ci: drop the alignment.yml paths change — it would have been a green check for a check that never ran

Reverting my own half of this PR. The reviewer proved the alignment.yml change
was theatre, and my issue #198 was filed on a wrong premise.

What I verified myself before reverting:
  - the alignment job BODY references models.json zero times; only the paths
    filter I added mentioned it
  - test.yml is `pull_request:` with NO paths filter, so it already runs on
    every PR, models.json-only ones included
  - on a deliberately corrupted models.json (contextWindow 1000000, a typo'd
    openclawName), `npm test` catches it: 455 passed, 2 failed

So the real guard on models.json already existed and always ran. Adding the
path would only have made a job execute that inspects nothing about
models.json, and then reported a green "Alignment Guardrail" — implying a check
that did not happen. That is strictly worse than the job not running, which is
precisely the reviewer's point.

#198's premise was also wrong. The blacklist greps server.mjs for known
hallucinated tokens. A models.json-only PR cannot introduce a token into
server.mjs, so CLAUDE.md hard-requirement #2 is INAPPLICABLE on such a PR, not
vacuous. I read "the guardrail didn't run" as "coverage gap" without checking
what the guardrail actually inspects.

The release.yml half is unaffected and stays: that one is a real, reproduced
failure (the no-CHANGELOG branch never wrote the file the create step consumes).

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017gbqUZ8HfBZpjjbzQ85oH8

.github/workflows/release.yml

@@ -21,24 +21,31 @@ jobs:
       - name: Extract CHANGELOG section
         id: notes
         run: |
+          set -euo pipefail
           VERSION="${{ steps.ver.outputs.version }}"
+          NOTES=/tmp/release-notes.md
           # Extract section for this version from CHANGELOG.md
           # Pattern: "## v${VERSION}" through the next "## " or EOF
           if [ ! -f CHANGELOG.md ]; then
             echo "No CHANGELOG.md found; using minimal release notes"
-            echo "notes=Release v${VERSION}" >> $GITHUB_OUTPUT
+            # MUST write the file, not just an output: the create step consumes a FILE, so an
+            # early exit here used to leave --notes-file pointing at a path that never existed,
+            # turning "degrade to minimal notes" into a failed release job (#202).
+            echo "Release v${VERSION}" > "$NOTES"
+            echo "notes_file=$NOTES" >> $GITHUB_OUTPUT
             exit 0
           fi
           awk -v ver="v${VERSION}" '
             $0 ~ "^## " ver { found=1; print; next }
             found && /^## v/ { exit }
             found { print }
-          ' CHANGELOG.md > /tmp/release-notes.md
-          if [ ! -s /tmp/release-notes.md ]; then
+          ' CHANGELOG.md > "$NOTES"
+          if [ ! -s "$NOTES" ]; then
             echo "No matching section in CHANGELOG for v${VERSION}; using minimal notes"
-            echo "Release v${VERSION}" > /tmp/release-notes.md
+            echo "Release v${VERSION}" > "$NOTES"
           fi
-          echo "notes_file=/tmp/release-notes.md" >> $GITHUB_OUTPUT
+          echo "--- release notes (${VERSION}) ---"; cat "$NOTES"
+          echo "notes_file=$NOTES" >> $GITHUB_OUTPUT
       - name: Create GitHub Release
         env:
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
@@ -49,5 +56,5 @@ jobs:
           fi
           gh release create "v${{ steps.ver.outputs.version }}" \
             --title "v${{ steps.ver.outputs.version }}" \
-            --notes-file /tmp/release-notes.md \
+            --notes-file "${{ steps.notes.outputs.notes_file }}" \
             --latest

CHANGELOG.md

@@ -1,11 +1,5 @@
 # Changelog
 
-## Unreleased
-
-### Changed
-
-- **`maxTokens` now matches the CLI registry instead of a uniform 16384 (#195).** Every Opus entry and `claude-sonnet-5` go to **64000**, `claude-sonnet-4-6` and `claude-haiku-4-5` to **32000** — the `max_output_tokens.default` each model actually declares in the compiled CLI 2.1.220 registry. OCP never enforced this value; it is propagated to OpenClaw, where it **caps the outbound request**: `maxTokens = Math.min(baseMaxTokens + thinkingBudget, modelMaxTokens)`. OpenClaw's reasoning budgets are medium 8192 / high 16384, and when `maxTokens <= thinkingBudget` it clamps thinking to `maxTokens - 1024` — so a model declared at 16384 running at **high** reasoning spent ~15360 on thinking and left **~1024 tokens for the actual answer**. `ocp-connect`'s independent family table moves to the family floor (opus 64000, sonnet 32000, haiku 32000) since prefixes cannot distinguish versions. Expect longer answers and correspondingly higher per-request quota burn on long generations.
-
 ## v3.25.0 — 2026-07-27
 
 Minor release. Headline: **Claude Opus 5** joins the model list and the `opus` alias now resolves to it. Alongside it, two `server.mjs` correctness fixes found by review rather than by users — a monotonic in-flight-counter leak, and cache keys that were hashing the alias string instead of the model it resolves to. The three TUI/prompt fixes that landed after v3.24.0 are included here too.

models.json

@@ -8,7 +8,7 @@
       "openclawName": "Claude Opus 5 (via CLI)",
       "reasoning": true,
       "contextWindow": 200000,
-      "maxTokens": 64000
+      "maxTokens": 16384
     },
     {
       "id": "claude-opus-4-8",
@@ -16,7 +16,7 @@
       "openclawName": "Claude Opus 4.8 (via CLI)",
       "reasoning": true,
       "contextWindow": 200000,
-      "maxTokens": 64000
+      "maxTokens": 16384
     },
     {
       "id": "claude-opus-4-7",
@@ -24,7 +24,7 @@
       "openclawName": "Claude Opus 4.7 (via CLI)",
       "reasoning": true,
       "contextWindow": 200000,
-      "maxTokens": 64000
+      "maxTokens": 16384
     },
     {
       "id": "claude-opus-4-6",
@@ -32,7 +32,7 @@
       "openclawName": "Claude Opus 4.6 (via CLI)",
       "reasoning": true,
       "contextWindow": 200000,
-      "maxTokens": 64000
+      "maxTokens": 16384
     },
     {
       "id": "claude-sonnet-5",
@@ -40,7 +40,7 @@
       "openclawName": "Claude Sonnet 5 (via CLI)",
       "reasoning": true,
       "contextWindow": 200000,
-      "maxTokens": 64000
+      "maxTokens": 16384
     },
     {
       "id": "claude-sonnet-4-6",
@@ -48,7 +48,7 @@
       "openclawName": "Claude Sonnet 4.6 (via CLI)",
       "reasoning": true,
       "contextWindow": 200000,
-      "maxTokens": 32000
+      "maxTokens": 16384
     },
     {
       "id": "claude-haiku-4-5-20251001",
@@ -56,7 +56,7 @@
       "openclawName": "Claude Haiku 4.5 (via CLI)",
       "reasoning": false,
       "contextWindow": 200000,
-      "maxTokens": 32000
+      "maxTokens": 8192
     }
   ],
   "aliases": {

ocp-connect

@@ -129,17 +129,10 @@ provider = {
 # re-trip it. Family prefixes classify any versioned ID correctly with no per-model
 # edit. (ADR 0003: models.json is the SPOT for model existence; /v1/models does not
 # expose reasoning/maxTokens, so family classification stays here.)
-# maxTokens values are the FAMILY FLOOR of the CLI registry max_output_tokens.default
-# (opus family 64000; sonnet 32000 because sonnet-4-6 is 32000 while sonnet-5 is 64000;
-# haiku 32000). Family prefixes cannot distinguish versions, so the floor is used
-# deliberately: under-advertising caps a client lower than the model allows, which is safe,
-# whereas over-advertising would promise capacity a member of the family does not have.
-# models.json is authoritative per ADR 0003; this table only exists because /v1/models does
-# not expose maxTokens.
 model_meta = {
-    "claude-opus": {"name": "Claude Opus (OCP)", "reasoning": True, "maxTokens": 64000},
-    "claude-sonnet": {"name": "Claude Sonnet (OCP)", "reasoning": True, "maxTokens": 32000},
-    "claude-haiku": {"name": "Claude Haiku (OCP)", "reasoning": False, "maxTokens": 32000},
+    "claude-opus": {"name": "Claude Opus (OCP)", "reasoning": True, "maxTokens": 16384},
+    "claude-sonnet": {"name": "Claude Sonnet (OCP)", "reasoning": True, "maxTokens": 16384},
+    "claude-haiku": {"name": "Claude Haiku (OCP)", "reasoning": False, "maxTokens": 8192},
 }
 
 def get_model_meta(mid):

test-features.mjs

@@ -4299,24 +4299,6 @@ test("models.json: every aliases value resolves to a real models[].id (referenti
   }
 });
 
-// maxTokens must leave room for a visible answer once a client's thinking budget is taken out
-// (#195). OCP never enforces maxTokens itself — it is propagated to OpenClaw (setup.mjs,
-// scripts/sync-openclaw.mjs) where it CAPS the outbound request:
-//     maxTokens = Math.min(baseMaxTokens + thinkingBudget, modelMaxTokens)
-// OpenClaw's reasoning budgets are medium 8192 / high 16384, and when maxTokens <= thinkingBudget
-// it clamps thinking to maxTokens - 1024. So a model declared at 16384 running at `high` spent
-// ~15360 on thinking and left ~1024 for the actual answer — which is what this repo shipped until
-// v3.25.0. Asserting the PRINCIPLE rather than pinning per-model numbers: a value test would need
-// editing every time a model is added, and would not say why.
-const _spotHighThinkingBudget = 16384; // OpenClaw's `high` reasoning budget
-test("models.json: every maxTokens exceeds the high thinking budget, leaving room for output (#195)", () => {
-  for (const m of _spotModels.models) {
-    assert.ok(m.maxTokens > _spotHighThinkingBudget,
-      `${m.id} declares maxTokens=${m.maxTokens} <= ${_spotHighThinkingBudget}: at OpenClaw's 'high' reasoning ` +
-      `level the thinking budget would consume all but ~1024 tokens of the response`);
-  }
-});
-
 test("models.json: every legacyAliases value resolves to a real models[].id (referential integrity)", () => {
   for (const [name, target] of Object.entries(_spotModels.legacyAliases || {})) {
     assert.ok(_spotModelIds.has(target), `legacyAliases.${name} -> '${target}' is a dangling alias (no matching models[].id)`);