Merge remote-tracking branch 'origin/main' into bb/gui

# Conflicts:
#	tui_gateway/server.py

hermes_cli/auth.py

@@ -284,7 +284,7 @@ PROVIDER_REGISTRY: Dict[str, ProviderConfig] = {
     ),
     "alibaba": ProviderConfig(
         id="alibaba",
-        name="Alibaba Cloud (DashScope)",
+        name="Qwen Cloud",
         auth_type="api_key",
         inference_base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
         api_key_env_vars=("DASHSCOPE_API_KEY",),

hermes_cli/config.py

@@ -735,15 +735,8 @@ DEFAULT_CONFIG = {
 
     # Anthropic prompt caching (Claude via OpenRouter or native Anthropic API).
     # cache_ttl must be "5m" or "1h" (Anthropic-supported tiers); other values are ignored.
-    # long_lived_prefix: when true (default), Claude on Anthropic / OpenRouter / Nous
-    #   Portal uses a split layout: tools[-1] + stable system prefix at long_lived_ttl
-    #   (cross-session cache), last 2 messages at cache_ttl (within-session rolling).
-    #   Set false to keep the legacy "system + last 3 messages" single-tier layout.
-    # long_lived_ttl: TTL for the cross-session prefix tier ("5m" or "1h"; default "1h").
     "prompt_caching": {
         "cache_ttl": "5m",
-        "long_lived_prefix": True,
-        "long_lived_ttl": "1h",
     },
 
     # OpenRouter-specific settings.

hermes_cli/goals.py

@@ -307,7 +307,7 @@ def judge_goal(
         return "continue", "empty response (nothing to evaluate)", False
 
     try:
-        from agent.auxiliary_client import get_text_auxiliary_client
+        from agent.auxiliary_client import get_auxiliary_extra_body, get_text_auxiliary_client
     except Exception as exc:
         logger.debug("goal judge: auxiliary client import failed: %s", exc)
         return "continue", "auxiliary client unavailable", False
@@ -336,6 +336,7 @@ def judge_goal(
             temperature=0,
             max_tokens=200,
             timeout=timeout,
+            extra_body=get_auxiliary_extra_body() or None,
         )
     except Exception as exc:
         logger.info("goal judge: API call failed (%s) — falling through to continue", exc)

hermes_cli/kanban_specify.py

@@ -155,7 +155,7 @@ def specify_task(
         )
 
     try:
-        from agent.auxiliary_client import get_text_auxiliary_client
+        from agent.auxiliary_client import get_auxiliary_extra_body, get_text_auxiliary_client
     except Exception as exc:  # pragma: no cover — import smoke test
         logger.debug("specify: auxiliary client import failed: %s", exc)
         return SpecifyOutcome(task_id, False, "auxiliary client unavailable")
@@ -187,6 +187,7 @@ def specify_task(
             temperature=0.3,
             max_tokens=1500,
             timeout=timeout or 120,
+            extra_body=get_auxiliary_extra_body() or None,
         )
     except Exception as exc:
         logger.info(

hermes_cli/models.py

@@ -908,10 +908,10 @@ CANONICAL_PROVIDERS: list[ProviderEntry] = [
     ProviderEntry("lmstudio",       "LM Studio",                "LM Studio (local desktop app with built-in model server)"),
     ProviderEntry("anthropic",      "Anthropic",                "Anthropic (Claude models — API key or Claude Code)"),
     ProviderEntry("openai-codex",   "OpenAI Codex",             "OpenAI Codex"),
+    ProviderEntry("alibaba",        "Qwen Cloud",               "Qwen Cloud / DashScope Coding (Qwen + multi-provider)"),
     ProviderEntry("xiaomi",         "Xiaomi MiMo",              "Xiaomi MiMo (MiMo-V2.5 and V2 models — pro, omni, flash)"),
     ProviderEntry("tencent-tokenhub", "Tencent TokenHub",       "Tencent TokenHub (Hy3 Preview — direct API via tokenhub.tencentmaas.com)"),
     ProviderEntry("nvidia",         "NVIDIA NIM",               "NVIDIA NIM (Nemotron models — build.nvidia.com or local NIM)"),
-    ProviderEntry("qwen-oauth",     "Qwen OAuth (Portal)",      "Qwen OAuth (reuses local Qwen CLI login)"),
     ProviderEntry("copilot",        "GitHub Copilot",           "GitHub Copilot (uses GITHUB_TOKEN or gh auth token)"),
     ProviderEntry("copilot-acp",    "GitHub Copilot ACP",       "GitHub Copilot ACP (spawns `copilot --acp --stdio`)"),
     ProviderEntry("huggingface",    "Hugging Face",             "Hugging Face Inference Providers (20+ open models)"),
@@ -926,7 +926,6 @@ CANONICAL_PROVIDERS: list[ProviderEntry] = [
     ProviderEntry("minimax",        "MiniMax",                  "MiniMax (global direct API)"),
     ProviderEntry("minimax-oauth",  "MiniMax (OAuth)",          "MiniMax via OAuth browser login (Coding Plan, minimax.io)"),
     ProviderEntry("minimax-cn",     "MiniMax (China)",          "MiniMax China (domestic direct API)"),
-    ProviderEntry("alibaba",        "Alibaba Cloud (DashScope)","Alibaba Cloud / DashScope Coding (Qwen + multi-provider)"),
     ProviderEntry("ollama-cloud",   "Ollama Cloud",             "Ollama Cloud (cloud-hosted open models — ollama.com)"),
     ProviderEntry("arcee",          "Arcee AI",                 "Arcee AI (Trinity models — direct API)"),
     ProviderEntry("gmi",            "GMI Cloud",                "GMI Cloud (multi-model direct API)"),
@@ -936,6 +935,7 @@ CANONICAL_PROVIDERS: list[ProviderEntry] = [
     ProviderEntry("bedrock",        "AWS Bedrock",              "AWS Bedrock (Claude, Nova, Llama, DeepSeek — IAM or API key)"),
     ProviderEntry("azure-foundry",  "Azure Foundry",            "Azure Foundry (OpenAI-style or Anthropic-style endpoint — your Azure AI deployment)"),
     ProviderEntry("ai-gateway",     "Vercel AI Gateway",        "Vercel AI Gateway"),
+    ProviderEntry("qwen-oauth",     "Qwen OAuth (Portal)",      "Qwen OAuth (reuses local Qwen CLI login)"),
 ]
 
 # Auto-extend CANONICAL_PROVIDERS with any provider registered in providers/