Review on request

The review file starts with `Approved` or `Changes requested` instead of `Yes`/`No`/`With fixes`. The match is still the whole trimmed first line; `run.ts` prepends ✅, 🛑, or 💬 when posting, so the mark never takes part in the match.

Verified: `deno fmt`, `deno lint`, `deno check` pass; a scratch run of the matcher maps `Approved` → APPROVED, `Changes requested` → REQUEST_CHANGES, and `Approved, mostly`, `✅ Approved`, `Yes` → COMMENT.
Reviewed-on: #8
Co-authored-by: Danny Kim <temeddix@gmail.com>
Co-committed-by: Danny Kim <temeddix@gmail.com>

action.yml

@@ -20,6 +20,11 @@ inputs:
   bot-token:
     description: API key or token for the selected bot
     required: false
+  model:
+    description: >-
+      Model for the selected bot. Defaults to `claude-sonnet-5` or
+      `gpt-5.6-terra`, the mid tiers, which cover reviews and fixes.
+    required: false
 
 runs:
   using: composite
@@ -40,6 +45,7 @@ runs:
         ACTION_PATH: ${{ gitea.action_path }}
         BOT_TYPE: ${{ inputs.bot-type }}
         BOT_TOKEN: ${{ inputs.bot-token }}
+        MODEL: ${{ inputs.model }}
         GITEA_API_URL: ${{ gitea.api_url }}
         GITEA_REPOSITORY: ${{ gitea.repository }}
         GITEA_TOKEN: ${{ inputs.author-token }}

prompt.md

@@ -18,24 +18,26 @@ the head of the pull request when there is one, with full history and the
 author's push credentials. Read the code there, run its checks and tests when
 they bear on the task, and push from there.
 
-For a `pull_request` event, review the PR without changing code, using the
+For a `pull_request` event, and for a comment on a pull request that asks you to
+review it, review the PR without changing code, using the
 `requesting-code-review` skill from superpowers: run its code reviewer template
-against the PR's base and head, and make its complete output your final response
-instead of the short comment style above. Run the project's checks on the head
-and treat a failure as at least Important. Check the whole repository against
-the code rules at the end of this prompt, not only the diff; a violation is at
-least Important even when the diff did not cause it. Your final response is
-posted verbatim as a pull request review from the bot account, so it is the
-review text and nothing else: no narration about what you did, verified, or are
-about to post, whether you reviewed yourself or relayed a reviewer subagent. Its
-first line must be exactly the template's verdict and nothing else: `Yes`, `No`,
-or `With fixes`. `Yes` approves and the other two request changes; any other
-first line is posted as a plain comment, which wastes the run. Minor issues
-alone never block. When the verdict is not `Yes`, the second line names what
-must change in one line, addressed to the author; the author's own agent picks
-the fixes up, so never ask `@bot` to make them. For UI changes, check that the
-result is aligned, clean, and pixel-perfect, and that included screenshots prove
-the intended result was achieved.
+against the PR's base and head. Run the project's checks on the head and treat a
+failure as at least Important. Check the whole repository against the code rules
+at the end of this prompt, not only the diff; a violation is at least Important
+even when the diff did not cause it. Write the complete review, and nothing
+else, to the file `${REVIEW_PATH}`: it is posted verbatim as a pull request
+review from the bot account, and your final response is not posted at all. The
+file's first line must be exactly the verdict and nothing else: `Approved` when
+the template's answer is yes, `Changes requested` otherwise. The mark in front
+of it is added when posting, so write the words alone; any other first line is
+posted as a plain comment, which wastes the run. Minor issues alone never block,
+and neither does a finding the author has answered in the comment history below
+as intended or a false alarm, once the code or docs make that clear. When the
+verdict is `Changes requested`, the second line names what must change in one
+line, addressed to the author; the author's own agent picks the fixes up, so
+never ask `@bot` to make them. For UI changes, check that the result is aligned,
+clean, and pixel-perfect, and that included screenshots prove the intended
+result was achieved.
 
 The review must read at a glance: everything outside `<details>` blocks totals
 under 512 bytes. Only core information stays visible: the verdict, the summary

run.ts

@@ -20,6 +20,13 @@ const EVENT = env("EVENT_NAME");
 const AUTHOR_TOKEN = env("GITEA_TOKEN");
 const REVIEWER_TOKEN = env("REVIEWER_TOKEN");
 const RULES_PATH = "repos/commons/code-rules/raw/README.md";
+// The mid tiers: a run follows a fixed template and the project's checks.
+const DEFAULT_MODELS: Record<string, string> = {
+  claude: "claude-sonnet-5",
+  codex: "gpt-5.6-terra",
+};
+const model = (bot: string): string =>
+  Deno.env.get("MODEL") || DEFAULT_MODELS[bot];
 
 // The reviewer token is withheld so the agent cannot approve as the bot.
 const { REVIEWER_TOKEN: _, ...agentEnv } = Deno.env.toObject();
@@ -52,21 +59,30 @@ async function postComment(body: string): Promise<void> {
   });
 }
 
-// A pull request event is a review request, so the response becomes a review.
-// Its first line is the verdict; anything unexpected only comments, never
-// approves.
-const VERDICTS: Record<string, string> = {
-  Yes: "APPROVED",
-  No: "REQUEST_CHANGES",
-  "With fixes": "REQUEST_CHANGES",
+// A review is posted whenever the agent wrote one, whether a review request or
+// a comment asked for it. It comes through a file, because a final chat message
+// picks up narration while a file's first line is written on purpose. That line
+// is the verdict, matched whole; anything unexpected only comments, never
+// approves. The mark in front is added here, so it is never part of the match.
+const REVIEW_PATH = `${await Deno.makeTempDir()}/review.md`;
+const VERDICTS: Record<string, [event: string, mark: string]> = {
+  Approved: ["APPROVED", "✅"],
+  "Changes requested": ["REQUEST_CHANGES", "🛑"],
 };
 
 async function postResult(body: string): Promise<void> {
-  if (EVENT !== "pull_request") return postComment(body);
-  const [verdict] = body.split("\n", 1);
+  const review = await Deno.readTextFile(REVIEW_PATH).catch(() => null);
+  if (review === null) {
+    if (EVENT === "pull_request") {
+      throw new Error(`no review was written to ${REVIEW_PATH}`);
+    }
+    return postComment(body);
+  }
+  const [verdict, ...rest] = review.split("\n");
+  const [event, mark] = VERDICTS[verdict.trim()] ?? ["COMMENT", "💬"];
   await gitea(REVIEWER_TOKEN, `repos/${REPO}/pulls/${INDEX}/reviews`, {
-    body: stripAnsi(body),
-    event: VERDICTS[verdict.trim()] ?? "COMMENT",
+    body: stripAnsi([`${mark} ${verdict.trim()}`, ...rest].join("\n")),
+    event,
   });
 }
 
@@ -111,6 +127,7 @@ async function renderPrompt(): Promise<string> {
     GITEA_API_URL: API,
     GITEA_REPOSITORY: REPO,
     ISSUE_INDEX: INDEX,
+    REVIEW_PATH,
   };
   const template = await Deno.readTextFile(
     new URL("prompt.md", import.meta.url),
@@ -134,7 +151,7 @@ async function runClaude(prompt: string): Promise<string> {
       "--print",
       "--dangerously-skip-permissions",
       "--model",
-      "claude-fable-5",
+      model("claude"),
       "--output-format",
       "stream-json",
       "--verbose",
@@ -199,7 +216,7 @@ async function runCodex(prompt: string): Promise<string> {
     args: [
       "exec",
       "--model",
-      "gpt-5.5",
+      model("codex"),
       "--dangerously-bypass-approvals-and-sandbox",
       "--output-last-message",
       file,