fix: stop rejecting unlisted models, accept with warning instead
* fix: use session_key instead of chat_id for adapter interrupt lookups monitor_for_interrupt() in _run_agent was using source.chat_id to query the adapter's has_pending_interrupt() and get_pending_message() methods. But the adapter stores interrupt events under build_session_key(source), which produces a different string (e.g. 'agent:main:telegram:dm' vs '123456'). This key mismatch meant the interrupt was never detected through the adapter path, which is the only active interrupt path for all adapter-based platforms (Telegram, Discord, Slack, etc.). The gateway-level interrupt path (in dispatch_message) is unreachable because the adapter intercepts the 2nd message in handle_message() before it reaches dispatch_message(). Result: sending a new message while subagents were running had no effect — the interrupt was silently lost. Fix: replace all source.chat_id references in the interrupt-related code within _run_agent() with the session_key parameter, which matches the adapter's storage keys. Also adds regression tests verifying session_key vs chat_id consistency. * debug: add file-based logging to CLI interrupt path Temporary instrumentation to diagnose why message-based interrupts don't seem to work during subagent execution. Logs to ~/.hermes/interrupt_debug.log (immune to redirect_stdout). Two log points: 1. When Enter handler puts message into _interrupt_queue 2. When chat() reads it and calls agent.interrupt() This will reveal whether the message reaches the queue and whether the interrupt is actually fired. * fix: accept unlisted models with warning instead of rejecting validate_requested_model() previously hard-rejected any model not found in the provider's API listing. This was too aggressive — users on higher plan tiers (e.g. Z.AI Pro/Max) may have access to models not shown in the public listing (like glm-5 on coding endpoints). Changes: - validate_requested_model: accept unlisted models with a warning note instead of blocking. The model is saved to config and used immediately. - Z.AI setup: always offer glm-5 in the model list regardless of whether a coding endpoint was detected. Pro/Max plans support it. - Z.AI setup detection message: softened from 'GLM-5 is not available' to 'GLM-5 may still be available depending on your plan tier'
This commit is contained in:
Teknium
@@ -327,44 +327,35 @@ def validate_requested_model(
|
||||
"message": None,
|
||||
}
|
||||
else:
|
||||
# API responded but model is not listed
|
||||
# API responded but model is not listed. Accept anyway —
|
||||
# the user may have access to models not shown in the public
|
||||
# listing (e.g. Z.AI Pro/Max plans can use glm-5 on coding
|
||||
# endpoints even though it's not in /models). Warn but allow.
|
||||
suggestions = get_close_matches(requested, api_models, n=3, cutoff=0.5)
|
||||
suggestion_text = ""
|
||||
if suggestions:
|
||||
suggestion_text = "\n Did you mean: " + ", ".join(f"`{s}`" for s in suggestions)
|
||||
suggestion_text = "\n Similar models: " + ", ".join(f"`{s}`" for s in suggestions)
|
||||
|
||||
return {
|
||||
"accepted": False,
|
||||
"persist": False,
|
||||
"accepted": True,
|
||||
"persist": True,
|
||||
"recognized": False,
|
||||
"message": (
|
||||
f"Error: `{requested}` is not a valid model for this provider."
|
||||
f"Note: `{requested}` was not found in this provider's model listing. "
|
||||
f"It may still work if your plan supports it."
|
||||
f"{suggestion_text}"
|
||||
),
|
||||
}
|
||||
|
||||
# api_models is None — couldn't reach API, fall back to catalog check
|
||||
# api_models is None — couldn't reach API. Accept and persist,
|
||||
# but warn so typos don't silently break things.
|
||||
provider_label = _PROVIDER_LABELS.get(normalized, normalized)
|
||||
known_models = provider_model_ids(normalized)
|
||||
|
||||
if requested in known_models:
|
||||
return {
|
||||
"accepted": True,
|
||||
"persist": True,
|
||||
"recognized": True,
|
||||
"message": None,
|
||||
}
|
||||
|
||||
# Can't validate — accept for session only
|
||||
suggestion = get_close_matches(requested, known_models, n=1, cutoff=0.6)
|
||||
suggestion_text = f" Did you mean `{suggestion[0]}`?" if suggestion else ""
|
||||
return {
|
||||
"accepted": True,
|
||||
"persist": False,
|
||||
"persist": True,
|
||||
"recognized": False,
|
||||
"message": (
|
||||
f"Could not validate `{requested}` against the live {provider_label} API. "
|
||||
"Using it for this session only; config unchanged."
|
||||
f"{suggestion_text}"
|
||||
f"Could not reach the {provider_label} API to validate `{requested}`. "
|
||||
f"If the service isn't down, this model may not be valid."
|
||||
),
|
||||
}
|
||||
|
||||
@@ -889,7 +889,8 @@ def setup_model_provider(config: dict):
|
||||
print_info(f" URL: {detected['base_url']}")
|
||||
if detected["id"].startswith("coding"):
|
||||
print_info(
|
||||
f" Note: Coding Plan detected — GLM-5 is not available, using {detected['model']}"
|
||||
f" Note: Coding Plan endpoint detected (default model: {detected['model']}). "
|
||||
f"GLM-5 may still be available depending on your plan tier."
|
||||
)
|
||||
save_env_value("GLM_BASE_URL", zai_base_url)
|
||||
else:
|
||||
@@ -1107,14 +1108,11 @@ def setup_model_provider(config: dict):
|
||||
_update_config_for_provider("openai-codex", DEFAULT_CODEX_BASE_URL)
|
||||
_set_model_provider(config, "openai-codex", DEFAULT_CODEX_BASE_URL)
|
||||
elif selected_provider == "zai":
|
||||
# Coding Plan endpoints don't have GLM-5
|
||||
is_coding_plan = get_env_value("GLM_BASE_URL") and "coding" in (
|
||||
get_env_value("GLM_BASE_URL") or ""
|
||||
)
|
||||
if is_coding_plan:
|
||||
zai_models = ["glm-4.7", "glm-4.5", "glm-4.5-flash"]
|
||||
else:
|
||||
zai_models = ["glm-5", "glm-4.7", "glm-4.5", "glm-4.5-flash"]
|
||||
# Always offer all models — Pro/Max plans support GLM-5 even
|
||||
# on coding endpoints. If the user's plan doesn't support a
|
||||
# model, the API will return an error at runtime (not our job
|
||||
# to gatekeep).
|
||||
zai_models = ["glm-5", "glm-4.7", "glm-4.5", "glm-4.5-flash"]
|
||||
model_choices = list(zai_models)
|
||||
model_choices.append("Custom model")
|
||||
model_choices.append(f"Keep current ({current_model})")
|
||||
|
||||
@@ -160,7 +160,8 @@ class TestValidateFormatChecks:
|
||||
|
||||
def test_no_slash_model_rejected_if_not_in_api(self):
|
||||
result = _validate("gpt-5.4", api_models=["openai/gpt-5.4"])
|
||||
assert result["accepted"] is False
|
||||
assert result["accepted"] is True
|
||||
assert "not found" in result["message"]
|
||||
|
||||
|
||||
# -- validate — API found ----------------------------------------------------
|
||||
@@ -184,37 +185,39 @@ class TestValidateApiFound:
|
||||
# -- validate — API not found ------------------------------------------------
|
||||
|
||||
class TestValidateApiNotFound:
|
||||
def test_model_not_in_api_rejected(self):
|
||||
def test_model_not_in_api_accepted_with_warning(self):
|
||||
result = _validate("anthropic/claude-nonexistent")
|
||||
assert result["accepted"] is False
|
||||
assert "not a valid model" in result["message"]
|
||||
assert result["accepted"] is True
|
||||
assert result["persist"] is True
|
||||
assert "not found" in result["message"]
|
||||
|
||||
def test_rejection_includes_suggestions(self):
|
||||
def test_warning_includes_suggestions(self):
|
||||
result = _validate("anthropic/claude-opus-4.5")
|
||||
assert result["accepted"] is False
|
||||
assert "Did you mean" in result["message"]
|
||||
assert result["accepted"] is True
|
||||
assert "Similar models" in result["message"]
|
||||
|
||||
|
||||
# -- validate — API unreachable (fallback) -----------------------------------
|
||||
# -- validate — API unreachable — accept and persist everything ----------------
|
||||
|
||||
class TestValidateApiFallback:
|
||||
def test_known_catalog_model_accepted_when_api_down(self):
|
||||
def test_any_model_accepted_when_api_down(self):
|
||||
result = _validate("anthropic/claude-opus-4.6", api_models=None)
|
||||
assert result["accepted"] is True
|
||||
assert result["persist"] is True
|
||||
|
||||
def test_unknown_model_session_only_when_api_down(self):
|
||||
def test_unknown_model_also_accepted_when_api_down(self):
|
||||
"""No hardcoded catalog gatekeeping — accept, persist, and warn."""
|
||||
result = _validate("anthropic/claude-next-gen", api_models=None)
|
||||
assert result["accepted"] is True
|
||||
assert result["persist"] is False
|
||||
assert "session only" in result["message"].lower()
|
||||
assert result["persist"] is True
|
||||
assert "could not reach" in result["message"].lower()
|
||||
|
||||
def test_zai_known_model_accepted_when_api_down(self):
|
||||
def test_zai_model_accepted_when_api_down(self):
|
||||
result = _validate("glm-5", provider="zai", api_models=None)
|
||||
assert result["accepted"] is True
|
||||
assert result["persist"] is True
|
||||
|
||||
def test_unknown_provider_session_only_when_api_down(self):
|
||||
def test_unknown_provider_accepted_when_api_down(self):
|
||||
result = _validate("some-model", provider="totally-unknown", api_models=None)
|
||||
assert result["accepted"] is True
|
||||
assert result["persist"] is False
|
||||
assert result["persist"] is True
|
||||
|
||||
@@ -31,7 +31,7 @@ class TestModelCommand:
|
||||
assert cli_obj.model == "anthropic/claude-sonnet-4.5"
|
||||
save_mock.assert_called_once_with("model.default", "anthropic/claude-sonnet-4.5")
|
||||
|
||||
def test_invalid_model_from_api_is_rejected(self, capsys):
|
||||
def test_unlisted_model_accepted_with_warning(self, capsys):
|
||||
cli_obj = self._make_cli()
|
||||
|
||||
with patch("hermes_cli.models.fetch_api_models",
|
||||
@@ -40,12 +40,10 @@ class TestModelCommand:
|
||||
cli_obj.process_command("/model anthropic/fake-model")
|
||||
|
||||
output = capsys.readouterr().out
|
||||
assert "not a valid model" in output
|
||||
assert "Model unchanged" in output
|
||||
assert cli_obj.model == "anthropic/claude-opus-4.6"
|
||||
save_mock.assert_not_called()
|
||||
assert "not found" in output or "Model changed" in output
|
||||
assert cli_obj.model == "anthropic/fake-model" # accepted
|
||||
|
||||
def test_api_unreachable_falls_back_session_only(self, capsys):
|
||||
def test_api_unreachable_accepts_and_persists(self, capsys):
|
||||
cli_obj = self._make_cli()
|
||||
|
||||
with patch("hermes_cli.models.fetch_api_models", return_value=None), \
|
||||
@@ -53,12 +51,11 @@ class TestModelCommand:
|
||||
cli_obj.process_command("/model anthropic/claude-sonnet-next")
|
||||
|
||||
output = capsys.readouterr().out
|
||||
assert "session only" in output
|
||||
assert "will revert on restart" in output
|
||||
assert "saved to config" in output
|
||||
assert cli_obj.model == "anthropic/claude-sonnet-next"
|
||||
save_mock.assert_not_called()
|
||||
save_mock.assert_called_once()
|
||||
|
||||
def test_no_slash_model_probes_api_and_rejects(self, capsys):
|
||||
def test_no_slash_model_accepted_with_warning(self, capsys):
|
||||
cli_obj = self._make_cli()
|
||||
|
||||
with patch("hermes_cli.models.fetch_api_models",
|
||||
@@ -67,11 +64,8 @@ class TestModelCommand:
|
||||
cli_obj.process_command("/model gpt-5.4")
|
||||
|
||||
output = capsys.readouterr().out
|
||||
assert "not a valid model" in output
|
||||
assert "Model unchanged" in output
|
||||
assert cli_obj.model == "anthropic/claude-opus-4.6" # unchanged
|
||||
assert cli_obj.agent is not None # not reset
|
||||
save_mock.assert_not_called()
|
||||
# Model is accepted (with warning) even if not in API listing
|
||||
assert cli_obj.model == "gpt-5.4"
|
||||
|
||||
def test_validation_crash_falls_back_to_save(self, capsys):
|
||||
cli_obj = self._make_cli()
|
||||
|
||||
Reference in New Issue
Block a user