mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-06-09 08:21:50 +00:00
fix(completion): remove /model <arg> autocomplete from CLI/TUI (#39727)
* 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
GitHub
parent
14fee4f112
commit
7583aedacd
2 changed files with 1 additions and 151 deletions
|
|
@ -1148,41 +1148,6 @@ def slack_subcommand_map() -> dict[str, str]:
|
|||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
# Per-process cache for /model<space> LM Studio autocomplete. Probing on
|
||||
# every keystroke would block the UI; a short TTL keeps it live without
|
||||
# hammering the server.
|
||||
_LMSTUDIO_COMPLETION_CACHE: tuple[float, list[str]] | None = None
|
||||
|
||||
|
||||
def _lmstudio_completion_models() -> list[str]:
|
||||
"""Locally-loaded LM Studio models for /model autocomplete (cached, gated)."""
|
||||
global _LMSTUDIO_COMPLETION_CACHE
|
||||
# Gate: don't probe 127.0.0.1 on every keystroke for users who don't use LM Studio.
|
||||
if not (os.environ.get("LM_API_KEY") or os.environ.get("LM_BASE_URL")):
|
||||
try:
|
||||
from hermes_cli.auth import _load_auth_store
|
||||
store = _load_auth_store() or {}
|
||||
if "lmstudio" not in (store.get("providers") or {}) \
|
||||
and "lmstudio" not in (store.get("credential_pool") or {}):
|
||||
return []
|
||||
except Exception:
|
||||
return []
|
||||
now = time.time()
|
||||
if _LMSTUDIO_COMPLETION_CACHE and (now - _LMSTUDIO_COMPLETION_CACHE[0]) < 30.0:
|
||||
return _LMSTUDIO_COMPLETION_CACHE[1]
|
||||
try:
|
||||
from hermes_cli.models import fetch_lmstudio_models
|
||||
models = fetch_lmstudio_models(
|
||||
api_key=os.environ.get("LM_API_KEY", ""),
|
||||
base_url=os.environ.get("LM_BASE_URL") or "http://127.0.0.1:1234/v1",
|
||||
timeout=0.8,
|
||||
)
|
||||
except Exception:
|
||||
models = []
|
||||
_LMSTUDIO_COMPLETION_CACHE = (now, models)
|
||||
return models
|
||||
|
||||
|
||||
class SlashCommandCompleter(Completer):
|
||||
"""Autocomplete for built-in slash commands, subcommands, and skill commands."""
|
||||
|
||||
|
|
@ -1599,52 +1564,6 @@ class SlashCommandCompleter(Completer):
|
|||
except Exception:
|
||||
pass
|
||||
|
||||
def _model_completions(self, sub_text: str, sub_lower: str):
|
||||
"""Yield completions for /model from config aliases + built-in aliases."""
|
||||
seen = set()
|
||||
# Config-based direct aliases (preferred — include provider info)
|
||||
try:
|
||||
from hermes_cli.model_switch import (
|
||||
_ensure_direct_aliases, DIRECT_ALIASES, MODEL_ALIASES,
|
||||
)
|
||||
_ensure_direct_aliases()
|
||||
for name, da in DIRECT_ALIASES.items():
|
||||
if name.startswith(sub_lower) and name != sub_lower:
|
||||
seen.add(name)
|
||||
yield Completion(
|
||||
name,
|
||||
start_position=-len(sub_text),
|
||||
display=name,
|
||||
display_meta=f"{da.model} ({da.provider})",
|
||||
)
|
||||
# Built-in catalog aliases not already covered
|
||||
for name in sorted(MODEL_ALIASES.keys()):
|
||||
if name in seen:
|
||||
continue
|
||||
if name.startswith(sub_lower) and name != sub_lower:
|
||||
identity = MODEL_ALIASES[name]
|
||||
yield Completion(
|
||||
name,
|
||||
start_position=-len(sub_text),
|
||||
display=name,
|
||||
display_meta=f"{identity.vendor}/{identity.family}",
|
||||
)
|
||||
except Exception:
|
||||
pass
|
||||
# LM Studio: surface locally-loaded models. Gated on the user actually
|
||||
# having LM Studio configured (env var or auth-store entry) so we
|
||||
# don't probe 127.0.0.1 on every keystroke for users who don't use it.
|
||||
for name in _lmstudio_completion_models():
|
||||
if name in seen:
|
||||
continue
|
||||
if name.startswith(sub_lower) and name != sub_lower:
|
||||
yield Completion(
|
||||
name,
|
||||
start_position=-len(sub_text),
|
||||
display=name,
|
||||
display_meta="LM Studio",
|
||||
)
|
||||
|
||||
def get_completions(self, document, complete_event):
|
||||
text = document.text_before_cursor
|
||||
if not text.startswith("/"):
|
||||
|
|
@ -1668,9 +1587,6 @@ class SlashCommandCompleter(Completer):
|
|||
|
||||
# Dynamic completions for commands with runtime lists
|
||||
if " " not in sub_text:
|
||||
if base_cmd == "/model":
|
||||
yield from self._model_completions(sub_text, sub_lower)
|
||||
return
|
||||
if base_cmd == "/skin":
|
||||
yield from self._skin_completions(sub_text, sub_lower)
|
||||
return
|
||||
|
|
@ -1788,7 +1704,7 @@ class SlashCommandAutoSuggest(AutoSuggest):
|
|||
return Suggestion(cmd_name[len(word):])
|
||||
return None
|
||||
|
||||
# Command is complete — suggest subcommands or model names
|
||||
# Command is complete — suggest subcommands
|
||||
sub_text = parts[1] if len(parts) > 1 else ""
|
||||
sub_lower = sub_text.lower()
|
||||
|
||||
|
|
|
|||
|
|
@ -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
|
||||
# ---------------------------------------------------------------------------
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue