fix(chat): real fixes for thinking-model + URL conventions, not test tweaks

Five real bugs surfaced by the agent-chat smoke against live
qwen3-thinking. None of these are fixed by changing the test — the
test was right to fail.

1. openai-passthrough adapter doubled `/v1` in the request URL. The
   adapter hard-codes `/v1/chat/completions` after the configured base,
   but every OpenAI-compat provider documents its base URL with a
   trailing `/v1` (api.openai.com/v1, llm.example.com/v1, …). Users
   pasting that conventional shape produced
   `https://x/v1/v1/chat/completions` → 404. endpointUrl now strips a
   trailing `/v1` so both forms canonicalize. `/v1beta` (Anthropic-style)
   is preserved.

2. Non-streaming chat returned an empty assistant when thinking models
   (qwen3-thinking, deepseek-reasoner, OpenAI o1) emitted only
   `reasoning_content` with `content: null`. extractChoice now also
   pulls reasoning (every spelling the streaming parser already knows
   about), and a new pickAssistantText helper falls back to it when
   content is empty. A `[response truncated by max_tokens]` marker is
   appended when finish_reason is `length`, so users see the cut-off
   instead of guessing why the answer is short. Symmetric streaming
   fix: the chatStream loop accumulates reasoning and yields ONE
   synthesized `text` frame at the end when content stayed empty,
   keeping the CLI's stdout (which only prints `text` deltas) in sync
   with the persisted thread message.

3. `mcpctl get agent X -o yaml` emitted `kind: public` (the v3
   lifecycle field) instead of `kind: agent` (apply envelope), so
   round-tripping through `apply -f` failed. Same fix shape as the v1
   Llm strip in toApplyDocs — drop kind/status/lastHeartbeatAt/
   inactiveSince/providerSessionId for the agents resource too.

4. Non-streaming `mcpctl chat` printed `thread:<cuid>` (no space) on
   stderr; streaming printed `(thread: <cuid>)` (with space). Tests
   and any other regex watching for one form missed the other.
   Standardize on `thread: <cuid>` (single space) in both paths.

5. agent-chat.smoke's `run()` used `execSync`, which discards stderr on
   success — making any `expect(stderr).toMatch(...)` assertion
   structurally impossible to satisfy in the happy path. Switch to
   `spawnSync` so stderr is actually captured. Includes a small
   shell-style argv splitter so the existing call sites with quoted
   multi-word values (`--system-prompt "..."`) keep working.

Tests: +6 new mcpd unit tests (4 chat-service for the reasoning
fallback / truncation marker / content-preference / streaming synth;
2 llm-adapters for the URL strip + /v1beta preservation). Full mcpd
+ mcplocal + smoke green: 860/860 + 723/723 + 139/139.

src/mcpd/tests/llm-adapters.test.ts

@@ -71,6 +71,36 @@ describe('OpenAiPassthroughAdapter', () => {
     await expect(adapter.infer(makeCtx())).rejects.toThrow(/no default endpoint/);
   });
 
+  it('infer: strips a trailing /v1 from the configured URL', async () => {
+    // Users naturally paste the OpenAI-style base URL with /v1 because
+    // every provider documents it that way (https://api.openai.com/v1,
+    // https://llm.example.com/v1). The adapter then re-appends
+    // /v1/chat/completions; without normalization this would produce a
+    // doubled-/v1 404 against LiteLLM and friends.
+    const fetchFn = mockFetch([{ match: /\/v1\/chat\/completions$/, status: 200, body: {} }]);
+    const adapter = new OpenAiPassthroughAdapter('openai', { fetch: fetchFn as unknown as typeof fetch });
+    await adapter.infer(makeCtx({ url: 'https://llm.example.com/v1' }));
+    const [url1] = fetchFn.mock.calls[0] as [string];
+    expect(url1).toBe('https://llm.example.com/v1/chat/completions');
+
+    // Trailing slash + /v1 should also normalize correctly.
+    const fetchFn2 = mockFetch([{ match: /\/v1\/chat\/completions$/, status: 200, body: {} }]);
+    const adapter2 = new OpenAiPassthroughAdapter('openai', { fetch: fetchFn2 as unknown as typeof fetch });
+    await adapter2.infer(makeCtx({ url: 'https://llm.example.com/v1/' }));
+    const [url2] = fetchFn2.mock.calls[0] as [string];
+    expect(url2).toBe('https://llm.example.com/v1/chat/completions');
+  });
+
+  it('infer: preserves a trailing /v1beta suffix (only exact /v1 is stripped)', async () => {
+    // Some providers expose `/v1beta` as a parallel API surface — don't
+    // accidentally rewrite that to `/v1` or strip it.
+    const fetchFn = mockFetch([{ match: /\/v1beta\/v1\/chat\/completions$/, status: 200, body: {} }]);
+    const adapter = new OpenAiPassthroughAdapter('openai', { fetch: fetchFn as unknown as typeof fetch });
+    await adapter.infer(makeCtx({ url: 'https://api.example.com/v1beta' }));
+    const [url] = fetchFn.mock.calls[0] as [string];
+    expect(url).toBe('https://api.example.com/v1beta/v1/chat/completions');
+  });
+
   it('infer: omits Authorization when apiKey is empty', async () => {
     const fetchFn = mockFetch([{ match: /ollama/, status: 200, body: {} }]);
     const adapter = new OpenAiPassthroughAdapter('ollama', { fetch: fetchFn as unknown as typeof fetch });