seb/hermes-agent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

test: remove low-value model-catalog mirror tests

Browse Source 
These tests asserted that hardcoded curated model lists/constants still
contained specific model strings (e.g. 'glm-5' in provider_model_ids('zai'),
exact context-length values per model key, PROVIDER_TO_MODELS_DEV entries).
They mirror a constant rather than exercise logic, so they only ever break
when models are added/retired and never catch a real bug.

Removed 22 such functions across 7 files (149 deletions, 0 additions).
Behavioral siblings are kept: live-catalog-wins, fallback ordering,
substring/longest-match resolution, normalization, credential discovery,
and probe-tier stepping all still tested.
This commit is contained in:
kshitijk4poor
2026-05-29 23:45:05 -07:00
committed by kshitij
parent 0437137fff
commit 7b0915037c
7 changed files with 0 additions and 150 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/agent/test_model_metadata.py
-62
View File
@@ -123,55 +123,6 @@ class TestEstimateMessagesTokensRough:
# =========================================================================
class TestDefaultContextLengths:
def test_claude_models_context_lengths(self):
for key, value in DEFAULT_CONTEXT_LENGTHS.items():
if "claude" not in key:
continue
# Claude 4.6+ models (4.6, 4.7, 4.8) have 1M context at standard
# API pricing (no long-context premium). Older Claude 4.x and
# 3.x models cap at 200k.
if any(tag in key for tag in ("4.6", "4-6", "4.7", "4-7", "4.8", "4-8")):
assert value == 1000000, f"{key} should be 1000000"
else:
assert value == 200000, f"{key} should be 200000"
def test_gpt4_models_128k_or_1m(self):
# gpt-4.1 and gpt-4.1-mini have 1M context; other gpt-4* have 128k
for key, value in DEFAULT_CONTEXT_LENGTHS.items():
if "gpt-4" in key and "gpt-4.1" not in key:
assert value == 128000, f"{key} should be 128000"
def test_gpt41_models_1m(self):
for key, value in DEFAULT_CONTEXT_LENGTHS.items():
if "gpt-4.1" in key:
assert value == 1047576, f"{key} should be 1047576"
def test_gemini_models_1m(self):
for key, value in DEFAULT_CONTEXT_LENGTHS.items():
if "gemini" in key:
assert value == 1048576, f"{key} should be 1048576"
def test_grok_models_context_lengths(self):
# xAI /v1/models does not return context_length metadata, so
# DEFAULT_CONTEXT_LENGTHS must cover the Grok family explicitly.
# Values sourced from models.dev (2026-04).
expected = {
"grok-4.20": 2000000,
"grok-4-fast": 2000000,
"grok-4": 256000,
"grok-build": 256000,
"grok-code-fast": 256000,
"grok-3": 131072,
"grok-2": 131072,
"grok-2-vision": 8192,
"grok": 131072,
}
for key, value in expected.items():
assert key in DEFAULT_CONTEXT_LENGTHS, f"{key} missing from DEFAULT_CONTEXT_LENGTHS"
assert DEFAULT_CONTEXT_LENGTHS[key] == value, (
f"{key} should be {value}, got {DEFAULT_CONTEXT_LENGTHS[key]}"
)
def test_grok_substring_matching(self):
# Longest-first substring matching must resolve the real xAI model
# IDs to the correct fallback entries without 128k probe-down.
@@ -268,13 +219,6 @@ class TestDefaultContextLengths:
f"{model_id}: expected {expected_ctx}, got {actual}"
)
def test_all_values_positive(self):
for key, value in DEFAULT_CONTEXT_LENGTHS.items():
assert value > 0, f"{key} has non-positive context length"
def test_dict_is_not_empty(self):
assert len(DEFAULT_CONTEXT_LENGTHS) >= 10
# =========================================================================
# Codex OAuth context-window resolution (provider="openai-codex")
@@ -1141,12 +1085,6 @@ class TestContextProbeTiers:
for i in range(len(CONTEXT_PROBE_TIERS) - 1):
assert CONTEXT_PROBE_TIERS[i] > CONTEXT_PROBE_TIERS[i + 1]
def test_first_tier_is_256k(self):
assert CONTEXT_PROBE_TIERS[0] == 256_000
def test_last_tier_is_8k(self):
assert CONTEXT_PROBE_TIERS[-1] == 8_000
class TestGetNextProbeTier:
def test_from_256k(self):
tests/agent/test_models_dev.py
-11
View File
@@ -82,17 +82,6 @@ SAMPLE_REGISTRY = {
class TestProviderMapping:
def test_all_mapped_providers_are_strings(self):
for hermes_id, mdev_id in PROVIDER_TO_MODELS_DEV.items():
assert isinstance(hermes_id, str)
assert isinstance(mdev_id, str)
def test_known_providers_mapped(self):
assert PROVIDER_TO_MODELS_DEV["anthropic"] == "anthropic"
assert PROVIDER_TO_MODELS_DEV["copilot"] == "github-copilot"
assert PROVIDER_TO_MODELS_DEV["stepfun"] == "stepfun"
assert PROVIDER_TO_MODELS_DEV["kilocode"] == "kilo"
def test_xai_oauth_uses_xai_catalog(self):
assert PROVIDER_TO_MODELS_DEV["xai"] == "xai"
assert PROVIDER_TO_MODELS_DEV["xai-oauth"] == "xai"