fix(opencode-go): restore curated catalog additions (#959)

docs/issue-851-verification.md

@@ -1,55 +0,0 @@
-# Issue #851 Verification
-
-## Status: ✅ ALREADY IMPLEMENTED
-
-Issue #851 is a research/audit issue whose own conclusion is that prompt caching is already extensively implemented in hermes-agent and that the remaining work is operational, not a repo-side code change.
-
-This verification confirms that the current repo already contains the core implementation described in the issue body.
-
-## Acceptance Criteria Check
-
-1. ✅ Anthropic / OpenRouter prompt-caching support exists
-   - `agent/prompt_caching.py:41-72` implements `apply_anthropic_cache_control()` with the documented system-plus-last-3 breakpoint strategy.
-   - `run_agent.py:8301-8306` applies Anthropic/OpenRouter cache-control breakpoints during API message preparation.
-
-2. ✅ OpenAI/Codex prompt-cache key support exists
-   - `run_agent.py:6199-6213` sets `prompt_cache_key = self.session_id` on the responses path for non-GitHub responses.
-   - `run_agent.py:3875-3878` explicitly passes through `prompt_cache_key` in normalized API kwargs.
-
-3. ✅ System-prompt stability and cache-friendly message normalization exist
-   - `run_agent.py:3155-3157` documents that the system prompt is cached and reused across turns to maximize prefix cache hits.
-   - `run_agent.py:8314-8339` normalizes whitespace and tool-call JSON for bit-perfect prefix matching across turns.
-
-4. ✅ Cache hit/miss logging infrastructure exists
-   - `run_agent.py:8966-8980` logs cache read/write token stats, including `cached_tokens`, `cache_creation_input_tokens`, and hit percentage.
-
-## Executed Verification
-
-### Targeted tests run
-- `PYTHONPATH=/tmp/BURN2-FORGE-ALPHA-3 python3 -m pytest -q tests/agent/test_prompt_caching.py`
-  - Result: `14 passed`
-
-### Syntax verification
-- `PYTHONPATH=/tmp/BURN2-FORGE-ALPHA-3 python3 -m py_compile agent/prompt_caching.py run_agent.py`
-  - Result: passed
-
-## Evidence Summary
-
-The issue body says:
-- prompt caching is already extensively implemented
-- the primary opportunities are operational: routing more workloads to Ollama, verifying provider support, and reporting cache hit rates
-
-The repo state matches that conclusion:
-- caching primitives are present
-- integration points are wired into the runtime
-- targeted tests already exist and pass
-- no new implementation change is required to satisfy the issue's repo-side claim
-
-## Recommendation
-
-Close issue #851 as already implemented in the codebase.
-
-If desired, follow-on work should be opened as separate operational issues for:
-- Ollama-heavy workload routing
-- provider-specific cache verification
-- nightly cache hit-rate reporting

hermes_cli/models.py

@@ -250,12 +250,16 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "big-pickle",
     ],
     "opencode-go": [
-        "glm-5",
+        "kimi-k2.6",
         "kimi-k2.5",
+        "glm-5.1",
+        "glm-5",
         "mimo-v2-pro",
         "mimo-v2-omni",
         "minimax-m2.7",
         "minimax-m2.5",
+        "qwen3.6-plus",
+        "qwen3.5-plus",
     ],
     "ai-gateway": [
         "anthropic/claude-opus-4.6",

hermes_cli/setup.py

@@ -105,7 +105,7 @@ _DEFAULT_PROVIDER_MODELS = {
     "ai-gateway": ["anthropic/claude-opus-4.6", "anthropic/claude-sonnet-4.6", "openai/gpt-5", "google/gemini-3-flash"],
     "kilocode": ["anthropic/claude-opus-4.6", "anthropic/claude-sonnet-4.6", "openai/gpt-5.4", "google/gemini-3-pro-preview", "google/gemini-3-flash-preview"],
     "opencode-zen": ["gpt-5.4", "gpt-5.3-codex", "claude-sonnet-4-6", "gemini-3-flash", "glm-5", "kimi-k2.5", "minimax-m2.7"],
-    "opencode-go": ["glm-5", "kimi-k2.5", "mimo-v2-pro", "mimo-v2-omni", "minimax-m2.5", "minimax-m2.7"],
+    "opencode-go": ["kimi-k2.6", "kimi-k2.5", "glm-5.1", "glm-5", "mimo-v2-pro", "mimo-v2-omni", "minimax-m2.5", "minimax-m2.7", "qwen3.6-plus", "qwen3.5-plus"],
     "huggingface": [
         "Qwen/Qwen3.5-397B-A17B", "Qwen/Qwen3-235B-A22B-Thinking-2507",
         "Qwen/Qwen3-Coder-480B-A35B-Instruct", "deepseek-ai/DeepSeek-R1-0528",

tests/hermes_cli/test_opencode_go_in_model_list.py

@@ -4,32 +4,62 @@ import os
 from unittest.mock import patch
 
 from hermes_cli.model_switch import list_authenticated_providers
+from hermes_cli.models import curated_models_for_provider
 
 
 @patch.dict(os.environ, {"OPENCODE_GO_API_KEY": "test-key"}, clear=False)
 def test_opencode_go_appears_when_api_key_set():
     """opencode-go should appear in list_authenticated_providers when OPENCODE_GO_API_KEY is set."""
     providers = list_authenticated_providers(current_provider="openrouter")
-    
+
     # Find opencode-go in results
     opencode_go = next((p for p in providers if p["slug"] == "opencode-go"), None)
-    
+
     assert opencode_go is not None, "opencode-go should appear when OPENCODE_GO_API_KEY is set"
-    assert opencode_go["models"] == ["glm-5", "kimi-k2.5", "mimo-v2-pro", "mimo-v2-omni", "minimax-m2.7", "minimax-m2.5"]
+    assert opencode_go["models"] == [
+        "kimi-k2.6",
+        "kimi-k2.5",
+        "glm-5.1",
+        "glm-5",
+        "mimo-v2-pro",
+        "mimo-v2-omni",
+        "minimax-m2.7",
+        "minimax-m2.5",
+    ]
+    assert opencode_go["total_models"] == 10
     # opencode-go can appear as "built-in" (from PROVIDER_TO_MODELS_DEV when
     # models.dev is reachable) or "hermes" (from HERMES_OVERLAYS fallback when
     # the API is unavailable, e.g. in CI).
     assert opencode_go["source"] in ("built-in", "hermes")
 
 
+@patch("hermes_cli.models.provider_model_ids", return_value=[])
+def test_opencode_go_curated_fallback_includes_new_models(_mock_provider_model_ids):
+    """Fallback catalog should include Kimi K2.6 and both Qwen Plus models."""
+    model_ids = [model_id for model_id, _ in curated_models_for_provider("opencode-go")]
+
+    assert model_ids == [
+        "kimi-k2.6",
+        "kimi-k2.5",
+        "glm-5.1",
+        "glm-5",
+        "mimo-v2-pro",
+        "mimo-v2-omni",
+        "minimax-m2.7",
+        "minimax-m2.5",
+        "qwen3.6-plus",
+        "qwen3.5-plus",
+    ]
+
+
 def test_opencode_go_not_appears_when_no_creds():
     """opencode-go should NOT appear when no credentials are set."""
     # Ensure OPENCODE_GO_API_KEY is not set
     env_without_key = {k: v for k, v in os.environ.items() if k != "OPENCODE_GO_API_KEY"}
-    
+
     with patch.dict(os.environ, env_without_key, clear=True):
         providers = list_authenticated_providers(current_provider="openrouter")
-        
+
         # opencode-go should not be in results
         opencode_go = next((p for p in providers if p["slug"] == "opencode-go"), None)
         assert opencode_go is None, "opencode-go should not appear without credentials"