Commit graph

12 commits

Author SHA1 Message Date
Yiorgis Gozadinos
485a8f901e
Document the real max_searches default
Both configuration pages said 3; the default has been 5.
2026-07-30 14:56:17 +03:00
Yiorgis Gozadinos
221c90af72
Bound a compute-only call at code_timeout
The pool watchdog counts only the time a worker spends running code, so a read
that blocks the worker never trips it. The margin above code_timeout therefore
guarded a race that cannot happen, and only bought a runaway call 90s where 60s
was configured. Pass code_timeout straight through. The two limits are disjoint:
the watchdog bounds a call that computes, and the read deadline bounds a call
that reads.

Drop the ordering test, which was true for any positive margin. The containment
test no longer sets code_timeout to zero, because that value now also disables
the watchdog and kills the worker before the read guard can refuse. It patches
the guard instead.

Monty 0.0.19 runs a plain class and a class with __enter__ and __exit__. Only
inheritance and metaclasses raise. Say that in the instructions.

MemoryFile is no longer constructed, so drop the import, the annotation, and the
stale references in the sandbox docstring and CLAUDE.md. That CLAUDE.md line
also still claimed a ThreadPoolExecutor, _run_async, and a fresh interpreter per
call.
2026-07-28 19:11:19 +03:00
Yiorgis Gozadinos
522959d9b4
Check the code timeout before each document read
The VFS bridge suspends the Monty worker for the length of a read. Monty checks
its duration budget between interpreter steps, so it cannot check while a read
is in flight. Code that reads in a loop overran a 60s budget by minutes. A read
takes about 20ms on a 2789-document corpus, so a full scan spends about 55s in
reads alone.

Check the deadline before each read. Raising from inside the callback answers the
worker's suspension, which keeps the session usable.

Monty also spends max_duration_secs across the session rather than per call, and
the sandbox reuses the session so that variables persist. Budget it for
code_timeout * max_executions. At the old per-call value the first slow call
starved every later one.

Do not wrap feed_run in asyncio.wait_for. Cancelling during pure compute is
clean, but cancelling while a read waits for an answer wedges the session with a
protocol RuntimeError that escapes execute(). A call that computes without
reading stays bounded by the session budget alone.
2026-07-28 19:11:19 +03:00
Yiorgis Gozadinos
43c17a6777
fix capability execution limits and chat loading 2026-07-24 15:26:17 +03:00
Yiorgis Gozadinos
9deb1f2bd4
replace haiku.skills with native Pydantic AI capabilities 2026-07-24 15:26:17 +03:00
Yiorgis Gozadinos
c1ec13f081
Lower search.max_context_chars default to 5000 2026-07-14 11:58:42 +03:00
Yiorgis Gozadinos
b14152a45b
Keep picture and table hits section-bounded during context expansion 2026-07-09 11:05:40 +03:00
Yiorgis Gozadinos
cd77bd9889
Bound analysis execute_code calls to avoid request-limit nulls 2026-06-06 14:52:05 +03:00
Yiorgis Gozadinos
e55125763f
Document setting thinking on OpenAI compat providers 2026-05-21 10:25:48 +03:00
Yiorgis Gozadinos
0ee00334c7
drop prose emdashes and semicolons; minor fixes 2026-05-20 14:27:16 +03:00
Yiorgis Gozadinos
910d178b00
docs: rebuild Skills section, drop pitch prose 2026-05-20 14:27:16 +03:00
Yiorgis Gozadinos
8c57a3ca99
Drop the multi-agent research workflow 2026-05-20 12:46:48 +03:00
Renamed from docs/configuration/qa-research.md (Browse further)