ahead-pi 0.5.0 → 0.7.0

package/README.md

@@ -19,7 +19,7 @@ pi install npm:ahead-pi
 Pin an exact version for a team or project:
 
 ```sh
-pi install -l npm:ahead-pi@0.3.1
+pi install -l npm:ahead-pi@0.5.0
 ```
 
 Or try it for one session without changing settings:
@@ -28,6 +28,42 @@ Or try it for one session without changing settings:
 pi -e npm:ahead-pi
 ```
 
+## Install with oh-my-pi
+
+[oh-my-pi (OMP)](https://github.com/can1357/oh-my-pi) can load Pi-compatible extension packages. `ahead-pi` declares its extension entry point in the `omp` and legacy `pi` package manifests, so install it through OMP's plugin manager:
+
+```sh
+omp install ahead-pi
+```
+
+Restart OMP after installing the package, then start a session in the repository where the engineering work will occur. Use the same AHEAD commands as in Pi, starting with:
+
+```text
+/ahead <short title>
+```
+
+Pin a version with the normal OMP package syntax:
+
+```sh
+omp install ahead-pi@0.5.0
+```
+
+Do not pass the npm package name to `omp -e`. In OMP, `-e` / `--extension` is a direct filesystem loader for local extension files or directories, not a remote npm-package loader. For a local checkout, use the extension entry file directly:
+
+```sh
+omp -e ./integrations/pi/src/index.ts
+```
+
+OMP loads extensions in-process and uses its Pi compatibility remapping for the Pi package imports used by AHEAD. If the package installs but `/ahead` is missing, inspect OMP's extension-load log:
+
+```sh
+tail -F ~/.omp/logs/omp.$(date +%F).log
+```
+
+Errors mentioning `legacy-pi-coding-agent-shim`, `@oh-my-pi/pi-coding-agent`, or a `/$bunfs/` path indicate an OMP loader/runtime compatibility issue rather than an AHEAD command or configuration problem. Check [OMP issue #2166](https://github.com/can1357/oh-my-pi/issues/2166) and report the exact error with the OMP version and platform. The OMP binary's extension loader and compatibility layer are maintained by OMP, not by AHEAD.
+
+The bundled AHEAD extension commands and workflow state work through OMP. AHEAD's Pi-specific Agent Skills are currently exposed through Pi's `pi.skills` manifest; use the extension commands and `/ahead-guide` in OMP, and do not assume `/skill:research`, `/skill:to-tickets`, or `/skill:diagnosing-bugs` are available unless OMP's skill discovery lists them.
+
 ## Guided mode
 
 1. Start Pi in the repository where the engineering work will occur.

package/generated/decision/compare.md

@@ -1,5 +1,5 @@
 <!-- GENERATED FILE. DO NOT EDIT. -->
-<!-- workflow=decision@0.1.0 phase=compare sha256=45dd4e63965da74605742ee0fa17d758717fd30f00bf865b93de1e6caaf8cdaa -->
+<!-- workflow=decision@0.2.0 phase=compare sha256=f4f58b0edb987e6e53df60cca0bf8b31119edad600b7250c5a44e70ad882381e -->
 
 # AHEAD agent profile
 
@@ -34,7 +34,7 @@ Keep value choices, risk acceptance, product intent, and irreversible tradeoffs
 
 ## Enforced phase contract
 
-- Workflow: `decision@0.1.0`
+- Workflow: `decision@0.2.0`
 - Current phase: `compare`
 - Human gate: `comparison-accepted` — Human confirms the comparison represents the material tradeoffs
 - Normal next phase: `decide`

package/generated/decision/criteria.md

@@ -1,5 +1,5 @@
 <!-- GENERATED FILE. DO NOT EDIT. -->
-<!-- workflow=decision@0.1.0 phase=criteria sha256=89be55ecac424a5abd45e8d2fa76740b75e6788e7d68e07e989b11238feef2e5 -->
+<!-- workflow=decision@0.2.0 phase=criteria sha256=0daf7412dbe92d30d62c5fb23f6ae025f8fc9c4f574301c77de46595710ee345 -->
 
 # AHEAD agent profile
 
@@ -34,7 +34,7 @@ Keep value choices, risk acceptance, product intent, and irreversible tradeoffs
 
 ## Enforced phase contract
 
-- Workflow: `decision@0.1.0`
+- Workflow: `decision@0.2.0`
 - Current phase: `criteria`
 - Human gate: `criteria-accepted` — Human accepts the criteria before comparing options
 - Normal next phase: `research`

package/generated/decision/decide.md

@@ -1,5 +1,5 @@
 <!-- GENERATED FILE. DO NOT EDIT. -->
-<!-- workflow=decision@0.1.0 phase=decide sha256=92131b089672f71004be7c8e900620cb826bd8cca357aa1ab588d0a73178b92e -->
+<!-- workflow=decision@0.2.0 phase=decide sha256=be63e473a27c0e27e6181e58b313ee58f358e1f74dcc68a4b9a9c5c7dbfbe164 -->
 
 # AHEAD agent profile
 
@@ -34,7 +34,7 @@ Keep value choices, risk acceptance, product intent, and irreversible tradeoffs
 
 ## Enforced phase contract
 
-- Workflow: `decision@0.1.0`
+- Workflow: `decision@0.2.0`
 - Current phase: `decide`
 - Human gate: `decision-approved` — Accountable human approves the decision
 - Normal next phase: `publish`

package/generated/decision/frame.md

@@ -1,5 +1,5 @@
 <!-- GENERATED FILE. DO NOT EDIT. -->
-<!-- workflow=decision@0.1.0 phase=frame sha256=d9176492d364a56dbdbcbc3f75490711a16582899a0fe11cae2fd1efce1a4e7b -->
+<!-- workflow=decision@0.2.0 phase=frame sha256=ff4170dae9f5a75f2ae599f8558e7df210312ef79e53123289e686291907a002 -->
 
 # AHEAD agent profile
 
@@ -34,7 +34,7 @@ Keep value choices, risk acceptance, product intent, and irreversible tradeoffs
 
 ## Enforced phase contract
 
-- Workflow: `decision@0.1.0`
+- Workflow: `decision@0.2.0`
 - Current phase: `frame`
 - Human gate: `decision-framed` — Human confirms the decision is correctly framed
 - Normal next phase: `criteria`

package/generated/decision/manifest.json

@@ -1,6 +1,6 @@
 {
   "workflow": "decision",
-  "version": "0.1.0",
+  "version": "0.2.0",
   "generated": [
     "frame.md",
     "criteria.md",
@@ -11,7 +11,7 @@
     "publish.md"
   ],
   "sources": [
-    "spec/workflows/decision-v0.1.json",
+    "spec/workflows/decision-v0.2.json",
     "policy/common.md",
     "policy/decision/<phase>.md or policy/shared/<phase>.md",
     "policy/methods/index.json",

package/generated/decision/options.md

@@ -1,5 +1,5 @@
 <!-- GENERATED FILE. DO NOT EDIT. -->
-<!-- workflow=decision@0.1.0 phase=options sha256=6fc3c9cfb7c58f03ee881fd63fcdab943182de292d479881ca5ca23c06a88e16 -->
+<!-- workflow=decision@0.2.0 phase=options sha256=e93aa085f8233916b4e7998406aec2b6b1904337aada7cc9e4a7cfd5841b4859 -->
 
 # AHEAD agent profile
 
@@ -34,7 +34,7 @@ Keep value choices, risk acceptance, product intent, and irreversible tradeoffs
 
 ## Enforced phase contract
 
-- Workflow: `decision@0.1.0`
+- Workflow: `decision@0.2.0`
 - Current phase: `options`
 - Human gate: `options-understood` — Human confirms viable options are understood
 - Normal next phase: `compare`

package/generated/decision/publish.md

@@ -1,5 +1,5 @@
 <!-- GENERATED FILE. DO NOT EDIT. -->
-<!-- workflow=decision@0.1.0 phase=publish sha256=3cebabb95b98d04673d4ff737efc21ee8821f86788e8fb65eb34ae63b4f814c2 -->
+<!-- workflow=decision@0.2.0 phase=publish sha256=6a4ff9d1bf4a57ad5df6577a11abf51319bb01d4c191225ba2f52d46c85b9d5a -->
 
 # AHEAD agent profile
 
@@ -27,14 +27,14 @@ The human makes the decision durable and understandable to affected people, link
 
 ## Enforced phase contract
 
-- Workflow: `decision@0.1.0`
+- Workflow: `decision@0.2.0`
 - Current phase: `publish`
-- Human gate: `decision-published` — Human confirms the decision is recorded and communicated
+- Human gate: `decision-published` — Human confirms the decision record is written, communicated, and cross-linked
 - Normal next phase: `close run`
 - Human-authorized return targets: frame, research, options, compare, decide
-- AI unlock artifacts: none
+- AI unlock artifacts: `decision-record`
 - AI capabilities after unlock: `inspect`, `analyze`
 
 ### Phase artifacts
 
-- `published-decision`: Decision record, affected work, communication, review trigger, and revisit date (required; actor: human)
+- `decision-record`: Durable decision record with context, drivers, options, outcome, consequences, review trigger, and revisit date; MADR-shaped and stored in the project's decision-record directory (required; actor: human)

package/generated/decision/research.md

@@ -1,5 +1,5 @@
 <!-- GENERATED FILE. DO NOT EDIT. -->
-<!-- workflow=decision@0.1.0 phase=research sha256=5159100c5fecf5e5352299a4db2ce997f12355a00bb2a8a98d1e51611a8ce787 -->
+<!-- workflow=decision@0.2.0 phase=research sha256=b834768ec18c3a967d671fc5adb0df28ade8f63eec2326ce4391e30b5fc9290d -->
 
 # AHEAD agent profile
 
@@ -34,7 +34,7 @@ Research should change a decision, hypothesis, plan, or confidence level. Put pr
 
 ## Enforced phase contract
 
-- Workflow: `decision@0.1.0`
+- Workflow: `decision@0.2.0`
 - Current phase: `research`
 - Human gate: `research-reviewed` — Human confirms the decision has adequate evidence or accepts the gaps
 - Normal next phase: `options`

package/generated/internal-improvement/ai-audit.md

@@ -1,5 +1,5 @@
 <!-- GENERATED FILE. DO NOT EDIT. -->
-<!-- workflow=internal-improvement@0.1.0 phase=ai-audit sha256=2445815c576227b3bd53a6aca0a5ed3dc82464a22127397f7ccab914213bfdb9 -->
+<!-- workflow=internal-improvement@0.2.0 phase=ai-audit sha256=ed3fe7415968afb2435bd7ed64f053513db43c88ea47ac3f6947349f100abb9a -->
 
 # AHEAD agent profile
 
@@ -27,7 +27,7 @@ Audit the completed work against the recorded framing, decision, plan, evidence,
 
 ## Enforced phase contract
 
-- Workflow: `internal-improvement@0.1.0`
+- Workflow: `internal-improvement@0.2.0`
 - Current phase: `ai-audit`
 - Human gate: `audit-disposed` — Human reviews and disposes material audit findings; acceptance identity must match `audit-disposition`
 - Normal next phase: `outcome`
@@ -37,5 +37,5 @@ Audit the completed work against the recorded framing, decision, plan, evidence,
 
 ### Phase artifacts
 
-- `ai-audit`: AI audit findings (required; actor: ai)
+- `ai-audit`: AI audit findings evaluated against the full open run (required; actor: ai)
 - `audit-disposition`: Human disposition of material AI audit findings (required; actor: human)

package/generated/internal-improvement/ai-review.md

@@ -1,5 +1,5 @@
 <!-- GENERATED FILE. DO NOT EDIT. -->
-<!-- workflow=internal-improvement@0.1.0 phase=ai-review sha256=37a2f388516bddf462c1c93c8b3d2aa79332f0d4ffbc0f940b88e016af4a8dfc -->
+<!-- workflow=internal-improvement@0.2.0 phase=ai-review sha256=4d66be1f50fe7e2c7c3d13390454419d2c1ba8e07866a0fce1be0aa0938daffd -->
 
 # AHEAD agent profile
 
@@ -34,7 +34,7 @@ AI findings are hypotheses, not verdicts. The implementing human must dispositio
 
 ## Enforced phase contract
 
-- Workflow: `internal-improvement@0.1.0`
+- Workflow: `internal-improvement@0.2.0`
 - Current phase: `ai-review`
 - Human gate: `ai-review-disposed` — Implementing human disposes blocking AI findings; acceptance identity must match `review-disposition`
 - Normal next phase: `human-review`
@@ -44,5 +44,6 @@ AI findings are hypotheses, not verdicts. The implementing human must dispositio
 
 ### Phase artifacts
 
-- `ai-review`: AI review findings bound to the current changeset (required; actor: ai)
+- `review-inputs`: Enumeration of run inputs read for review: decision, plan, plan-deviations, reference-updates, changeset, tests, and evidence (required; actor: ai)
+- `ai-review`: AI review findings bound to the current changeset and evaluated against the full open run (required; actor: ai)
 - `review-disposition`: Implementing-human disposition of every material AI finding (required; actor: human; actor identity must match latest changeset)

package/generated/internal-improvement/baseline.md

@@ -1,5 +1,5 @@
 <!-- GENERATED FILE. DO NOT EDIT. -->
-<!-- workflow=internal-improvement@0.1.0 phase=baseline sha256=c6681cb018e61c13084e0b35fc969aebfc6ebbd1d2c3313f14fa584c5c7d136e -->
+<!-- workflow=internal-improvement@0.2.0 phase=baseline sha256=9fd7a1977ad0f35bed9a9e0c657c0599707e20e05bed8f8424108274bdc3faa2 -->
 
 # AHEAD agent profile
 
@@ -34,7 +34,7 @@ Research should change a decision, hypothesis, plan, or confidence level. Put pr
 
 ## Enforced phase contract
 
-- Workflow: `internal-improvement@0.1.0`
+- Workflow: `internal-improvement@0.2.0`
 - Current phase: `baseline`
 - Human gate: `baseline-accepted` — Human accepts the baseline as adequate for comparison
 - Normal next phase: `target`

package/generated/internal-improvement/decision.md

@@ -1,5 +1,5 @@
 <!-- GENERATED FILE. DO NOT EDIT. -->
-<!-- workflow=internal-improvement@0.1.0 phase=decision sha256=ea1f08dcc57e7bccdcf697783f31160cdafba70b66c4ec673bc98356f4b1c9c3 -->
+<!-- workflow=internal-improvement@0.2.0 phase=decision sha256=5a581f655863151aa6150d44a099669e7ac4e9cb24909d00b5501fd9182c211c -->
 
 # AHEAD agent profile
 
@@ -34,7 +34,7 @@ Keep value choices, risk acceptance, product intent, and irreversible tradeoffs
 
 ## Enforced phase contract
 
-- Workflow: `internal-improvement@0.1.0`
+- Workflow: `internal-improvement@0.2.0`
 - Current phase: `decision`
 - Human gate: `decision-approved` — Accountable human approves the improvement approach
 - Normal next phase: `plan`

package/generated/internal-improvement/deploy.md

@@ -1,5 +1,5 @@
 <!-- GENERATED FILE. DO NOT EDIT. -->
-<!-- workflow=internal-improvement@0.1.0 phase=deploy sha256=c8c59de77167b2f7f4617511d65b666ee57765176929d4efdaa4bb5766e14405 -->
+<!-- workflow=internal-improvement@0.2.0 phase=deploy sha256=160f8867e877564e5119f8249d92518e80d162137041a87c716022f4e2269c38 -->
 
 # AHEAD agent profile
 
@@ -27,7 +27,7 @@ Keep authorization, attempted action, and observed result distinct. A human reco
 
 ## Enforced phase contract
 
-- Workflow: `internal-improvement@0.1.0`
+- Workflow: `internal-improvement@0.2.0`
 - Current phase: `deploy`
 - Human gate: `deployment-confirmed` — Human confirms the intended version reached the target or deployment is not applicable
 - Normal next phase: `verify`

package/generated/internal-improvement/human-review.md

@@ -1,5 +1,5 @@
 <!-- GENERATED FILE. DO NOT EDIT. -->
-<!-- workflow=internal-improvement@0.1.0 phase=human-review sha256=cd14cf4c8537924a57e796434a368757aab34202793cf2939d404bcbc0456ef2 -->
+<!-- workflow=internal-improvement@0.2.0 phase=human-review sha256=f8ba53819295e6717e5d972a7e54a1941632ccd0158e65faa7eaf42d6c58cb23 -->
 
 # AHEAD agent profile
 
@@ -34,7 +34,7 @@ AI findings are hypotheses, not verdicts. The implementing human must dispositio
 
 ## Enforced phase contract
 
-- Workflow: `internal-improvement@0.1.0`
+- Workflow: `internal-improvement@0.2.0`
 - Current phase: `human-review`
 - Human gate: `human-review-accepted` — Independent human reviewer accepts the current change; acceptance identity must match `human-review`
 - Normal next phase: `deploy`
@@ -44,4 +44,4 @@ AI findings are hypotheses, not verdicts. The implementing human must dispositio
 
 ### Phase artifacts
 
-- `human-review`: Independent human review (required; actor: human; actor identity must differ from latest changeset)
+- `human-review`: Independent human review made against the full open run (required; actor: human; actor identity must differ from latest changeset)

package/generated/internal-improvement/implement.md

@@ -1,5 +1,5 @@
 <!-- GENERATED FILE. DO NOT EDIT. -->
-<!-- workflow=internal-improvement@0.1.0 phase=implement sha256=87fa58b7265be5b17c2af80d61f27048f02f3a837dbd6af599c060e4f1e4ac1c -->
+<!-- workflow=internal-improvement@0.2.0 phase=implement sha256=3b252bce2aa7136fc993c75e6342db67d4d26a94f4b63f2ec07445c02912fd34 -->
 
 # AHEAD agent profile
 
@@ -29,12 +29,12 @@ Ask for the human's current model, attempted approach, or intended behavior befo
 
 ## Enforced phase contract
 
-- Workflow: `internal-improvement@0.1.0`
+- Workflow: `internal-improvement@0.2.0`
 - Current phase: `implement`
-- Human gate: `implementation-ready` — Human confirms work is ready for review and checks pass
+- Human gate: `implementation-ready` — Human confirms work, tests, and durable reference updates are ready for review
 - Normal next phase: `ai-review`
 - Human-authorized return targets: plan
-- AI unlock artifacts: none
+- AI unlock artifacts: `reference-updates`
 - AI capabilities after unlock: `inspect`, `search`, `analyze`, `modify`, `execute`
 
 ### Phase artifacts
@@ -42,3 +42,4 @@ Ask for the human's current model, attempted approach, or intended behavior befo
 - `changeset`: Linked changeset (required; actor: human)
 - `tests`: Invariant, test, and check evidence (required; actor: human)
 - `plan-deviations`: Plan deviations and rationale, including none (required; actor: human)
+- `reference-updates`: Actual creates or updates of decision records, design docs, and runbooks during implementation, or explicit none; AI may propose entries, human accepts each (required; actor: human)

package/generated/internal-improvement/invariants.md

@@ -1,5 +1,5 @@
 <!-- GENERATED FILE. DO NOT EDIT. -->
-<!-- workflow=internal-improvement@0.1.0 phase=invariants sha256=52335b37be328b0278b504624641e8cf2b645ee348e932a3b4c384c7accd4781 -->
+<!-- workflow=internal-improvement@0.2.0 phase=invariants sha256=dc706d370298a42b4c81b8bb6ea778805b017a626648a419b2ed42097bc98453 -->
 
 # AHEAD agent profile
 
@@ -27,7 +27,7 @@ The human identifies behavior, compatibility, safety, operability, and other pro
 
 ## Enforced phase contract
 
-- Workflow: `internal-improvement@0.1.0`
+- Workflow: `internal-improvement@0.2.0`
 - Current phase: `invariants`
 - Human gate: `invariants-accepted` — Human confirms the protected behavior is explicit and testable
 - Normal next phase: `baseline`

package/generated/internal-improvement/manifest.json

@@ -1,6 +1,6 @@
 {
   "workflow": "internal-improvement",
-  "version": "0.1.0",
+  "version": "0.2.0",
   "generated": [
     "invariants.md",
     "baseline.md",
@@ -17,7 +17,7 @@
     "outcome.md"
   ],
   "sources": [
-    "spec/workflows/internal-improvement-v0.1.json",
+    "spec/workflows/internal-improvement-v0.2.json",
     "policy/common.md",
     "policy/internal-improvement/<phase>.md or policy/shared/<phase>.md",
     "policy/methods/index.json",

package/generated/internal-improvement/options.md

@@ -1,5 +1,5 @@
 <!-- GENERATED FILE. DO NOT EDIT. -->
-<!-- workflow=internal-improvement@0.1.0 phase=options sha256=6ea367b248068491760a3f140f7dbef7c27d8767f7e7c4e5b0e4146c8580c58f -->
+<!-- workflow=internal-improvement@0.2.0 phase=options sha256=b9e13f33aafe24ab866b217f9b793fae991bcd1dbd3692655b7f8d38a8780030 -->
 
 # AHEAD agent profile
 
@@ -34,7 +34,7 @@ Keep value choices, risk acceptance, product intent, and irreversible tradeoffs
 
 ## Enforced phase contract
 
-- Workflow: `internal-improvement@0.1.0`
+- Workflow: `internal-improvement@0.2.0`
 - Current phase: `options`
 - Human gate: `options-understood` — Human confirms viable options and tradeoffs are understood
 - Normal next phase: `decision`

package/generated/internal-improvement/outcome.md

@@ -1,5 +1,5 @@
 <!-- GENERATED FILE. DO NOT EDIT. -->
-<!-- workflow=internal-improvement@0.1.0 phase=outcome sha256=bfbbe413253e561851999982330c73f477e05fccdf54e99251c33a763492b335 -->
+<!-- workflow=internal-improvement@0.2.0 phase=outcome sha256=5dd75c61b5152bafdc6464adb9402cf0f9558083c26101dd3b71054e5cfb6aeb -->
 
 # AHEAD agent profile
 
@@ -27,9 +27,9 @@ The human decides to adopt, roll back, accept a missed target or tradeoff, follo
 
 ## Enforced phase contract
 
-- Workflow: `internal-improvement@0.1.0`
+- Workflow: `internal-improvement@0.2.0`
 - Current phase: `outcome`
-- Human gate: `outcome-accepted` — Human accepts closure
+- Human gate: `outcome-accepted` — Human accepts closure and explicitly closes the run
 - Normal next phase: `close run`
 - Human-authorized return targets: baseline, target, plan, implement
 - AI unlock artifacts: none

package/generated/internal-improvement/plan.md

@@ -1,5 +1,5 @@
 <!-- GENERATED FILE. DO NOT EDIT. -->
-<!-- workflow=internal-improvement@0.1.0 phase=plan sha256=3b050ec6653ac18b8e5c9bdf348e8c91243d9bc3fbee718c147c9e56f5186a37 -->
+<!-- workflow=internal-improvement@0.2.0 phase=plan sha256=9d5297ef85ec984f9bd5407152b6001199c0ba5940a3d06263180164320b2d2e -->
 
 # AHEAD agent profile
 
@@ -40,12 +40,12 @@ For broad migrations, use expand, migrate, verify, and contract stages so interm
 
 ## Enforced phase contract
 
-- Workflow: `internal-improvement@0.1.0`
+- Workflow: `internal-improvement@0.2.0`
 - Current phase: `plan`
-- Human gate: `plan-approved` — Human approves the final plan
+- Human gate: `plan-approved` — Human approves the final plan and its planned durable reference updates
 - Normal next phase: `implement`
 - Human-authorized return targets: target, options, decision
-- AI unlock artifacts: `first-pass-plan`
+- AI unlock artifacts: `first-pass-plan`, `reference-updates`
 - AI capabilities after unlock: `inspect`, `search`, `analyze`, `record`
 
 ### Phase artifacts
@@ -53,3 +53,4 @@ For broad migrations, use expand, migrate, verify, and contract stages so interm
 - `first-pass-plan`: Human first-pass implementation and measurement plan (required; actor: human)
 - `ai-plan-review`: AI plan challenge (optional; actor: ai)
 - `plan`: Human-approved sequenced plan, invariant checks, measurement, rollout, recovery, and deviations policy (required; actor: human)
+- `reference-updates`: Planned creates or updates of decision records, design docs, and runbooks, or explicit none (required; actor: human)

package/generated/internal-improvement/target.md

@@ -1,5 +1,5 @@
 <!-- GENERATED FILE. DO NOT EDIT. -->
-<!-- workflow=internal-improvement@0.1.0 phase=target sha256=ec0e695950ed2478fa62821860ba4e6972faa3defa6007b221e1fc200ac89b04 -->
+<!-- workflow=internal-improvement@0.2.0 phase=target sha256=0f86d666c1d892299234e5f4caa968aa60240539a3a68cd4c830641aa875ae5f -->
 
 # AHEAD agent profile
 
@@ -34,7 +34,7 @@ Keep value choices, risk acceptance, product intent, and irreversible tradeoffs
 
 ## Enforced phase contract
 
-- Workflow: `internal-improvement@0.1.0`
+- Workflow: `internal-improvement@0.2.0`
 - Current phase: `target`
 - Human gate: `target-approved` — Human approves the improvement target and guardrails
 - Normal next phase: `options`

package/generated/internal-improvement/verify.md

@@ -1,5 +1,5 @@
 <!-- GENERATED FILE. DO NOT EDIT. -->
-<!-- workflow=internal-improvement@0.1.0 phase=verify sha256=f1eec011ca5dea07be27bbca6124198b9e64815695be9684290c646ab784ad01 -->
+<!-- workflow=internal-improvement@0.2.0 phase=verify sha256=0aef7f8fc713b16c71b489cb637576f407c917ff5b712a22abab890b61920be9 -->
 
 # AHEAD agent profile
 
@@ -34,7 +34,7 @@ Research should change a decision, hypothesis, plan, or confidence level. Put pr
 
 ## Enforced phase contract
 
-- Workflow: `internal-improvement@0.1.0`
+- Workflow: `internal-improvement@0.2.0`
 - Current phase: `verify`
 - Human gate: `improvement-demonstrated` — Human confirms invariants hold and the improvement is demonstrated or failure is recorded
 - Normal next phase: `ai-audit`

package/generated/operational-stabilization/assess.md

@@ -1,5 +1,5 @@
 <!-- GENERATED FILE. DO NOT EDIT. -->
-<!-- workflow=operational-stabilization@0.1.0 phase=assess sha256=f5ec3c7e432b733a06dd3eca4e801c323c5a0b15dfcc5d03e677dd91b4d1a16e -->
+<!-- workflow=operational-stabilization@0.2.0 phase=assess sha256=434b74d12de17c52686b87970b3ef976aabbd4913a972edea7432d085704e02d -->
 
 # AHEAD agent profile
 
@@ -34,7 +34,7 @@ Research should change a decision, hypothesis, plan, or confidence level. Put pr
 
 ## Enforced phase contract
 
-- Workflow: `operational-stabilization@0.1.0`
+- Workflow: `operational-stabilization@0.2.0`
 - Current phase: `assess`
 - Human gate: `response-owned` — Human confirms response ownership, boundaries, and recovery criteria
 - Normal next phase: `respond`

package/generated/operational-stabilization/execute-observe.md

@@ -1,5 +1,5 @@
 <!-- GENERATED FILE. DO NOT EDIT. -->
-<!-- workflow=operational-stabilization@0.1.0 phase=execute-observe sha256=665b6172929167b323db29f726ebc9d36a0c9674b77346e9e30f04bf0c1061d5 -->
+<!-- workflow=operational-stabilization@0.2.0 phase=execute-observe sha256=31f7aab26157b0805525277ef60ec914c2e759e9a26d3c33bd99fbb78f034bfb -->
 
 # AHEAD agent profile
 
@@ -34,7 +34,7 @@ Research should change a decision, hypothesis, plan, or confidence level. Put pr
 
 ## Enforced phase contract
 
-- Workflow: `operational-stabilization@0.1.0`
+- Workflow: `operational-stabilization@0.2.0`
 - Current phase: `execute-observe`
 - Human gate: `action-observed` — Human confirms the action and immediate observations are recorded
 - Normal next phase: `verify-recovery`

package/generated/operational-stabilization/manifest.json

@@ -1,6 +1,6 @@
 {
   "workflow": "operational-stabilization",
-  "version": "0.1.0",
+  "version": "0.2.0",
   "generated": [
     "assess.md",
     "respond.md",
@@ -10,7 +10,7 @@
     "outcome.md"
   ],
   "sources": [
-    "spec/workflows/operational-stabilization-v0.1.json",
+    "spec/workflows/operational-stabilization-v0.2.json",
     "policy/common.md",
     "policy/operational-stabilization/<phase>.md or policy/shared/<phase>.md",
     "policy/methods/index.json",

package/generated/operational-stabilization/monitor.md

@@ -1,5 +1,5 @@
 <!-- GENERATED FILE. DO NOT EDIT. -->
-<!-- workflow=operational-stabilization@0.1.0 phase=monitor sha256=a745c7020a92d5dd4d2e23ce93db4224052ceca8bba2401eb84067599a9c9af0 -->
+<!-- workflow=operational-stabilization@0.2.0 phase=monitor sha256=1ccdfbfd6ade86dceb03cb2d8290b0586d312b7402f362d247e33ebf5d7f22e9 -->
 
 # AHEAD agent profile
 
@@ -34,7 +34,7 @@ Research should change a decision, hypothesis, plan, or confidence level. Put pr
 
 ## Enforced phase contract
 
-- Workflow: `operational-stabilization@0.1.0`
+- Workflow: `operational-stabilization@0.2.0`
 - Current phase: `monitor`
 - Human gate: `stability-observed` — Human confirms stability over the chosen observation window
 - Normal next phase: `outcome`

package/generated/operational-stabilization/outcome.md

@@ -1,5 +1,5 @@
 <!-- GENERATED FILE. DO NOT EDIT. -->
-<!-- workflow=operational-stabilization@0.1.0 phase=outcome sha256=20e0ed9f764e387135f66ebb85915138e1170d36bd34e8c72587695e270e730d -->
+<!-- workflow=operational-stabilization@0.2.0 phase=outcome sha256=1669ac7a293cd8b94c33e469b0d18c8df1c8875c32f306017470acfc4009edfa -->
 
 # AHEAD agent profile
 
@@ -27,14 +27,15 @@ The human closes response mode, records operational outcome and residual risk, a
 
 ## Enforced phase contract
 
-- Workflow: `operational-stabilization@0.1.0`
+- Workflow: `operational-stabilization@0.2.0`
 - Current phase: `outcome`
-- Human gate: `response-closed` — Human accepts operational closure and owns follow-up work
+- Human gate: `response-closed` — Human accepts operational closure, records durable reference updates or their explicit deferral, and explicitly closes the run
 - Normal next phase: `close run`
 - Human-authorized return targets: assess, respond
-- AI unlock artifacts: none
+- AI unlock artifacts: `reference-updates`
 - AI capabilities after unlock: `inspect`, `analyze`
 
 ### Phase artifacts
 
 - `outcome`: Operational outcome, residual risk, causal uncertainty, rollback state, follow-up work, and learning (required; actor: human)
+- `reference-updates`: Runbook, design-doc, and decision-record creates or updates arising from this stabilization, or explicit none; may be deferred to a postmortem when emergency policy applies, with the deferral itself recorded (required; actor: human)

package/generated/operational-stabilization/respond.md

@@ -1,5 +1,5 @@
 <!-- GENERATED FILE. DO NOT EDIT. -->
-<!-- workflow=operational-stabilization@0.1.0 phase=respond sha256=ff92cdcf56f02d1819f12630b86b18d426903913e85ab848d6173f39a469548a -->
+<!-- workflow=operational-stabilization@0.2.0 phase=respond sha256=efa131e4d764e05726b4c2f2371da510c5b4810062ce48fcf8cd41f8a9b8ee76 -->
 
 # AHEAD agent profile
 
@@ -27,7 +27,7 @@ Investigation and stabilization may proceed in parallel; there is no requirement
 
 ## Enforced phase contract
 
-- Workflow: `operational-stabilization@0.1.0`
+- Workflow: `operational-stabilization@0.2.0`
 - Current phase: `respond`
 - Human gate: `action-authorized` — Authorized human approves the bounded stabilizing action
 - Normal next phase: `execute-observe`

package/generated/operational-stabilization/verify-recovery.md

@@ -1,5 +1,5 @@
 <!-- GENERATED FILE. DO NOT EDIT. -->
-<!-- workflow=operational-stabilization@0.1.0 phase=verify-recovery sha256=0cf0fce584ec74179800e0de14c705794879febedb2a9fb0c8f93491e06a2c22 -->
+<!-- workflow=operational-stabilization@0.2.0 phase=verify-recovery sha256=24afac8c299092366f42e2301f46971f2fb14a5317bca6a6068f858c70e7da6d -->
 
 # AHEAD agent profile
 
@@ -34,7 +34,7 @@ Research should change a decision, hypothesis, plan, or confidence level. Put pr
 
 ## Enforced phase contract
 
-- Workflow: `operational-stabilization@0.1.0`
+- Workflow: `operational-stabilization@0.2.0`
 - Current phase: `verify-recovery`
 - Human gate: `recovery-demonstrated` — Human confirms recovery is demonstrated or returns for another bounded action
 - Normal next phase: `monitor`

package/generated/product-change/ai-audit.md

@@ -1,5 +1,5 @@
 <!-- GENERATED FILE. DO NOT EDIT. -->
-<!-- workflow=product-change@0.2.0 phase=ai-audit sha256=f96c02eed7d85afff47183285dda58fbfbdefea52313dc7da61d12cff62dd88a -->
+<!-- workflow=product-change@0.3.0 phase=ai-audit sha256=330c2b1c17dd332c73710cfd97a7b0769f62ca557017e448de0b3c32c2f675db -->
 
 # AHEAD agent profile
 
@@ -27,7 +27,7 @@ Compare the result with the problem, research, decision, plan, implementation, r
 
 ## Enforced phase contract
 
-- Workflow: `product-change@0.2.0`
+- Workflow: `product-change@0.3.0`
 - Current phase: `ai-audit`
 - Human gate: `audit-disposed` — Human reviews and disposes material audit findings; acceptance identity must match `audit-disposition`
 - Normal next phase: `outcome`
@@ -37,5 +37,5 @@ Compare the result with the problem, research, decision, plan, implementation, r
 
 ### Phase artifacts
 
-- `ai-audit`: AI audit findings (required; actor: ai)
+- `ai-audit`: AI audit findings evaluated against the full open run (required; actor: ai)
 - `audit-disposition`: Human disposition of material AI audit findings (required; actor: human)