KrustyPlanet/hermes-agent
6
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix(completion): remove /model <arg> autocomplete from CLI/TUI (#39727)

Browse source 
* fix: respect disabled auto-compaction on context overflow

Port from anomalyco/opencode#30749.

When compression.enabled is false, NO automatic compaction trigger may
fire. The proactive token-threshold paths (preflight + post-response
should_compress gate) already honoured the setting, but the three
provider-overflow recovery paths in the agent loop — long-context-tier
429, 413 payload-too-large, and context-overflow — called
_compress_context() unconditionally, silently compressing and rotating
the session against the user's explicit choice.

Add a single guard at the top of the overflow-recovery dispatch: when
compression is disabled and the error is one of those three overflow
classes, surface a terminal error (compaction_disabled: True) telling the
user to /compress manually, /new, switch to a larger-context model, or
reduce attachments. Manual /compress (force=True) is unaffected — it never
enters this loop.

Tests: new TestOverflowWithCompactionDisabled (413 + 400 overflow don't
compress when disabled; control case still compresses when enabled).
Existing overflow-recovery tests updated to enable compaction explicitly
(they verify the recovery fires); fixture defaults flipped to True to
match production (compression.enabled defaults to True).

* fix(completion): remove /model <arg> autocomplete from CLI/TUI

The TUI frontend already suppressed /model argument completion in favor of
the two-step ModelPicker (useCompletion.ts), but the CLI prompt_toolkit
completer and the gateway-backed complete.slash RPC (TUI + desktop) still
emitted model aliases and probed LM Studio on every keystroke.

Drops the /model branch in SlashCommandCompleter.get_completions, the
_model_completions method, and the LM Studio probe/cache helper that only
fed it. Command-name completion (/mod -> model) and sibling arg completers
(/skin, /personality) are untouched. Removes the now-dead TestModelTabCompletion
tests.
This commit is contained in:
Teknium 2026-06-05 06:43:51 -07:00 • committed by GitHub
parent 14fee4f112
commit 7583aedacd
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 1 additions and 151 deletions
Download patch file Download diff file Expand all files Collapse all files

66
tests/hermes_cli/test_ollama_cloud_auth.py
View file

@ -178,72 +178,6 @@ class TestModelSwitchPersistence:
assert result.base_url == "https://api.anthropic.com"
# ---------------------------------------------------------------------------
# /model tab completion
# ---------------------------------------------------------------------------
class TestModelTabCompletion:
"""SlashCommandCompleter provides model alias completions for /model."""
def test_model_completions_yields_direct_aliases(self, monkeypatch):
"""_model_completions yields direct aliases with model and provider info."""
from hermes_cli.commands import SlashCommandCompleter
from hermes_cli.model_switch import DirectAlias
import hermes_cli.model_switch as ms
test_aliases = {
"opus": DirectAlias("claude-opus-4-6", "anthropic", ""),
"qwen": DirectAlias("qwen3.5:397b", "custom", "https://ollama.com/v1"),
}
monkeypatch.setattr(ms, "DIRECT_ALIASES", test_aliases)
completer = SlashCommandCompleter()
completions = list(completer._model_completions("", ""))
names = [c.text for c in completions]
assert "opus" in names
assert "qwen" in names
def test_model_completions_filters_by_prefix(self, monkeypatch):
"""Completions filter by typed prefix."""
from hermes_cli.commands import SlashCommandCompleter
from hermes_cli.model_switch import DirectAlias
import hermes_cli.model_switch as ms
test_aliases = {
"opus": DirectAlias("claude-opus-4-6", "anthropic", ""),
"qwen": DirectAlias("qwen3.5:397b", "custom", "https://ollama.com/v1"),
}
monkeypatch.setattr(ms, "DIRECT_ALIASES", test_aliases)
completer = SlashCommandCompleter()
completions = list(completer._model_completions("o", "o"))
names = [c.text for c in completions]
assert "opus" in names
assert "qwen" not in names
def test_model_completions_shows_metadata(self, monkeypatch):
"""Completions include model name and provider in display_meta."""
from hermes_cli.commands import SlashCommandCompleter
from hermes_cli.model_switch import DirectAlias
import hermes_cli.model_switch as ms
test_aliases = {
"glm": DirectAlias("glm-4.7", "custom", "https://ollama.com/v1"),
}
monkeypatch.setattr(ms, "DIRECT_ALIASES", test_aliases)
completer = SlashCommandCompleter()
completions = list(completer._model_completions("g", "g"))
assert len(completions) >= 1
glm_comp = [c for c in completions if c.text == "glm"][0]
meta_str = str(glm_comp.display_meta)
assert "glm-4.7" in meta_str
assert "custom" in meta_str
# ---------------------------------------------------------------------------
# Fallback base_url passthrough
# ---------------------------------------------------------------------------