tai/taicpp/docs/glue-issues.md

# glue issues and gaps

Found while wiring `src/glue`. Each entry names the file and the smallest repro. Nothing here was patched
around silently; items marked "glue side" are limits the glue itself has.

## Open

1. **No vault seal.** `src/seal` is empty (another agent ports `Seal`). `repl::Boot` uses `store::NullSeal`
   when `TAI_PASSPHRASE` is unset: the banner says `seal: off`, python says `on (default key)`. An explicit
   `TAI_PASSPHRASE=x` is refused: `seal error: TAI_PASSPHRASE is set but this build links no vault seal` (exit 2).
   Repro: `TAI_PASSPHRASE=x build/detz --version` works (before boot), `TAI_PASSPHRASE=x build/detz hi` exits 2.
   Closes with a `store::SealPort` implementation passed as `BootOptions::seal_factory` in
   `src/glue/app_bundle.cpp` (one line).
2. **`SysInfo.collect_sysinfo` was ported by no module** (`tai.py` 8978-9008). `src/comms/comms.cpp` only has a
   stub `sys_info()`. The glue carries `SysInfoProbe` (sequential, each check timed, 10 s ceiling); the python
   runs the checks on threads. `python` and `venv` checks report the native binary instead of an interpreter.
3. **`release` tool cannot work natively.** `do_release` rewrites the `VERSION =` line of the running script.
   The binary has no script. `OpsAdapter::do_release` throws and the tool reports the error; the native flow is
   `make release PART=... MSG=...` in `taicpp/`. `ensure_self_backup` at boot is not called for the same reason.
4. **Ctrl-C does not kill the call in flight** (glue side). `AgentReplHost` expires `agent.deadline`, the loop stops at
   the next step. A running HTTP call, shell command or sandbox exec finishes first. `agent::Agent` has no
   cancellation point inside `ChatClient::complete`.
5. **MCP port is bound to the main agent** (glue side). `McpHostAdapter` asks approvals, names the audit actor and
   runs the resolver subagent through the primary agent, and uses the primary store connection. A worker agent on its
   own thread that calls an MCP tool therefore shares the primary sqlite connection. tai.py passes the calling
   agent (`app`) instead. Needs the port to carry the caller, i.e. `McpPort::call(..., Agent&)`.
6. **`docs/wiring/capmcp.md` does not exist.** The task listed it; `cap`/`mcp` were wired from the headers
   (`cap_agent_port.h`, `mcp_serve_main.h`, `mcp_host.h`) and `cap.md`/`mcp.md`.
7. **`src/cli`**: `Command::run()` is still the stub (`--help`/`--version` only) and `Parser::parse` maps `argc <= 1` to
   `--help`, whereas tai.py starts the REPL. `main.cpp` therefore calls `Parser::parseOpts` and `GlueApp::run`
   (which prints help only for an explicit `--help`). The other agent that rewrites `src/cli` should drop `Command`
   or keep `parseOpts` and the `Options` fields stable.
8. **`Makefile`**: `-I../../moloapp/src` resolves from `taicpp/` of the main checkout only. From a git worktree
   (`.claude/worktrees/*/taicpp`) it needs `CXXFLAGS=... -I/home/retoor/projects/moloapp/src`. `make test` builds
   `tests/test_main.cpp`, which still calls the removed placeholder API (`llm::ChatClient("openai", ...)`,
   `ModelHealth`, `Opencode`, `feed_sse`, `provider_info`; docs/wiring/agent.md); not touched here.
9. **`probe_backend` in the REPL banner** runs sequentially with a 6 s timeout per backend, like python: a dead
   backend delays the prompt. Not changed.
10. **Not covered by a committed test:** `--tui-local` (driven once over a pty by a throwaway script: it drew, ran a real
    model turn whose answer reached the vault session, and `/quit` exited 0), `--tui` (grr client; without a tty it
    exits 2 with `tui unavailable`, no grr server was started), `--mplex` and `--plexer-wrap` (without a tty they answer
    `no server running on ...` / `open terminal failed: not a terminal`, exit 1; the multiplexer session itself was not
    started), `--install` (run once against a throwaway `HOME`: binary copy, bash hook, venv and six bundled skills
    written, exit 0), `--update-models` (read-only discovery ran), `--eval-retrieval` and `--stats-rag` (empty vault only).
11. **`--cap-speak` string content.** A `{"type":"user","message":{"role":"user","content":"text"}}` frame (content a
    plain string) is split into one character per line before it reaches the model. This is the literal tai.py
    behavior (`cap_stream_json.cpp` mirrors `for block in message.get("content")`); real clients send a block list,
    which `tests/glue_flags.py` uses. Noted so nobody files it as a port bug.

## Fixed in the glue (one-line integration errors)

- None needed in other modules: every compile error was on the glue side.