@diegopetrucci/pi-extensions 0.1.54 → 0.1.55

package/README.md

@@ -2,10 +2,11 @@
 
 [![Total npm downloads](https://img.shields.io/npm/dt/%40diegopetrucci%2Fpi-extensions?label=total%20npm%20downloads)](https://www.npmjs.com/package/@diegopetrucci/pi-extensions)
 
-A collection of [pi](https://pi.dev) agent extensions I made.
+A collection of [pi](https://pi.dev) agent extensions I made. (btw, [I am also building my own harness on top of pi](https://github.com/diegopetrucci/the-last-harness). have a look!)
 
 ### Subagents
 
+- [`code-reviewer`](./extensions/code-reviewer): Adds a read-only `code_reviewer` subagent tool that reviews local changes for ticket fit, diff mismatches, correctness, security, simplicity, and validation gaps without implementing fixes, auto-selects a contrarian-style opposite-provider review model when available, and clamps requested thinking to the chosen model's capabilities.
 - [`contrarian`](./extensions/contrarian): Adds a read-only contrarian tool that spins up an isolated subprocess to stress-test plans, designs, assumptions, bug hypotheses, and conclusions by steelmanning the strongest opposing case.
 - [`librarian`](./extensions/librarian): Adds a GitHub research scout with a local repo checkout cache disabled by default under the OS user cache directory, toggleable with `/librarian-cache`, configurable subagent model/thinking defaults via `/librarian-config`, and cached repos expiring after 7 days of non-use.
 - [`oracle`](./extensions/oracle): Adds an Amp-style read-only oracle tool that auto-selects the strongest reasoning model on the current provider/subscription, supports persisted `/oracle` model/thinking defaults, requests xhigh reasoning by default and clamps to model capabilities, and shows live status while running.
@@ -33,6 +34,7 @@ A collection of [pi](https://pi.dev) agent extensions I made.
 
 - [`context-cap`](./extensions/context-cap): Caps effective model context windows at 200k tokens by default so pi avoids the `dumb zone`; toggle temporarily with `/context-cap`.
 - [`context-inspector`](./extensions/context-inspector): Adds `/context`, a local self-contained HTML dashboard that breaks down where the current session context is going, with category overview, top offenders, and drilldown search.
+- [`dynamic-context-pruning`](./extensions/dynamic-context-pruning): Automatically prunes duplicate tool results, stale errored inputs, and superseded file-op outputs from long sessions behind a cache-aware net-benefit gate, with a `/prune` picker and `/context-pruning` status/control commands.
 
 ### Safety
 

package/extensions/code-reviewer/.pi-fleet-tested-version

@@ -0,0 +1 @@
+0.80.3

package/extensions/code-reviewer/README.md

@@ -0,0 +1,84 @@
+# code-reviewer
+
+Adds a read-only `code_reviewer` subagent tool that adapts The Last Harness [`code-reviewer`](https://github.com/diegopetrucci/the-last-harness/blob/main/agents/subagents/code-reviewer.md) prompt into a standalone pi extension.
+
+Use it when you want an isolated second-pass review of a proposed change against the local checkout. The tool stays read-only, checks ticket fit and scope first, then looks for diff mismatches, correctness bugs, security/safety issues, unnecessary complexity, and missing validation.
+
+This package is adapted from the TLH code-reviewer workflow for use as a standalone pi extension.
+
+## Install
+
+### Standalone npm package
+
+```bash
+pi install npm:@diegopetrucci/pi-code-reviewer
+```
+
+### Collection package
+
+```bash
+pi install npm:@diegopetrucci/pi-extensions
+```
+
+### GitHub package
+
+```bash
+pi install git:github.com/diegopetrucci/pi-extensions
+```
+
+Then reload pi:
+
+```text
+/reload
+```
+
+## `code_reviewer` tool behavior
+
+The tool accepts:
+
+- `task` — required review target and success criteria
+- `diff` — optional diff, patch, or change summary
+- `context` — optional extra constraints or known risks
+
+When called, it launches an isolated in-memory child agent with:
+
+- no inherited extensions, skills, prompt templates, themes, context files, or agents files;
+- an auto-selected review model that prefers contrarian-style opposite-provider and opposite-family candidates before same-provider fallbacks;
+- requested thinking taken from the active session when available, otherwise defaulting to `high` for reasoning models and `off` for non-reasoning models, then clamped to the selected model's supported level;
+- read-only tools only: `read`, `grep`, `find`, `ls`, and guarded `bash`;
+- a local-checkout path guard for file inspection;
+- a bash guard that allows only direct read-only `git`, `gh`, or `pwd` invocations.
+
+The review prompt prioritizes:
+
+1. ticket fit and scope
+2. diff accuracy
+3. correctness and regressions
+4. security and safety
+5. simplicity and maintainability
+6. tests and validation gaps
+
+The final output is concise and includes a verdict, findings, validation notes, a scope check, and run details that show the final selected model and effective thinking level.
+
+## Read-only guarantees
+
+- The subagent is explicitly instructed not to implement changes.
+- Runtime guards block write/edit tools, shell control operators, pipelines, redirection, path traversal outside the checkout, mutating `git`/`gh` commands, `npm`/publish commands, and other filesystem mutation.
+- Built-in file-inspection tools are preferred over shell commands for local files.
+
+## Example
+
+```text
+Use code_reviewer on this task before merging:
+
+{
+  "task": "Review ticket pe-7lpt implementation for scope fit and correctness.",
+  "context": "Focus on whether the new extension stays runtime-only and keeps tools read-only."
+}
+```
+
+## Limitations
+
+- The subagent has an 8-turn and 8-minute budget.
+- The review quality depends on the local checkout matching the change being reviewed.
+- `gh`-based inspection is available only when GitHub CLI is installed and authenticated, but the tool can still review local changes without it.