chore(release): v3.20.0 — TUI billing-safety hardening for 2026-06-15 (PR-A/B/C, #137-139) (#140 )

Bump 3.19.0 → 3.20.0 + CHANGELOG. Aggregates three already-reviewed, already-merged PRs: - #137 (PR-A) TUI honesty/cache correctness - #139 (PR-B) TUI concurrency limit + /health observability - #138 (PR-C) 6/15 canary + flip/rollback runbooks + setup auth-probe guard README env-var / endpoint tables were updated in the respective feature PRs. Co-authored-by: dtzp555 <dtzp555@gmail.com> Co-authored-by: Claude <claude-fable-5> <noreply@anthropic.com>
feat(tui): per-path concurrency limit + /health observability (PR-B) (#139 )
2026-07-21 21:15:09 +00:00 · 2026-06-10 21:56:56 +10:00 · 2026-06-10 21:54:07 +10:00 · 2026-06-10 21:41:03 +10:00 · 2026-06-10 21:39:01 +10:00 · 2026-06-02 11:03:20 +10:00
22 changed files with 2052 additions and 152 deletions
@@ -29,10 +29,14 @@ jobs:
            exit 0
          fi

-          # Known-hallucinated tokens. Extend only via an ALIGNMENT.md amendment PR.
-          # Each token is matched as a fixed string against server.mjs only.
+          # Blacklisted tokens — two kinds (see ALIGNMENT.md "OAuth token-host verification"):
+          #   (1) known LLM hallucinations (e.g. the 2026-04-11 /api/oauth/usage drift), and
+          #   (2) pinned wrong-host variants of a VERIFIED Class A endpoint (a hit means a
+          #       drift to a known-wrong host, not necessarily a hallucination).
+          # Extend only via an ALIGNMENT.md amendment PR. Matched as fixed strings vs server.mjs.
          BLACKLIST=(
            "api.anthropic.com/api/oauth/usage"
+            "console.anthropic.com/v1/oauth/token"
          )

          FAIL=0
@@ -51,8 +55,8 @@ jobs:
          ============================================================
          server.mjs contains a token on the OCP alignment blacklist.

-          These tokens were introduced by LLM hallucinations and do
-          not appear in cli.js at any shipped Claude Code version.
+          These tokens are either LLM hallucinations that never appeared in cli.js,
+          or pinned wrong-host variants of a verified Class A endpoint (a drift).
          See ALIGNMENT.md -> "Historical Lesson: The 2026-04-11 Drift"
          (commit b87992f) for the full incident record.

@@ -52,6 +52,26 @@ The following Rules apply to **Class A operations** (the `cli.js`-mirror surface

 The audit pin is updated once per year (see Annual Alignment Audit) and whenever a drift incident forces a re-verification.

+### OAuth token-host verification (2026-05-31)
+
+Motivating evidence: the 2026-05-31 code audit (issues #112 / #119 / #123). The OAuth bearer
+machinery is a Class A surface (Rules 1–5). Because `cli.js` now ships as a
+compiled binary, the token-refresh host was re-verified against `claude.exe` (Claude Code
+`2.1.154`) on 2026-05-31 using the compiled-binary protocol — `strings` on the Mach-O, **no
+live OAuth probe** (a `refresh_token` grant would rotate the operator's real credentials):
+
+- **Verified host:** `https://platform.claude.com/v1/oauth/token` — present in the binary
+  byte-for-byte, paired with `OAUTH_CLIENT_ID` in the same `prod` config object (matches
+  `server.mjs` `OAUTH_TOKEN_URL` / `OAUTH_CLIENT_ID`). The legacy `console.anthropic.com/v1/oauth`
+  host is absent (0 hits).
+- **Pinned wrong-host variant:** `console.anthropic.com/v1/oauth/token` is added to the
+  `alignment.yml` blacklist so a future accidental revert to the legacy host hard-fails CI.
+
+The blacklist therefore now holds two kinds of token: (1) known hallucinations (e.g.
+`api.anthropic.com/api/oauth/usage`, the 2026-04-11 drift), and (2) pinned wrong-host variants
+of a *verified* Class A endpoint. A blacklist hit means either a re-introduced hallucination
+**or** a drift to a known-wrong host — both are alignment failures under Rules 2 and 3.
+
 ---

 ## Historical Lesson: The 2026-04-11 Drift
@@ -1,6 +1,74 @@
 # Changelog

-## Unreleased
+## v3.20.0 — 2026-06-10
+
+TUI-mode billing-safety hardening for the 2026-06-15 Anthropic billing split. A 5-dimension multi-agent audit (adversarial verification + live tests on all three hosts — PI231 / Oracle / Mac mini, claude 2.1.104 / 2.1.114 / 2.1.170) found the TUI subscription-pool path could silently bill the metered Agent SDK pool or poison the cache under realistic failure modes. Three PRs, each with a fresh-context reviewer (Iron Rule 10) and CI; the default path (`CLAUDE_TUI_MODE` unset) is byte-for-byte unchanged.
+
+### TUI — honesty & cache correctness (#137)
+
+- **C-1** — `callClaudeTui` now throws on a claude-CLI auth-failure banner (e.g. `Please run /login · API Error: 401 …`, `Failed to authenticate. API Error: 401 …`) instead of returning it as a real answer, so it is never cached, singleflight-shared, or counted as a model success. Conservative detector (whole trimmed text ≤100 chars + `API Error: 4xx` + auth keyword + no code/quote char); overridable via `CLAUDE_TUI_ERROR_PATTERNS`. Live-reproduced on PI231.
+- **C-2** — `readTuiTranscript` distinguishes a complete turn from a wallclock-truncated partial (`truncated` flag); `callClaudeTui` throws `tui_wallclock_truncated` so a partial is never cached or counted as success.
+- **C-3** — `verifyEntrypoint` reads the `entrypoint` field from any transcript line, not just `{system, turn_duration}` — some claude builds emit zero turn_duration lines (live-confirmed on Oracle's claude 2.1.114), which previously left the billing-drift assertion blind on those builds.
+- **C-4 (paste)** — short prompts (e.g. `hi`) could never pass paste-landing detection; threshold lowered. Live-reproduced on PI231.
+
+### TUI — concurrency & observability (#139)
+
+- **Concurrency** — `OCP_TUI_MAX_CONCURRENT` (default 2) bounds concurrent interactive `claude` boots via a queuing semaphore (`lib/tui/semaphore.mjs`); the slot is released on throw so honesty-gate / spawn failures never leak it; bounded wait-queue → `tui_queue_full` (503). Independent of the global `MAX_CONCURRENT` (8) — a TUI turn is a heavy per-request cold-boot of tmux+claude + up to 120s wallclock.
+- **Observability** — additive `/health` `tui` block (`enabled` / `entrypointMode` / `lastEntrypoint` / `entrypointMismatches` / `inflight` / `maxConcurrent`) so an operator can poll for a silent `sdk-cli` metered-pool drift (the audit's top risk) instead of grepping journald. Authorized by the ADR 0007 PR-B amendment under the ALIGNMENT grandfather provision (additive, behaviour-preserving — every pre-existing `/health` field unchanged).
+
+### Operations (#138)
+
+- `docs/runbooks/615-canary.md` — the 2026-06-15 credit-balance canary: quiesce, read the Agent SDK credit balance (manual — no programmatic API exists for that pool; OCP's `/usage` headers are subscription rate-limit data, not the credit pool), one TUI canary turn, confirm `entrypoint:cli` in the transcript, green/red decision tree, periodic auto-mode self-classification mini-canary.
+- `docs/runbooks/tui-flip-rollback.md` — flip/rollback per deployment (systemd `daemon-reload`; launchd `bootout`/`bootstrap`, not `kickstart -k`).
+- `setup.mjs` auth quick-test gated behind `OCP_SKIP_AUTH_TEST=1` (the `claude -p` probe draws from the metered Agent SDK pool after 6/15).
+
+### New environment variables
+
+- `OCP_TUI_MAX_CONCURRENT` — max concurrent interactive TUI turns (default 2) (#139).
+- `OCP_SKIP_AUTH_TEST` — skip the `claude -p` auth probe in `setup.mjs` (default off) (#138).
+
+## v3.19.0 — 2026-06-02
+
+TUI-mode reliability + proxy-purity release. Two fixes diagnosed and verified live on both test hosts (PI231 / Oracle, claude 2.1.104 / 2.1.114), each its own PR with a fresh-context reviewer (Iron Rule 10), then an adversarial multi-host test battery (0 hangs / 0 crashes / 0 injection / 0 leaks). The default path (`CLAUDE_TUI_MODE` unset) is byte-for-byte unchanged.
+
+### TUI
+
+- **#130** — Fixed the "stuck typing" hang on large multi-line prompts. Three root causes: (1) terminal-turn detection only recognized `{system, turn_duration}`, which older claude builds (e.g. 2.1.114) don't emit → the reader ran to the wallclock and returned partial text; now also accepts an `assistant` line with a final `stop_reason` (`end_turn`/`stop_sequence`/`max_tokens`), while `tool_use` stays non-terminal. (2) Large prompts pasted via `send-keys -l` delivered embedded newlines as separate Enter events → the prompt never landed; now uses `tmux load-buffer` + `paste-buffer -p` (bracketed paste, atomic). (3) The paste-landed check false-positived on claude's empty curly-quote placeholder → Enter fired into an empty box; now positive-signal-only (`[Pasted text]` / prompt text) with a readiness/paste-verify poll + fast-fail (deterministic ~5s error instead of a 120s wallclock hang).
+- **#4** — TUI-mode never injects the host's `CLAUDE.md` / auto-memory into proxied turns. OCP is a proxy: the proxied client (OpenClaw / an IDE) owns its own context and memory. `buildTuiCmd` now always sets `CLAUDE_CODE_DISABLE_CLAUDE_MDS` + `CLAUDE_CODE_DISABLE_AUTO_MEMORY` (unconditional — proxy purity is not an opt-in). Verified live with a marker `CLAUDE.md`: obeyed by the proxied turn before the fix, blocked after, on both hosts. Residual host-context vectors (managed-policy / `settings.json` / output-styles) tracked in #133. The env is delivered via an `env`-prefix on the tmux pane command (tmux does not forward the spawning process's environment, and `new-session -e` requires tmux ≥3.2 while the cloud host runs 2.7).
+
+## v3.18.0 — 2026-06-01
+
+Hardening release from a multi-agent code audit (1 P0 + 14 P2 + 2 P3 findings, each adversarially verified and independently reviewed) plus three follow-ups (#123–#125). Every change shipped as its own PR with a fresh-context reviewer (Iron Rule 10). The single-user default path (`AUTH_MODE=none`, no TUI) is behavior-identical **except** the `/health` change in #109.
+
+### Security
+
+- **#109 (P0)** — `/health` no longer advertises `PROXY_ANONYMOUS_KEY` to remote callers by default. The `anonymousKey` field is gated behind a new `PROXY_ADVERTISE_ANON_KEY=1` opt-in env var; localhost callers are always exempt. Prevents any LAN-reachable device from harvesting a working, quota-spending bearer credential from the unauthenticated `/health` endpoint. **Behavior change:** `ocp-connect` zero-config Path A now requires the server to set `PROXY_ADVERTISE_ANON_KEY=1`; otherwise pass `--key` or use anonymous access.
+- **#114** — Dashboard escapes all DB-sourced strings (key names, usage rows) before `innerHTML`; the revoke button uses a `data-` attribute + listener instead of an inline `onclick` a quote could break out of; `POST /api/keys` validates key names server-side (`[A-Za-z0-9 ._-]{1,64}`).
+- **#124** — Dashboard status/plan summary cards escaped too (uniform defense-in-depth over all `innerHTML` sinks).
+- **#111** — Streaming error paths strip filesystem paths from claude error text / stderr before sending them to clients (`sanitizeError`), matching the non-streaming path.
+
+### Reliability / correctness
+
+- **#110** — Non-array `messages` is rejected with a 400 (was silently hanging the connection until socket timeout); OpenAI array `content` is flattened into the prompt instead of dumped as raw JSON; a streamed upstream error now emits an SSE `error` frame instead of a success-looking `finish_reason:"stop"`.
+- **#111** — `res.on("close")` escalates SIGTERM→SIGKILL on client disconnect (closes a narrow re-occurrence of the #37 concurrency-slot leak on the hottest exit path); `overallTimer` is cleared on semantic completion so a slow-exiting child can't record a spurious post-success timeout; per-key quota is documented as best-effort (bounded overshoot ≤ `MAX_CONCURRENT`, cache hits uncounted).
+- **#113** — CLI/installer hardening: `ocp-plugin` restart uses the live uid + `dev.ocp.proxy`/`ocp-proxy` labels and drops the unsafe `pkill` fallback; `ocp-connect` quotes + `chmod 600`s the persisted key; `setup.mjs` XML-escapes and newline-validates injected service-unit secrets.
+
+### Alignment / governance
+
+- **#112** — OAuth token-refresh host (`platform.claude.com/v1/oauth/token`) re-verified against the compiled cli.js v2.1.154 (`strings`, no live probe) and recorded in `ALIGNMENT.md`; usage-probe and default request model now derive from `models.json` (ADR 0003 SPOT) instead of hardcoded IDs.
+- **#123** — The legacy `console.anthropic.com/v1/oauth/token` host is pinned in the `alignment.yml` blacklist so a future OAuth-host drift hard-fails CI; the blacklist now documents its dual purpose (known hallucinations + pinned wrong-host variants of a verified Class A endpoint).
+
+### TUI
+
+- **#115** — The TUI LAN gate refuses any non-loopback bind (not just literal `0.0.0.0`); the achieved `cc_entrypoint` is asserted each turn and a `tui_entrypoint_mismatch` warning is logged on a silent degrade to the metered sdk-cli pool.
+
+### Refactor
+
+- **#125** — `isLoopbackBind` extracted to `lib/net.mjs`, shared by `server.mjs` and the test suite (was duplicated via a copy-paste mirror).
+
+### New environment variables
+
+- `PROXY_ADVERTISE_ANON_KEY` — opt-in (default off); advertise `PROXY_ANONYMOUS_KEY` on the public `/health` body for remote zero-config discovery (#109).

 ## v3.17.1 — 2026-05-31

@@ -50,6 +50,10 @@ OCP and the alternatives serve adjacent but distinct needs. Pick the one that fi

 **Plain English**: `claude-code-router` is the routing-and-switching power tool — pick it if you want to mix Anthropic, OpenAI, Gemini, and local models behind one endpoint. `anthropic-proxy` is the minimal forwarder. **OCP focuses on disciplined `cli.js`-aligned forwarding plus subscription multiplexing** — pick it if you want to share one Claude Pro/Max subscription across IDEs, devices, and people, with LAN auth, quotas, and a governance contract that prevents endpoint drift.

+### Related: OLP — Open LLM Proxy
+
+OCP is Claude-only by design. If you want to spread across **multiple LLM providers** (not just Claude), see the sibling project **[OLP — Open LLM Proxy](https://github.com/dtzp555-max/olp)**: the same spawn-the-provider-CLI approach, but across several provider CLIs behind one OpenAI-compatible endpoint, with intelligent fallback chains. It grew out of OCP in response to Anthropic's 2026-06-15 billing split — the idea being to spread subscription/quota risk across more than one provider. OCP remains the focused, Claude-only option; OLP is the multi-provider one.
+
 OCP is single-maintainer + LLM-assisted, currently pre-1.0. It runs the maintainer's daily Claude Code workflow. If something breaks, [open an issue](https://github.com/dtzp555-max/ocp/issues).

 ## Supported Tools
@@ -281,7 +285,7 @@ chmod +x ocp-connect
 ./ocp-connect <server-ip>
 ```

-**Zero-config** — when the server admin has set `PROXY_ANONYMOUS_KEY` (see [Anonymous Access](#anonymous-access-optional) below), just pass the server IP and nothing else. `ocp-connect` reads the anonymous key from `/health` and uses it automatically:
+**Zero-config** — when the server admin has set `PROXY_ANONYMOUS_KEY` *and* opted in with `PROXY_ADVERTISE_ANON_KEY=1` (see [Anonymous Access](#anonymous-access-optional) below), just pass the server IP and nothing else. `ocp-connect` reads the anonymous key from `/health` and uses it automatically. Without the opt-in, `/health` does not expose the key (issue #109); pass `--key` or rely on anonymous access instead:

 ```bash
 ./ocp-connect <server-ip>
@@ -366,7 +370,7 @@ OCP Connect v1.3.0
 The script automatically:
 - Writes env vars to all relevant shell rc files (`.bashrc`, `.zshrc`)
 - Sets system-level env vars (`launchctl setenv` on macOS, `environment.d` on Linux)
- **Auto-discovers anonymous key** from `/health.anonymousKey` when no `--key` given (v1.3.0+, requires server v3.10.0+)
+- **Auto-discovers anonymous key** from `/health.anonymousKey` when no `--key` given (v1.3.0+, requires server v3.10.0+; server must also set `PROXY_ADVERTISE_ANON_KEY=1` — see [Anonymous Access](#anonymous-access-optional))
 - Configures OpenClaw automatically (including per-agent `auth-profiles.json` for multi-agent setups)
 - Detects Cline, Continue.dev, Cursor, and opencode, and prints setup hints (manual configuration required for these IDEs)

@@ -405,10 +409,22 @@ ocp keys revoke son-ipad   # Revoke a key
 |------|-----|----------|
 | `none` | `CLAUDE_AUTH_MODE=none` | Trusted home network, no auth needed |
 | `shared` | `CLAUDE_AUTH_MODE=shared` + `PROXY_API_KEY=xxx` | Everyone shares one key |
-| `multi` | `CLAUDE_AUTH_MODE=multi` + `OCP_ADMIN_KEY=xxx` | Per-person keys with usage tracking (recommended) |
+| `multi` | `CLAUDE_AUTH_MODE=multi` + `OCP_ADMIN_KEY=xxx` | Per-person keys for usage tracking + quotas (trusted users only — see Deployment model below) |

 > **Usage scope (v3.14.0+):** `/api/usage` returns the caller's own rows by default. Admin callers must pass `?all=true` to retrieve data for all keys; doing so emits an audit log line.

+### Deployment model & security (read this)
+
+**What OCP is built for today: single-user, multi-IDE.** Run OCP as a server on one machine and point all of *your own* IDEs/devices at it — one Claude Pro/Max subscription, used everywhere. This is the primary, solid use case.
+
+**Sharing with family / a team — honest limits.** You *can* share OCP on a LAN, but be clear about what the auth modes do and don't give you:
+
+- The per-key modes (`shared` / `multi`) give per-key **usage tracking, quotas, and cache separation** — useful for seeing who used what and capping budgets.
+- They do **not** give a **security isolation boundary**. The spawned `claude` runs with the **operator's filesystem access** and is *not* sandboxed per key. **Only share with people you fully trust, on a trusted network.**
+- For simple trusted family sharing, the easiest setup is a single shared **anonymous key** (see [Anonymous Access](#anonymous-access-optional)) — no per-person separation, same trust assumption.
+
+**Real per-user isolation (sandboxed, multi-tenant-safe) is planned for after 2026-06-15** — per-key ephemeral home + tool lockdown + an OS sandbox. Until then, treat a multi-user OCP as a *trusted-group convenience*, not a security boundary. (This is also why `CLAUDE_TUI_MODE` is single-user-only — see [Subscription-pool (TUI) mode](#subscription-pool-tui-mode).)
+
 ### Anonymous Access (optional)

 In `multi` mode, the admin can designate a single well-known "anonymous" key that bypasses `validateKey()` and grants public read/write access. This is useful for letting LAN users (or clients like OpenClaw multi-agent setups) connect without individual per-user keys.
@@ -424,7 +440,7 @@ node setup.mjs --bind 0.0.0.0 --auth-mode multi

 If OCP is already installed without it, re-export the env var and re-run `node setup.mjs` (the installer is idempotent — it refreshes the service unit). Then `ocp restart` so the running proxy picks up the new env. Setting `PROXY_ANONYMOUS_KEY` only in your interactive shell **does not** affect the auto-started proxy — the service unit is the source of truth for its environment.

-**Client side**: the anonymous key value is exposed via `GET /health` as the field `anonymousKey` (null when not set). Clients like `ocp-connect` can auto-discover and use it, so the end user doesn't need to get a personal key from the admin.
+**Client side**: the anonymous key value is exposed via `GET /health` as the field `anonymousKey` (null when not set) **only to localhost callers** or when the admin has also set `PROXY_ADVERTISE_ANON_KEY=1` (default off — see issue #109). With that opt-in, clients like `ocp-connect` can auto-discover and use it, so the end user doesn't need to get a personal key from the admin.

 **Security note**: setting this env var is an **opt-in** to public access — anyone who can reach your OCP endpoint can use it, up to any rate limits you configure. Don't enable this on internet-exposed OCP instances without additional protection.

@@ -470,6 +486,8 @@ When a key exceeds its quota, OCP returns HTTP 429 with a structured error:
 - Admin and anonymous users are never subject to quotas
 - PATCH is a partial update — omitted fields are left unchanged

+> **Note:** quotas are best-effort. Under concurrent bursts a key can exceed its cap by up to the server's max-concurrency (default 8), and cache hits are not counted toward quota. They cap budgets for cooperative family use, not adversarial abuse.
+
 ### Important Notes

 - All users share your Claude Pro/Max **rate limits** (5h session + 7d weekly)
@@ -707,7 +725,7 @@ The canonical list lives in [`models.json`](./models.json) — the single source
 |----------|--------|-------------|
 | `/v1/models` | GET | List available models |
 | `/v1/chat/completions` | POST | Chat completion (streaming + non-streaming) |
-| `/health` | GET | Comprehensive health check |
+| `/health` | GET | Comprehensive health check (includes a `tui` block for TUI-mode drift/concurrency monitoring) |
 | `/usage` | GET | Plan usage limits + per-model stats |
 | `/status` | GET | Combined overview (usage + health) |
 | `/settings` | GET/PATCH | View or update settings at runtime |
@@ -873,12 +891,16 @@ Future `ocp update` invocations sync automatically.
 | `CLAUDE_SKIP_PERMISSIONS` | `false` | Bypass all permission checks |
 | `CLAUDE_NO_CONTEXT` | `false` | Suppress CLAUDE.md and auto-memory injection (pure API mode) |
 | `PROXY_API_KEY` | *(unset)* | Bearer token for shared-mode authentication |
-| `PROXY_ANONYMOUS_KEY` | *(unset)* | Well-known anonymous key allowlist (multi mode). When set, this exact string bypasses `validateKey()` and grants public access. Exposed via `/health.anonymousKey` so clients auto-discover. See [Anonymous Access](#anonymous-access-optional). |
+| `PROXY_ANONYMOUS_KEY` | *(unset)* | Well-known anonymous key allowlist (multi mode). When set, this exact string bypasses `validateKey()` and grants public access. Exposed via `/health.anonymousKey` only to localhost, or to all callers when `PROXY_ADVERTISE_ANON_KEY=1`. See [Anonymous Access](#anonymous-access-optional). |
+| `PROXY_ADVERTISE_ANON_KEY` | *(unset)* | When `=1`, advertise `PROXY_ANONYMOUS_KEY` in the public `/health` body for remote zero-config discovery. Default off — `/health` is unauthenticated, so this exposes the shared key to any LAN-reachable device (issue #109). Localhost always sees it regardless. |
 | `CLAUDE_TUI_MODE` | `false` | **Opt-in.** Set to `"true"` to serve requests via interactive `claude` (no `-p` / `--output-format` → `cc_entrypoint=cli`, subscription pool). **Single-user only** — see [Subscription-pool (TUI) mode](#subscription-pool-tui-mode) for the security constraint. |
 | `CLAUDE_TUI_WALLCLOCK_MS` | `120000` | (TUI-mode) Maximum time in ms to wait for the native transcript to signal turn completion. Increase for long Opus thinking turns. |
 | `OCP_TUI_CWD` | `$HOME/.ocp-tui/work` | (TUI-mode) Scratch working directory where interactive claude sessions run. Transcripts land under `<HOME>/.claude/projects/<encoded-cwd>/`. Created automatically. |
 | `OCP_TUI_HOME` | `$HOME` (real home) | (TUI-mode) `HOME` claude runs under. Default is the operator's real home (shared credentials, existing onboarding). Set to a separate path for scratch-home isolation — see ADR 0007 for the credential-fork caveat. |
 | `OCP_TUI_ENTRYPOINT` | `cli` | (TUI-mode) Billing-classifier labeling: `cli` (default) pins `cc_entrypoint=cli` deterministically; `auto` lets claude self-classify via TTY detection; `off` leaves the inherited env untouched. Honest only when the spawn is a genuine interactive PTY — see ADR 0007. |
+| `OCP_TUI_MAX_CONCURRENT` | `2` | (TUI-mode) Max concurrent interactive TUI turns. **Independent** of `CLAUDE_MAX_CONCURRENT` (which bounds the `-p`/stream-json path; TUI never uses it). A TUI turn is heavy (per-request cold-boot of tmux+claude + up to `CLAUDE_TUI_WALLCLOCK_MS` wallclock), so the default is low to keep small hosts (e.g. a Pi 4) alive under a burst. Excess turns **queue** (bounded); a full queue yields a 503. See ADR 0007 PR-B amendment. |
+| `OCP_SKIP_AUTH_TEST` | *(unset)* | When `=1`, skip the `claude -p` auth probe during `setup.mjs`. After 2026-06-15 this probe draws from the Agent SDK credit pool; set this to avoid burning a metered credit on re-installs or `ocp update` runs. Auth is validated at the first real request. |
+| `OCP_TUI_FULL_TOOLS` | *(unset)* | (TUI-mode, **single-user only**) When `=1`, grant the interactive session the **same tool surface as the `-p` path** — `--allowedTools` (+ optional `--mcp-config` / `--dangerously-skip-permissions`, read from `CLAUDE_ALLOWED_TOOLS` / `CLAUDE_MCP_CONFIG` / `CLAUDE_SKIP_PERMISSIONS`) — instead of the default MCP-walled, built-in-tools-only set. Lets a trusted single-operator TUI deployment run a **tool-using / MCP agent** (e.g. an OpenClaw assistant) on the subscription pool. Safe because TUI **refuses to boot under `AUTH_MODE=multi`** (hard exit) — no guest key can ever reach the TUI path, so this gate cannot expose tools to an untrusted caller. (Under `AUTH_MODE=shared` + `OCP_TUI_ALLOW_LAN=1`, anyone holding the single shared key reaches it — that is the existing TUI trust model, unchanged.) See [Subscription-pool (TUI) mode](#subscription-pool-tui-mode) and ADR 0007. |

 ### Streaming heartbeat

@@ -942,7 +964,27 @@ Then restart OCP. At boot you will see:
 - **Callers see no API change.** The response is a normal OpenAI completion object or chunked SSE — identical wire format.
 - **No real token streaming.** TUI-mode buffers the full response then replays it as chunked SSE. You will see a delay then the complete response rather than real-time tokens.
 - **Cache and singleflight work normally.** TUI-mode writes the buffered response to the cache on success; cache-hits skip the interactive turn entirely.
+- **The host's `CLAUDE.md` / auto-memory is never injected.** OCP is a proxy — the proxied client (OpenClaw / your IDE) owns its own context and memory. TUI-mode always runs `claude` with `CLAUDE_CODE_DISABLE_CLAUDE_MDS` + `CLAUDE_CODE_DISABLE_AUTO_MEMORY`, so a `CLAUDE.md` on the OCP host can never leak into proxied turns (verified live; see #4). Built-in tool schemas + the interactive system prompt remain (the inherent ~20–35K context floor of interactive mode); MCP is hard-disabled.
 - **Default path unchanged.** Unset `CLAUDE_TUI_MODE` and restart → `callClaude` / `callClaudeStreaming` are used again, byte-for-byte identical to today.
+- **Concurrency is bounded separately.** TUI turns are heavy (per-request cold-boot + long wallclock), so the TUI path has its own limiter — `OCP_TUI_MAX_CONCURRENT` (default `2`), independent of `CLAUDE_MAX_CONCURRENT`. Excess turns queue; a full queue returns a 503. Tune it up only on a host that can run more interactive `claude` sessions at once.
+
+### Monitoring drift via `/health`
+
+`GET /health` includes a `tui` block so you can poll for a silent billing-pool drift (the top risk after the 6/15 flip — a lost TTY flipping `cc_entrypoint` from `cli` to the metered `sdk-cli` pool would still return answers but burn metered credits). The block is **always present** (with `enabled:false` when TUI-mode is off):
+
+```jsonc
+"tui": {
+  "enabled": true,             // CLAUDE_TUI_MODE === "true"
+  "entrypointMode": "cli",     // OCP_TUI_ENTRYPOINT (cli | auto | off)
+  "lastEntrypoint": "cli",     // last cc_entrypoint observed in a transcript, or null
+  "entrypointMismatches": 0,   // count of cli-expected-but-got-other turns — ALERT if this climbs
+  "inflight": 1,               // TUI turns running right now
+  "queued": 0,                 // TUI turns waiting for a concurrency slot
+  "maxConcurrent": 2           // OCP_TUI_MAX_CONCURRENT
+}
+```
+
+Alert on `entrypointMismatches > 0` (or `lastEntrypoint !== "cli"`): it means a turn drew from the metered Agent SDK pool instead of the subscription. `inflight` / `queued` show how close the TUI path is to its concurrency cap.

 ### Kill-switch

@@ -953,6 +995,13 @@ unset CLAUDE_TUI_MODE

 The stream-json path is restored immediately. No other change is needed.

+### 2026-06-15 operator checklist
+
+Every host serving traffic must be flipped to TUI-mode **and** canary-verified before 2026-06-15, or it will bill the metered Agent SDK credit pool instead of the subscription.
+
+- **[Flip/rollback runbook](docs/runbooks/tui-flip-rollback.md)** — how to set `CLAUDE_TUI_MODE=true` on systemd (Linux) and launchd (macOS) hosts. Covers the `daemon-reload` requirement (systemd) and the `bootout`+`bootstrap` cycle requirement (launchd — `launchctl kickstart -k` does not reload plist env).
+- **[615-canary runbook](docs/runbooks/615-canary.md)** — after each flip, run one quiesced request and compare the Agent SDK credit balance before and after. `entrypoint:cli` in the transcript (the `cc_entrypoint` billing classifier) is necessary but not sufficient — only a stable credit balance confirms the subscription pool is being used. Balance check is a manual step (no known programmatic API for the Agent SDK credit pool balance).
+
 ### Architecture and design decisions

 See [`docs/adr/0007-tui-interactive-mode.md`](docs/adr/0007-tui-interactive-mode.md) for the full rationale, home-strategy options, MCP-disable mechanism, coexistence rules, and the B-path (multi-tenant isolation) roadmap.
@@ -132,6 +132,10 @@ function fmtChars(n) {
  return n > 1000 ? (n/1000).toFixed(0) + "K" : String(n);
 }

+function escapeHtml(s) {
+  return String(s ?? "").replace(/[&<>"']/g, c => ({ "&": "&amp;", "<": "&lt;", ">": "&gt;", '"': "&quot;", "'": "&#39;" }[c]));
+}
+
 function barColor(pct) {
  if (pct >= 80) return "bar-red";
  if (pct >= 50) return "bar-amber";
@@ -144,8 +148,8 @@ async function refreshStatus() {
  const r = data.requests || {};

  document.getElementById("status-cards").innerHTML = `
-    <div class="card"><div class="label">Status</div><div class="value"><span class="tag ${p.status === 'ok' ? 'tag-ok' : 'tag-err'}">${p.status || '?'}</span></div><div class="sub">v${p.version || '?'}</div></div>
-    <div class="card"><div class="label">Uptime</div><div class="value">${p.uptime || '?'}</div></div>
+    <div class="card"><div class="label">Status</div><div class="value"><span class="tag ${p.status === 'ok' ? 'tag-ok' : 'tag-err'}">${escapeHtml(p.status || '?')}</span></div><div class="sub">v${escapeHtml(p.version || '?')}</div></div>
+    <div class="card"><div class="label">Uptime</div><div class="value">${escapeHtml(p.uptime || '?')}</div></div>
    <div class="card"><div class="label">Requests</div><div class="value">${r.total || 0}</div><div class="sub">${r.active || 0} active</div></div>
    <div class="card"><div class="label">Errors</div><div class="value">${r.errors || 0}</div><div class="sub">${r.timeouts || 0} timeouts</div></div>
    <div class="card"><div class="label">Sessions</div><div class="value">${p.activeSessions || 0}</div></div>
@@ -160,15 +164,15 @@ async function refreshStatus() {
    document.getElementById("plan-cards").innerHTML = `
      <div class="card">
        <div class="label">Session (5h)</div>
-        <div class="value">${s.percent || '?'}</div>
+        <div class="value">${escapeHtml(s.percent || '?')}</div>
        <div class="bar-bg"><div class="bar-fill ${barColor(sPct)}" style="width:${sPct}%"></div></div>
-        <div class="sub">Resets in ${s.resetsIn || '?'}</div>
+        <div class="sub">Resets in ${escapeHtml(s.resetsIn || '?')}</div>
      </div>
      <div class="card">
        <div class="label">Weekly (7d)</div>
-        <div class="value">${w.percent || '?'}</div>
+        <div class="value">${escapeHtml(w.percent || '?')}</div>
        <div class="bar-bg"><div class="bar-fill ${barColor(wPct)}" style="width:${wPct}%"></div></div>
-        <div class="sub">Resets in ${w.resetsIn || '?'}</div>
+        <div class="sub">Resets in ${escapeHtml(w.resetsIn || '?')}</div>
      </div>
    `;
  }
@@ -181,21 +185,21 @@ async function refreshUsage() {
    const tbody = document.querySelector("#key-usage-table tbody");
    tbody.innerHTML = (data.byKey || []).map(k => `
      <tr>
-        <td>${k.key_name}</td>
+        <td>${escapeHtml(k.key_name)}</td>
        <td>${k.requests}</td>
        <td>${k.successes}</td>
        <td>${k.errors}</td>
        <td>${fmtTime(k.avg_elapsed_ms)}</td>
-        <td class="mono">${k.last_request || '-'}</td>
+        <td class="mono">${escapeHtml(k.last_request || '-')}</td>
      </tr>
    `).join("") || '<tr><td colspan="6" style="color:#475569">No usage data yet</td></tr>';

    const rtbody = document.querySelector("#recent-table tbody");
    rtbody.innerHTML = (data.recent || []).slice(0, 20).map(r => `
      <tr>
-        <td class="mono">${r.created_at?.slice(11, 19) || '?'}</td>
-        <td>${r.key_name}</td>
-        <td>${r.model}</td>
+        <td class="mono">${escapeHtml(r.created_at?.slice(11, 19) || '?')}</td>
+        <td>${escapeHtml(r.key_name)}</td>
+        <td>${escapeHtml(r.model)}</td>
        <td>${fmtChars(r.prompt_chars)}</td>
        <td>${fmtChars(r.response_chars)}</td>
        <td>${fmtTime(r.elapsed_ms)}</td>
@@ -216,13 +220,16 @@ async function refreshKeys() {
    const tbody = document.querySelector("#keys-table tbody");
    tbody.innerHTML = (data.keys || []).map(k => `
      <tr>
-        <td>${k.name}</td>
-        <td class="mono">${k.keyPreview}</td>
-        <td class="mono">${k.created_at}</td>
+        <td>${escapeHtml(k.name)}</td>
+        <td class="mono">${escapeHtml(k.keyPreview)}</td>
+        <td class="mono">${escapeHtml(k.created_at)}</td>
        <td><span class="tag ${k.revoked ? 'tag-err' : 'tag-ok'}">${k.revoked ? 'revoked' : 'active'}</span></td>
-        <td>${k.revoked ? '' : `<button class="btn btn-sm btn-danger" onclick="revokeKeyUI('${k.name}')">Revoke</button>`}</td>
+        <td>${k.revoked ? '' : `<button class="btn btn-sm btn-danger" data-revoke="${escapeHtml(k.name)}">Revoke</button>`}</td>
      </tr>
    `).join("");
+    tbody.querySelectorAll("button[data-revoke]").forEach(btn =>
+      btn.addEventListener("click", () => revokeKeyUI(btn.getAttribute("data-revoke")))
+    );
  } catch(e) { /* not admin */ }
 }

@@ -139,6 +139,101 @@ B-path is **deferred** and is not implemented in this ADR. Until B-path lands, T

 ---

+## Observability and concurrency (PR-B amendment)
+
+**Date:** 2026-06-10
+**Status:** Accepted — amends ADR 0007.
+**Motivation:** the post-PR-A code audit, findings C-4 (P1) and C-5 (P1).
+
+### C-4 — independent concurrency bound for the TUI path
+
+The global `MAX_CONCURRENT` gate lives in `spawnClaudeProcess()` (the `-p` / stream-json
+path). `callClaudeTui()` never calls `spawnClaudeProcess` — it calls `runTuiTurn()`, which
+cold-boots a full interactive `claude` inside a fresh tmux session. So the TUI path had **no**
+concurrency bound: N concurrent TUI requests spawned N simultaneous cold-boot tmux+claude
+processes. On a small host (e.g. a Pi 4 serving a family) a burst of ~5 is an OOM risk and
+also multiplies subscription rate-limit pressure.
+
+PR-B adds an **independent** limiter for the TUI path (`lib/tui/semaphore.mjs`,
+`TuiSemaphore`):
+
+- **`OCP_TUI_MAX_CONCURRENT`, default `2`.** Rationale: a TUI turn is heavy — a per-request
+  cold-boot of tmux+claude plus up to `CLAUDE_TUI_WALLCLOCK_MS` (120 s) of wallclock — so a
+  small host cannot run many at once. `2` is the conservative default that keeps a Pi-class
+  host alive under a family burst while still allowing some overlap. It is deliberately **not**
+  the same knob as `MAX_CONCURRENT` (default 8): the two pools have different shapes (a
+  stream-json spawn is cheap and fast; a TUI turn is a heavy cold-boot + long wallclock), so
+  coupling them would mis-size one of the two paths.
+- **Queue, don't reject.** The limiter **queues** (awaits a slot), mirroring the spirit of
+  `MAX_CONCURRENT` — requests are not dropped on contention. To bound memory against a runaway
+  client, the wait queue itself is capped (`maxQueue`, default 32× the limit); when the queue
+  is full `run()` rejects with `tui_queue_full`, surfaced as a 503 — deterministic backpressure
+  rather than silent OOM.
+- **Slot released in a `finally`.** `TuiSemaphore.run(fn)` releases the slot in a `finally`, so
+  any throw — PR-A's honesty gates (`tui_wallclock_truncated`, `tui_upstream_error`), a
+  `tui_paste_not_landed`, or a `tui_spawn_failed` — can never leak a slot.
+
+This limiter has **zero effect when `TUI_MODE` is off**: `callClaudeTui` is never reached, so
+the semaphore is never entered. The default stream-json path is untouched.
+
+### C-5 — operator-visible drift surface on `/health` (additive)
+
+The `tui_entrypoint_mismatch` warning only reached journald. After the 2026-06-15 flip, a
+silent `sdk-cli` drift (the documented top risk in this ADR — a lost TTY flipping the
+self-classification to the metered Agent SDK pool) would drain metered credits **invisibly**.
+PR-B adds a `tui` block to the `/health` JSON response so an operator can poll it:
+
+```
+tui: {
+  enabled:              <TUI_MODE>,
+  entrypointMode:       <OCP_TUI_ENTRYPOINT>,   // cli | auto | off
+  lastEntrypoint:       <last observed cc_entrypoint, e.g. "cli", or null>,
+  entrypointMismatches: <count of cli-expected-but-got-other turns>,
+  inflight:             <current concurrent TUI turns>,
+  queued:               <turns waiting for a slot>,
+  maxConcurrent:        <OCP_TUI_MAX_CONCURRENT>
+}
+```
+
+`lastEntrypoint` is recorded and `entrypointMismatches` incremented inside `callClaudeTui` in
+the same mismatch branch that already emits the journald warning (via `recordTuiEntrypoint`).
+`inflight` / `queued` / `maxConcurrent` come from the C-4 semaphore. When `TUI_MODE` is off the
+block still appears with `enabled:false` (cheap, harmless) so the response shape is stable for
+consumers regardless of mode.
+
+### ALIGNMENT authorization for the `/health` change
+
+`/health` is a **grandfathered B.2 endpoint** under ADR 0006, frozen at its v3.16.4 behaviour.
+`ALIGNMENT.md`'s grandfather provision states: *"Any change to the contract (request shape,
+response shape, semantics) of a grandfathered B.2 endpoint is treated as a new authorization
+request and requires either a behaviour-preserving refactor PR or its own ADR."*
+
+This amendment **is** that authorization. The argument:
+
+- The change is **additive**: it adds one new top-level field (`tui`) containing only new
+  sub-fields. **No existing `/health` field is changed, renamed, removed, or re-typed**, and no
+  existing semantics change. Existing `/health` consumers (the dashboard, `ocp-connect`,
+  monitoring) read the fields they already read and are unaffected — the change is
+  **behaviour-preserving** for them, which is exactly the bar the grandfather provision sets for
+  a non-ADR contract change.
+- The TUI observability surface is an **intrinsic part of the TUI feature** whose authorizing
+  authority is **this ADR (0007)**, not a brand-new B.2 endpoint. We are not adding a new B.2
+  endpoint or a new method (which would each require their own fresh ADR under the New Class B
+  endpoint procedure) — we are extending the response of an existing grandfathered endpoint with
+  fields that report state owned by an ADR-0007 feature. ADR 0007 is the natural home for that
+  authority, and this amendment records it explicitly.
+- `cli.js` does not perform this operation — `/health` is OCP-owned (Class B), so no `cli.js`
+  citation applies; the citation is this ADR + ADR 0006 (grandfathered B.2) per
+  `ALIGNMENT.md`'s Class B citation requirement.
+
+### `OCP_TUI_MAX_CONCURRENT` summary
+
+| Env var | Default | Meaning |
+|---|---|---|
+| `OCP_TUI_MAX_CONCURRENT` | `2` | Max concurrent interactive TUI turns. Independent of `CLAUDE_MAX_CONCURRENT` (the stream-json path). Excess turns queue (bounded); a full queue yields a 503. |
+
+---
+
 ## Consequences

 ### Positive
@@ -0,0 +1,151 @@
+# 2026-06-15 Canary Runbook
+
+**Purpose:** Confirm that a TUI-mode turn is billed to the **Pro/Max subscription pool** (not the Agent SDK credit pool) after Anthropic's 2026-06-15 billing split activates.
+
+The billing classifier reading `cli` is **necessary but NOT sufficient** proof. (Note the naming: the value is stored in the JSONL transcript under the field name `entrypoint`, and sent to Anthropic on the wire as the `cc_entrypoint` header — they carry the same value after claude's startup classification. The commands below grep the transcript, so they match `entrypoint`.) A `cli` label tells you OCP sent the right classification; it does not tell you Anthropic billed the right pool. The only authoritative test is to observe whether the **Agent SDK credit balance** moves or not before and after the canary turn.
+
+---
+
+## Prerequisites
+
+- `CLAUDE_TUI_MODE=true` already set and OCP restarted (see [TUI-mode setup in README](../../README.md#enabling-tui-mode-opt-in))
+- `tmux` installed on the host
+- No other OCP traffic during the canary (quiesce — see below)
+- Access to your Anthropic account billing page (manual step — see below)
+
+---
+
+## Step 1 — Quiesce the host
+
+Stop any IDE or client that is actively sending requests through this OCP instance.
+
+Confirm the proxy is idle:
+
+```bash
+curl -s http://127.0.0.1:3456/health | python3 -m json.tool | grep activeRequests
+# Expected: "activeRequests": 0
+```
+
+Wait until `activeRequests` is `0` before proceeding. If you cannot quiesce (e.g. family members are actively using it), run the canary on a separate OCP instance or during a quiet window.
+
+---
+
+## Step 2 — Read the Agent SDK credit balance BEFORE the canary
+
+> **Manual step — no programmatic API available.**
+>
+> OCP's `/usage` endpoint reads `anthropic-ratelimit-unified-*` response headers from the Pro/Max plan quota (5-hour and 7-day subscription windows). These headers report **subscription usage**, not the Agent SDK credit pool balance. There is no known programmatic API to query the Agent SDK credit pool balance from outside the Anthropic web app.
+
+To read the balance:
+
+1. Open [https://claude.ai/settings/billing](https://claude.ai/settings/billing) (or your Anthropic Console billing page) in a browser.
+2. Find the **Agent SDK Credits** section (sometimes labeled "API Credits" or "Agent SDK usage").
+3. Note the current balance (e.g. `$18.43 remaining of $20.00`).
+
+Write the value down — you will compare it after the canary turn.
+
+---
+
+## Step 3 — Send the canary turn
+
+With TUI-mode on and the host quiesced, send exactly one small request:
+
+```bash
+curl -s -X POST http://127.0.0.1:3456/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "claude-haiku-4-5-20251001",
+    "messages": [{"role": "user", "content": "Reply with the single word: pong"}],
+    "max_tokens": 10
+  }' | python3 -m json.tool
+```
+
+Use Haiku (the cheapest model) to minimize any hypothetical impact if the canary turns red.
+
+Wait for the response to arrive completely (TUI-mode buffers the full response before returning — you will see a delay of several seconds, then the full reply).
+
+---
+
+## Step 4 — Confirm the transcript shows `entrypoint:"cli"`
+
+After the canary turn completes, inspect the most recent JSONL transcript for the billing-classifier label:
+
+```bash
+# The canary was run quiesced (Step 1), so the most recent JSONL across ALL project
+# dirs IS the canary turn. We glob every projects subdir instead of recomputing
+# claude's cwd-encoding rule (it maps every "/" AND "." to "-", e.g. ~/.ocp-tui/work
+# => projects/-home-<user>--ocp-tui-work/; see lib/tui/transcript.mjs encodeCwd) —
+# a glob is robust even if that encoding changes in a future claude build.
+LATEST=$(ls -t "$HOME"/.claude/projects/*/*.jsonl 2>/dev/null | head -1)
+echo "Transcript: $LATEST"
+grep -o '"entrypoint":"[^"]*"' "$LATEST" | tail -1
+# Expected: "entrypoint":"cli"
+```
+
+If the output shows `"entrypoint":"cli"`, the billing-classifier label is correct. If it shows `"entrypoint":"sdk-cli"`, the spawn did not get a real PTY — stop immediately and do not re-enable TUI-mode without investigation. Check `tmux new-session` manually and review ADR 0007 § spawn/PTY gate. (If the grep returns nothing, the transcript may not yet be flushed — re-run after a second, or confirm the turn completed.)
+
+**Reminder: an `entrypoint:cli` label (the `cc_entrypoint=cli` wire header) is necessary but not sufficient.** It tells you OCP sent the right label to Anthropic. You must still check the credit balance in Step 5.
+
+---
+
+## Step 5 — Re-read the Agent SDK credit balance AFTER the canary
+
+Return to [https://claude.ai/settings/billing](https://claude.ai/settings/billing) and reload the page. Note the current balance again.
+
+---
+
+## Step 6 — Green/Red decision
+
+### Green (balance unchanged)
+
+The Agent SDK credit balance did not decrease. The turn billed against the Pro/Max subscription pool as expected. TUI-mode is working correctly.
+
+**Actions:**
+- Keep `CLAUDE_TUI_MODE=true` on this host.
+- Monitor the balance periodically for the first week to catch any delayed attribution.
+- Resume normal traffic.
+
+### Red (Agent SDK credit balance decreased)
+
+The Agent SDK credit balance decreased. The subscription pool is not being used for TUI-mode turns on this host, despite `cc_entrypoint=cli` being set. This may indicate a backend routing change on Anthropic's side, a TTY detection failure, or a policy change.
+
+**Actions — immediate:**
+1. Unset `CLAUDE_TUI_MODE` (or set to any value other than `"true"`) in the service unit:
+   - systemd: edit `/etc/ocp/ocp.env` (or the unit's `Environment=` line), then `sudo systemctl daemon-reload && sudo systemctl restart ocp.service`
+   - launchd: edit the plist `EnvironmentVariables` section, then `launchctl bootout gui/$(id -u)/dev.ocp.proxy && launchctl bootstrap gui/$(id -u) <plist-path>`
+2. Restart OCP and confirm the `/health` response no longer shows TUI-mode active.
+3. If you share this OCP with family or other Max users: freeze their access temporarily until you understand the billing impact.
+4. Consider pivoting to OLP multi-provider (see [OLP](https://github.com/dtzp555-max/olp)) which can spread load across other providers to avoid the Agent SDK credit drain.
+
+Per ALIGNMENT.md Rule 2 / ADR 0007 § Kill-switch: "Per the constitution, the response is to drop the Anthropic provider rather than escalate spoofing."
+
+---
+
+## Ongoing monitoring — self-classification mini-canary
+
+To detect future drift (e.g. a claude CLI upgrade that changes TTY-detection behavior), you can run a periodic one-liner that sends a tiny TUI turn with `OCP_TUI_ENTRYPOINT=auto` (so claude self-classifies rather than having OCP pin the value) and alerts if the transcript self-classification is not `cli`:
+
+```bash
+# Run with OCP temporarily configured OCP_TUI_ENTRYPOINT=auto
+# Then check the most recent transcript:
+# Glob the most recent transcript across all project dirs (robust to claude's
+# cwd-encoding rule; run this right after the auto-mode mini-canary turn).
+LATEST=$(ls -t "$HOME"/.claude/projects/*/*.jsonl 2>/dev/null | head -1)
+RESULT=$(grep -o '"entrypoint":"[^"]*"' "$LATEST" | tail -1)
+echo "Self-classified entrypoint: $RESULT"
+if echo "$RESULT" | grep -q '"entrypoint":"cli"'; then
+  echo "OK — subscription pool"
+else
+  echo "ALERT — not cli; check TTY and billing"
+fi
+```
+
+Run this after any major `claude` CLI upgrade. The `auto` mode lets the CLI's own `t$A` startup function determine the value from the actual TTY state (see ADR 0007 § Billing-classifier labeling).
+
+---
+
+## Related
+
+- [Flip/rollback runbook](./tui-flip-rollback.md) — how to set and unset `CLAUDE_TUI_MODE` on systemd and launchd hosts
+- [ADR 0007](../adr/0007-tui-interactive-mode.md) — TUI-mode architecture and governing rules
+- README § [Subscription-pool (TUI) mode](../../README.md#subscription-pool-tui-mode)
@@ -0,0 +1,180 @@
+# TUI-Mode Flip and Rollback Runbook
+
+**Purpose:** Step-by-step instructions for enabling (`CLAUDE_TUI_MODE=true`) or disabling TUI-mode on real OCP deployments managed by **systemd** (Linux) or **launchd** (macOS).
+
+Run the [615-canary](./615-canary.md) runbook after any flip to confirm billing pool routing is correct.
+
+---
+
+## Critical pitfalls — read first
+
+### systemd: `daemon-reload` is required after editing the unit
+
+Editing the unit file (or EnvironmentFile) and then doing `systemctl restart ocp.service` **without** `daemon-reload` will restart the process with the **old** environment from the cached unit. Always run `daemon-reload` after editing any unit file.
+
+### launchd: `launchctl kickstart -k` does NOT reload plist env
+
+`launchctl kickstart -k gui/$(id -u)/dev.ocp.proxy` kills the running process and re-launches it, but it **re-uses the launchd-cached environment** — not the current plist file. If you edited the plist's `EnvironmentVariables` section, you must do a full `bootout` + `bootstrap` cycle for the change to take effect. `kickstart` is not sufficient.
+
+---
+
+## Flip — enable TUI-mode
+
+### systemd (Linux, e.g. Raspberry Pi, VPS)
+
+**Option A — EnvironmentFile (recommended for clean separation)**
+
+If your unit uses `EnvironmentFile=/etc/ocp/ocp.env` (or similar):
+
+```bash
+# 1. Edit the environment file
+sudo nano /etc/ocp/ocp.env
+# Add or update:
+#   CLAUDE_TUI_MODE=true
+#
+# If OCP binds to 0.0.0.0 AND you trust the network:
+#   OCP_TUI_ALLOW_LAN=1
+#   (WARNING: TUI-mode is single-user only — only enable OCP_TUI_ALLOW_LAN=1
+#    if you fully trust every caller that can reach the OCP port on your network)
+
+# 2. Reload the unit definition and restart
+sudo systemctl daemon-reload
+sudo systemctl restart ocp.service
+
+# 3. Verify
+curl -s http://127.0.0.1:3456/health | python3 -m json.tool | grep -E "tui|version"
+# Expected: "tuiMode": true (or similar TUI indicator in the health response)
+```
+
+**Option B — inline Environment= in the unit file**
+
+```bash
+# 1. Edit the unit file
+sudo systemctl edit --full ocp.service
+# Add or update in the [Service] section:
+#   Environment=CLAUDE_TUI_MODE=true
+
+# 2. Reload and restart
+sudo systemctl daemon-reload
+sudo systemctl restart ocp.service
+
+# 3. Verify
+systemctl show ocp.service --property=Environment
+# Expected: Environment=CLAUDE_TUI_MODE=true ...
+```
+
+### launchd (macOS)
+
+Locate the OCP plist. The standard label is `dev.ocp.proxy`:
+
+```bash
+# Find the plist path
+ls ~/Library/LaunchAgents/dev.ocp.proxy.plist
+```
+
+**Edit the plist:**
+
+```bash
+# 1. Stop the service first (bootout)
+launchctl bootout gui/$(id -u)/dev.ocp.proxy
+
+# 2. Edit the plist — add CLAUDE_TUI_MODE to EnvironmentVariables
+#    Use your editor of choice:
+nano ~/Library/LaunchAgents/dev.ocp.proxy.plist
+```
+
+Inside the plist, in the `<key>EnvironmentVariables</key>` `<dict>` block, add:
+
+```xml
+<key>CLAUDE_TUI_MODE</key>
+<string>true</string>
+```
+
+If `OCP_TUI_ALLOW_LAN=1` is also needed (only if OCP binds to `0.0.0.0` and you trust the network):
+
+```xml
+<key>OCP_TUI_ALLOW_LAN</key>
+<string>1</string>
+```
+
+```bash
+# 3. Bootstrap (reload from disk + start)
+launchctl bootstrap gui/$(id -u) ~/Library/LaunchAgents/dev.ocp.proxy.plist
+
+# 4. Verify
+curl -s http://127.0.0.1:3456/health | python3 -m json.tool | grep -E "tui|version"
+```
+
+**Confirm env was actually loaded** (not just set in your shell):
+
+```bash
+ps aux | grep server.mjs | grep -v grep
+# Get the PID, then:
+# macOS: ps -E -p <PID> | tr ' ' '\n' | grep CLAUDE_TUI_MODE
+# Expected: CLAUDE_TUI_MODE=true
+```
+
+---
+
+## Rollback — disable TUI-mode
+
+Rollback is the same procedure as flip, but you **remove** `CLAUDE_TUI_MODE` or set it to any value other than `"true"` (e.g. `false`, or simply omit it).
+
+After rollback, OCP returns to the default `callClaude` / `callClaudeStreaming` stream-json path — byte-for-byte identical to the pre-TUI code path. No other change is required.
+
+### systemd rollback
+
+```bash
+# Option A — EnvironmentFile
+sudo nano /etc/ocp/ocp.env
+# Remove or comment out:
+#   CLAUDE_TUI_MODE=true
+#   OCP_TUI_ALLOW_LAN=1  (if set)
+
+sudo systemctl daemon-reload
+sudo systemctl restart ocp.service
+
+# Verify
+curl -s http://127.0.0.1:3456/health | python3 -m json.tool | grep tui
+# Expected: "tuiMode": false (or the field absent)
+```
+
+### launchd rollback
+
+```bash
+# 1. Stop
+launchctl bootout gui/$(id -u)/dev.ocp.proxy
+
+# 2. Edit plist — remove the CLAUDE_TUI_MODE and OCP_TUI_ALLOW_LAN entries from EnvironmentVariables
+
+# 3. Bootstrap
+launchctl bootstrap gui/$(id -u) ~/Library/LaunchAgents/dev.ocp.proxy.plist
+
+# 4. Verify
+curl -s http://127.0.0.1:3456/health | python3 -m json.tool | grep tui
+```
+
+---
+
+## Billing impact of staying on the default (non-TUI) path after 2026-06-15
+
+If you do NOT flip to TUI-mode and keep `CLAUDE_TUI_MODE` unset (the default), OCP continues using `claude -p --output-format stream-json`, which sets `cc_entrypoint=sdk-cli`. After 2026-06-15, every OCP request on the default path will draw from the Agent SDK credit pool (approximately $20/month on a Pro plan, or $100/month on a Max plan) rather than the Pro/Max subscription. The subscription pool usage (5-hour and 7-day windows) will be unaffected, but the Agent SDK credit balance will drain with each request.
+
+If you want to continue using OCP without TUI-mode after 2026-06-15, budget for the Agent SDK credit cost accordingly — or switch to [OLP](https://github.com/dtzp555-max/olp) for multi-provider fallback.
+
+---
+
+## Verify after any flip
+
+1. Check `/health` shows the expected `tuiMode` state.
+2. Run the [615-canary](./615-canary.md) to confirm billing pool routing.
+3. If TUI-mode is ON: check `ocp logs 10` for any TUI spawn errors (`tui_spawn_failed`, tmux errors).
+
+---
+
+## Related
+
+- [615-canary runbook](./615-canary.md) — how to verify billing pool routing after a flip
+- [ADR 0007](../adr/0007-tui-interactive-mode.md) — TUI-mode architecture; Kill-switch section
+- README § [Subscription-pool (TUI) mode](../../README.md#subscription-pool-tui-mode)
+- README § [Environment Variables](../../README.md#environment-variables) — `CLAUDE_TUI_MODE`, `OCP_TUI_ALLOW_LAN=1`
@@ -0,0 +1,9 @@
+// OCP network helpers — shared so server.mjs and tests use one definition. (issue #125)
+
+// A bind address is "loopback" only if it cannot be reached from another host.
+// Any other address (0.0.0.0, ::, a concrete LAN/Tailscale IP, etc.) is
+// network-exposed and must trigger the TUI LAN gate.
+export function isLoopbackBind(addr) {
+  return addr === "127.0.0.1" || addr === "::1" || addr === "localhost" ||
+         addr === "::ffff:127.0.0.1" || /^127\./.test(addr);
+}
@@ -0,0 +1,2 @@
+{"type":"user","entrypoint":"cli","cwd":"/tmp/tui-test","sessionId":"bbbb2222-3333-4444-5555-666677778888","version":"2.1.104","message":{"role":"user","content":[{"type":"text","text":"What is 2 + 2?"}]}}
+{"type":"assistant","entrypoint":"cli","cwd":"/tmp/tui-test","sessionId":"bbbb2222-3333-4444-5555-666677778888","version":"2.1.104","message":{"role":"assistant","model":"claude-haiku-4-5-20251001","stop_reason":"end_turn","content":[{"type":"text","text":"Failed to authenticate. API Error: 401 Invalid authentication credentials"}]}}
@@ -0,0 +1,2 @@
+{"type":"user","entrypoint":"cli","cwd":"/tmp/tui-test","sessionId":"aaaa1111-2222-3333-4444-555566667777","version":"2.1.104","message":{"role":"user","content":[{"type":"text","text":"What is 2 + 2?"}]}}
+{"type":"assistant","entrypoint":"cli","cwd":"/tmp/tui-test","sessionId":"aaaa1111-2222-3333-4444-555566667777","version":"2.1.104","message":{"role":"assistant","model":"claude-haiku-4-5-20251001","stop_reason":"end_turn","content":[{"type":"text","text":"Please run /login · API Error: 401 Invalid authentication credentials"}]}}
@@ -0,0 +1,2 @@
+{"type":"user","entrypoint":"cli","cwd":"/tmp/tui-test","sessionId":"bbbb1111-2222-3333-4444-555566667777","version":"2.1.104","message":{"role":"user","content":[{"type":"text","text":"Say PONG and nothing else."}]}}
+{"type":"assistant","entrypoint":"cli","cwd":"/tmp/tui-test","sessionId":"bbbb1111-2222-3333-4444-555566667777","version":"2.1.104","message":{"role":"assistant","model":"claude-haiku-4-5-20251001","stop_reason":"end_turn","content":[{"type":"text","text":"PONG"}]}}
@@ -0,0 +1,102 @@
+// TUI-path concurrency limiter (audit finding C-4).
+//
+// WHY THIS EXISTS, SEPARATE FROM server.mjs's MAX_CONCURRENT:
+//   The global MAX_CONCURRENT gate lives in spawnClaudeProcess() (the -p / stream-json
+//   path). callClaudeTui() NEVER calls spawnClaudeProcess — it calls runTuiTurn(), which
+//   boots a full interactive `claude` inside a fresh tmux session. So nothing bounded the
+//   TUI path: N concurrent TUI requests spawned N simultaneous cold-boot tmux+claude
+//   processes. On a small host (a Pi 4 serving a family) a burst of ~5 is an OOM risk, and
+//   it also multiplies subscription rate-limit pressure. This is an INDEPENDENT limiter for
+//   the TUI path that mirrors MAX_CONCURRENT's intent without coupling to it (the two pools
+//   are different shapes: a stream-json spawn is cheap and fast; a TUI turn is a heavy
+//   cold-boot + up to 120s wallclock).
+//
+// QUEUE vs REJECT: we QUEUE (await a slot), mirroring the spirit of MAX_CONCURRENT's
+//   intent not to drop requests, rather than rejecting immediately. To avoid unbounded
+//   memory growth from a runaway client, the wait queue itself is bounded by maxQueue
+//   (default: a generous multiple of the concurrency limit). When the queue is full, run()
+//   rejects with a tui_queue_full error (the caller surfaces it as a 503) — a deterministic
+//   backpressure signal rather than silent OOM.
+//
+// Pure + importable so test-features.mjs can assert the bound directly (no server boot).
+
+export class TuiSemaphore {
+  // limit: max concurrent slots. maxQueue: max waiters before run() rejects with backpressure.
+  constructor(limit, { maxQueue } = {}) {
+    this.limit = Math.max(1, parseInt(limit, 10) || 1);
+    // Default queue cap: 32× the limit. Large enough that real family-burst traffic never
+    // hits it, small enough that a pathological flood can't grow the queue without bound.
+    this.maxQueue = Number.isFinite(maxQueue) ? maxQueue : this.limit * 32;
+    this._inflight = 0;
+    this._waiters = []; // FIFO queue of resolve callbacks waiting for a slot
+  }
+
+  get inflight() { return this._inflight; }
+  get queued() { return this._waiters.length; }
+
+  // Acquire a slot. Resolves once a slot is free (immediately if under the limit, otherwise
+  // when an in-flight task releases). Rejects synchronously-ish if the wait queue is full.
+  acquire() {
+    if (this._inflight < this.limit) {
+      this._inflight++;
+      return Promise.resolve();
+    }
+    if (this._waiters.length >= this.maxQueue) {
+      return Promise.reject(new Error(
+        `tui_queue_full: TUI concurrency limit (${this.limit}) reached and wait queue ` +
+        `(${this.maxQueue}) is full`));
+    }
+    return new Promise((resolve) => { this._waiters.push(resolve); });
+  }
+
+  // Release a slot. If a waiter is queued, hand the slot directly to it (inflight stays
+  // constant across the handoff); otherwise decrement.
+  release() {
+    const next = this._waiters.shift();
+    if (next) {
+      next(); // the woken waiter already "owns" the slot — inflight unchanged
+    } else if (this._inflight > 0) {
+      this._inflight--;
+    }
+  }
+
+  // Run fn() under one slot. Releases in a finally so a throw (PR-A's honesty gates,
+  // wallclock truncation, paste-not-landed, tmux spawn failure) NEVER leaks a slot.
+  async run(fn) {
+    await this.acquire();
+    try {
+      return await fn();
+    } finally {
+      this.release();
+    }
+  }
+}
+
+// ── TUI drift observability (audit C-5) — pure helpers, importable for testing ──
+
+// Record an observed cc_entrypoint into the (mutable) tuiStats counter. Sets lastEntrypoint
+// unconditionally and increments entrypointMismatches when the spawn was supposed to be
+// subscription-pool ("cli") but the transcript reported something else (a silent drift to
+// the metered Agent SDK pool — the audit's top risk after the 6/15 billing flip).
+// Returns true iff this observation was a mismatch (so the caller can also emit a log).
+export function recordTuiEntrypoint(tuiStats, observed, expectedMode = "cli") {
+  tuiStats.lastEntrypoint = observed ?? null;
+  const mismatch = expectedMode === "cli" && observed !== "cli";
+  if (mismatch) tuiStats.entrypointMismatches++;
+  return mismatch;
+}
+
+// Build the additive /health `tui` block (ADR 0007 PR-B amendment). Pure: given the
+// config + live counters, returns the exact object embedded in /health. New fields only —
+// behaviour-preserving for existing /health consumers (grandfathered B.2 under ADR 0006).
+export function buildTuiHealthBlock({ enabled, entrypointMode, maxConcurrent }, tuiStats, semaphore) {
+  return {
+    enabled,
+    entrypointMode,                                  // cli | auto | off
+    lastEntrypoint: tuiStats.lastEntrypoint,         // last observed cc_entrypoint, or null
+    entrypointMismatches: tuiStats.entrypointMismatches,
+    inflight: semaphore.inflight,                    // current concurrent TUI turns
+    queued: semaphore.queued,                        // turns waiting for a slot
+    maxConcurrent,
+  };
+}
@@ -39,11 +39,56 @@ export function reapStaleTuiSessions({ tmux = defaultTmux } = {}) {
 // ── Task 5: runTuiTurn ───────────────────────────────────────────────────

 // Boot + paste-settle timing. Conservative defaults validated on PI231; env-tunable.
-const BOOT_MS         = parseInt(process.env.OCP_TUI_BOOT_MS  || "4000", 10);
-const PASTE_SETTLE_MS = parseInt(process.env.OCP_TUI_PASTE_MS || "1800", 10);
+const BOOT_MS         = parseInt(process.env.OCP_TUI_BOOT_MS  || "4000", 10);   // max wait for input-ready
+const READY_POLL_MS   = parseInt(process.env.OCP_TUI_READY_POLL_MS || "400", 10); // readiness / paste-verify poll interval
+const PASTE_VERIFY_MS = parseInt(process.env.OCP_TUI_PASTE_VERIFY_MS || "5000", 10); // max wait for pasted prompt to render

 const sleep = (ms) => new Promise((r) => setTimeout(r, ms));

+// Capture the visible tmux pane as plain text (for readiness / paste verification).
+function tuiCapturePane(tmux, tmuxName) {
+  const r = tmux(["capture-pane", "-p", "-t", tmuxName]);
+  return (r && typeof r.stdout === "string") ? r.stdout : "";
+}
+
+// True once claude's input bar is rendered and ready for keystrokes.
+function tuiInputReady(pane) {
+  return /\? for shortcuts/.test(pane);
+}
+
+// True once the pasted prompt has POSITIVELY landed in the input box. We only trust
+// affirmative signals — NOT "the placeholder is gone", which is unreliable (claude's
+// placeholder uses a curly quote `"`, randomized example text, and renders the big paste
+// a beat after paste-buffer returns; a "placeholder-gone" heuristic false-positived on the
+// still-empty box and made us submit Enter into nothing → issue #130 hang). Landed iff:
+//   (a) the bracketed-paste indicator "[Pasted text" is present (large/multi-line paste), OR
+//   (b) the prompt's own leading text appears in the pane (short/literal paste).
+function tuiPromptLanded(pane, prompt) {
+  const flatPane = pane.replace(/\s+/g, " ");
+  if (flatPane.includes("[Pasted text")) return true;
+  const firstLine = String(prompt).split("\n").map(s => s.trim()).find(Boolean) || "";
+  const needle = firstLine.replace(/\s+/g, " ").slice(0, 24);
+  // C-4/#133: threshold lowered 3 → 2. A prompt whose first non-blank line is 1–2
+  // chars ("hi", "ok") previously NEVER matched (needle.length >= 3) and never
+  // surfaced "[Pasted text", so EVERY short prompt 5s-failed with tui_paste_not_landed
+  // (live-reproduced: "hi"). The input box starts EMPTY (the curly-quote placeholder
+  // is excluded by the affirmative-signal design above), so a >=2-char needle present
+  // in the pane is the pasted prompt, not placeholder noise — false-positive risk is
+  // low. We keep >=2 rather than >=1 because a single visible char is more likely to
+  // collide with incidental glyphs in claude's chrome (borders, the "❯" prompt mark);
+  // 2 chars is the floor that lands real prompts while staying conservative.
+  return needle.length >= 2 && flatPane.includes(needle);
+}
+
+async function pollUntil(fn, { timeoutMs, intervalMs }) {
+  const deadline = Date.now() + timeoutMs;
+  while (Date.now() < deadline) {
+    try { if (fn()) return true; } catch { /* ignore, keep polling */ }
+    await sleep(intervalMs);
+  }
+  return false;
+}
+
 // Single-quote escaper for sh -c arguments.
 function shq(s) {
  return `'${String(s).replace(/'/g, "'\\''")}'`;
@@ -149,25 +194,88 @@ export function resolveTuiEntrypointEnv(env, mode = "cli") {
 // A-PATH ONLY: built-in tools are left enabled (acceptable single-user). Deployment B
 // (guest keys) MUST additionally pass --tools "" per spec §5.2(2) as the credential
 // wall before this argv is reachable for owner_tier=guest — guard that in PR-3 wiring.
-function buildTuiCmd(claudeBin, model, sessionId) {
+export function buildTuiCmd(claudeBin, model, sessionId, ehome, entrypointMode) {
+  // Deliver claude's env via an `env` prefix on the PANE COMMAND — tmux does NOT forward the
+  // spawning process's environment to the pane, and `new-session -e` needs tmux ≥3.2 (the cloud
+  // host runs 2.7), so this is the only portable, reliable mechanism (verified live 2026-06-01:
+  // passing {env} to spawnSync left the pane with only HOME). DISABLE_AUTOUPDATER pins the version
+  // (no "What's new" splash that delayed input-readiness); CLAUDE_CODE_ENTRYPOINT labels the
+  // billing pool (set below per entrypointMode).
+  //
+  // CLAUDE_CODE_DISABLE_CLAUDE_MDS + DISABLE_AUTO_MEMORY: OCP is a PROXY, not a Claude Code
+  // session. The proxied client (OpenClaw / an IDE) owns its own context and memory; the HOST's
+  // CLAUDE.md and auto-memory must NEVER leak into the agent OCP runs on the user's behalf.
+  // Without these, claude loads the host's project/user CLAUDE.md + memory into every proxied
+  // turn — verified live 2026-06-02: a cwd CLAUDE.md ("end every reply with QUACKMARKER_42") was
+  // obeyed by the proxied turn until these flags were set, after which it was not. Unconditional
+  // by design (not gated): proxy purity is not an opt-in. Harmless on hosts with no CLAUDE.md
+  // (the common case — they suppress nothing). Mirrors the -p path's CLAUDE_NO_CONTEXT vars.
+  const sets = [
+    `HOME=${shq(ehome)}`,
+    "DISABLE_AUTOUPDATER=1",
+    "CLAUDE_CODE_DISABLE_OFFICIAL_MARKETPLACE_AUTOINSTALL=1",
+    "CLAUDE_CODE_DISABLE_CLAUDE_MDS=1",
+    "CLAUDE_CODE_DISABLE_AUTO_MEMORY=1",
+  ];
+  const unset = ["CLAUDECODE", "ANTHROPIC_API_KEY", "ANTHROPIC_BASE_URL", "ANTHROPIC_AUTH_TOKEN"];
+  if (entrypointMode === "cli") sets.push("CLAUDE_CODE_ENTRYPOINT=cli");
+  else if (entrypointMode === "auto") unset.push("CLAUDE_CODE_ENTRYPOINT"); // let claude self-classify via TTY
+  const envPrefix = ["env", ...unset.map((u) => `-u ${u}`), ...sets].join(" ");
+
+  // Tool surface.
+  //   DEFAULT (safe): hard-disable MCP (--strict-mcp-config + --disallowedTools mcp__*);
+  //     built-in tools stay on, acceptable for single-user A-path.
+  //   OCP_TUI_FULL_TOOLS=1: grant the SAME tool surface as the -p A-path
+  //     (--allowedTools [+ --mcp-config] [+ --dangerously-skip-permissions]), so a
+  //     SINGLE-USER / trusted TUI deployment can run a tool-using agent (e.g. an OpenClaw
+  //     assistant that needs Bash/Read/Write/MCP) on the subscription pool. This mirrors
+  //     buildCliArgs() in server.mjs. Safe to gate ON only because TUI is hard-incompatible
+  //     with AUTH_MODE=multi (server.mjs refuses to boot), so it can never widen a guest's
+  //     surface. Env mirrors server.mjs's CLAUDE_ALLOWED_TOOLS / _SKIP_PERMISSIONS / _MCP_CONFIG.
+  let toolArgs;
+  if (process.env.OCP_TUI_FULL_TOOLS === "1") {
+    toolArgs = [];
+    if (process.env.CLAUDE_SKIP_PERMISSIONS === "true") {
+      toolArgs.push("--dangerously-skip-permissions");
+    } else {
+      const allowed = (process.env.CLAUDE_ALLOWED_TOOLS ||
+        "Bash,Read,Write,Edit,Glob,Grep,WebSearch,WebFetch,Agent")
+        .split(",").map((s) => s.trim()).filter(Boolean);
+      // shq EACH token: buildTuiCmd returns a SHELL STRING (run by tmux via sh -c), unlike
+      // buildCliArgs which returns an argv array to spawn(). claude accepts scoped specifiers
+      // like "Bash(npm run test:*)" / "Read(~/**)" whose ( ) * ~ would break/inject the shell
+      // command if pasted bare. (operator-self-injection only — guests can't reach TUI.)
+      if (allowed.length) toolArgs.push("--allowedTools", ...allowed.map(shq));
+    }
+    if (process.env.CLAUDE_MCP_CONFIG) toolArgs.push("--mcp-config", shq(process.env.CLAUDE_MCP_CONFIG));
+  } else {
+    toolArgs = ["--strict-mcp-config", "--disallowedTools", shq("mcp__*")];
+  }
  return [
+    envPrefix,
    shq(claudeBin),
    "--model",          shq(model),
    "--session-id",     sessionId,
-    "--strict-mcp-config",
-    "--disallowedTools", shq("mcp__*"),
+    ...toolArgs,
  ].join(" ");
 }

 // Full per-request TUI lifecycle:
 //   1. Pre-trust the scratch cwd (no trust dialog will appear).
 //   2. Write prompt to a 0600 temp file (no shell injection from prompt content).
-//   3. Boot an interactive `claude` in a fresh tmux session in the scratch cwd.
-//   4. Submit the prompt via `send-keys -- "$(cat file)"` + a SEPARATE Enter key
-//      event (spec §5 / T3: literal "\n" in paste does NOT submit; Enter token does).
+//   3. Boot an interactive `claude` in a fresh tmux session in the scratch cwd; poll
+//      capture-pane until the `? for shortcuts` input bar appears (readiness-poll
+//      replaces the old blind boot sleep). BOOT_MS is the max wait, not a fixed delay.
+//   4. Paste the prompt via tmux load-buffer + paste-buffer -p (bracketed paste) —
+//      reliable for large multi-line prompts where send-keys -l is not (issue #130).
+//      Poll-verify the prompt landed in the input (placeholder gone / [Pasted text]);
+//      fast-fail with tui_paste_not_landed if it never lands (prevents the 120s
+//      wallclock "stuck typing" hang). Then submit with a SEPARATE Enter key event.
 //   5. Block on the native JSONL transcript (located by session-id) until terminal
 //      marker or wall-clock cap.
 //   6. Always teardown: kill session + rm temp dir (even on throw).
+// Returns { text, entrypoint } from readTuiTranscript (entrypoint is the billing-pool
+// classifier, e.g. "cli", or null if the transcript did not include a turn_duration).
 export async function runTuiTurn({
  prompt,
  model,
@@ -213,34 +321,52 @@ export async function runTuiTurn({
    //    is a no-op when the session never existed).
    const spawnResult = tmux(
      ["new-session", "-d", "-s", tmuxName, "-x", "220", "-y", "50", "-c", cwd,
-       buildTuiCmd(claudeBin, model, sessionId)],
+       buildTuiCmd(claudeBin, model, sessionId, ehome, entrypointMode)],
      { env },
    );
    if (!spawnResult || spawnResult.status !== 0) {
      throw new Error("tui_spawn_failed: tmux session not created");
    }
-    await sleep(BOOT_MS);

-    // 2. Submit prompt body via `"$(cat file)"` — byte-safe for any content —
-    //    then settle, then send a SEPARATE Enter key event to submit the line.
-    //
-    //    The `-l` (literal) flag is required on the paste send-keys call so that
-    //    a prompt that happens to equal a tmux key token (e.g. "C-c", "Escape")
-    //    is typed literally as text rather than being interpreted as a key binding.
-    //    The SEPARATE Enter event below deliberately omits -l so that tmux sends a
-    //    real keypress (carriage return) to submit the prompt line.
-    spawnSync(
-      "sh",
-      ["-c", `${shq(TMUX)} send-keys -t ${shq(tmuxName)} -l -- "$(cat ${shq(promptFile)})"`],
-      { env, encoding: "utf8" },
-    );
-    await sleep(PASTE_SETTLE_MS);
+    // 2. Wait until claude's input bar is actually ready (was: blind sleep(BOOT_MS)).
+    //    BOOT_MS is now the MAX readiness wait, not a fixed delay.
+    const ready = await pollUntil(() => tuiInputReady(tuiCapturePane(tmux, tmuxName)),
+      { timeoutMs: BOOT_MS, intervalMs: READY_POLL_MS });
+    if (!ready) {
+      // (readiness timed out; relying on paste-verify)
+      console.error("[tui] input_not_ready", tmuxName);
+    }
+
+    // 3. Paste the prompt via a tmux PASTE BUFFER with bracketed paste (-p), NOT
+    //    `send-keys -l`. send-keys of a large multi-line prompt is unreliable: the
+    //    embedded newlines arrive as separate key events (effectively repeated Enter),
+    //    so a big OpenClaw-style prompt never lands and the turn hangs to the wallclock
+    //    (issue #130 — reproduced at ~300 lines; fixed by bracketed paste). load-buffer
+    //    reads the file directly (no shell arg limit, no `"$(cat)"`), and paste-buffer -p
+    //    wraps it in bracketed-paste markers so claude ingests it atomically as ONE paste
+    //    ("[Pasted text #N +M lines]"). -d deletes the buffer afterward. Buffer name is the
+    //    per-session tmuxName, so concurrent turns never collide.
+    tmux(["load-buffer", "-b", tmuxName, promptFile]);
+    tmux(["paste-buffer", "-b", tmuxName, "-t", tmuxName, "-p", "-d"]);
+
+    // Verify the prompt POSITIVELY landed before submitting; poll (a large bracketed paste
+    // takes a beat to render the "[Pasted text]" indicator). This is load-bearing: firing
+    // Enter before the paste renders submits an empty box → the turn hangs to the wallclock
+    // (issue #130). Fast-fail if it never lands → deterministic error in seconds.
+    const landed = await pollUntil(() => tuiPromptLanded(tuiCapturePane(tmux, tmuxName), prompt),
+      { timeoutMs: PASTE_VERIFY_MS, intervalMs: READY_POLL_MS });
+    if (!landed) {
+      throw new Error("tui_paste_not_landed: prompt did not reach claude's input within " + PASTE_VERIFY_MS + "ms");
+    }
+
+    // Submit (separate Enter key event).
    tmux(["send-keys", "-t", tmuxName, "Enter"]);

-    // 3. Block on the native transcript (resolved by session-id) until terminal.
+    // 4. Block on the native transcript (resolved by session-id) until terminal.
+    //    Returns { text, entrypoint } from readTuiTranscript.
    return await readTuiTranscript({ home: ehome, sessionId, wallclockMs });
  } finally {
-    // 4. Teardown — always, even on throw.
+    // 5. Teardown — always, even on throw.
    try { tmux(["kill-session", "-t", tmuxName]); } catch { /* already gone */ }
    try { rmSync(tmpDir, { recursive: true, force: true }); } catch { /* best effort */ }
  }
@@ -51,19 +51,29 @@ export function parseTranscriptLines(text) {
  return out;
 }

-// A line marks the assistant turn complete when it is the turn_duration system
-// event. That is the ONLY reliable terminal marker in interactive TUI mode.
+// A line marks the assistant turn complete when EITHER:
+//   (a) {type:"system", subtype:"turn_duration"} — emitted by newer claude builds
+//       (e.g. 2.1.159), OR
+//   (b) {type:"assistant"} whose message.stop_reason is a FINAL reason
+//       ("end_turn" / "stop_sequence" / "max_tokens"). This is the API-level
+//       end-of-turn signal, present across claude builds whose transcripts do NOT
+//       emit turn_duration (e.g. 2.1.114 — verified live on the cloud host). Without
+//       it OCP can't detect completion on those builds and hangs to the wallclock,
+//       then returns only partial text (issue #130, cloud/server-side symptom).
 //
-// Why tool_use is NOT a terminal marker:
-//   In interactive claude, when the model decides to call a tool (stop_reason=
-//   "tool_use"), claude handles the tool call internally and then continues
-//   generating — the turn is NOT complete. The transcript advances to another
-//   assistant entry after the tool result. Only {type:"system",
-//   subtype:"turn_duration"} signals that claude has fully finished the turn.
-//   Treating tool_use as terminal would truncate tool-using turns mid-flight.
+// stop_reason "tool_use" is deliberately NOT terminal: the model is mid-turn (it will
+// run a tool and continue with a later assistant entry). Matching on a FINAL
+// stop_reason — not on the mere presence of a tool_use — keeps tool-using turns intact.
+// (The v3.17.1 narrowing dropped a buggy "tool_use is terminal" rule; this restores
+// cross-version completion detection without bringing that bug back.)
+const TERMINAL_STOP_REASONS = new Set(["end_turn", "stop_sequence", "max_tokens"]);
 export function isTerminalLine(obj) {
  if (!obj || typeof obj !== "object") return false;
-  return obj.type === "system" && obj.subtype === "turn_duration";
+  if (obj.type === "system" && obj.subtype === "turn_duration") return true;
+  if (obj.type === "assistant" && obj.message && typeof obj.message === "object") {
+    return TERMINAL_STOP_REASONS.has(obj.message.stop_reason);
+  }
+  return false;
 }

 // Text of the LAST assistant turn: concatenate its text content blocks
@@ -90,22 +100,169 @@ export function extractLatestAssistantText(events) {
  return text;
 }

-// Returns the entrypoint string from the turn_duration line (e.g. "cli"),
+// Returns the entrypoint string (e.g. "cli") used for the billing-pool assertion,
 // or null if absent. Lets callers assert the subscription-classified path.
-// Fixture-confirmed: entrypoint field lives directly on the turn_duration line.
+//
+// Resolution order (C-3, issue #133):
+//   1. PREFER the turn_duration system line's `entrypoint` — the authoritative
+//      end-of-turn classifier emitted by builds that produce turn_duration
+//      (e.g. claude-2.1.104/2.1.157 on PI231).
+//   2. FALL BACK to the `entrypoint` field on ANY ordinary transcript line
+//      (assistant / user / attachment / system) — present on BOTH emitting and
+//      non-emitting builds. Some claude builds (e.g. certain Mac mini transcripts)
+//      do NOT emit a turn_duration line at all; reading ONLY turn_duration made the
+//      caller's tui_entrypoint_mismatch assertion (server.mjs) get got:null every
+//      turn and go blind. The entrypoint value is identical across line types within
+//      a single interactive session (fixture-confirmed: every line in
+//      complete-haiku.jsonl carrying `entrypoint` reads "cli"), so the fallback
+//      yields the same classifier. Last-writer-wins on the fallback.
 export function verifyEntrypoint(events) {
+  let fallback = null;
  for (const ev of events) {
-    if (ev && ev.type === "system" && ev.subtype === "turn_duration") {
-      return ev.entrypoint != null ? ev.entrypoint : null;
+    if (!ev || typeof ev !== "object") continue;
+    if (ev.type === "system" && ev.subtype === "turn_duration" && ev.entrypoint != null) {
+      return ev.entrypoint; // authoritative — short-circuit
    }
+    if (ev.entrypoint != null) fallback = ev.entrypoint;
+  }
+  return fallback;
+}
+
+// ── C-1: honest AUTH-FAILURE banner detection (issue #133) ───────────────
+// When the interactive `claude` CLI hits an in-session error it does NOT crash —
+// it renders the error as ordinary assistant text in the transcript. The specific
+// failure C-1 exists to catch is R-1: EXPIRED / INVALID credentials, where every
+// turn comes back as the same one-line auth-failure banner and OCP, none the wiser,
+// caches that banner (server.mjs setCachedResponse), shares it via singleflight, and
+// records a model SUCCESS — so a hard auth error is silently served (and cached for
+// the 5-min TTL) as a real answer. The two live-reproduced banners on PI231
+// (2026-06-10) are:
+//   "Please run /login · API Error: 401 Invalid authentication credentials"  (69 chars)
+//   "Failed to authenticate. API Error: 401 Invalid authentication credentials" (73 chars)
+//
+// WHY THE SCOPE IS NARROW (conservatism — the load-bearing design choice).
+// An earlier generalised rule (^<short-prefix>?API Error:\s*\d{3}\b.*$) was TOO
+// BROAD: its unbounded `.*` tail let any short prefix + "API Error: NNN" + an
+// arbitrarily long sentence match, so it KILLED legitimate long answers that merely
+// DISCUSS an API error (e.g. "API Error: 500 happened because the server was
+// overloaded. To fix this, retry with exponential backoff …"). That is the worst
+// outcome: a false-positive costs the user a missing answer AND a double-burn retry,
+// whereas the rare false-negative (caching one transient error for the 5-min TTL) is
+// cheap and self-healing. So C-1 is reframed from "detect ANY API error" to "detect
+// a claude-CLI AUTHENTICATION-FAILURE banner", and when unsure it PASSES (does not
+// kill). Transient 5xx server errors are deliberately NOT detected — they are not the
+// R-1 case and the conservative choice is to let them through.
+//
+// THE SIGNAL — a turn is an auth-failure banner only if ALL of these hold over the
+// WHOLE trimmed assistant text (a conjunction; any one failing => PASS):
+//   1. SHORT whole-message. Real banners are one short line (the two live samples are
+//      69 and 73 chars). Cap = TUI_ERR_MAX_LEN (100) — headroom over 73 for a
+//      slightly longer future banner, while still rejecting multi-sentence prose. A
+//      long answer that happens to discuss auth (no code chars, e.g. 226 chars) is
+//      rejected on length alone.
+//   2. Contains "API Error: 4\d{2}" — auth failures are 4xx (401/403). This rejects
+//      transient 5xx ("API Error: 500/503 …") and bare "HTTP 401 means unauthorized."
+//      (no "API Error:" core).
+//   3. Contains an auth KEYWORD — authenticat | /login | credential (case-insensitive).
+//      This rejects answers that quote a 4xx but are not auth banners, e.g.
+//      "To debug a 401: the server returns API Error: 401 Unauthorized …"
+//      ("Unauthorized" is authoriz-, not authenticat-; no /login, no credential).
+//   4. Contains NO backtick or quote char (` ' "). A real CLI banner is plain text;
+//      backticked/quoted text signals an answer that is QUOTING the error rather than
+//      being the banner, e.g. "You'll see `API Error: 401` … run /login to fix it."
+//      (75 chars — passes 1-3 but is excluded here). This is the conservative tie-
+//      breaker for short instructional answers.
+//
+// Worked matrix (all required cases pass — see test-features.mjs C-1 block):
+//   KILL: "Please run /login · API Error: 401 Invalid authentication credentials"
+//   KILL: "Failed to authenticate. API Error: 401 Invalid authentication credentials"
+//   PASS: "API Error: 500 happened because the server was overloaded. …"      (not 4xx)
+//   PASS: "Failed to parse the config. Here are the API Error: 401 details …"  (too long + no auth-kw)
+//   PASS: "To debug a 401: … API Error: 401 Unauthorized, then you refresh …"  (no auth-kw)
+//   PASS: "Here is the handler … It logs the string API Error: 503 …"          (not 4xx)
+//   PASS: "You'll see `API Error: 401` … run /login to fix it."                (has backtick)
+//   PASS: "HTTP 401 means unauthorized."                                       (no API Error core)
+//   PASS: "The capital of France is Paris."                                    (nothing matches)
+//
+// OPERATOR OVERRIDE (unchanged): CLAUDE_TUI_ERROR_PATTERNS lets an operator REPLACE
+// the default auth-banner detector with their own newline- or `||`-separated JS regex
+// source strings (each auto-anchored ^…$ over the trimmed text, case-insensitive). A
+// non-empty override uses ONLY those regexes (the narrowed default is bypassed); an
+// empty / whitespace-only override DISABLES detection entirely (escape hatch).
+
+// Whole-message length cap for the default auth-banner detector. Real banners are
+// 69/73 chars; 100 gives headroom while still rejecting multi-sentence prose.
+const TUI_ERR_MAX_LEN = 100;
+// 4xx "API Error:" core — auth failures are 4xx (401/403), never 5xx.
+const TUI_ERR_4XX = /API Error:\s*4\d{2}\b/i;
+// Auth keyword — the message must be about authentication, not just quote a 4xx.
+const TUI_ERR_AUTH_KW = /authenticat|\/login|credential/i;
+// Code/quote chars — their presence signals prose QUOTING an error, not the banner.
+const TUI_ERR_CODE_CHAR = /[`'"]/;
+
+// Default detector: returns true iff `trimmed` IS a claude-CLI auth-failure banner
+// (all four signals above). Conservative — any signal failing => false (PASS).
+function isDefaultAuthFailureBanner(trimmed) {
+  if (trimmed.length > TUI_ERR_MAX_LEN) return false; // 1. short whole-message
+  if (!TUI_ERR_4XX.test(trimmed)) return false;       // 2. 4xx API Error core
+  if (!TUI_ERR_AUTH_KW.test(trimmed)) return false;   // 3. auth keyword
+  if (TUI_ERR_CODE_CHAR.test(trimmed)) return false;  // 4. no code/quote chars
+  return true;
+}
+
+// Compile an OPERATOR-SUPPLIED pattern set (override path only). Each source is
+// anchored ^…$ over the trimmed text and matched case-insensitively (`s` so `.` spans
+// a multi-line banner). A pattern that fails to compile is skipped (never throws into
+// the request path).
+function compileTuiErrorPatterns(raw) {
+  const sources = String(raw).split(/\r?\n|\|\|/).map((s) => s.trim()).filter(Boolean);
+  const out = [];
+  for (const src of sources) {
+    try { out.push(new RegExp(`^(?:${src})$`, "is")); } catch { /* skip bad pattern */ }
+  }
+  return out;
+}
+
+// Returns the matched banner text (the trimmed assistant text) if `text` IS a claude-
+// CLI auth-failure banner in its entirety, else null. `patternsRaw` defaults to
+// process.env.CLAUDE_TUI_ERROR_PATTERNS:
+//   - undefined  → narrowed default auth-banner detector (isDefaultAuthFailureBanner).
+//   - non-empty  → operator regex override REPLACES the default.
+//   - empty/ws   → detection disabled (escape hatch).
+export function detectTuiUpstreamError(text, patternsRaw = process.env.CLAUDE_TUI_ERROR_PATTERNS) {
+  if (typeof text !== "string") return null;
+  const trimmed = text.trim();
+  if (!trimmed) return null;
+  if (patternsRaw == null) {
+    return isDefaultAuthFailureBanner(trimmed) ? trimmed : null;
+  }
+  // Operator override path: empty/whitespace disables; otherwise use only their regexes.
+  const patterns = compileTuiErrorPatterns(patternsRaw);
+  if (patterns.length === 0) return null;
+  for (const re of patterns) {
+    if (re.test(trimmed)) return trimmed;
  }
  return null;
 }

-// Block until the session transcript is terminal (turn_duration) or
-// the wall-clock cap elapses, polling the file (no fs.watch — robust over NFS /
-// editors). Returns the latest assistant text. On cap with text, returns the
-// partial text; on cap with no text at all, throws.
+// Block until the session transcript is terminal (turn_duration / final
+// stop_reason) or the wall-clock cap elapses, polling the file (no fs.watch —
+// robust over NFS / editors). Returns { text, entrypoint, truncated }:
+//   - text:       latest assistant text.
+//   - entrypoint: billing-pool classifier (see verifyEntrypoint), or null.
+//   - truncated:  FALSE when a terminal marker was reached (the turn completed);
+//                 TRUE when the wall-clock cap was hit with partial text but NO
+//                 terminal marker (the turn is INCOMPLETE — what we have is a
+//                 cut-off prefix). (C-2, issue #133.)
+//
+// Why `truncated` matters: previously the terminal-marker path and the
+// cap-with-partial-text path BOTH returned `{text, entrypoint}` identically, so
+// callClaudeTui could not tell a complete answer from a truncated one and cached +
+// returned the partial as finish_reason:stop (silent success). The caller now
+// throws on `truncated` so a cut-off turn is neither cached nor counted as success.
+// The field is additive — existing call sites that ignore it keep working.
+//
+// On cap with NO text at all, still throws (unchanged) — there is nothing to return.
 //
 // No quiescence heuristic by design: a long Opus thinking turn stalls transcript
 // growth and a "file stable for N s" rule would false-abort it (spec §4.3).
@@ -115,15 +272,22 @@ export function verifyEntrypoint(events) {
 export async function readTuiTranscript({ transcriptPath: p, home, sessionId, wallclockMs = 120000, pollMs = 250 }) {
  const deadline = Date.now() + wallclockMs;
  let lastText = "";
+  let lastEntrypoint = null;
  while (Date.now() < deadline) {
    const resolved = p || findTranscriptPath(home, sessionId);
    if (resolved && existsSync(resolved)) {
      const events = parseTranscriptLines(readFileSync(resolved, "utf8"));
      lastText = extractLatestAssistantText(events) || lastText;
-      if (events.some(isTerminalLine)) return lastText;
+      const ep = verifyEntrypoint(events);
+      if (ep != null) lastEntrypoint = ep;
+      // Terminal marker reached → the turn is COMPLETE.
+      if (events.some(isTerminalLine)) return { text: lastText, entrypoint: lastEntrypoint, truncated: false };
    }
    await sleep(pollMs);
  }
-  if (lastText) return lastText;
+  // Cap elapsed with no terminal marker. If we have partial text, flag it truncated
+  // so the caller rejects it (don't cache / don't count as success). No text at all
+  // → throw (nothing to return).
+  if (lastText) return { text: lastText, entrypoint: lastEntrypoint, truncated: true };
  throw new Error("tui_transcript_timeout: no assistant text within wallclock cap");
 }
@@ -506,9 +506,11 @@ main() {
  echo ""

  # Step 2.5: auto-discover anonymous key from /health (issue #12 §14 Path A).
-  # When the OCP admin set PROXY_ANONYMOUS_KEY, the server advertises it via
-  # /health.anonymousKey. If the user didn't pass --key, use it automatically so
-  # `ocp-connect <host>` works zero-config for OpenClaw multi-agent setups.
+  # The server advertises anonymousKey in /health ONLY when the admin has set
+  # PROXY_ADVERTISE_ANON_KEY=1 (default off — /health is unauthenticated, so
+  # advertising exposes the shared key to any LAN-reachable device; issue #109).
+  # Localhost callers always receive it regardless. When the field is absent,
+  # ocp-connect falls back to anonymous access / interactive --key (step 3 below).
  if [[ -z "$key" ]]; then
    local anon_key
    anon_key=$(echo "$health_json" | python3 -c "
@@ -632,11 +634,12 @@ PYEOF
    {
      echo ""
      echo "# OCP LAN (added by ocp connect)"
-      echo "export OPENAI_BASE_URL=$base_url/v1"
+      echo "export OPENAI_BASE_URL='$base_url/v1'"
      if [[ -n "$key" ]]; then
-        echo "export OPENAI_API_KEY=$key"
+        echo "export OPENAI_API_KEY='$key'"
      fi
    } >> "$rc_file"
+    chmod 600 "$rc_file" 2>/dev/null || true
  done

  echo "  Shell config:"
@@ -669,6 +672,7 @@ PYEOF
        echo "OPENAI_API_KEY=$key"
      fi
    } > "$env_dir/ocp.conf"
+    chmod 600 "$env_dir/ocp.conf" 2>/dev/null || true
    echo ""
    echo "  System-level (systemd):"
    echo "    ✓ $env_dir/ocp.conf"
@@ -208,31 +208,34 @@ async function cmdTest() {
 async function cmdRestart(args) {
  const target = (args || "").trim().toLowerCase();
  const { execSync } = await import("node:child_process");
+  const uid = typeof process.getuid === "function" ? process.getuid() : 501;
+  const macProxy = `launchctl kickstart -k gui/${uid}/dev.ocp.proxy`;
+  const macGateway = `launchctl kickstart -k gui/${uid}/ai.openclaw.gateway`;
  try {
    if (target === "gateway") {
-      execSync("launchctl kickstart -k gui/501/ai.openclaw.gateway", { timeout: 15000 });
+      execSync(macGateway, { timeout: 15000 });
      return "✓ Gateway restarted";
    } else if (target === "all") {
-      execSync("launchctl kickstart -k gui/501/ai.openclaw.proxy", { timeout: 15000 });
+      execSync(macProxy, { timeout: 15000 });
      // Gateway restart will kill this plugin too, so do it last
-      execSync("launchctl kickstart -k gui/501/ai.openclaw.gateway", { timeout: 15000 });
+      execSync(macGateway, { timeout: 15000 });
      return "✓ Proxy + Gateway restarted";
    } else {
-      execSync("launchctl kickstart -k gui/501/ai.openclaw.proxy", { timeout: 15000 });
+      execSync(macProxy, { timeout: 15000 });
      return "✓ Proxy restarted";
    }
  } catch (e) {
-    // Try systemd for Linux
+    // Linux: systemd user services
    try {
      if (target === "gateway") {
        execSync("systemctl --user restart openclaw-gateway", { timeout: 15000 });
        return "✓ Gateway restarted";
      } else {
-        execSync("systemctl --user restart openclaw-proxy 2>/dev/null || pkill -f 'node.*server.mjs' && sleep 2 && cd ~/.openclaw/projects/*/; node server.mjs &", { timeout: 15000, shell: true });
+        execSync("systemctl --user restart ocp-proxy", { timeout: 15000 });
        return "✓ Proxy restarted";
      }
    } catch (e2) {
-      return `✗ Restart failed: ${e2.message?.slice(0, 100)}`;
+      return `✗ Restart failed: ${e2.message?.slice(0, 100)}. Run \`ocp restart\` on the server host manually.`;
    }
  }
 }
@@ -1,6 +1,6 @@
 {
  "name": "open-claude-proxy",
-  "version": "3.17.1",
+  "version": "3.20.0",
  "description": "OCP (Open Claude Proxy) — use your Claude Pro/Max subscription as an OpenAI-compatible API for any IDE. Works with Cline, OpenCode, Aider, Continue.dev, OpenClaw, and more.",
  "type": "module",
  "bin": {
@@ -9,6 +9,8 @@
 // No new dependencies — regex-based, plist <key>X</key><string>Y</string> shape
 // is stable enough for our hand-written templates in setup.mjs.

+// Note: setup.mjs XML-escapes all injected values before writing (via xmlEscape()),
+// so raw `<` / `>` / `&` never appear in plist <string> bodies — the [^<]* regex below is safe.
 const PLIST_KV_RE = /<key>([^<]+)<\/key>\s*<string>([^<]*)<\/string>/g;

 export function parsePlistEnv(plistContent) {
@@ -19,7 +19,8 @@
 *   CLAUDE_SYSTEM_PROMPT         — system prompt appended to all requests
 *   CLAUDE_MCP_CONFIG            — path to MCP server config JSON file
 *   CLAUDE_SESSION_TTL           — session TTL in ms (default: 3600000 = 1h)
- *   CLAUDE_MAX_CONCURRENT        — max concurrent claude processes (default: 8)
+ *   CLAUDE_MAX_CONCURRENT        — max concurrent claude processes, -p/stream-json path (default: 8)
+ *   OCP_TUI_MAX_CONCURRENT       — max concurrent interactive TUI turns, TUI-mode path (default: 2)
 *   CLAUDE_BREAKER_THRESHOLD     — failures in window before circuit opens (default: 6)
 *   CLAUDE_BREAKER_COOLDOWN      — base ms to wait before retrying after circuit opens (default: 120000)
 *   CLAUDE_BREAKER_WINDOW        — sliding window duration in ms (default: 300000 = 5min)
@@ -36,7 +37,10 @@ import { dirname, join } from "node:path";
 import { homedir } from "node:os";
 import { validateKey, recordUsage, getUsageByKey, getUsageTimeline, getRecentUsage, createKey, listKeys, revokeKey, closeDb, checkQuota, updateKeyQuota, getKeyQuota, findKey, cacheHash, getCachedResponse, setCachedResponse, clearCache, getCacheStats, hasCacheControl, singleflight, getInflightStats } from "./keys.mjs";
 import { DEFAULT_PORT } from "./lib/constants.mjs";
+import { isLoopbackBind } from "./lib/net.mjs";
 import { runTuiTurn, reapStaleTuiSessions } from "./lib/tui/session.mjs";
+import { detectTuiUpstreamError } from "./lib/tui/transcript.mjs";
+import { TuiSemaphore, recordTuiEntrypoint, buildTuiHealthBlock } from "./lib/tui/semaphore.mjs";

 const __dirname = dirname(fileURLToPath(import.meta.url));
 const _pkg = JSON.parse(readFileSync(join(__dirname, "package.json"), "utf8"));
@@ -144,7 +148,7 @@ function extractSystemPrompt(messages) {
    return OCP_SYSTEM_PROMPT_WRAPPER;
  }
  const clientContent = systemMessages.map(m =>
-    typeof m.content === "string" ? m.content : JSON.stringify(m.content)
+    contentToText(m.content)
  ).join("\n\n");
  return `${OCP_SYSTEM_PROMPT_WRAPPER}\n\n${clientContent}`;
 }
@@ -278,6 +282,12 @@ const NO_CONTEXT = process.env.CLAUDE_NO_CONTEXT === "true";
 const AUTH_MODE = process.env.CLAUDE_AUTH_MODE || (PROXY_API_KEY ? "shared" : "none");
 const ADMIN_KEY = process.env.OCP_ADMIN_KEY || "";
 const PROXY_ANONYMOUS_KEY = process.env.PROXY_ANONYMOUS_KEY || "";
+// When set to "1", advertise PROXY_ANONYMOUS_KEY in the public /health body so
+// remote `ocp-connect` devices can zero-config auto-discover it (issue #12 §14 Path A).
+// Default OFF: /health is unauthenticated, so advertising hands the shared key to any
+// LAN-reachable device (issue #109 P0). Localhost callers always see it regardless,
+// since localhost is already fully trusted by the auth path.
+const ADVERTISE_ANON_KEY = process.env.PROXY_ADVERTISE_ANON_KEY === "1";
 let CACHE_TTL = parseInt(process.env.CLAUDE_CACHE_TTL || "0", 10); // 0 = disabled, value in ms

 // ── TUI-mode (subscription-pool bridge) — opt-in; default OFF ───────────
@@ -292,13 +302,29 @@ const TUI_WALLCLOCK_MS = parseInt(process.env.CLAUDE_TUI_WALLCLOCK_MS || "120000
 const TUI_CWD  = process.env.OCP_TUI_CWD  || `${process.env.HOME}/.ocp-tui/work`;
 const TUI_HOME = process.env.OCP_TUI_HOME  || process.env.HOME;
 const TUI_ENTRYPOINT = process.env.OCP_TUI_ENTRYPOINT || "cli"; // cli|auto|off — see ADR 0007
+// Independent concurrency bound for the TUI path (audit C-4). Default 2: a TUI turn is
+// HEAVY (per-request cold-boot of a tmux+claude session + up to TUI_WALLCLOCK_MS=120s of
+// wallclock), so a small host (e.g. a Pi 4 serving a family) cannot run many at once
+// without OOM + multiplied subscription rate-limit pressure. This is NOT the global
+// MAX_CONCURRENT gate (that lives in spawnClaudeProcess, the -p/stream-json path, which
+// callClaudeTui never reaches). See ADR 0007 PR-B amendment + lib/tui/semaphore.mjs.
+const TUI_MAX_CONCURRENT = parseInt(process.env.OCP_TUI_MAX_CONCURRENT || "2", 10);
+const tuiSemaphore = new TuiSemaphore(TUI_MAX_CONCURRENT);
+// Operator-visible TUI drift surface (audit C-5). lastEntrypoint + entrypointMismatches
+// let the operator poll /health to catch a silent metered-pool drift (the audit's top
+// risk: after the 6/15 flip a TTY-loss could flip cc_entrypoint cli→sdk-cli and drain
+// metered credits invisibly — the warning currently only reaches journald).
+const tuiStats = {
+  lastEntrypoint: null,      // last observed cc_entrypoint from the transcript ("cli" | "sdk-cli" | null)
+  entrypointMismatches: 0,   // count of cli-expected-but-got-other turns
+};

 // SECURITY fail-loud: TUI-mode is incompatible with any configuration that allows
 // non-operator prompts to reach the interactive claude session. Three cases:
 //   1. AUTH_MODE=multi — guest/anonymous keys can submit prompts.
-//   2. BIND_ADDRESS=0.0.0.0 — server is LAN-exposed; any LAN peer can send prompts
-//      unless per-request trust is in place. Override with OCP_TUI_ALLOW_LAN=1
-//      ONLY if you have a separate network-layer trust (firewall, VPN).
+//   2. a non-loopback BIND_ADDRESS — server is network-exposed; any reachable peer
+//      can send prompts unless per-request trust is in place. Override with
+//      OCP_TUI_ALLOW_LAN=1 ONLY if you have a separate network-layer trust (firewall, VPN).
 //   3. PROXY_ANONYMOUS_KEY set — anonymous callers can submit prompts without a key.
 // In all three cases TUI runs interactive claude with the OPERATOR's full filesystem
 // access — home is NOT isolation. Refuse to boot. See ADR 0007.
@@ -311,11 +337,11 @@ if (TUI_MODE && AUTH_MODE === "multi") {
  );
  process.exit(1);
 }
-if (TUI_MODE && BIND_ADDRESS === "0.0.0.0" && process.env.OCP_TUI_ALLOW_LAN !== "1") {
+if (TUI_MODE && !isLoopbackBind(BIND_ADDRESS) && process.env.OCP_TUI_ALLOW_LAN !== "1") {
  console.error(
-    "FATAL: CLAUDE_TUI_MODE=true with CLAUDE_BIND=0.0.0.0 is unsafe.\n" +
-    "  TUI runs interactive claude with operator filesystem access; LAN-exposed without\n" +
-    "  per-request isolation means any LAN peer could drive the operator's claude session.\n" +
+    `FATAL: CLAUDE_TUI_MODE=true with a non-loopback CLAUDE_BIND (${BIND_ADDRESS}) is unsafe.\n` +
+    "  TUI runs interactive claude with operator filesystem access; network-exposed without\n" +
+    "  per-request isolation means any reachable peer could drive the operator's claude session.\n" +
    "  Either bind to 127.0.0.1 (default) or set OCP_TUI_ALLOW_LAN=1 if you have a\n" +
    "  separate network-layer trust (firewall/VPN). See docs/adr/0007-tui-interactive-mode.md."
  );
@@ -630,9 +656,22 @@ function buildCliArgs(cliModel, systemPrompt) {
 // This prevents runaway context from gateway-side conversation accumulation.
 let MAX_PROMPT_CHARS = parseInt(process.env.CLAUDE_MAX_PROMPT_CHARS || "150000", 10);

+// Flatten OpenAI content (string | array of parts) to plain text for the prompt.
+// Array content: concatenate text parts; replace non-text parts (e.g. image_url)
+// with a placeholder rather than dumping raw JSON. (issue #110)
+function contentToText(content) {
+  if (typeof content === "string") return content;
+  if (Array.isArray(content)) {
+    return content.map(p =>
+      p && p.type === "text" && typeof p.text === "string" ? p.text : "[non-text content omitted]"
+    ).join("");
+  }
+  return content == null ? "" : JSON.stringify(content);
+}
+
 function messagesToPrompt(messages) {
  const full = messages.map((m) => {
-    const text = typeof m.content === "string" ? m.content : JSON.stringify(m.content);
+    const text = contentToText(m.content);
    if (m.role === "system") return `[System] ${text}`;
    if (m.role === "assistant") return `[Assistant] ${text}`;
    return text;
@@ -800,7 +839,12 @@ function spawnClaudeProcess(model, messages, conversationId, keyName) {
    }
  }, TIMEOUT);

-  return { proc, cliModel, conversationId, t0, cleanup, handleSessionFailure, markFirstByte };
+  // Clear ONLY the request timer (not the slot accounting) when the response has
+  // semantically completed (result/[DONE]) but the child hasn't exited yet — prevents
+  // a spurious post-success timeout. cleanup() (on exit) still clears it idempotently. (issue #111)
+  function clearOverallTimer() { clearTimeout(overallTimer); }
+
+  return { proc, cliModel, conversationId, t0, cleanup, clearOverallTimer, handleSessionFailure, markFirstByte };
 }

 // ── Call claude CLI (non-streaming) ─────────────────────────────────────
@@ -892,7 +936,11 @@ function callClaudeTui(model, messages, _conversationId, _keyName) {
  const cliModel = MODEL_MAP[model] || model;
  const prompt = messagesToPrompt(messages); // includes system as [System] inline
  recordModelRequest(cliModel, prompt.length);
-  return runTuiTurn({
+  // C-4: gate the heavy interactive boot behind the TUI semaphore. run() acquires a slot
+  // (queuing if all are busy, up to maxQueue), then releases in a finally so any throw from
+  // runTuiTurn (tmux spawn failure, paste-not-landed) OR from the honesty gates below
+  // (truncation / error banner) can NEVER leak a slot. tuiSemaphore.inflight feeds /health.
+  return tuiSemaphore.run(() => runTuiTurn({
    prompt,
    model: cliModel,
    claudeBin: CLAUDE,
@@ -901,13 +949,47 @@ function callClaudeTui(model, messages, _conversationId, _keyName) {
    cwd: TUI_CWD,
    wallclockMs: TUI_WALLCLOCK_MS,
    entrypointMode: TUI_ENTRYPOINT,
-  }).then((text) => {
+  }).then(({ text, entrypoint, truncated }) => {
+    // ── Honesty gates (issue #133) ─ run BEFORE recordModelSuccess / cache write-back.
+    // A throw here propagates to the .catch below (recordModelError + reject), so the
+    // result never reaches the downstream setCachedResponse / singleflight / SUCCESS path.
+
+    // C-2: the wall-clock cap hit with partial text and NO terminal marker — the turn
+    // is INCOMPLETE. Returning the cut-off prefix would cache it and report it as
+    // finish_reason:stop (a truncated answer served as a complete one). Reject instead.
+    if (truncated) {
+      logEvent("error", "tui_wallclock_truncated", { model: cliModel, chars: (text || "").length, wallclockMs: TUI_WALLCLOCK_MS });
+      throw new Error("tui_wallclock_truncated: turn hit the wall-clock cap before completing; partial text dropped");
+    }
+
+    // C-1: the interactive claude CLI renders in-session errors (expired/invalid
+    // credentials, transient API failure) as ordinary assistant text. Returning that
+    // banner would cache an error AS an answer and record a model SUCCESS. Detect a
+    // known error banner (anchored whole-text match — see detectTuiUpstreamError) and
+    // reject so it does NOT enter the cache and the client gets a 5xx.
+    const banner = detectTuiUpstreamError(text);
+    if (banner) {
+      logEvent("error", "tui_upstream_error", { model: cliModel, banner: banner.slice(0, 200) });
+      throw new Error("tui_upstream_error: claude CLI returned an in-session error banner instead of an answer");
+    }
+
    recordModelSuccess(cliModel, 0); // elapsed not measurable here; wallclock at reader level
+    // Assert the subscription-pool classification. TUI exists to keep cc_entrypoint=cli
+    // (subscription pool); a silent degrade to sdk-cli (metered Agent SDK pool) would still
+    // return text but cost money — warn loudly so it's visible. (issue #115)
+    // C-5: also surface the observation on /health. recordTuiEntrypoint sets lastEntrypoint
+    // unconditionally (operators can poll it to confirm cli) and increments
+    // entrypointMismatches when expected=cli but observed≠cli — the same condition the
+    // journald warning already covers — so a silent metered-pool drift is visible on /health
+    // without tailing logs.
+    if (recordTuiEntrypoint(tuiStats, entrypoint, TUI_ENTRYPOINT)) {
+      logEvent("warn", "tui_entrypoint_mismatch", { expected: "cli", got: entrypoint, model: cliModel });
+    }
    return text;
  }).catch((err) => {
    recordModelError(cliModel, false);
    throw err;
-  });
+  }));
 }

 // ── SSE heartbeat (opt-in idle watchdog) ────────────────────────────────
@@ -954,10 +1036,10 @@ function callClaudeStreaming(model, messages, conversationId, res, authInfo = {}
  try {
    ctx = spawnClaudeProcess(model, messages, conversationId, authInfo.keyName);
  } catch (err) {
-    return jsonResponse(res, 500, { error: { message: err.message, type: "proxy_error" } });
+    return jsonResponse(res, 500, { error: { message: sanitizeError(err.message), type: "proxy_error" } });
  }

-  const { proc, cliModel, conversationId: convId, t0, cleanup, handleSessionFailure, markFirstByte } = ctx;
+  const { proc, cliModel, conversationId: convId, t0, cleanup, clearOverallTimer, handleSessionFailure, markFirstByte } = ctx;
  let stderr = "";
  let headersSent = false;
  let totalChars = 0;
@@ -1028,6 +1110,7 @@ function callClaudeStreaming(model, messages, conversationId, res, authInfo = {}
          res.write("data: [DONE]\n\n");
          res.end();
        }
+        clearOverallTimer();

      } else if (parsed.error) {
        // is_error result — emit error stop; do NOT set resultEventSeen (that would
@@ -1037,12 +1120,12 @@ function callClaudeStreaming(model, messages, conversationId, res, authInfo = {}
        logEvent("error", "claude_result_error", { model: cliModel, error: errStr.slice(0, 200) });
        trackError(errStr.slice(0, 200));
        if (!headersSent && !res.writableEnded && !res.destroyed) {
-          jsonResponse(res, 500, { error: { message: errStr, type: "provider_error" } });
+          jsonResponse(res, 500, { error: { message: sanitizeError(errStr), type: "provider_error" } });
        } else if (!res.writableEnded && !res.destroyed) {
-          sendSSE(res, {
-            id, object: "chat.completion.chunk", created, model,
-            choices: [{ index: 0, delta: {}, finish_reason: "stop" }],
-          }, hb);
+          // Headers already sent (eager ensureHeaders) — can't send a JSON 500. Surface the
+          // failure as an SSE error frame so the client can distinguish an upstream error
+          // from a legitimately empty completion, instead of a success-looking finish_reason:"stop". (issue #110)
+          sendSSE(res, { error: { message: sanitizeError(errStr), type: "provider_error" } }, hb);
          res.write("data: [DONE]\n\n");
          res.end();
        }
@@ -1064,7 +1147,7 @@ function callClaudeStreaming(model, messages, conversationId, res, authInfo = {}
    // never record success or write cache for an errored response.
    if ((code !== 0 && !resultEventSeen) || errored) {
      recordModelError(cliModel, false);
-      try { recordUsage({ keyId: authInfo.keyId, keyName: authInfo.keyName, model, promptChars: messages.reduce((a, m) => a + (typeof m.content === "string" ? m.content.length : JSON.stringify(m.content).length), 0), responseChars: 0, elapsedMs: elapsed, success: false }); } catch (e) { logEvent("error", "usage_record_failed", { error: e.message }); }
+      try { recordUsage({ keyId: authInfo.keyId, keyName: authInfo.keyName, model, promptChars: messages.reduce((a, m) => a + contentToText(m.content).length, 0), responseChars: 0, elapsedMs: elapsed, success: false }); } catch (e) { logEvent("error", "usage_record_failed", { error: e.message }); }
      logEvent("error", "claude_exit", { model: cliModel, code, signal: signal || "none", elapsed, errored, stderr: stderr.slice(0, 300) });
      trackError(stderr.slice(0, 300) || `claude exit ${code}`);
      handleSessionFailure();
@@ -1072,19 +1155,19 @@ function callClaudeStreaming(model, messages, conversationId, res, authInfo = {}
      // If the error was already sent inline (parsed.error branch above), the
      // response may be writableEnded — nothing more to send.
      if (!headersSent && !res.writableEnded && !res.destroyed) {
-        jsonResponse(res, 500, { error: { message: stderr.slice(0, 300) || `claude exit ${code}`, type: "proxy_error" } });
+        jsonResponse(res, 500, { error: { message: sanitizeError(stderr.slice(0, 300) || `claude exit ${code}`), type: "proxy_error" } });
      } else if (!res.writableEnded && !res.destroyed) {
-        sendSSE(res, {
-          id, object: "chat.completion.chunk", created, model,
-          choices: [{ index: 0, delta: {}, finish_reason: "stop" }],
-        }, hb);
+        // Headers already sent — surface the failure as an SSE error frame instead of a
+        // success-looking finish_reason:"stop", so the client can tell the upstream crashed
+        // rather than returned empty. (issue #110 — sibling of the parsed.error branch above.)
+        sendSSE(res, { error: { message: sanitizeError(stderr.slice(0, 300) || `claude exit ${code}`), type: "proxy_error" } }, hb);
        res.write("data: [DONE]\n\n");
        res.end();
      }
    } else {
      recordModelSuccess(cliModel, elapsed);
      breakerRecordSuccess(cliModel);
-      try { recordUsage({ keyId: authInfo.keyId, keyName: authInfo.keyName, model, promptChars: messages.reduce((a, m) => a + (typeof m.content === "string" ? m.content.length : JSON.stringify(m.content).length), 0), responseChars: totalChars, elapsedMs: elapsed, success: true }); } catch (e) { logEvent("error", "usage_record_failed", { error: e.message }); }
+      try { recordUsage({ keyId: authInfo.keyId, keyName: authInfo.keyName, model, promptChars: messages.reduce((a, m) => a + contentToText(m.content).length, 0), responseChars: totalChars, elapsedMs: elapsed, success: true }); } catch (e) { logEvent("error", "usage_record_failed", { error: e.message }); }
      logEvent("info", "claude_ok", { model: cliModel, chars: totalChars, elapsed, session: convId ? convId.slice(0, 12) + "..." : "none" });
      // Cache write-back for streaming — only on true success (not errored)
      if (CACHE_TTL > 0 && authInfo.cacheHash) {
@@ -1114,7 +1197,7 @@ function callClaudeStreaming(model, messages, conversationId, res, authInfo = {}
    trackError(err.message);
    handleSessionFailure();
    if (!headersSent && !res.writableEnded && !res.destroyed) {
-      jsonResponse(res, 500, { error: { message: err.message, type: "proxy_error" } });
+      jsonResponse(res, 500, { error: { message: sanitizeError(err.message), type: "proxy_error" } });
    } else if (!res.writableEnded && !res.destroyed) {
      res.end();
    }
@@ -1123,12 +1206,27 @@ function callClaudeStreaming(model, messages, conversationId, res, authInfo = {}
  // If client disconnects, kill the process to free resources
  res.on("close", () => {
    hb.stop();
-    if (!proc.killed) {
+    // Only escalate when the child is still alive. On the normal-success path res.end()
+    // also fires "close", but the child has usually already exited — skip the spurious
+    // SIGTERM and the 5s kill-timer entirely (a post-exit proc.once("exit") never fires,
+    // so the timer would otherwise leak a closure over proc for 5s per request). (issue #111)
+    if (!proc.killed && proc.exitCode === null && proc.signalCode === null) {
      try { proc.kill("SIGTERM"); } catch {}
+      // Mirror the overallTimer escalation (server.mjs ~818): a SIGTERM-resistant child would
+      // otherwise hold its concurrency slot until the request timeout — #37 on the disconnect path. (issue #111)
+      const killTimer = setTimeout(() => { try { proc.kill("SIGKILL"); } catch {} }, 5000);
+      killTimer.unref();
+      proc.once("exit", () => clearTimeout(killTimer));
    }
  });
 }

+// Strip absolute filesystem paths from an error message before sending it to a client.
+// claude error_message / stderr routinely embed home-dir / credential-file paths. (issue #111)
+function sanitizeError(msg) {
+  return String(msg || "Internal error").replace(/\/[\w/.\-]+/g, "[path]");
+}
+
 // ── Response helpers ────────────────────────────────────────────────────
 function jsonResponse(res, status, data) {
  if (res.headersSent || res.writableEnded || res.destroyed) return;
@@ -1182,6 +1280,12 @@ function streamStringAsSSE(res, id, model, content) {

 let usageCache = { data: null, fetchedAt: 0 };
 const USAGE_CACHE_TTL = 5 * 60 * 1000; // 5 min
+// ALIGNMENT (Class A — OAuth bearer machinery). Verified against the compiled cli.js
+// (claude.exe v2.1.154) on 2026-05-31 via `strings`: both OAUTH_CLIENT_ID and
+// OAUTH_TOKEN_URL appear in the binary byte-for-byte; the legacy host
+// console.anthropic.com/v1/oauth is absent (0 hits). Re-verify on cli.js major bumps
+// using the compiled-binary protocol (strings on the Mach-O/ELF; no live OAuth probe —
+// a refresh-token grant would rotate the operator's real credentials). (issue #112)
 const OAUTH_CLIENT_ID = "9d1c250a-e61b-44d9-88ed-5944d1962f5e";
 const OAUTH_TOKEN_URL = "https://platform.claude.com/v1/oauth/token";

@@ -1289,7 +1393,7 @@ async function fetchUsageFromApi() {
  // Minimal /v1/messages request — we only need the response headers.
  // Mirrors Claude Code cli.js vE4: headers anthropic-ratelimit-unified-{5h,7d}-{utilization,reset}.
  const body = JSON.stringify({
-    model: "claude-haiku-4-5-20251001",
+    model: modelsConfig.aliases.haiku,
    max_tokens: 1,
    messages: [{ role: "user", content: "." }],
  });
@@ -1630,7 +1734,7 @@ async function handleChatCompletions(req, res) {
  try { parsed = JSON.parse(body); } catch { return jsonResponse(res, 400, { error: "Invalid JSON" }); }

  const messages = parsed.messages || parsed.input || [{ role: "user", content: parsed.prompt || "" }];
-  const model = parsed.model || "claude-sonnet-4-6";
+  const model = parsed.model || modelsConfig.aliases.sonnet;
  const stream = parsed.stream;

  // Validate model against known models
@@ -1641,8 +1745,15 @@ async function handleChatCompletions(req, res) {
  // Session ID: from request body, header, or null (one-off)
  const conversationId = parsed.session_id || parsed.conversation_id || req.headers["x-session-id"] || req.headers["x-conversation-id"] || null;

-  if (!messages?.length) return jsonResponse(res, 400, { error: "messages required" });
+  if (!Array.isArray(messages) || messages.length === 0) {
+    return jsonResponse(res, 400, { error: { message: "'messages' must be a non-empty array", type: "invalid_request_error" } });
+  }

+  // NOTE: quota is best-effort / eventually-consistent. The gate reads the recorded count
+  // at entry and records only after the upstream completes, so concurrent requests at the
+  // boundary can overshoot the cap by up to MAX_CONCURRENT, and cache hits (served before
+  // recordUsage) are not counted. This is internal family rate-limiting, not a payment
+  // boundary — bounded overshoot is acceptable. (issue #111)
  // Quota check — only for identified per-key users (not anonymous/admin/local)
  if (req._authKeyId) {
    let exceeded;
@@ -1697,7 +1808,7 @@ async function handleChatCompletions(req, res) {
      // Default path (TUI_MODE===false) falls through to callClaudeStreaming below,
      // which is byte-for-byte unchanged from before this gate was added.
      const t0TuiStream = Date.now();
-      const promptCharsTuiStream = messages.reduce((a, m) => a + (typeof m.content === "string" ? m.content.length : JSON.stringify(m.content).length), 0);
+      const promptCharsTuiStream = messages.reduce((a, m) => a + contentToText(m.content).length, 0);
      try {
        const content = await callClaudeTui(model, messages, conversationId, req._authKeyName);
        if (CACHE_TTL > 0 && req._cacheHash) {
@@ -1709,8 +1820,7 @@ async function handleChatCompletions(req, res) {
        return;
      } catch (err) {
        if (res.headersSent || res.writableEnded || res.destroyed) { try { res.end(); } catch {} return; }
-        const safeMessage = (err.message || "Internal error").replace(/\/[\w/.\-]+/g, "[path]");
-        return jsonResponse(res, 500, { error: { message: safeMessage, type: "proxy_error" } });
+        return jsonResponse(res, 500, { error: { message: sanitizeError(err.message), type: "proxy_error" } });
      }
    }
    // Default: real stream-json streaming, unchanged.
@@ -1718,7 +1828,7 @@ async function handleChatCompletions(req, res) {
  }

  const t0Usage = Date.now();
-  const promptChars = messages.reduce((a, m) => a + (typeof m.content === "string" ? m.content.length : JSON.stringify(m.content).length), 0);
+  const promptChars = messages.reduce((a, m) => a + contentToText(m.content).length, 0);

  // Select upstream based on TUI_MODE flag. With TUI_MODE===false (default),
  // upstreamCall===callClaude — identical to the pre-TUI code path.
@@ -1752,8 +1862,7 @@ async function handleChatCompletions(req, res) {
        try { res.end(); } catch {}
        return;
      }
-      const safeMessage = (err.message || "Internal error").replace(/\/[\w/.\-]+/g, "[path]");
-      return jsonResponse(res, 500, { error: { message: safeMessage, type: "proxy_error" } });
+      return jsonResponse(res, 500, { error: { message: sanitizeError(err.message), type: "proxy_error" } });
    }
  }

@@ -1771,8 +1880,7 @@ async function handleChatCompletions(req, res) {
      return;
    }
    // Sanitize error: strip internal file paths before sending to client
-    const safeMessage = (err.message || "Internal error").replace(/\/[\w/.\-]+/g, "[path]");
-    jsonResponse(res, 500, { error: { message: safeMessage, type: "proxy_error" } });
+    jsonResponse(res, 500, { error: { message: sanitizeError(err.message), type: "proxy_error" } });
  }
 }

@@ -1918,7 +2026,7 @@ const server = createServer(async (req, res) => {
      claudeBinary: CLAUDE,
      claudeBinaryOk: binaryOk,
      authMode: AUTH_MODE,
-      anonymousKey: PROXY_ANONYMOUS_KEY || null,
+      ...((isLocalhost || ADVERTISE_ANON_KEY) ? { anonymousKey: PROXY_ANONYMOUS_KEY || null } : {}),
      auth: authStatus,
      config: {
        timeout: TIMEOUT,
@@ -1933,6 +2041,17 @@ const server = createServer(async (req, res) => {
      circuitBreaker: "disabled",
      sessions: sessionList,
      recentErrors: recentErrors.slice(-5),
+      // ── TUI observability (audit C-5) — ADDITIVE block (ADR 0007 PR-B amendment) ──
+      // /health is a grandfathered B.2 endpoint (ADR 0006). This block is NEW fields only;
+      // every existing field above is byte-identical → behaviour-preserving for existing
+      // consumers per ALIGNMENT.md's grandfather provision. When TUI_MODE is off the block
+      // still appears with enabled:false (cheap, harmless) so the shape is stable.
+      // entrypointMismatches/lastEntrypoint exist so an operator can poll /health to catch a
+      // silent metered-pool drift (the audit's top risk after the 6/15 billing flip).
+      tui: buildTuiHealthBlock(
+        { enabled: TUI_MODE, entrypointMode: TUI_ENTRYPOINT, maxConcurrent: TUI_MAX_CONCURRENT },
+        tuiStats, tuiSemaphore,
+      ),
    });
  }

@@ -1998,6 +2117,9 @@ const server = createServer(async (req, res) => {
    let parsed;
    try { parsed = JSON.parse(body); } catch { return jsonResponse(res, 400, { error: "Invalid JSON" }); }
    const name = parsed.name || `key-${Date.now()}`;
+    if (!/^[A-Za-z0-9 ._-]{1,64}$/.test(name)) {
+      return jsonResponse(res, 400, { error: { message: "Invalid key name: 1-64 chars of letters, digits, space, dot, underscore, hyphen", type: "invalid_request_error" } });
+    }
    const newKey = createKey(name);
    return jsonResponse(res, 201, newKey);
  }
@@ -2220,7 +2342,7 @@ server.listen(PORT, BIND_ADDRESS, () => {
  else console.log(`Cache: disabled (set CLAUDE_CACHE_TTL to enable)`);
  if (TUI_MODE) {
    console.warn(`⚠️  TUI-mode ON — single-user only; do NOT enable on a multi-user OCP (guest prompts would run claude with operator filesystem access). See ADR 0007.`);
-    console.log(`  TUI-mode: ON home=${TUI_HOME} cwd=${TUI_CWD} wallclock=${TUI_WALLCLOCK_MS}ms`);
+    console.log(`  TUI-mode: ON home=${TUI_HOME} cwd=${TUI_CWD} wallclock=${TUI_WALLCLOCK_MS}ms maxConcurrent=${TUI_MAX_CONCURRENT}`);
    try {
      const n = reapStaleTuiSessions();
      if (n) logEvent("info", "tui_reaped_stale_sessions", { count: n });
@@ -65,6 +65,28 @@ const OCP_ADMIN_KEY_INJECT = process.env.OCP_ADMIN_KEY || null;
 // PROXY_ANONYMOUS_KEY — same pattern
 const PROXY_ANON_KEY_INJECT = process.env.PROXY_ANONYMOUS_KEY || null;

+// ── Inject-value helpers ─────────────────────────────────────────────────
+// Escape a value for safe inclusion in a plist <string>…</string> body.
+function xmlEscape(v) {
+  return String(v).replace(/&/g, "&amp;").replace(/</g, "&lt;").replace(/>/g, "&gt;").replace(/"/g, "&quot;").replace(/'/g, "&apos;");
+}
+// Validate an injected service value: no control chars (a newline would inject a
+// rogue systemd Environment= directive; other control chars corrupt the unit/plist).
+// Spaces are allowed — filesystem paths (CLAUDE_BIN) may legitimately contain them.
+function assertSafeInjectValue(name, v) {
+  if (v == null) return v;
+  if (/[\x00-\x1f]/.test(String(v))) {
+    console.error(`FATAL: ${name} contains a newline or control character — refusing to write it into the service unit.`);
+    process.exit(1);
+  }
+  return v;
+}
+
+// Validate all three INJECT values before they are written into any service unit.
+assertSafeInjectValue("CLAUDE_BIN", CLAUDE_BIN_INJECT);
+assertSafeInjectValue("OCP_ADMIN_KEY", OCP_ADMIN_KEY_INJECT);
+assertSafeInjectValue("PROXY_ANONYMOUS_KEY", PROXY_ANON_KEY_INJECT);
+
 // ── Models: derived from models.json (single source of truth) ──────────
 const modelsConfig = JSON.parse(readFileSync(join(__dirname, "models.json"), "utf-8"));

@@ -119,18 +141,26 @@ try {
 }

 // Check claude auth (quick test)
-try {
-  const out = execSync('claude -p --output-format text --no-session-persistence -- "ping"', {
-    encoding: "utf-8",
-    timeout: 30000,
-    env: { ...process.env, CLAUDECODE: undefined, ANTHROPIC_API_KEY: undefined, ANTHROPIC_BASE_URL: undefined, ANTHROPIC_AUTH_TOKEN: undefined },
-  }).trim();
-  if (out.length > 0) {
-    log(`Claude CLI authenticated (test response: "${out.slice(0, 40)}...")`);
+// NOTE: This probe uses `claude -p` (sdk-cli spawn). After the 2026-06-15 Anthropic billing
+// split, every `claude -p` call draws from the Agent SDK credit pool rather than the
+// Pro/Max subscription. Re-running setup after 6/15 will consume one metered credit.
+// Set OCP_SKIP_AUTH_TEST=1 to skip this probe (auth is still validated at first real request).
+if (process.env.OCP_SKIP_AUTH_TEST === "1") {
+  warn("OCP_SKIP_AUTH_TEST=1 — skipping claude auth probe (will be validated at first request).");
+} else {
+  try {
+    const out = execSync('claude -p --output-format text --no-session-persistence -- "ping"', {
+      encoding: "utf-8",
+      timeout: 30000,
+      env: { ...process.env, CLAUDECODE: undefined, ANTHROPIC_API_KEY: undefined, ANTHROPIC_BASE_URL: undefined, ANTHROPIC_AUTH_TOKEN: undefined },
+    }).trim();
+    if (out.length > 0) {
+      log(`Claude CLI authenticated (test response: "${out.slice(0, 40)}...")`);
+    }
+  } catch (e) {
+    warn(`Claude CLI auth test failed: ${e.message.slice(0, 100)}`);
+    warn("Make sure you're logged in: claude login");
  }
-} catch (e) {
-  warn(`Claude CLI auth test failed: ${e.message.slice(0, 100)}`);
-  warn("Make sure you're logged in: claude login");
 }

 // Check openclaw config (optional — OCP runs standalone without OpenClaw)
@@ -403,17 +433,17 @@ if (!DRY_RUN) {
  <key>EnvironmentVariables</key>
  <dict>
    <key>CLAUDE_PROXY_PORT</key>
-    <string>${PORT}</string>
+    <string>${xmlEscape(PORT)}</string>
    <key>CLAUDE_BIND</key>
-    <string>${BIND_ADDRESS}</string>
+    <string>${xmlEscape(BIND_ADDRESS)}</string>
    <key>CLAUDE_AUTH_MODE</key>
-    <string>${AUTH_MODE_CONFIG}</string>${CLAUDE_BIN_INJECT ? `
+    <string>${xmlEscape(AUTH_MODE_CONFIG)}</string>${CLAUDE_BIN_INJECT ? `
    <key>CLAUDE_BIN</key>
-    <string>${CLAUDE_BIN_INJECT}</string>` : ""}${OCP_ADMIN_KEY_INJECT ? `
+    <string>${xmlEscape(CLAUDE_BIN_INJECT)}</string>` : ""}${OCP_ADMIN_KEY_INJECT ? `
    <key>OCP_ADMIN_KEY</key>
-    <string>${OCP_ADMIN_KEY_INJECT}</string>` : ""}${PROXY_ANON_KEY_INJECT ? `
+    <string>${xmlEscape(OCP_ADMIN_KEY_INJECT)}</string>` : ""}${PROXY_ANON_KEY_INJECT ? `
    <key>PROXY_ANONYMOUS_KEY</key>
-    <string>${PROXY_ANON_KEY_INJECT}</string>` : ""}
+    <string>${xmlEscape(PROXY_ANON_KEY_INJECT)}</string>` : ""}
  </dict>
  <key>RunAtLoad</key>
  <true/>
@@ -4,6 +4,7 @@
 * Tests database layer functions directly — no server needed.
 */
 import { getDb, createKey, listKeys, validateKey, recordUsage, checkQuota, updateKeyQuota, getKeyQuota, findKey, cacheHash, getCachedResponse, setCachedResponse, clearCache, getCacheStats, closeDb, hasCacheControl, singleflight, getInflightStats } from "./keys.mjs";
+import { isLoopbackBind } from "./lib/net.mjs";
 import { createHash } from "node:crypto";
 import { strict as assert } from "node:assert";
 import { unlinkSync } from "node:fs";
@@ -858,6 +859,74 @@ test("gcSnapshots keeps last N regardless of age", () => {
  rmSync(root, { recursive: true, force: true });
 });

+// ── setup.mjs helpers: xmlEscape + assertSafeInjectValue ──
+// setup.mjs cannot be imported (top-level side effects run the installer).
+// Replicated verbatim from setup.mjs for unit-testing — keep in sync with source.
+console.log("\nsetup.mjs inject helpers:");
+
+function xmlEscape(v) {
+  return String(v).replace(/&/g, "&amp;").replace(/</g, "&lt;").replace(/>/g, "&gt;").replace(/"/g, "&quot;").replace(/'/g, "&apos;");
+}
+function assertSafeInjectValueTest(name, v) {
+  if (v == null) return v;
+  // eslint-disable-next-line no-control-regex
+  if (/[\x00-\x1f]/.test(String(v))) {
+    throw new Error(`FATAL: ${name} contains a newline or control character`);
+  }
+  return v;
+}
+
+test("xmlEscape encodes all five special XML chars", () => {
+  assert.equal(xmlEscape('a<b>&"\''), "a&lt;b&gt;&amp;&quot;&apos;");
+});
+
+test("xmlEscape leaves normal ocp_ token untouched", () => {
+  assert.equal(xmlEscape("ocp_abc123"), "ocp_abc123");
+});
+
+test("assertSafeInjectValue rejects value with newline", () => {
+  assert.throws(() => assertSafeInjectValueTest("OCP_ADMIN_KEY", "a\nb"), /FATAL/);
+});
+
+test("assertSafeInjectValue rejects value with carriage return", () => {
+  assert.throws(() => assertSafeInjectValueTest("OCP_ADMIN_KEY", "a\rb"), /FATAL/);
+});
+
+test("assertSafeInjectValue rejects value with a tab (control char)", () => {
+  assert.throws(() => assertSafeInjectValueTest("OCP_ADMIN_KEY", "a\tb"), /FATAL/);
+});
+
+test("assertSafeInjectValue ACCEPTS a path with a space (CLAUDE_BIN may legitimately contain one)", () => {
+  assert.equal(assertSafeInjectValueTest("CLAUDE_BIN", "/Users/x/My Apps/node"), "/Users/x/My Apps/node");
+});
+
+test("assertSafeInjectValue accepts normal ocp_ token", () => {
+  assert.doesNotThrow(() => assertSafeInjectValueTest("OCP_ADMIN_KEY", "ocp_abc123"));
+});
+
+test("assertSafeInjectValue accepts null (omit path)", () => {
+  assert.doesNotThrow(() => assertSafeInjectValueTest("OCP_ADMIN_KEY", null));
+});
+
+test("plist-merge round-trips XML-escaped value correctly via mergePlistEnv", () => {
+  // A value written with xmlEscape must survive a merge cycle — the [^<]* regex in
+  // parsePlistEnv only sees the escaped form (no raw < reaches it), so round-trip is safe.
+  const escaped = xmlEscape("a<b>&\"'");  // "a&lt;b&gt;&amp;&quot;&apos;"
+  const template = `<?xml version="1.0" encoding="UTF-8"?>
+<plist version="1.0">
+<dict>
+  <key>EnvironmentVariables</key>
+  <dict>
+    <key>CLAUDE_AUTH_MODE</key>
+    <string>${escaped}</string>
+  </dict>
+</dict>
+</plist>`;
+  // mergePlistEnv with no existing plist returns template unchanged.
+  const merged = mergePlistEnv(null, template);
+  assert.ok(merged.includes(escaped), "escaped value should survive unchanged through plist merge");
+});
+
 test("gcSnapshots keeps snapshots newer than keepDays regardless of count", () => {
  const root = mkdtempSync(testJoin(tmpdir(), "ocp-gc-days-"));
  const dotOcp = testJoin(root, ".ocp");
@@ -1271,7 +1340,7 @@ test("streamStringAsSSE empty content: role + stop + [DONE] only", () => {
 });

 // ── Suite: TUI transcript reader ────────────────────────────────────────
-import { encodeCwd, transcriptPath, findTranscriptPath, parseTranscriptLines, isTerminalLine, extractLatestAssistantText, verifyEntrypoint } from "./lib/tui/transcript.mjs";
+import { encodeCwd, transcriptPath, findTranscriptPath, parseTranscriptLines, isTerminalLine, extractLatestAssistantText, verifyEntrypoint, detectTuiUpstreamError } from "./lib/tui/transcript.mjs";
 import { readFileSync as tuiReadFileSync, mkdtempSync as tuiMkdtemp0, mkdirSync as tuiMkdir0, writeFileSync as tuiWrite0 } from "node:fs";
 import { tmpdir as tuiTmp0 } from "node:os";

@@ -1318,6 +1387,15 @@ test("isTerminalLine false on stop_reason tool_use (flat) — claude continues a
 test("isTerminalLine false on ordinary assistant text line", () => {
  assert.equal(isTerminalLine({ type: "assistant", message: { content: [{ type: "text", text: "hi" }] } }), false);
 });
+// issue #130 cloud/server-side: claude builds (e.g. 2.1.114) that DON'T emit
+// turn_duration mark turn-end via assistant message.stop_reason — must be terminal.
+test("isTerminalLine true on assistant stop_reason end_turn (version-robust, e.g. 2.1.114)", () => {
+  assert.equal(isTerminalLine({ type: "assistant", message: { stop_reason: "end_turn", content: [{ type: "text", text: "ok" }] } }), true);
+});
+test("isTerminalLine true on assistant stop_reason stop_sequence / max_tokens", () => {
+  assert.equal(isTerminalLine({ type: "assistant", message: { stop_reason: "stop_sequence" } }), true);
+  assert.equal(isTerminalLine({ type: "assistant", message: { stop_reason: "max_tokens" } }), true);
+});
 test("extractLatestAssistantText concatenates text blocks of LAST assistant entry", () => {
  const evs = [
    { type: "assistant", message: { content: [{ type: "text", text: "first" }] } },
@@ -1358,6 +1436,173 @@ test("real complete fixture: verifyEntrypoint returns 'cli'", () => {
  assert.equal(verifyEntrypoint(evs), "cli");
 });

+// ── C-3 (#133): verifyEntrypoint is version-robust ───────────────────────
+// Some claude builds do NOT emit a turn_duration line; entrypoint lives on
+// ordinary lines on BOTH emitting and non-emitting builds. Reading ONLY
+// turn_duration made the server.mjs tui_entrypoint_mismatch assertion get null
+// every turn on non-emitting builds. verifyEntrypoint must fall back to ANY line.
+console.log("\nTUI transcript — verifyEntrypoint version-robustness (C-3, #133):");
+
+test("verifyEntrypoint PREFERS the turn_duration line's entrypoint", () => {
+  // turn_duration says "cli"; an earlier ordinary line says "sdk-cli" — the
+  // authoritative turn_duration value must win, not last-writer-wins on the fallback.
+  const evs = [
+    { type: "assistant", entrypoint: "sdk-cli", message: { content: [{ type: "text", text: "x" }] } },
+    { type: "system", subtype: "turn_duration", entrypoint: "cli" },
+  ];
+  assert.equal(verifyEntrypoint(evs), "cli");
+});
+test("verifyEntrypoint falls back to entrypoint on an ordinary assistant line when no turn_duration", () => {
+  const evs = [
+    { type: "user", entrypoint: "cli", message: { content: "hi" } },
+    { type: "assistant", entrypoint: "cli", message: { stop_reason: "end_turn", content: [{ type: "text", text: "ok" }] } },
+  ];
+  assert.equal(verifyEntrypoint(evs), "cli");
+});
+test("verifyEntrypoint returns null when NO line carries an entrypoint", () => {
+  const evs = [
+    { type: "assistant", message: { stop_reason: "end_turn", content: [{ type: "text", text: "ok" }] } },
+  ];
+  assert.equal(verifyEntrypoint(evs), null);
+});
+test("real no-turn_duration fixture: verifyEntrypoint still resolves 'cli' (was null before C-3)", () => {
+  const evs = parseTranscriptLines(tuiReadFileSync("./lib/tui/fixtures/no-turn-duration.jsonl", "utf8"));
+  // Sanity: the fixture genuinely lacks a turn_duration line (so this exercises the fallback).
+  assert.ok(!evs.some((e) => e && e.type === "system" && e.subtype === "turn_duration"), "fixture must NOT emit turn_duration");
+  assert.equal(verifyEntrypoint(evs), "cli");
+});
+
+// ── C-1 (#133): honest AUTH-FAILURE banner detection ─────────────────────
+// The interactive claude CLI renders in-session errors as ordinary assistant text.
+// C-1 catches the R-1 case: expired/invalid creds, where EVERY turn returns the same
+// one-line auth-failure banner and OCP would cache it as a real answer. The detector
+// is deliberately NARROW/conservative: a false-positive (killing a real long answer
+// that merely DISCUSSES an API error) costs the user a missing answer + a double-burn
+// retry, which is worse than the rare false-negative (caching one transient error for
+// the 5-min TTL). Signal = ALL of: SHORT whole-message (≤100; live samples 69/73) AND
+// "API Error: 4xx" AND an auth keyword (authenticat | /login | credential) AND NO
+// backtick/quote char. When unsure → PASS. The earlier generalised rule
+// (^<short-prefix>?API Error:\d{3}.*$) was TOO BROAD: its unbounded .* tail killed
+// legit long answers; this block encodes the full narrowed matrix.
+console.log("\nTUI transcript — auth-failure banner detection (C-1, #133):");
+
+// ---- Required matrix: MUST detect (kill) ----
+test("C-1 KILL: live /login 401 auth banner", () => {
+  const banner = "Please run /login · API Error: 401 Invalid authentication credentials";
+  assert.equal(detectTuiUpstreamError(banner), banner);
+});
+test("C-1 KILL: live 'Failed to authenticate.' 401 banner variant", () => {
+  // Second real PI231 banner: a different short auth-failure prefix before the same
+  // "API Error: 4xx" core. Still short, still 4xx, still has 'authenticate'/'credentials'.
+  const banner = "Failed to authenticate. API Error: 401 Invalid authentication credentials";
+  assert.equal(detectTuiUpstreamError(banner), banner);
+});
+
+// ---- Required matrix: MUST NOT kill (pass) ----
+test("C-1 PASS: long answer discussing a 500 (not 4xx, too long)", () => {
+  // The exact false-positive the over-broad .* rule produced. 166 chars; 5xx.
+  const legit = "API Error: 500 happened because the server was overloaded. To fix this, retry with exponential backoff and verify your rate limits before resending the request again.";
+  assert.equal(detectTuiUpstreamError(legit), null);
+});
+test("C-1 PASS: long answer with 'API Error: 401 details' (too long, no auth keyword)", () => {
+  // 142 chars; the literal word 'authenticate'/'credential'/'/login' never appears, and
+  // it is far over the length cap — rejected on length AND keyword.
+  const legit = "Failed to parse the config. Here are the API Error: 401 details you asked about: the token expired and must be refreshed before the next call.";
+  assert.equal(detectTuiUpstreamError(legit), null);
+});
+test("C-1 PASS: 'To debug a 401 … API Error: 401 Unauthorized' (no auth keyword)", () => {
+  // 91 chars (short!) and 4xx, but 'Unauthorized' is authoriz-, not authenticat-, and
+  // there is no /login or credential — the auth-keyword signal rejects it.
+  const legit = "To debug a 401: the server returns API Error: 401 Unauthorized, then you refresh the token.";
+  assert.equal(detectTuiUpstreamError(legit), null);
+});
+test("C-1 PASS: handler answer logging 'API Error: 503' (not 4xx)", () => {
+  const legit = "Here is the handler you asked for. It logs the string API Error: 503 on failure and retries.";
+  assert.equal(detectTuiUpstreamError(legit), null);
+});
+test("C-1 PASS: short instructional answer quoting `API Error: 401` + /login (has backtick)", () => {
+  // 75 chars: short, 4xx, has '/login' — passes signals 1-3. Rejected ONLY by the
+  // backtick/quote constraint: it QUOTES the error in code formatting, it is not the banner.
+  const legit = "You'll see `API Error: 401` when your token expires — run /login to fix it.";
+  assert.equal(detectTuiUpstreamError(legit), null);
+});
+test("C-1 PASS: bare HTTP-status sentence (no 'API Error:' core)", () => {
+  assert.equal(detectTuiUpstreamError("HTTP 401 means unauthorized."), null);
+});
+test("C-1 PASS: plain unrelated answer", () => {
+  assert.equal(detectTuiUpstreamError("The capital of France is Paris."), null);
+});
+
+// ---- Supporting / regression coverage ----
+test("C-1 PASS: transient 5xx banner is NOT detected (narrowed to 4xx auth only)", () => {
+  // The old rule flagged any 3-digit code; the narrowed detector is 4xx-only by design
+  // (5xx is transient/server-side, not the R-1 auth case). Accepted false-negative.
+  assert.equal(detectTuiUpstreamError("API Error: 500 Internal Server Error"), null);
+});
+test("C-1 PASS: bare 4xx with no auth keyword is NOT detected", () => {
+  // 'API Error: 403 Forbidden' alone — 4xx and short, but no authenticat/login/credential.
+  assert.equal(detectTuiUpstreamError("API Error: 403 Forbidden"), null);
+});
+test("detectTuiUpstreamError trims surrounding whitespace before matching", () => {
+  const out = detectTuiUpstreamError("\n\n  Please run /login · API Error: 401 credential boom  \n");
+  assert.equal(out, "Please run /login · API Error: 401 credential boom");
+});
+test("detectTuiUpstreamError is case-insensitive on the banner keywords", () => {
+  // lower-cased: /login + api error: 401 + 'credential' keyword, short, no code char.
+  assert.ok(detectTuiUpstreamError("please run /login · api error: 401 bad credential") !== null);
+});
+test("detectTuiUpstreamError does NOT match prose that mentions an API error mid-paragraph (#133 regression guard)", () => {
+  // A long, legit answer that merely discusses an API error — rejected on length alone.
+  const para = "When integrating with the upstream service you may occasionally hit an API Error: 401 response if the bearer token has lapsed; the recommended remediation is to re-run the login flow and retry the request with a fresh credential, after which the 401 should clear.";
+  assert.equal(detectTuiUpstreamError(para), null);
+});
+test("detectTuiUpstreamError does NOT match a long plain-text auth answer with NO code chars (length cap is load-bearing)", () => {
+  // 226 chars, no backtick/quote, has 4xx + /login + credential + authenticate — passes
+  // signals 2-4. ONLY the length cap rejects it. Guards against dropping the cap.
+  const para = "If you call the endpoint without a bearer token the API Error: 401 response tells you the credential is missing; just authenticate again with /login and the request will succeed on the next attempt without any further changes.";
+  assert.equal(detectTuiUpstreamError(para), null);
+});
+test("detectTuiUpstreamError returns null on empty / whitespace / non-string", () => {
+  assert.equal(detectTuiUpstreamError(""), null);
+  assert.equal(detectTuiUpstreamError("   \n  "), null);
+  assert.equal(detectTuiUpstreamError(null), null);
+  assert.equal(detectTuiUpstreamError(undefined), null);
+  assert.equal(detectTuiUpstreamError(42), null);
+});
+test("detectTuiUpstreamError respects CLAUDE_TUI_ERROR_PATTERNS override (custom banner)", () => {
+  // Override with a single custom pattern; the default 401 banner no longer matches,
+  // but the custom one does (anchored whole-text).
+  assert.equal(detectTuiUpstreamError("Please run /login · API Error: 401 x", "Session expired, please re-auth"), null);
+  assert.equal(detectTuiUpstreamError("Session expired, please re-auth", "Session expired, please re-auth"), "Session expired, please re-auth");
+});
+test("detectTuiUpstreamError with an empty override disables detection (escape hatch)", () => {
+  assert.equal(detectTuiUpstreamError("API Error: 500 boom", ""), null);
+  assert.equal(detectTuiUpstreamError("API Error: 500 boom", "   "), null);
+});
+test("detectTuiUpstreamError override accepts '||'-separated patterns", () => {
+  const raw = "First banner||Second banner";
+  assert.equal(detectTuiUpstreamError("First banner", raw), "First banner");
+  assert.equal(detectTuiUpstreamError("Second banner", raw), "Second banner");
+  assert.equal(detectTuiUpstreamError("Third", raw), null);
+});
+test("real error fixture: latest assistant text IS the banner and detectTuiUpstreamError flags it", () => {
+  const evs = parseTranscriptLines(tuiReadFileSync("./lib/tui/fixtures/error-401.jsonl", "utf8"));
+  const text = extractLatestAssistantText(evs);
+  assert.equal(text, "Please run /login · API Error: 401 Invalid authentication credentials");
+  assert.ok(detectTuiUpstreamError(text) !== null, "error fixture's final turn must be flagged as an upstream error");
+});
+test("real error fixture (Failed-to-authenticate variant): final turn is flagged (#133 runtime gap)", () => {
+  const evs = parseTranscriptLines(tuiReadFileSync("./lib/tui/fixtures/error-401-failauth.jsonl", "utf8"));
+  const text = extractLatestAssistantText(evs);
+  assert.equal(text, "Failed to authenticate. API Error: 401 Invalid authentication credentials");
+  assert.ok(detectTuiUpstreamError(text) !== null, "Failed-to-authenticate banner must be flagged as an upstream error");
+});
+test("real complete fixture: final answer is NOT flagged as an upstream error", () => {
+  const evs = parseTranscriptLines(tuiReadFileSync("./lib/tui/fixtures/complete-haiku.jsonl", "utf8"));
+  const text = extractLatestAssistantText(evs);
+  assert.equal(detectTuiUpstreamError(text), null);
+});
+
 // ── TUI transcript — polling reader (async) ──────────────────────────────
 import { readTuiTranscript } from "./lib/tui/transcript.mjs";
 import { mkdtempSync as tuiMkdtemp, writeFileSync as tuiWriteFile } from "node:fs";
@@ -1370,18 +1615,42 @@ await asyncTest("readTuiTranscript returns assistant text when terminal marker p
  const p = `${dir}/s.jsonl`;
  tuiWriteFile(p, [
    JSON.stringify({ type: "assistant", message: { content: [{ type: "text", text: "hello world" }] } }),
-    JSON.stringify({ type: "system", subtype: "turn_duration", durationMs: 1200 }),
+    JSON.stringify({ type: "system", subtype: "turn_duration", durationMs: 1200, entrypoint: "cli" }),
  ].join("\n") + "\n");
  const out = await readTuiTranscript({ transcriptPath: p, wallclockMs: 2000, pollMs: 50 });
-  assert.equal(out, "hello world");
+  assert.equal(out.text, "hello world");
+  assert.equal(out.entrypoint, "cli");
 });

-await asyncTest("readTuiTranscript honours wall-clock cap and returns partial text", async () => {
+// C-2 (#133): the terminal-marker path must signal a COMPLETE turn.
+await asyncTest("readTuiTranscript signals truncated:false when a terminal marker is hit (complete turn)", async () => {
  const dir = tuiMkdtemp(`${tuiTmpdir()}/tui-`);
  const p = `${dir}/s.jsonl`;
+  tuiWriteFile(p, [
+    JSON.stringify({ type: "assistant", message: { content: [{ type: "text", text: "done" }] } }),
+    JSON.stringify({ type: "system", subtype: "turn_duration", durationMs: 1200, entrypoint: "cli" }),
+  ].join("\n") + "\n");
+  const out = await readTuiTranscript({ transcriptPath: p, wallclockMs: 2000, pollMs: 50 });
+  assert.equal(out.truncated, false);
+});
+
+// C-2 (#133): cap-with-partial-text must be DISTINGUISHABLE from a complete turn.
+// Previously both returned {text, entrypoint} identically and the partial was cached
+// + returned as finish_reason:stop. The cap path now returns truncated:true so the
+// caller (callClaudeTui) can throw instead of serving a cut-off answer.
+await asyncTest("readTuiTranscript honours wall-clock cap and flags partial text truncated:true", async () => {
+  const dir = tuiMkdtemp(`${tuiTmpdir()}/tui-`);
+  const p = `${dir}/s.jsonl`;
+  // No terminal marker → reader will spin to the cap then return the partial.
  tuiWriteFile(p, JSON.stringify({ type: "assistant", message: { content: [{ type: "text", text: "partial" }] } }) + "\n");
  const out = await readTuiTranscript({ transcriptPath: p, wallclockMs: 300, pollMs: 50 });
-  assert.equal(out, "partial");
+  assert.equal(out.text, "partial");
+  assert.equal(out.truncated, true);
+});
+
+await asyncTest("readTuiTranscript against real fixture: entrypoint is 'cli'", async () => {
+  const out = await readTuiTranscript({ transcriptPath: "./lib/tui/fixtures/complete-haiku.jsonl", wallclockMs: 2000, pollMs: 50 });
+  assert.equal(out.entrypoint, "cli");
 });

 await asyncTest("readTuiTranscript throws when no text and cap elapses", async () => {
@@ -1394,7 +1663,7 @@ await asyncTest("readTuiTranscript throws when no text and cap elapses", async (
 });

 // ── TUI session reaper ───────────────────────────────────────────────────
-import { reapStaleTuiSessions, SESSION_PREFIX } from "./lib/tui/session.mjs";
+import { reapStaleTuiSessions, SESSION_PREFIX, buildTuiCmd } from "./lib/tui/session.mjs";

 console.log("\nTUI session reaper:");

@@ -1402,6 +1671,70 @@ test("SESSION_PREFIX is ocp-tui-", () => {
  assert.equal(SESSION_PREFIX, "ocp-tui-");
 });

+console.log("\nTUI command construction (proxy-purity / #4):");
+
+test("buildTuiCmd suppresses host CLAUDE.md + auto-memory (proxy purity, #4)", () => {
+  const cmd = buildTuiCmd("/usr/bin/claude", "claude-haiku", "sid-1", "/home/u", "cli");
+  // OCP is a proxy: the host's CLAUDE.md / auto-memory must never leak into the proxied turn.
+  assert.ok(/(^| )CLAUDE_CODE_DISABLE_CLAUDE_MDS=1( |$)/.test(cmd), "must disable CLAUDE.md injection");
+  assert.ok(/(^| )CLAUDE_CODE_DISABLE_AUTO_MEMORY=1( |$)/.test(cmd), "must disable auto-memory injection");
+});
+
+test("buildTuiCmd keeps version pin + entrypoint label + MCP wall", () => {
+  const cli = buildTuiCmd("/usr/bin/claude", "m", "sid-2", "/home/u", "cli");
+  assert.ok(cli.includes("DISABLE_AUTOUPDATER=1"), "version pin retained");
+  assert.ok(cli.includes("CLAUDE_CODE_ENTRYPOINT=cli"), "cli mode labels the subscription pool");
+  assert.ok(cli.includes("--strict-mcp-config") && cli.includes('mcp__*'), "MCP wall retained");
+  // 'auto' mode must NOT pin the entrypoint (claude self-classifies via TTY).
+  const auto = buildTuiCmd("/usr/bin/claude", "m", "sid-3", "/home/u", "auto");
+  assert.ok(!/CLAUDE_CODE_ENTRYPOINT=/.test(auto), "auto mode leaves entrypoint unset");
+  assert.ok(/-u CLAUDE_CODE_ENTRYPOINT/.test(auto), "auto mode unsets any inherited entrypoint");
+});
+
+test("buildTuiCmd OCP_TUI_FULL_TOOLS=1 grants -p-equivalent tool surface (single-user opt-in)", () => {
+  const save = { ...process.env };
+  const restore = () => {
+    for (const k of ["OCP_TUI_FULL_TOOLS", "CLAUDE_SKIP_PERMISSIONS", "CLAUDE_MCP_CONFIG", "CLAUDE_ALLOWED_TOOLS"]) {
+      if (k in save) process.env[k] = save[k]; else delete process.env[k];
+    }
+  };
+  try {
+    // default (gate off) keeps the MCP wall, no --allowedTools
+    delete process.env.OCP_TUI_FULL_TOOLS;
+    const off = buildTuiCmd("/usr/bin/claude", "m", "s", "/home/u", "cli");
+    assert.ok(off.includes("--strict-mcp-config") && !off.includes("--allowedTools"), "gate off = MCP wall");
+
+    // gate on: --allowedTools (default set incl Bash), MCP wall dropped
+    process.env.OCP_TUI_FULL_TOOLS = "1";
+    delete process.env.CLAUDE_SKIP_PERMISSIONS;
+    delete process.env.CLAUDE_MCP_CONFIG;
+    delete process.env.CLAUDE_ALLOWED_TOOLS;
+    const full = buildTuiCmd("/usr/bin/claude", "m", "s", "/home/u", "cli");
+    assert.ok(full.includes("--allowedTools") && full.includes("Bash"), "full-tools grants --allowedTools incl Bash");
+    assert.ok(!full.includes("--strict-mcp-config") && !/--disallowedTools/.test(full), "full-tools drops the MCP wall");
+
+    // skip-permissions supersedes --allowedTools
+    process.env.CLAUDE_SKIP_PERMISSIONS = "true";
+    const skip = buildTuiCmd("/usr/bin/claude", "m", "s", "/home/u", "cli");
+    assert.ok(skip.includes("--dangerously-skip-permissions") && !skip.includes("--allowedTools"), "skip-permissions honored");
+
+    // mcp-config threaded through
+    delete process.env.CLAUDE_SKIP_PERMISSIONS;
+    process.env.CLAUDE_MCP_CONFIG = "/tmp/mcp.json";
+    const mcp = buildTuiCmd("/usr/bin/claude", "m", "s", "/home/u", "cli");
+    assert.ok(/--mcp-config '\/tmp\/mcp.json'/.test(mcp), "mcp-config passed through (shq'd)");
+
+    // operator-supplied scoped tool specifiers must be shell-quoted (no injection via ()*~)
+    delete process.env.CLAUDE_MCP_CONFIG;
+    process.env.CLAUDE_ALLOWED_TOOLS = "Bash(npm run test:*),Read";
+    const scoped = buildTuiCmd("/usr/bin/claude", "m", "s", "/home/u", "cli");
+    assert.ok(scoped.includes("'Bash(npm run test:*)'"), "scoped tool tokens are shq'd in the shell string");
+    assert.ok(!/--allowedTools Bash\(npm/.test(scoped), "scoped token must NOT appear unquoted");
+  } finally {
+    restore();
+  }
+});
+
 test("reaper kills ONLY ocp-tui- sessions, never olp-tui-", () => {
  const killed = [];
  const fakeTmux = (args) => {
@@ -1518,6 +1851,147 @@ test("default mode (no second arg) behaves like 'cli'", () => {
  assert.equal(env.CLAUDE_CODE_ENTRYPOINT, "cli");
 });

+// ── TUI concurrency limiter + drift observability (PR-B: audit C-4 / C-5) ──
+import { TuiSemaphore, recordTuiEntrypoint, buildTuiHealthBlock } from "./lib/tui/semaphore.mjs";
+
+console.log("\nTUI concurrency limiter (C-4):");
+
+const deferred = () => { let resolve, reject; const p = new Promise((res, rej) => { resolve = res; reject = rej; }); return { p, resolve, reject }; };
+
+await asyncTest("limit=1 serializes two overlapping calls (second waits for the first)", async () => {
+  const sem = new TuiSemaphore(1);
+  const order = [];
+  const g1 = deferred();
+  // First task acquires the only slot and blocks on g1.
+  const t1 = sem.run(async () => { order.push("t1-start"); await g1.p; order.push("t1-end"); });
+  await new Promise((r) => setImmediate(r)); // let t1 acquire
+  assert.equal(sem.inflight, 1, "t1 holds the only slot");
+  // Second task must QUEUE — it has not started yet.
+  const t2 = sem.run(async () => { order.push("t2-start"); });
+  await new Promise((r) => setImmediate(r));
+  assert.equal(sem.queued, 1, "t2 is queued, not running");
+  assert.deepEqual(order, ["t1-start"], "t2 has not started while t1 holds the slot");
+  // Release t1 → t2 runs.
+  g1.resolve();
+  await t1; await t2;
+  assert.deepEqual(order, ["t1-start", "t1-end", "t2-start"], "t2 ran only after t1 finished");
+  assert.equal(sem.inflight, 0, "all slots released");
+  assert.equal(sem.queued, 0, "queue drained");
+});
+
+await asyncTest("limit=2 allows two concurrent, queues the third", async () => {
+  const sem = new TuiSemaphore(2);
+  const g = [deferred(), deferred(), deferred()];
+  const started = [];
+  const tasks = g.map((d, i) => sem.run(async () => { started.push(i); await d.p; }));
+  await new Promise((r) => setImmediate(r));
+  assert.equal(sem.inflight, 2, "exactly 2 run concurrently");
+  assert.equal(sem.queued, 1, "the third is queued");
+  assert.deepEqual(started.sort(), [0, 1], "only the first two started");
+  g.forEach((d) => d.resolve());
+  await Promise.all(tasks);
+  assert.equal(sem.inflight, 0);
+});
+
+await asyncTest("slot is RELEASED on throw (finally) — a rejecting task never leaks its slot", async () => {
+  const sem = new TuiSemaphore(1);
+  await assert.rejects(sem.run(async () => { throw new Error("boom"); }), /boom/);
+  assert.equal(sem.inflight, 0, "throwing task released its slot");
+  // Prove the slot is reusable: a subsequent task acquires immediately.
+  let ran = false;
+  await sem.run(async () => { ran = true; });
+  assert.equal(ran, true);
+  assert.equal(sem.inflight, 0);
+});
+
+await asyncTest("wait queue is bounded — run() rejects with tui_queue_full when full (backpressure, not OOM)", async () => {
+  const sem = new TuiSemaphore(1, { maxQueue: 1 });
+  const g1 = deferred();
+  const t1 = sem.run(async () => { await g1.p; });          // holds the slot
+  await new Promise((r) => setImmediate(r));
+  const t2 = sem.run(async () => {});                        // fills the 1-deep queue
+  await new Promise((r) => setImmediate(r));
+  assert.equal(sem.queued, 1, "queue is full");
+  await assert.rejects(sem.run(async () => {}), /tui_queue_full/, "third request rejects");
+  g1.resolve();
+  await t1; await t2;
+  assert.equal(sem.inflight, 0);
+});
+
+console.log("\nTUI drift observability (C-5):");
+
+test("recordTuiEntrypoint: observed 'cli' is NOT a mismatch and sets lastEntrypoint", () => {
+  const ts = { lastEntrypoint: null, entrypointMismatches: 0 };
+  const mism = recordTuiEntrypoint(ts, "cli", "cli");
+  assert.equal(mism, false);
+  assert.equal(ts.lastEntrypoint, "cli");
+  assert.equal(ts.entrypointMismatches, 0);
+});
+
+test("recordTuiEntrypoint: expected cli but observed 'sdk-cli' increments the mismatch counter (drift)", () => {
+  const ts = { lastEntrypoint: null, entrypointMismatches: 0 };
+  assert.equal(recordTuiEntrypoint(ts, "sdk-cli", "cli"), true);
+  assert.equal(ts.lastEntrypoint, "sdk-cli");
+  assert.equal(ts.entrypointMismatches, 1);
+  // A second drift increments again (counter accumulates across turns).
+  assert.equal(recordTuiEntrypoint(ts, "sdk-cli", "cli"), true);
+  assert.equal(ts.entrypointMismatches, 2);
+});
+
+test("recordTuiEntrypoint: null observation → lastEntrypoint null, counts as mismatch when expected cli", () => {
+  const ts = { lastEntrypoint: "cli", entrypointMismatches: 0 };
+  assert.equal(recordTuiEntrypoint(ts, null, "cli"), true);
+  assert.equal(ts.lastEntrypoint, null);
+  assert.equal(ts.entrypointMismatches, 1);
+});
+
+test("recordTuiEntrypoint: non-cli expected mode (auto) never counts a mismatch", () => {
+  const ts = { lastEntrypoint: null, entrypointMismatches: 0 };
+  assert.equal(recordTuiEntrypoint(ts, "sdk-cli", "auto"), false);
+  assert.equal(ts.lastEntrypoint, "sdk-cli");
+  assert.equal(ts.entrypointMismatches, 0);
+});
+
+test("buildTuiHealthBlock: shape + live counters (the additive /health tui block)", () => {
+  const sem = new TuiSemaphore(2);
+  const ts = { lastEntrypoint: "cli", entrypointMismatches: 3 };
+  const block = buildTuiHealthBlock(
+    { enabled: true, entrypointMode: "cli", maxConcurrent: 2 }, ts, sem);
+  assert.deepEqual(Object.keys(block).sort(),
+    ["enabled", "entrypointMismatches", "entrypointMode", "inflight", "lastEntrypoint", "maxConcurrent", "queued"]);
+  assert.equal(block.enabled, true);
+  assert.equal(block.entrypointMode, "cli");
+  assert.equal(block.lastEntrypoint, "cli");
+  assert.equal(block.entrypointMismatches, 3);
+  assert.equal(block.inflight, 0);
+  assert.equal(block.queued, 0);
+  assert.equal(block.maxConcurrent, 2);
+});
+
+test("buildTuiHealthBlock: TUI off → enabled:false but block still present (stable shape)", () => {
+  const sem = new TuiSemaphore(2);
+  const ts = { lastEntrypoint: null, entrypointMismatches: 0 };
+  const block = buildTuiHealthBlock(
+    { enabled: false, entrypointMode: "cli", maxConcurrent: 2 }, ts, sem);
+  assert.equal(block.enabled, false);
+  assert.equal(block.lastEntrypoint, null);
+  assert.equal(block.entrypointMismatches, 0);
+});
+
+await asyncTest("buildTuiHealthBlock reflects live inflight/queued while turns are in flight", async () => {
+  const sem = new TuiSemaphore(1);
+  const ts = { lastEntrypoint: null, entrypointMismatches: 0 };
+  const g1 = deferred();
+  const t1 = sem.run(async () => { await g1.p; });
+  const t2 = sem.run(async () => {}); // queued behind t1
+  await new Promise((r) => setImmediate(r));
+  const block = buildTuiHealthBlock({ enabled: true, entrypointMode: "cli", maxConcurrent: 1 }, ts, sem);
+  assert.equal(block.inflight, 1, "one turn in flight");
+  assert.equal(block.queued, 1, "one turn queued");
+  g1.resolve();
+  await t1; await t2;
+});
+
 // ── TUI session driver: runTuiTurn (live-only, guarded) ──────────────────
 console.log("\nTUI session driver:");

@@ -1532,7 +2006,7 @@ if (process.env.OCP_TUI_LIVE === "1") {
      cwd: `${process.env.HOME}/.ocp-tui/work`,
      wallclockMs: 120000,
    });
-    assert.ok(/PONG/i.test(out), `expected PONG, got: ${out.slice(0, 200)}`);
+    assert.ok(/PONG/i.test(out.text), `expected PONG, got: ${out.text.slice(0, 200)}`);
  });
 } else {
  test("runTuiTurn (live) — SKIPPED (set OCP_TUI_LIVE=1 on PI231 to run)", () => {
@@ -1540,6 +2014,290 @@ if (process.env.OCP_TUI_LIVE === "1") {
  });
 }

+// ── TUI readiness / paste-verify predicates (issue #130) ────────────────────
+// Replicates tuiInputReady, tuiPromptLanded verbatim from lib/tui/session.mjs.
+// Keep in sync with the definitions there.
+function _tuiInputReady(pane) {
+  return /\? for shortcuts/.test(pane);
+}
+function _tuiPromptLanded(pane, prompt) {
+  const flatPane = pane.replace(/\s+/g, " ");
+  if (flatPane.includes("[Pasted text")) return true;
+  const firstLine = String(prompt).split("\n").map(s => s.trim()).find(Boolean) || "";
+  const needle = firstLine.replace(/\s+/g, " ").slice(0, 24);
+  return needle.length >= 2 && flatPane.includes(needle); // C-4 (#133): 3 → 2 (see lib/tui/session.mjs)
+}
+
+// Real captured pane samples (empirically confirmed via live capture-pane on PI231,
+// claude v2.1.114 and v2.1.159). Source: issue #130 spec.
+const TUI_READY_PANE = `❯ Try "how does <filepath> work?"
+  ? for shortcuts · ← for agents`;
+
+const TUI_LANDED_PANE = `❯ Reply with exactly: PONG_TEST
+  ? for shortcuts · ← for agents`;
+
+// Welcome splash shown before input bar is rendered — no `? for shortcuts`.
+const TUI_BOOT_PANE = `╭─ Claude Code v2.1.114 ─ Welcome back Tao! ─╮\n│ Tips for getting started │`;
+
+console.log("\nTUI readiness + paste-verify predicates (issue #130):");
+
+test("tuiInputReady(READY_PANE) === true  (input bar rendered)", () => {
+  assert.equal(_tuiInputReady(TUI_READY_PANE), true);
+});
+test("tuiInputReady(LANDED_PANE) === true  (input bar still present after paste)", () => {
+  assert.equal(_tuiInputReady(TUI_LANDED_PANE), true);
+});
+test("tuiInputReady(BOOT_PANE) === false  (welcome splash, no input bar yet)", () => {
+  assert.equal(_tuiInputReady(TUI_BOOT_PANE), false);
+});
+
+test("tuiPromptLanded(READY_PANE, 'Reply with exactly: PONG_TEST') === false  (still placeholder)", () => {
+  assert.equal(_tuiPromptLanded(TUI_READY_PANE, "Reply with exactly: PONG_TEST"), false);
+});
+test("tuiPromptLanded(LANDED_PANE, 'Reply with exactly: PONG_TEST') === true  (prompt prefix visible)", () => {
+  assert.equal(_tuiPromptLanded(TUI_LANDED_PANE, "Reply with exactly: PONG_TEST"), true);
+});
+test("tuiPromptLanded(READY_PANE, 'ping') === false  (prompt text absent from placeholder pane)", () => {
+  assert.equal(_tuiPromptLanded(TUI_READY_PANE, "ping"), false);
+});
+test("tuiPromptLanded('❯ ping\\n  ? for shortcuts', 'ping') === true  (needle present, no placeholder)", () => {
+  assert.equal(_tuiPromptLanded("❯ ping\n  ? for shortcuts", "ping"), true);
+});
+// C-4 (#133): short prompts (1–2 char first line) MUST be able to land. Threshold
+// lowered 3 → 2. A 2-char prompt ("hi") present in the pane now lands instead of
+// 5s-failing with tui_paste_not_landed every time (live-reproduced: "hi").
+test("tuiPromptLanded('❯ hi\\n  ? for shortcuts', 'hi') === true  (2-char prompt lands — C-4)", () => {
+  assert.equal(_tuiPromptLanded("❯ hi\n  ? for shortcuts", "hi"), true);
+});
+// False-positive guard for the lowered threshold: a 2-char needle ABSENT from the
+// still-empty placeholder pane must NOT land (no spurious Enter into an empty box).
+test("tuiPromptLanded(READY_PANE, 'hi') === false  (2-char prompt not yet visible — no false positive)", () => {
+  assert.equal(_tuiPromptLanded(TUI_READY_PANE, "hi"), false);
+});
+// issue #130 root cause: a big bracketed paste shows "[Pasted text #N +M lines]" — must be landed.
+test("tuiPromptLanded(bracketed-paste pane, big prompt) === true", () => {
+  assert.equal(_tuiPromptLanded("❯ [Pasted text #1 +301 lines]\n  ? for shortcuts", "[System] Context 0."), true);
+});
+// issue #130 false-positive guard: the EMPTY placeholder uses a CURLY quote (“) and randomized
+// example text — the old placeholder-gone heuristic wrongly reported landed=true here, so Enter
+// fired into an empty box. Must be FALSE (no positive signal: not [Pasted text], prompt not shown).
+test("tuiPromptLanded(curly-quote placeholder, big prompt) === false  (no false-positive)", () => {
+  assert.equal(_tuiPromptLanded("❯ Try “how do I log an error?”\n  ? for shortcuts", "[System] Context 0."), false);
+});
+
+// ── /health anonymousKey gate (issue #109) ──────────────────────────────────
+// MIRRORS the predicate in server.mjs (search ADVERTISE_ANON_KEY) — copied
+// verbatim to avoid importing server.mjs (top-level server.listen() would
+// start a live HTTP server, per the stream-JSON parser tests convention above).
+console.log("\n/health anonymousKey gate (issue #109):");
+
+// Replicate the gating predicate from server.mjs line ~286/1927:
+//   ...((isLocalhost || ADVERTISE_ANON_KEY) ? { anonymousKey: ... } : {})
+function shouldAdvertiseAnonKey(isLocalhost, advertise) { return isLocalhost || advertise; }
+
+test("(localhost=false, flag=false) → omit key", () => {
+  assert.equal(shouldAdvertiseAnonKey(false, false), false);
+});
+test("(localhost=true, flag=false) → include key (localhost always exempt)", () => {
+  assert.equal(shouldAdvertiseAnonKey(true, false), true);
+});
+test("(localhost=false, flag=true) → include key (opt-in set)", () => {
+  assert.equal(shouldAdvertiseAnonKey(false, true), true);
+});
+test("(localhost=true, flag=true) → include key (both true)", () => {
+  assert.equal(shouldAdvertiseAnonKey(true, true), true);
+});
+
+// ── contentToText helper tests (issue #110) ──────────────────────────────────
+// MIRRORS server.mjs contentToText — copied verbatim to avoid importing server.mjs
+// (top-level server.listen() would start a live HTTP server).
+// Keep in sync with the definition in server.mjs above messagesToPrompt.
+console.log("\ncontentToText helper (issue #110):");
+
+function contentToText(content) {
+  if (typeof content === "string") return content;
+  if (Array.isArray(content)) {
+    return content.map(p =>
+      p && p.type === "text" && typeof p.text === "string" ? p.text : "[non-text content omitted]"
+    ).join("");
+  }
+  return content == null ? "" : JSON.stringify(content);
+}
+
+test("contentToText: string input returned unchanged", () => {
+  assert.equal(contentToText("hello"), "hello");
+});
+
+test("contentToText: array of text parts concatenated", () => {
+  assert.equal(
+    contentToText([{ type: "text", text: "hello" }, { type: "text", text: " world" }]),
+    "hello world"
+  );
+});
+
+test("contentToText: non-text part (image_url) replaced with placeholder", () => {
+  assert.equal(
+    contentToText([{ type: "image_url", image_url: { url: "https://example.com/img.png" } }]),
+    "[non-text content omitted]"
+  );
+});
+
+test("contentToText: empty array returns empty string", () => {
+  assert.equal(contentToText([]), "");
+});
+
+test("contentToText: null returns empty string", () => {
+  assert.equal(contentToText(null), "");
+});
+
+// ── messages guard predicate truth-table (issue #110) ────────────────────────
+// Mirrors the guard at server.mjs line ~1650: Array.isArray(x) && x.length > 0
+console.log("\nmessages guard predicate (issue #110):");
+
+function isValidMessages(x) { return Array.isArray(x) && x.length > 0; }
+
+test("messages guard: string 'x' → invalid (non-array)", () => {
+  assert.equal(isValidMessages("x"), false);
+});
+
+test("messages guard: empty array [] → invalid", () => {
+  assert.equal(isValidMessages([]), false);
+});
+
+test("messages guard: [{role:'user',content:'hi'}] → valid", () => {
+  assert.equal(isValidMessages([{ role: "user", content: "hi" }]), true);
+});
+
+// ── sanitizeError helper (issue #111) ────────────────────────────────────
+// Replicated verbatim from server.mjs (cannot import server.mjs).
+// The SIGKILL-escalation and timer changes are process-lifecycle and are not
+// unit-testable here (no live-server harness).
+console.log("\nsanitizeError (issue #111):");
+
+function sanitizeError(msg) {
+  return String(msg || "Internal error").replace(/\/[\w/.\-]+/g, "[path]");
+}
+
+test("sanitizeError: strips home-dir path from message", () => {
+  const result = sanitizeError("failed at /Users/foo/.claude/creds.json");
+  assert.ok(result.includes("[path]"), `expected [path] in: ${result}`);
+  assert.ok(!result.includes("/Users/foo"), `expected /Users/foo stripped, got: ${result}`);
+});
+
+test("sanitizeError: null input returns 'Internal error'", () => {
+  assert.equal(sanitizeError(null), "Internal error");
+});
+
+test("sanitizeError: message with no path passes through unchanged", () => {
+  assert.equal(sanitizeError("no path here"), "no path here");
+});
+
+test("sanitizeError: multiple paths all stripped", () => {
+  const result = sanitizeError("err /a/b and /c/d");
+  assert.ok(!result.includes("/a/b"), `expected /a/b stripped, got: ${result}`);
+  assert.ok(!result.includes("/c/d"), `expected /c/d stripped, got: ${result}`);
+  assert.ok(result.includes("[path]"), `expected [path] in: ${result}`);
+});
+
+// ── models.json SPOT wiring (issue #112) ────────────────────────────────────
+// Asserts that the alias values used by server.mjs (usage probe + default model)
+// match the expected IDs. A future alias rename that silently breaks these
+// code paths is caught here.
+import { readFileSync as spotReadFileSync } from "node:fs";
+import { fileURLToPath as spotFileURLToPath } from "node:url";
+import { dirname as spotDirname, join as spotJoin } from "node:path";
+
+console.log("\nmodels.json SPOT aliases (issue #112):");
+
+const _spotDir = spotDirname(spotFileURLToPath(import.meta.url));
+const _spotModels = JSON.parse(spotReadFileSync(spotJoin(_spotDir, "models.json"), "utf8"));
+
+test("models.json aliases.haiku === 'claude-haiku-4-5-20251001' (usage-probe SPOT)", () => {
+  assert.equal(_spotModels.aliases.haiku, "claude-haiku-4-5-20251001");
+});
+
+test("models.json aliases.sonnet === 'claude-sonnet-4-6' (default-request-model SPOT)", () => {
+  assert.equal(_spotModels.aliases.sonnet, "claude-sonnet-4-6");
+});
+
+// ── escapeHtml + key-name validator (issue #114) ────────────────────────────
+// Replicated verbatim from dashboard.html so tests run without a browser.
+function escapeHtml(s) {
+  return String(s ?? "").replace(/[&<>"']/g, c => ({ "&": "&amp;", "<": "&lt;", ">": "&gt;", '"': "&quot;", "'": "&#39;" }[c]));
+}
+const KEY_NAME_RE = /^[A-Za-z0-9 ._-]{1,64}$/;
+
+console.log("\nescapeHtml (issue #114):");
+
+test("escapeHtml: XSS payload → &lt;img not <img", () => {
+  const out = escapeHtml('<img src=x onerror=alert(1)>');
+  assert.ok(out.includes("&lt;img"), `expected &lt;img in: ${out}`);
+  assert.ok(!out.includes("<img"), `expected no raw <img in: ${out}`);
+});
+
+test("escapeHtml: single-quote, double-quote, ampersand all escaped", () => {
+  assert.equal(escapeHtml("a'b\"c&d"), "a&#39;b&quot;c&amp;d");
+});
+
+test("escapeHtml: null → empty string", () => {
+  assert.equal(escapeHtml(null), "");
+});
+
+console.log("\nKey-name validator (issue #114):");
+
+test("KEY_NAME_RE: 'wife-laptop' → valid", () => {
+  assert.ok(KEY_NAME_RE.test("wife-laptop"));
+});
+
+test("KEY_NAME_RE: 'key-1700000000000' → valid", () => {
+  assert.ok(KEY_NAME_RE.test("key-1700000000000"));
+});
+
+test("KEY_NAME_RE: '<script>' → invalid", () => {
+  assert.ok(!KEY_NAME_RE.test("<script>"));
+});
+
+test("KEY_NAME_RE: \"a'); DROP\" → invalid", () => {
+  assert.ok(!KEY_NAME_RE.test("a'); DROP"));
+});
+
+test("KEY_NAME_RE: empty string → invalid", () => {
+  assert.ok(!KEY_NAME_RE.test(""));
+});
+
+test("KEY_NAME_RE: 65-char string → invalid", () => {
+  assert.ok(!KEY_NAME_RE.test("x".repeat(65)));
+});
+
+// ── isLoopbackBind helper (issue #115, extracted to lib/net.mjs via #125) ──────
+// Tests the imported lib/net.mjs helper — the real shared definition used by server.mjs.
+console.log("\nisLoopbackBind helper (issue #115):");
+
+test("isLoopbackBind: '127.0.0.1' → true", () => {
+  assert.equal(isLoopbackBind("127.0.0.1"), true);
+});
+test("isLoopbackBind: '::1' → true", () => {
+  assert.equal(isLoopbackBind("::1"), true);
+});
+test("isLoopbackBind: 'localhost' → true", () => {
+  assert.equal(isLoopbackBind("localhost"), true);
+});
+test("isLoopbackBind: '127.0.0.5' → true (127.x.x.x range)", () => {
+  assert.equal(isLoopbackBind("127.0.0.5"), true);
+});
+test("isLoopbackBind: '0.0.0.0' → false (any-interface)", () => {
+  assert.equal(isLoopbackBind("0.0.0.0"), false);
+});
+test("isLoopbackBind: '192.168.1.5' → false (LAN IP)", () => {
+  assert.equal(isLoopbackBind("192.168.1.5"), false);
+});
+test("isLoopbackBind: '::' → false (IPv6 any-interface)", () => {
+  assert.equal(isLoopbackBind("::"), false);
+});
+test("isLoopbackBind: '100.64.0.1' → false (Tailscale IP)", () => {
+  assert.equal(isLoopbackBind("100.64.0.1"), false);
+});
+
 // ── Cleanup ──
 closeDb();