fix(prompt): OCP_LOCAL_TOOLS wrapper no longer hard-codes a tool list (closes #185)

The positive local-tools wrapper (server.mjs) claimed the model has "full access
to the local filesystem, working directory, and shell through your available
tools (Bash, Read, Write, Edit, Glob, Grep, etc.)". That over-promises when an
operator narrows CLAUDE_ALLOWED_TOOLS (e.g. to Read,Grep): the model is told it
has Bash/Write/shell it doesn't hold, then attempts a non-granted tool and gets
denied. The default set matches the text, so the primary/OpenClaw path was fine —
but the enumeration was a prompt-honesty mismatch (flagged in the #182 fact-check).

Reworded to flip the POSTURE only ("you may use your available local tools … do
not assume access beyond the tool set provided to you in this session") without
enumerating specific tools or asserting shell/write capability. The model learns
its real tools from the tool definitions claude is given (--allowedTools), so the
enumeration was redundant as well as fragile — now honest under any allowed set.

No const reordering / no CONFIG_EPOCH change (still a constant; the epoch-fold
test confirms toggling still invalidates the cache with the new text). Test
markers updated (selectPromptWrapper unit + the boot-server integration assertion
that the positive wrapper reaches the -p spawn). Suite 449/0.

Rule 2: OCP-owned prompt composition, no wire change, no cli.js citation.

Closes #185

Co-Authored-By: Claude <claude-opus-4-8> <noreply@anthropic.com>

CHANGELOG.md

@@ -1,12 +1,5 @@
 # Changelog
 
-## Unreleased
-
-### Added
-
-- **Claude Opus 5 (`claude-opus-5`), and the `opus` alias now resolves to it.** New `models.json` entry — `/v1/models` goes 6 → 7 and OpenClaw picks it up on the next `ocp update` (via `scripts/sync-openclaw.mjs`). Verified against the installed CLI rather than assumed: the compiled `claude` 2.1.220 bundle carries `latest_per_family:{fable:"claude-fable-5",opus:"claude-opus-5",sonnet:"claude-sonnet-5",haiku:"claude-haiku-4-5"}`, so repointing `opus` mirrors what the CLI itself defaults to — the same reasoning as #168 (sonnet → sonnet-5). Availability confirmed with a live `claude -p --model claude-opus-5` completion on the subscription pool. Pricing is unchanged from Opus 4.8 ($5/$25 per MTok, CLI registry `pricing:"tier_5_25"`), so the alias repoint carries no cost change. `claude-opus-4-8` is retained for pinning.
-- `contextWindow` is deliberately **200000**, not Opus 5's native 1M. Two reasons, both verified: (1) `MAX_PROMPT_CHARS` is a **single global** budget — `derivePromptCharBudget` takes `max(contextWindow) × 3` across *all* entries (`lib/prompt.mjs`), so a 1M entry would raise the truncation ceiling to 3,000,000 chars for `claude-haiku-4-5` too, which is genuinely 200k native, converting clean OCP-side truncation into an upstream API rejection; (2) OpenClaw scales its history budget linearly off this value (`contextWindow × maxHistoryShare × SAFETY_MARGIN` = `× 0.6`, plus an oversized-message threshold at `× 0.5`, per `compaction-planning` in OpenClaw 2026.7.1), and its own bundled registry hardcodes 200000 for Claude — the upstream request to raise it to 1M ([openclaw#22979](https://github.com/openclaw/openclaw/issues/22979)) was closed *not planned*. A new regression test pins the invariant so a future 1M entry has to be a deliberate, reviewed change. Raising it for real needs per-model budgets — tracked separately, ADR-level.
-
 ## v3.24.0 — 2026-07-21
 
 Minor release. Headline: two long-requested **OpenAI-compat features** land — **multimodal vision** (`image_url` parts) and **structured outputs** (`response_format` / JSON schema). Also: the prompt-char budget now derives from the model SPOT instead of a hand-set constant, an agentic-turn bug that dropped the model's final answer is fixed, and `OCP_LOCAL_TOOLS` supports the OpenClaw-backend use case. Four of the six landed from external contributors (@vvlasy-openclaw). Every code PR carried a fresh-context reviewer (Iron Rule 10); no new endpoint, no new `cli.js` wire behavior.

README.md

@@ -113,11 +113,11 @@ node setup.mjs
 
 `setup.mjs` verifies the Claude CLI, starts the proxy on port 3456, and installs auto-start (launchd on macOS, systemd on Linux). The `ocp` CLI lands at `~/ocp/ocp` — symlink it onto your PATH (`sudo ln -sf ~/ocp/ocp /usr/local/bin/ocp`, or `ln -sf ~/ocp/ocp ~/.local/bin/ocp`) or alias it (`alias ocp=~/ocp/ocp`); the rest of the docs assume `ocp` is on your PATH.
 
-**Verify** — should list 7 models:
+**Verify** — should list 6 models:
 
 ```bash
 curl http://127.0.0.1:3456/v1/models
-# claude-opus-5, claude-opus-4-8, claude-opus-4-7, claude-opus-4-6, claude-sonnet-5, claude-sonnet-4-6, claude-haiku-4-5-20251001
+# claude-opus-4-8, claude-opus-4-7, claude-opus-4-6, claude-sonnet-5, claude-sonnet-4-6, claude-haiku-4-5-20251001
 ```
 
 **Connect one IDE** — point any OpenAI-compatible tool at the proxy, then reload your shell and start a tool (Cline / Continue / Cursor / OpenCode):
@@ -169,9 +169,8 @@ Any tool use happens server-side, under the `--allowedTools` set configured on t
 
 | Model ID | Notes |
 |----------|-------|
-| `claude-opus-5` | Most capable (default for `opus` alias) |
-| `claude-opus-4-8` | Previous Opus, retained for pinning |
-| `claude-opus-4-7` | Older Opus, retained for pinning |
+| `claude-opus-4-8` | Most capable (default for `opus` alias) |
+| `claude-opus-4-7` | Previous Opus, retained for pinning |
 | `claude-opus-4-6` | Older Opus, retained for pinning |
 | `claude-sonnet-5` | Latest Sonnet (default for `sonnet` alias) |
 | `claude-sonnet-4-6` | Previous Sonnet, retained for pinning |

docs/lan-mode.md

@@ -78,7 +78,7 @@ Run `ocp lan` to see your IP and ready-to-share instructions.
 **Verify:**
 ```bash
 curl http://127.0.0.1:3456/v1/models
-# Returns: claude-opus-5, claude-opus-4-8, claude-opus-4-7, claude-opus-4-6, claude-sonnet-5, claude-sonnet-4-6, claude-haiku-4-5-20251001
+# Returns: claude-opus-4-8, claude-opus-4-7, claude-opus-4-6, claude-sonnet-5, claude-sonnet-4-6, claude-haiku-4-5-20251001
 ```
 
 ### Headless install notes
@@ -114,7 +114,7 @@ Please follow https://github.com/dtzp555-max/ocp/blob/main/README.md
    installed and logged in (`claude auth status`). Install missing pieces
    using my system's package manager.
 2. git clone the repo, cd in, and run `node setup.mjs`.
-3. Verify with `curl http://127.0.0.1:3456/v1/models` (should list 7 models).
+3. Verify with `curl http://127.0.0.1:3456/v1/models` (should list 6 models).
 4. Add `export OPENAI_BASE_URL=http://127.0.0.1:3456/v1` to my shell rc.
 5. Tell me to reload my shell and try a tool like Cline / Continue / Cursor.
 
@@ -141,7 +141,7 @@ Please follow https://github.com/dtzp555-max/ocp/blob/main/docs/lan-mode.md
 5. Add OCP_ADMIN_KEY to my shell rc (~/.zshrc or ~/.bashrc).
 6. Run `ocp lan` to show me the LAN IP and connect command.
 7. Optionally create example keys: `ocp keys add laptop`, `ocp keys add tablet`.
-8. Verify: `curl http://127.0.0.1:3456/v1/models` returns 7 models.
+8. Verify: `curl http://127.0.0.1:3456/v1/models` returns 6 models.
 
 Tell me each step before running it. On error, diagnose before retrying.
 ```
@@ -163,7 +163,7 @@ Please follow https://github.com/dtzp555-max/ocp/blob/main/docs/lan-mode.md
      chmod +x ocp-connect
 2. Run `./ocp-connect <SERVER_IP>` (add `--key <KEY>` if you have one).
 3. Follow any IDE-specific manual hints it prints.
-4. Verify: `curl http://<SERVER_IP>:3456/v1/models` returns 7 models.
+4. Verify: `curl http://<SERVER_IP>:3456/v1/models` returns 6 models.
 5. Tell me to reload my shell + restart any IDE that was already running.
 
 Don't auto-retry on error. Tell me the failure mode first.
@@ -216,7 +216,7 @@ OCP Connect v1.3.0
     (set by admin via PROXY_ANONYMOUS_KEY; see issue #12 §14 Path A)
 
   Testing API access...
-  ✓ API accessible (7 models available)
+  ✓ API accessible (6 models available)
 
   Shell config:
     ✓ .bashrc
@@ -246,7 +246,6 @@ OCP Connect v1.3.0
   ✓ OpenClaw configured
     Provider: ocp
     Models:
-      • ocp/claude-opus-5
       • ocp/claude-opus-4-8
       • ocp/claude-opus-4-7
       • ocp/claude-opus-4-6

models.json

@@ -2,14 +2,6 @@
   "$schema": "./models.schema.json",
   "version": 1,
   "models": [
-    {
-      "id": "claude-opus-5",
-      "displayName": "Claude Opus 5",
-      "openclawName": "Claude Opus 5 (via CLI)",
-      "reasoning": true,
-      "contextWindow": 200000,
-      "maxTokens": 16384
-    },
     {
       "id": "claude-opus-4-8",
       "displayName": "Claude Opus 4.8",
@@ -60,7 +52,7 @@
     }
   ],
   "aliases": {
-    "opus": "claude-opus-5",
+    "opus": "claude-opus-4-8",
     "sonnet": "claude-sonnet-5",
     "haiku": "claude-haiku-4-5-20251001"
   },

test-features.mjs

@@ -4067,10 +4067,6 @@ test("models.json aliases.sonnet === 'claude-sonnet-5' (default-request-model SP
   assert.equal(_spotModels.aliases.sonnet, "claude-sonnet-5");
 });
 
-test("models.json aliases.opus === 'claude-opus-5' (opus-alias SPOT)", () => {
-  assert.equal(_spotModels.aliases.opus, "claude-opus-5");
-});
-
 // ── Referential integrity (PR #152 review) ──────────────────────────────────
 // The value-mirror assertions above only prove the alias equals a string literal —
 // they pass even if that literal points at a model that does not exist in
@@ -4084,25 +4080,6 @@ test("models.json: claude-sonnet-5 is present in models[] (the entry this PR add
   assert.ok(_spotModelIds.has("claude-sonnet-5"), "claude-sonnet-5 must exist as a models[].id");
 });
 
-test("models.json: claude-opus-5 is present in models[] (the entry this PR adds)", () => {
-  assert.ok(_spotModelIds.has("claude-opus-5"), "claude-opus-5 must exist as a models[].id");
-});
-
-// The prompt-char budget is GLOBAL (max across every entry × 3 chars/token), not
-// per-model — see lib/prompt.mjs derivePromptCharBudget. An entry declaring a native 1M
-// window would therefore raise the truncation ceiling for claude-haiku-4-5 too (genuinely
-// 200k), turning OCP-side truncation into an upstream API rejection.
-//
-// Asserts the MAX, deliberately, not every entry: ADR 0009 states the budget "scales
-// automatically — no code change", so a future entry with a SMALLER window (say a 128k
-// model) must stay legal and must not fail this suite. Only raising the ceiling is the
-// hazard, and that is an ADR-level decision requiring per-model budgets first.
-test("models.json: max contextWindow is 200000 (global prompt-budget ceiling)", () => {
-  const windows = _spotModels.models.map(m => m.contextWindow);
-  assert.equal(Math.max(...windows), 200000,
-    `max contextWindow re-scales MAX_PROMPT_CHARS for ALL models incl. the 200k-native haiku (see lib/prompt.mjs + ADR 0009)`);
-});
-
 test("models.json: every aliases value resolves to a real models[].id (referential integrity)", () => {
   for (const [name, target] of Object.entries(_spotModels.aliases)) {
     assert.ok(_spotModelIds.has(target), `aliases.${name} -> '${target}' is a dangling alias (no matching models[].id)`);