From dee4f27dce4a8837eea4b97b882314c50a2b74e3 Mon Sep 17 00:00:00 2001
From: "Jerome Sonnet (letzdoo)" <jerome.sonnet@letzdoo.com>
Date: Wed, 11 Mar 2026 07:43:28 +0400
Subject: [PATCH] feat: add Ollama as a local LLM provider

Add native Ollama support so local models (e.g. nemotron-3-nano) can be
used without an API key. Adds ProviderSpec with ollama_chat LiteLLM
prefix, ProvidersConfig field, and skips API key validation for local
providers.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---
 nanobot/cli/commands.py       |  2 +-
 nanobot/config/schema.py      |  5 +++--
 nanobot/providers/registry.py | 17 +++++++++++++++++
 3 files changed, 21 insertions(+), 3 deletions(-)

diff --git a/nanobot/cli/commands.py b/nanobot/cli/commands.py
index cf69450..8387b28 100644
--- a/nanobot/cli/commands.py
+++ b/nanobot/cli/commands.py
@@ -252,7 +252,7 @@ def _make_provider(config: Config):
     from nanobot.providers.litellm_provider import LiteLLMProvider
     from nanobot.providers.registry import find_by_name
     spec = find_by_name(provider_name)
-    if not model.startswith("bedrock/") and not (p and p.api_key) and not (spec and spec.is_oauth):
+    if not model.startswith("bedrock/") and not (p and p.api_key) and not (spec and (spec.is_oauth or spec.is_local)):
         console.print("[red]Error: No API key configured.[/red]")
         console.print("Set one in ~/.nanobot/config.json under providers section")
         raise typer.Exit(1)
diff --git a/nanobot/config/schema.py b/nanobot/config/schema.py
index a2de239..9b5821b 100644
--- a/nanobot/config/schema.py
+++ b/nanobot/config/schema.py
@@ -272,6 +272,7 @@ class ProvidersConfig(Base):
     moonshot: ProviderConfig = Field(default_factory=ProviderConfig)
     minimax: ProviderConfig = Field(default_factory=ProviderConfig)
     aihubmix: ProviderConfig = Field(default_factory=ProviderConfig)  # AiHubMix API gateway
+    ollama: ProviderConfig = Field(default_factory=ProviderConfig)  # Ollama local models
     siliconflow: ProviderConfig = Field(default_factory=ProviderConfig)  # SiliconFlow (硅基流动)
     volcengine: ProviderConfig = Field(default_factory=ProviderConfig)  # VolcEngine (火山引擎)
     openai_codex: ProviderConfig = Field(default_factory=ProviderConfig)  # OpenAI Codex (OAuth)
@@ -375,14 +376,14 @@ class Config(BaseSettings):
         for spec in PROVIDERS:
             p = getattr(self.providers, spec.name, None)
             if p and model_prefix and normalized_prefix == spec.name:
-                if spec.is_oauth or p.api_key:
+                if spec.is_oauth or spec.is_local or p.api_key:
                     return p, spec.name
 
         # Match by keyword (order follows PROVIDERS registry)
         for spec in PROVIDERS:
             p = getattr(self.providers, spec.name, None)
             if p and any(_kw_matches(kw) for kw in spec.keywords):
-                if spec.is_oauth or p.api_key:
+                if spec.is_oauth or spec.is_local or p.api_key:
                     return p, spec.name
 
         # Fallback: gateways first, then others (follows registry order)
diff --git a/nanobot/providers/registry.py b/nanobot/providers/registry.py
index 3ba1a0e..c4bcfe2 100644
--- a/nanobot/providers/registry.py
+++ b/nanobot/providers/registry.py
@@ -360,6 +360,23 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
         strip_model_prefix=False,
         model_overrides=(),
     ),
+    # === Ollama (local, OpenAI-compatible) ===================================
+    ProviderSpec(
+        name="ollama",
+        keywords=("ollama", "nemotron"),
+        env_key="OLLAMA_API_KEY",
+        display_name="Ollama",
+        litellm_prefix="ollama_chat",  # model → ollama_chat/model
+        skip_prefixes=("ollama/", "ollama_chat/"),
+        env_extras=(),
+        is_gateway=False,
+        is_local=True,
+        detect_by_key_prefix="",
+        detect_by_base_keyword="11434",
+        default_api_base="http://localhost:11434",
+        strip_model_prefix=False,
+        model_overrides=(),
+    ),
     # === Auxiliary (not a primary LLM provider) ============================
     # Groq: mainly used for Whisper voice transcription, also usable for LLM.
     # Needs "groq/" prefix for LiteLLM routing. Placed last — it rarely wins fallback.