feat(week-review): price the gpt-5.6, Kimi and GLM models

Unpriced models counted as zero, so every codex row read as free and the
tool comparison was wrong. Rates are the providers' published ones; the
sol row reproduces a pi-reported total to the cent, which also confirms
the 0.1 cache-read multiplier applies to OpenAI.

GLM-4.7-Flash has no published per-token rate and stays out.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

README.md

@@ -145,6 +145,14 @@ skill on arrival if it doesn't have it.
 bump `updated_at` and move nothing in the snapshot, so no hint is sent at all.
 With webhooks the filter is sharper still, by event action.
 
+**Hints are rate-limited per PR and role.** Every hint costs the receiving
+session a full model turn, so after one goes out the next waits
+`hintCooldownSeconds` (default 300) and arrives carrying every reason that
+accumulated meanwhile. A hint identical to the last one sent is dropped, and so
+is a `ci` hint to a `land` session whose own worktree already holds that head
+commit — it pushed it. Reasons are banked until they are actually delivered, so
+a busy pane or a cooldown delays a hint but never loses one.
+
 **An epoch guards the first run.** `~/.local/state/reviewer/epoch` is written
 once; PRs created before it never spawn a session, so switching the daemon on
 doesn't wake every open PR you have. It gates creation only — start a session

bin/agents-config.example.json

@@ -2,6 +2,7 @@
   "pollSeconds": 60,
   "reconcileSeconds": 120,
   "maxSessionsPerTick": 2,
+  "hintCooldownSeconds": 300,
   "reviewProfile": "review",
   "group": "pr",
   "webhookPort": 7474,

bin/reviewer-poll.ts

@@ -42,6 +42,7 @@ const ROLES_DEFAULT = ["review", "blitz"];
 type Config = {
   pollSeconds?: number;
   reconcileSeconds?: number;
+  hintCooldownSeconds?: number; // quiet period per PR and role between hints
   maxSessionsPerTick?: number;
   reviewProfile?: string;
   reviewTool?: string;
@@ -97,6 +98,17 @@ const dirty = new Set<string>();
 const noPulls = new Set<string>();
 let firstRun = false;
 
+// The snapshot advances on the tick that diffed it, so a reason not sent
+// immediately can never be recomputed. Held per PR and role until it goes out.
+const pending = new Map<string, Set<string>>();
+const hintedAt = new Map<string, number>();
+const lastHint = new Map<string, string>();
+const HINT_COOLDOWN_MS = (config.hintCooldownSeconds ?? 300) * 1000;
+
+// Canonical order, so a coalesced hint reads the same however it accumulated.
+// That is what makes the duplicate check below meaningful.
+const REASON_ORDER = ["ci", "state", "conflicts", "comments"];
+
 const log = (...args: unknown[]) => console.log(new Date().toISOString(), ...args);
 
 // A webhook has to cut the wait short, or its only effect would be to mark a
@@ -321,6 +333,14 @@ async function seenIds(worktree: string, n: number): Promise<Set<string> | null>
   }
 }
 
+// True when the session's own worktree already holds the PR head, which means
+// the session pushed it and does not need waking to hear about its own commit.
+function pushedLocally(worktree: string, sha: string): boolean {
+  if (!sha) return false;
+  const proc = Bun.spawnSync(["git", "-C", worktree, "rev-parse", "HEAD"]);
+  return proc.exitCode === 0 && proc.stdout.toString().trim() === sha;
+}
+
 // Ids of everything commented after `since`. null means the fetch failed.
 async function newCommentIds(pr: Pr, since: string): Promise<string[] | null> {
   try {
@@ -838,6 +858,16 @@ async function evaluate(prs: Pr[], mentioned: Set<string>, budget: { sessions: n
         log(`${session.title} is waiting on input (${full.key})`);
       }
 
+      // Conflicts are the author's to resolve on their own branch, so the
+      // reviewer never hears about them. Comments it does hear: a reply to a
+      // finding is addressed to the reviewer, and an addressed thread is the
+      // reviewer's to resolve (review-pr §3.1).
+      // Banked before anything can skip out of this iteration.
+      const pkey = `${full.key}:${role}`;
+      const banked = pending.get(pkey) ?? new Set<string>();
+      for (const r of role === "land" ? why : why.filter((w) => w !== "conflicts")) banked.add(r);
+      if (banked.size) pending.set(pkey, banked);
+
       // A send into a busy pane can be swallowed. Since hints are idempotent,
       // holding it costs one cycle and nothing else.
       if (st !== "idle") {
@@ -849,25 +879,53 @@ async function evaluate(prs: Pr[], mentioned: Set<string>, budget: { sessions: n
       if (known && !known.prompted) {
         await send(known.profile, session.id, opening(full, skill));
         known.prompted = true;
+        pending.delete(pkey); // the opening sends it to read the PR whole
+        hintedAt.set(pkey, Date.now());
         continue;
       }
 
-      // Conflicts are the author's to resolve on their own branch, so the
-      // reviewer never hears about them. Comments it does hear: a reply to a
-      // finding is addressed to the reviewer, and an addressed thread is the
-      // reviewer's to resolve (review-pr §3.1).
-      let mine = role === "land" ? why : why.filter((w) => w !== "conflicts");
-      if (mine.includes("comments") && prev) {
+      const acc = pending.get(pkey);
+      if (!acc?.size) continue; // label, assignee, edited title: nothing to act on
+
+      if (acc.has("comments") && prev) {
         const ids = await newCommentIds(full, prev.updatedAt);
         const seen = session.path ? await seenIds(session.path, full.number) : null;
         if (ids?.length && seen && ids.every((id) => seen.has(id))) {
-          mine = mine.filter((w) => w !== "comments");
+          acc.delete("comments");
           log(`comments on ${full.key} already in ${session.title}'s seen file, hint dropped`);
         }
       }
-      if (!mine.length) continue; // label, assignee, edited title: nothing to act on
+      // The land session pushed the commit CI is running on, so the run is no
+      // news to it. A reviewer still hears about it: the head moved under them.
+      if (acc.has("ci") && role === "land" && session.path && pushedLocally(session.path, full.headSha)) {
+        acc.delete("ci");
+        log(`ci on ${full.key} is ${session.title}'s own push, hint dropped`);
+      }
+      if (!acc.size) {
+        pending.delete(pkey);
+        continue;
+      }
+
+      const wait = HINT_COOLDOWN_MS - (Date.now() - (hintedAt.get(pkey) ?? 0));
+      if (wait > 0) {
+        dirty.add(full.key);
+        setTimeout(wake, wait + 1000);
+        log(`cooling ${full.key} (${[...acc].join(",")}): ${Math.round(wait / 1000)}s left`);
+        continue;
+      }
+
+      const mine = REASON_ORDER.filter((r) => acc.has(r));
+      const message = hint(full, mine, skill);
+      if (lastHint.get(pkey) === message) {
+        pending.delete(pkey);
+        log(`hint ${full.key} repeats the last one verbatim, dropped`);
+        continue;
+      }
       try {
-        await send(session.profile, session.id, hint(full, mine, skill));
+        await send(session.profile, session.id, message);
+        pending.delete(pkey);
+        hintedAt.set(pkey, Date.now());
+        lastHint.set(pkey, message);
         log(`hint ${full.key} reason=${mine.join(",")} -> ${session.title}`);
       } catch (e) {
         dirty.add(full.key);

skills/week-review/scripts/pricing.json

@@ -1,5 +1,6 @@
 {
-  "_note": "USD per million tokens. Anthropic rates from the claude-api skill (cached 2026-06-24); check them when a model is added or repriced. Used only for tools that do not report their own cost (Claude Code, Codex) — pi and opencode report real cost per message and are never estimated.",
+  "_note": "USD per million tokens. Anthropic rates from the claude-api skill (cached 2026-06-24); OpenAI and open-weight rates cached 2026-08-28. Check them when a model is added or repriced. Used only for tools that do not report their own cost (Claude Code, Codex) — pi and opencode report real cost per message and are never estimated.",
+  "_check": "The gpt-5.6-sol row reproduces a pi-reported total to the cent (411369 in, 38462 out, 8897536 cache read = $7.6595), which also confirms the 0.1 cache-read multiplier for OpenAI.",
   "cache_write_multiplier": 1.25,
   "cache_read_multiplier": 0.1,
   "models": {
@@ -11,6 +12,11 @@
     "claude-opus-4-6": {"input": 5.0, "output": 25.0},
     "claude-sonnet-5": {"input": 3.0, "output": 15.0},
     "claude-sonnet-4-6": {"input": 3.0, "output": 15.0},
-    "claude-haiku-4-5": {"input": 1.0, "output": 5.0}
+    "claude-haiku-4-5": {"input": 1.0, "output": 5.0},
+    "gpt-5.6-sol": {"input": 5.0, "output": 30.0},
+    "gpt-5.6-terra": {"input": 2.0, "output": 12.0},
+    "gpt-5.6-luna": {"input": 0.2, "output": 1.2},
+    "hf:moonshotai/Kimi-K3": {"input": 3.0, "output": 15.0},
+    "hf:zai-org/GLM-5.2": {"input": 1.4, "output": 4.4}
   }
 }