Commit Graph

10 Commits

Author SHA1 Message Date
David Gardner 6ee218602d feat(relay): pass API request metadata to Relay tracking
Signed-off-by: David Gardner <dagardner@nvidia.com>
2026-09-10 13:23:24 -07:00
Erosika 70b1ff6930 feat(memory): carry the turn's author into the memory-provider contract
`on_turn_start` documents a per-turn kwargs channel — "kwargs may include:
remaining_tokens, model, platform, tool_count" — and `MemoryManager`
forwards whatever it receives. Its only caller passed nothing, so a memory
provider had no way to learn who wrote the turn it was being told about.

Providers that key durable state on identity resolve one identity when the
session is created. A shared session does not work that way: threads are
shared by default (`thread_sessions_per_user` is False), so alice, bob, and
another agent all write turns into a session whose peer is whoever spoke
first. The gateway's answer today is the `[name]` prefix it prepends to the
message text, which the model reads and a provider cannot.

`turn_author` now travels from the gateway through `run_conversation` into
`build_turn_context`, which forwards `author_id`, `author_name`, and
`author_is_bot` to every provider. It stops there — the trio never reaches
the model, and providers that ignore the kwargs are unaffected.

The bot flag is sent on every transport, not only shared sessions: a
provider deciding whether a turn may write to durable memory needs it in a
DM too.

`SessionSource.is_bot` is only as good as its producers. `build_source`
defaults it to False and 3 of 32 adapter call sites pass it, so most
platforms still report every author as human. Populating the rest is
follow-up work; nothing here depends on the flag being right yet.
2026-09-10 10:27:07 -07:00
Teknium ac087e6ada fix(console): cancel/timeout interrupts the command's agent and waits for the worker
Hermes Console ran each command on a ThreadPoolExecutor and cancelled only
the asyncio waiter. A command that forks an AIAgent (`curator run
--consolidate`) kept its worker thread and its in-flight provider request
alive after the prompt said "cancelled" — a llama.cpp generation kept
decoding for 30+ minutes and held the inference slot (#106179).

Root cause: the host owning the thread never knew about the agent created
deep inside the synchronous command, so it could not call the existing
cooperative `interrupt()` path that closes the request sockets.

Fix: `agent/interrupt_scope.py` gives the host an `InterruptScope`; the
console binds it around the worker (ContextVar), and every
`AIAgent.run_conversation()` registers itself with the bound scope for the
turn. On cancel, timeout and disconnect the console calls `scope.cancel()`
(hard-interrupts every registered agent; an agent registering after the
cancel is interrupted on entry so the cancel cannot lose the race with a
turn that has not started) and awaits the worker Future with a 10s bound
before reporting cancelled/timeout. Queued-but-unstarted work is dropped via
`Future.cancel()` alone.

Live repro (fake OpenAI-compatible provider blocking like llama.cpp, real
/api/console, real curator dispatch, real AIAgent + direct request path):
origin/main at the "cancelled" frame -> request_exited=false,
worker_exited=false; with this change -> both true, provider saw the peer
close, prompt reported cancelled 0.27s after the frame.

Salvage of #106197 by @kyssta-exe (executor-future handle, cancel/timeout/
disconnect propagation) and #106320 by @Xixiartemis (deterministic
lifecycle regression: terminal(cancelled) => no owned request or worker
remains live; interrupt-on-late-registration). Both rebuilt slimmer: #106197 keyed its fallback on Future.cancel()
returning False, but the handle it held was run_in_executor's asyncio
wrapper, whose cancel() returns True while the thread keeps running, so its
thread-name abort registry was never consulted; #106320's command-scoped
ownership model is folded into one small module hooked at the turn facade
instead of a per-caller `bind_agent`.

Co-authored-by: kyssta-exe <218078013+kyssta-exe@users.noreply.github.com>
Co-authored-by: Xixiartemis <182932319+Xixiartemis@users.noreply.github.com>
2026-09-09 10:58:16 -07:00
Teknium fcbe4acbef simplify(compat): tools/mcp_tool — repoint 20 non-test callers to the defining mcp_tool_* siblings 2026-09-03 13:29:35 -07:00
Teknium e83816a4d1 review-fix(comments): restore lost #NNNN rationale comments across non-test source (mechanical sweep, condensed, code unchanged)
For each issue anchor present in BASE 63279301bc non-test .py and absent on HEAD, the BASE comment/docstring block was re-attached at the HEAD location of the code it explained (matched by the distinctive code line / enclosing def). Sentences already covered by an existing HEAD comment were deduped; the issue number always survives. Insert-only: no code lines changed.
2026-09-03 09:44:26 -07:00
Teknium c449a340b6 refactor(agent/turn): comment/docstring pass — keep WHYs, drop narrative and restated code 2026-09-02 19:26:50 -07:00
Teknium 8e923c8ea1 refactor(agent/turn): facade outcome ternary + suppress, summary pluralize table, liveness/finalizer docstring trims 2026-09-02 19:08:57 -07:00
Teknium c94ced6225 refactor(agent/turn): AST-neutral bracket/signature packing across r3-08 slice 2026-09-02 18:01:27 -07:00
Teknium b4c38f2aa9 refactor(turn): lift run_conversation lease/liveness closures into agent.turn_facade_lease 2026-09-02 16:43:09 -07:00
Teknium 9576b49c0b refactor(run_agent): extract TurnFacadeMixin (run_conversation/chat admission wrapper) 2026-09-02 13:29:40 -07:00