test(custom-model): make the harness smoke test dynamic, verify all 9 CLIs end-to-end

Rewrites scripts/test-local-llm-harnesses.mjs -> .ts to read the live CLI
registry (enabledClis()) and call the real production
buildCustomModelInjection()/applyConfigDirInjection() instead of keeping a
second hand-maintained copy of every CLI's env/config shape. A future
registry change (new CLI, edited env var, fixed config template) is now
picked up automatically with zero edits to this script; only the one-shot
invocation flags (info the registry genuinely doesn't model) stay in a
small hand-maintained ONE_SHOT table, and a registry CLI with no entry
there reports UNKNOWN rather than being silently skipped.

Extracted src/custom-model-injection-apply.ts (applyConfigDirInjection/
removeConfigDir) so the production route and this script share one
implementation instead of two.

Full end-to-end run against a real llama-swap server, inside a
codeman/agent:llm-test Docker image with all 9 CLI binaries:

- claude, opencode, pi, grok, omp: PASS, real "hello world" replies
- codex: confirmed FAIL for a real protocol reason, not a bug — it only
  speaks the Responses API since Feb 2026, which llama.cpp/llama-swap
  don't implement
- gemini: confirmed FAIL, unresolved after real investigation — an
  undocumented GATEWAY AuthType gemini-cli selects once
  GOOGLE_GEMINI_BASE_URL is set rejects every auth-key format/override
  tried
- deepseek: reaches the server (env vars are read) but gets a consistent
  HTTP_404; root cause not identified, documented as best-effort/unknown
- antigravity: SKIP, no known mechanism (unchanged)

Two real bugs found and fixed along the way (grok, pi/omp registry
entries in stock.ts): grok's original recipe (env vars) was flat-out
wrong, not just unverified — the real mechanism is a config.toml
[model.<name>] block redirected via GROK_HOME. pi/omp's PI_CONFIG_DIR
does nothing for either (grepped pi's entire bundled source — the string
appears nowhere); the real redirect is the child process's own HOME, and
both need `models` as an array of {id} objects, not an object keyed by
id (silently loaded zero models otherwise).

deployment_plan.md, PR.md, docs/custom-model-endpoints.md, and CLAUDE.md
updated with the final confidence table reflecting all of the above.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017HqNWfmtBU2KN29SvSVWB3

src/web/routes/session-routes.ts

@@ -8,7 +8,7 @@ import { FastifyInstance, type FastifyReply } from 'fastify';
 import { z } from 'zod';
 import { join, dirname, extname, basename } from 'node:path';
 import { homedir } from 'node:os';
-import { existsSync, statSync, mkdirSync, writeFileSync, rmSync } from 'node:fs';
+import { existsSync, statSync, mkdirSync, writeFileSync } from 'node:fs';
 import { execFile } from 'node:child_process';
 import fs from 'node:fs/promises';
 import { randomBytes } from 'node:crypto';
@@ -55,6 +55,7 @@ import {
 } from '../schemas.js';
 import { readCustomModelHosts } from '../../custom-model-hosts.js';
 import { buildCustomModelInjection } from '../../custom-model-injection.js';
+import { applyConfigDirInjection, removeConfigDir } from '../../custom-model-injection-apply.js';
 import { ownerLayoutKey } from '../../tab-layout-persistence.js';
 import { TabLayoutValidationError } from '../../tab-layout.js';
 import {
@@ -1184,7 +1185,7 @@ export function registerSessionRoutes(
 
     if ('clear' in body) {
       const previousConfigDir = session.setCustomModel(undefined);
-      if (previousConfigDir) rmSync(previousConfigDir, { recursive: true, force: true });
+      removeConfigDir(previousConfigDir);
       const restarted = await session.restartCli();
       persistAndBroadcastSession(ctx, session);
       return { customModel: session.customModel, restarted };
@@ -1216,16 +1217,8 @@ export function registerSessionRoutes(
     } else if (injection.kind === 'configDir') {
       // Isolated per-session dir — never the user's real CLI config path.
       configDir = join(dataPath('custom-model-configs'), session.id);
-      for (const file of injection.files) {
-        const filePath = join(configDir, file.relPath);
-        mkdirSync(dirname(filePath), { recursive: true });
-        writeFileSync(filePath, file.content, 'utf8');
-      }
-      // extraEnv: vars the written config file REFERENCES by name (codex's `env_key`
-      // convention) rather than embedding a literal value — must ride alongside
-      // dirEnvVar or the config points at a credential that was never actually set.
-      envOverrides = { [injection.dirEnvVar]: configDir, ...injection.extraEnv };
-      envKeys = [injection.dirEnvVar, ...Object.keys(injection.extraEnv ?? {})];
+      envOverrides = applyConfigDirInjection(configDir, injection);
+      envKeys = Object.keys(envOverrides);
     } else {
       // 'unsupported' is already handled above; this keeps the switch exhaustive.
       return createErrorResponse(ApiErrorCode.OPERATION_FAILED, `${session.mode} has no known custom-model mechanism`);
@@ -1238,7 +1231,7 @@ export function registerSessionRoutes(
     // Clean up the OLD config dir on disk, unless the new one happens to reuse the same
     // path (same session, configDir kind again) — never delete the dir we just wrote.
     if (previousConfigDir && previousConfigDir !== configDir) {
-      rmSync(previousConfigDir, { recursive: true, force: true });
+      removeConfigDir(previousConfigDir);
     }
 
     const restarted = await session.restartCli();