teddy-cli 0.1.16.dev1169__tar.gz → 0.1.16.dev1170__tar.gz

{teddy_cli-0.1.16.dev1169 → teddy_cli-0.1.16.dev1170}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: teddy-cli
-Version: 0.1.16.dev1169
+Version: 0.1.16.dev1170
 Summary: A local-first, file-based AI coding workflow that applies the UNIX philosophy to AI collaboration.
 Author: Raphael Atteritano
 License: AGPL-3.0-only

{teddy_cli-0.1.16.dev1169 → teddy_cli-0.1.16.dev1170}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "teddy-cli"
-version = "0.1.16.dev1169"
+version = "0.1.16.dev1170"
 description = "A local-first, file-based AI coding workflow that applies the UNIX philosophy to AI collaboration."
 authors = [{ name = "Raphael Atteritano" }]
 license = { text = "AGPL-3.0-only" }

{teddy_cli-0.1.16.dev1169 → teddy_cli-0.1.16.dev1170}/src/teddy_executor/core/services/session_service.py

@@ -127,8 +127,6 @@ class SessionService(ISessionManager):
         }
         if options.model:
             meta_data["model"] = options.model
-        if options.provider:
-            meta_data["provider"] = options.provider
         if options.api_key:
             meta_data["api_key"] = options.api_key
         return meta_data

{teddy_cli-0.1.16.dev1169 → teddy_cli-0.1.16.dev1170}/src/teddy_executor/resources/config/config.yaml

@@ -51,14 +51,28 @@ auto_pruning:
 # LiteLLM Configuration Reference: https://docs.litellm.ai/docs/completion/input
 # All keys under 'llm' are passed directly to litellm.completion().
 llm:
-  model: "openrouter/~deepseek/deepseek-flash-latest:nitro"  # Syntax: "openrouter/<model-path>" (paths from openrouter.ai/models); ":nitro"=fastest, ":floor"=cheapest.
+  model: "openrouter/~deepseek/deepseek-flash-latest:nitro"  # Syntax: "openrouter/<model-path>" (model paths: https://openrouter.ai/models); ":nitro"=fastest, ":floor"=cheapest.
   api_key: "${TEDDY_LLM_API_KEY}"  # Paste your key into .teddy/.env, or replace this with a literal value to override.
   max_retries: 3
   timeout: 300
 
-# Common additional parameters:
-  # temperature: 0.2
-  # max_tokens: 4096
-  # extra_body:
-  #   provider:
-  #     order: ["baseten"]
+# Local models (no API key needed — LiteLLM supplies a keyless default):
+#   model: "ollama/llama3.2"      # Ollama (default endpoint http://localhost:11434)
+#   model: "lm_studio/qwen2.5"    # LM Studio
+#   model: "hosted_vllm/mistral"  # vLLM (set api_base to your server, e.g. http://localhost:8000/v1)
+
+# Any OpenAI-compatible server (e.g. llama.cpp's llama-server) works via the
+# openai/ prefix with an explicit endpoint and a non-empty api_key (a dummy
+# value is fine). A provider prefix is required — an endpoint alone is rejected.
+#   model: "openai/<model-name>"
+#   api_base: "http://localhost:8080/v1"
+#   api_key: "sk-noop"
+
+# Any other LiteLLM/OpenAI-compatible parameters are forwarded unchanged
+# (e.g. temperature, top_p, max_tokens). Omit them to keep provider defaults.
+
+# OpenRouter provider routing (optional): prefer specific upstream providers,
+# in order.
+#   extra_body:
+#     provider:
+#       order: ["<provider-slug>"]  # Preference-ordered list of OpenRouter provider slugs.