@mzwing/pi-permission-auto-review 0.3.3 → 0.5.0

package/README.md

@@ -10,7 +10,7 @@ A [Pi](https://github.com/earendil-works/pi) extension that adds Codex-style aut
 
 Ours is mostly specialized for OpenAI's `codex-auto-review` model, which is trained to evaluate permission requests in the context of a coding assistant. Our extension aims at providing Codex-style automatic permission reviews for Pi's coding agent.
 
-The bundled baseline is a Pi-specific adaptation of OpenAI Codex Guardian's [`policy_template.md`](https://github.com/openai/codex/blob/6478a751fde8884b2fdc76486fe23175a8e795d4/codex-rs/core/assets/guardian/policy_template.md) and [`policy.md`](https://github.com/openai/codex/blob/6478a751fde8884b2fdc76486fe23175a8e795d4/codex-rs/core/assets/guardian/policy.md) at revision [`6478a751fde8884b2fdc76486fe23175a8e795d4`](https://github.com/openai/codex/commit/6478a751fde8884b2fdc76486fe23175a8e795d4). It is bundled at build time; the extension never fetches policy text while reviewing an action.
+The bundled baseline is a Pi-specific adaptation of OpenAI Codex Guardian's [`policy_template.md`](https://github.com/openai/codex/blob/a8c36ca6d265800c1b2c67d19d3583e23dee8382/codex-rs/prompts/templates/guardian/policy_template.md) and [`policy.md`](https://github.com/openai/codex/blob/a8c36ca6d265800c1b2c67d19d3583e23dee8382/codex-rs/prompts/templates/guardian/policy.md) at revision [`a8c36ca6d265800c1b2c67d19d3583e23dee8382`](https://github.com/openai/codex/commit/a8c36ca6d265800c1b2c67d19d3583e23dee8382). It is bundled at build time; the extension never fetches policy text while reviewing an action.
 
 Upstream's `Execution Environment` section and its MCP `connected_account_email` rule are deliberately left out: both describe Codex's sandbox and tool surface, which Pi's tool-free reviewer does not have. Upstream's `node_repl_policy.md` is likewise out of scope — it governs `node_repl` / `cua_repl` computer-use tools that Pi does not expose.
 
@@ -35,7 +35,7 @@ pi install npm:@gotgenes/pi-permission-system # dependency
 pi install npm:@mzwing/pi-permission-auto-review
 ```
 
-Pi 0.84.2+ (0.84.x and 0.85.x) and `@gotgenes/pi-permission-system` 27.x - 32.x are required.
+Pi 0.86.0+ and `@gotgenes/pi-permission-system` 33.x are required.
 
 The authorizer registers itself against the service keyed by its own session id, so a subagent's reviewer lands in its own node. A node that relays its asks to a live parent session runs no chain of its own, and the parent session's reviewer decides for it.
 
@@ -135,6 +135,26 @@ Each `auto_review.decision` emitted after transcript construction adds content-f
 
 These fields distinguish missing or truncated authorization evidence from a model decision made after receiving trusted evidence. Transcript text and model rationale are not persisted. The records are written through pi-permission-system's existing permission-review log when that log is enabled.
 
+## Programmatic use
+
+`@mzwing/pi-permission-auto-review/review` exposes the evidence, prompt, and verdict pipeline the live reviewer runs, for tools that test the classifier outside a Pi session.
+
+```ts
+import {
+  buildReviewPrompt,
+  DEFAULT_CONFIG,
+  parseReviewAssessment,
+  renderTranscript,
+} from '@mzwing/pi-permission-auto-review/review'
+
+const prompt = buildReviewPrompt(DEFAULT_CONFIG, renderTranscript(sessionEntries), details)
+const assessment = parseReviewAssessment(modelReply)
+```
+
+`details` is a `PromptPermissionDetails` from `@gotgenes/pi-permission-system`. The subpath needs no Pi peer dependency at runtime.
+
+`buildSystemPrompt`, `FIXED_REVIEW_PROTOCOL`, and `POLICY_REVISION` are exported alongside them. Prompt text tracks the bundled Guardian policy and changes with `POLICY_REVISION`; assert on that rather than on exact wording.
+
 ## License
 
 [MIT](LICENSE)