Pick openrouter/pareto-code as your model and OpenRouter auto-routes each
request to the cheapest model meeting your coding-quality bar (ranked by
Artificial Analysis). The new openrouter.min_coding_score config key (0.0-1.0,
default 0.65) tunes the floor.
- hermes_cli/models.py: add openrouter/pareto-code to OPENROUTER_MODELS so
it shows up in the picker with a description
- hermes_cli/config.py: add openrouter.min_coding_score (default 0.65 — lands
on a mid-tier coder on the current Pareto frontier)
- plugins/model-providers/openrouter: emit extra_body.plugins =
[{id: pareto-router, min_coding_score: X}] when model is openrouter/pareto-code
AND the score is a valid float in [0.0, 1.0]
- agent/transports/chat_completions.py: same emission on the legacy flag
path (when no provider profile is loaded)
- run_agent.py: openrouter_min_coding_score kwarg + storage; plumbed into
both build_kwargs() invocations and the context-summary extra_body path
- cli.py: read openrouter.min_coding_score once at init, validate float in
[0,1], pass to AIAgent constructions (CLI + background-task paths)
- cron/scheduler.py, batch_runner.py, tools/delegate_tool.py,
tui_gateway/server.py: propagate the kwarg (mirrors providers_order
plumbing — subagents inherit, cron/batch read from config)
- tests: profile-level + transport-level coverage of the model gating,
unset/empty/out-of-range handling, and the legacy flag path
- docs: new 'OpenRouter Pareto Code Router' section in providers.md
Verified end-to-end against api.openrouter.ai: at score=0.65 we land on a
mid-tier coder, at omission we get the strongest. Score is silently dropped
on any model other than openrouter/pareto-code, so it's safe to leave set.
Two unit tests that pin down the threading.local semantics the CLI freeze
fix (#13617 / #13618) relies on:
- main-thread registration must be invisible to child threads (documents
the underlying bug — if this ever starts passing visible, ACP's
GHSA-qg5c-hvr5-hjgr race has returned)
- child-thread registration must be visible from that same thread AND
cleared by the finally block (documents the fix pattern used by
cli.py's run_agent closure and acp_adapter/server.py)
Pairs with the fix in the preceding commit by @Societus.
* fix(cli): stop approval panel from clipping approve/deny off-screen
The dangerous-command approval panel had an unbounded Window height with
choices at the bottom. When tirith findings produced long descriptions or
the terminal was compact, HSplit clipped the bottom of the widget — which
is exactly where approve/session/always/deny live. Users were asked to
decide on commands without being able to see the choices (and sometimes
the command itself was hidden too).
Fix: reorder the panel so title → command → choices render first, with
description last. Budget vertical rows so the mandatory content (command
and every choice) always fits, and truncate the description to whatever
row budget is left. Handle three edge cases:
- Long description in a normal terminal: description gets truncated at
the bottom with a '… (description truncated)' marker. Command and
all four choices always visible.
- Compact terminal (≤ ~14 rows): description dropped entirely. Command
and choices are the only content, no overflow.
- /view on a giant command: command gets truncated with a marker so
choices still render. Keeps at least 2 rows of command.
Same row-budgeting pattern applied to the clarify widget, which had the
identical structural bug (long question would push choices off-screen).
Adds regression tests covering all three scenarios.
* fix(cli): add compact chrome mode for approval/clarify panels on short terminals
Live PTY test at 100x14 rows revealed reserved_below=4 was too optimistic
— the spinner/tool-progress line, status bar, input area, separators, and
prompt symbol actually consume ~6 rows below the panel. At 14 rows, the
panel still got 'Deny' clipped off the bottom.
Fix: bump reserved_below to 6 (measured from live PTY output) and add a
compact-chrome mode that drops the blank separators between title/command
and command/choices when the full-chrome panel wouldn't fit. Chrome goes
from 5 rows to 3 rows in tight mode, keeping command + all 4 choices on
screen in terminals as small as ~13 rows.
Same compact-chrome pattern applied to the clarify widget.
Verified live in PTY hermes chat sessions at 100x14 (compact chrome
triggered, all choices visible) and 100x30 (full chrome with blanks, nice
spacing) by asking the agent to run 'rm -rf /tmp/sandbox'.
---------
Co-authored-by: Teknium <teknium@nousresearch.com>
* refactor: re-architect tests to mirror the codebase
* Update tests.yml
* fix: add missing tool_error imports after registry refactor
* fix(tests): replace patch.dict with monkeypatch to prevent env var leaks under xdist
patch.dict(os.environ) can leak TERMINAL_ENV across xdist workers,
causing test_code_execution tests to hit the Modal remote path.
* fix(tests): fix update_check and telegram xdist failures
- test_update_check: replace patch("hermes_cli.banner.os.getenv") with
monkeypatch.setenv("HERMES_HOME") — banner.py no longer imports os
directly, it uses get_hermes_home() from hermes_constants.
- test_telegram_conflict/approval_buttons: provide real exception classes
for telegram.error mock (NetworkError, TimedOut, BadRequest) so the
except clause in connect() doesn't fail with "catching classes that do
not inherit from BaseException" when xdist pollutes sys.modules.
* fix(tests): accept unavailable_models kwarg in _prompt_model_selection mock
2026-04-07 17:19:07 -07:00
Renamed from tests/test_cli_approval_ui.py (Browse further)
