagnosis:
+Fingerprint the causal diagnosis, never the failing test or symptom. Reuse it while
+plausible. If a discriminating fix proves the cause absent but the symptom remains,
+preserve that diagnosis as a dead end and classify a new fingerprint. Failure alone
+never resets a budget.
 
 - `intent_gap`: desired behavior, scope, policy, or risk choice is unsettled.
 - `spec_gap`: an acceptance outcome or product decision is missing.
@@ -20,11 +22,9 @@ Ask the engine for the canonical owner and action:
 devrites-engine recovery route <class>
 ```
 
-Follow the `recovery-route/v1` result. `humanPause: true` routes an unresolved intent or
-spec choice through Clarify. Technical routes stay agent-owned: repair the implementation
-or proof tool, normalize the environment, or repair the plan without asking permission to
-retry. A credential, external quota, irreversible action, or user-owned process that only
-the human can handle gets an exact human-intervention gate; it is not retry authorization.
+Follow `recovery-route/v1`. `humanPause: true` routes unresolved intent/spec through
+Clarify. Technical routes stay agent-owned. Gate only an exact human credential, quota,
+irreversible action, or user-owned process—never retry authorization.
 
 Record the class with every new failed attempt and green clear:
 

package/pack/generated/claude/skills/rite-plan/reference/replan-and-repair.md

@@ -33,9 +33,9 @@ errors: `devrites-api-interface`), then split into a backend slice (can land wit
 stub consumer) and a frontend slice (can land against a mock/real contract).
 
 ## unblock
-A `/rite-prove` failure can't be fixed inside the current slice. Capture the blocker in
-`state.md`, decide: route around it (reorder), shrink the slice (reslice), or escalate
-to the user (if it changes scope). Don't loop on the same failing approach.
+An exhausted fingerprint blocks diagnosis, not symptom. Route around/reslice; escalate
+only for scope change. If proof removed that cause but symptom remains, keep the dead
+end and plan a new diagnosis/proof fingerprint. Never clear/reuse old one.
 
 ## Always
 Update `state.md` (phase, next step) and append a dated line to `decisions.md`

package/pack/generated/codex/skills/devrites-debug-recovery/reference/cleanup-and-classify.md

@@ -2,8 +2,10 @@
 
 ## Classify one causal fingerprint
 
-Use one class per normalized root cause. A class changes only when new evidence changes
-the diagnosis:
+Fingerprint the causal diagnosis, never the failing test or symptom. Reuse it while
+plausible. If a discriminating fix proves the cause absent but the symptom remains,
+preserve that diagnosis as a dead end and classify a new fingerprint. Failure alone
+never resets a budget.
 
 - `intent_gap`: desired behavior, scope, policy, or risk choice is unsettled.
 - `spec_gap`: an acceptance outcome or product decision is missing.
@@ -20,11 +22,9 @@ Ask the engine for the canonical owner and action:
 devrites-engine recovery route <class>
 ```
 
-Follow the `recovery-route/v1` result. `humanPause: true` routes an unresolved intent or
-spec choice through Clarify. Technical routes stay agent-owned: repair the implementation
-or proof tool, normalize the environment, or repair the plan without asking permission to
-retry. A credential, external quota, irreversible action, or user-owned process that only
-the human can handle gets an exact human-intervention gate; it is not retry authorization.
+Follow `recovery-route/v1`. `humanPause: true` routes unresolved intent/spec through
+Clarify. Technical routes stay agent-owned. Gate only an exact human credential, quota,
+irreversible action, or user-owned process—never retry authorization.
 
 Record the class with every new failed attempt and green clear:
 

package/pack/generated/codex/skills/rite-plan/reference/replan-and-repair.md

@@ -33,9 +33,9 @@ errors: `devrites-api-interface`), then split into a backend slice (can land wit
 stub consumer) and a frontend slice (can land against a mock/real contract).
 
 ## unblock
-A `$rite-prove` failure can't be fixed inside the current slice. Capture the blocker in
-`state.md`, decide: route around it (reorder), shrink the slice (reslice), or escalate
-to the user (if it changes scope). Don't loop on the same failing approach.
+An exhausted fingerprint blocks diagnosis, not symptom. Route around/reslice; escalate
+only for scope change. If proof removed that cause but symptom remains, keep the dead
+end and plan a new diagnosis/proof fingerprint. Never clear/reuse old one.
 
 ## Always
 Update `state.md` (phase, next step) and append a dated line to `decisions.md`

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "devrites",
-  "version": "3.2.26",
+  "version": "3.2.27",
   "description": "DevRites: a disciplined senior-engineer workflow pack for Claude Code and Codex",
   "license": "SEE LICENSE IN LICENSE",
   "homepage": "https://github.com/ViktorsBaikers/DevRites#readme",