[chore] Bump local LLM glm-5→glm-5.2 + swap Ollama fleet defaults off minimax

- llm_catalog: OLLAMA_DEFAULT_MODEL minimax-m3:cloud → kimi-k2.7-code:cloud;
  role defaults kimi-k2.6→kimi-k2.7-code, developer minimax→kimi, product_owner/
  ceo kimi→glm-5.2, documenter glm→kimi; GLM 5.1→5.2 comment fix.
- config + .env.example + docker-compose{.yml,.yaml,.registry.yml} + docs +
  memory_distiller + optimal_brain: glm-5:cloud → glm-5.2:cloud.
- panel ai-routing-card: typed SelfHostedModel/boolean annotations; drop the
  stale "Minimax M3 default" string (default is now catalog-driven).
- tests: glm-5:cloud → glm-5.2:cloud in pricing + rate-limit-retry fixtures.
This commit is contained in:
Renn F
2026-06-28 02:02:33 +02:00
parent a978efb3f9
commit 676a87985f
16 changed files with 43 additions and 42 deletions
+2 -2
View File
@@ -360,7 +360,7 @@ class TestProviderAwareness:
def test_ollama_cloud_model_returns_zero(self) -> None:
"""Ollama Cloud (``:cloud`` tag) is subscription-billed, not per token."""
cost = calculate_cost("glm-5:cloud", tokens_input=_M, tokens_output=_M)
cost = calculate_cost("glm-5.2:cloud", tokens_input=_M, tokens_output=_M)
assert cost == _ZERO_COST
def test_bare_local_model_returns_zero(self) -> None:
@@ -373,5 +373,5 @@ class TestProviderAwareness:
assert _is_anthropic_model(name) is True, name
def test_is_anthropic_model_false_for_non_claude_names(self) -> None:
for name in ("ollama/llama3", "glm-5:cloud", "qwen3-embedding", "gpt-4o"):
for name in ("ollama/llama3", "glm-5.2:cloud", "qwen3-embedding", "gpt-4o"):
assert _is_anthropic_model(name) is False, name
+1 -1
View File
@@ -130,7 +130,7 @@ def _make_journal_plugin() -> JournalsIndexPlugin:
plugin = JournalsIndexPlugin.__new__(JournalsIndexPlugin)
plugin._config = MagicMock()
plugin._config.llm_base_url = "http://ollama-test:11434/v1"
plugin._config.llm_model = "glm-5:cloud"
plugin._config.llm_model = "glm-5.2:cloud"
plugin._store = MagicMock()
plugin._chunker = MagicMock()
plugin._embedder = MagicMock()