From f55570ceebed1eb7d36ca9111394090289d85a43 Mon Sep 17 00:00:00 2001
From: Mark Randall Havens <mark@thefoldwithin.earth>
Date: Fri, 13 Mar 2026 18:16:38 +0000
Subject: [PATCH] fix: Infrastructure - GitHub token, API validation, cost
 controls

Team 3: Infrastructure & Config

Fixed:
- #4: GitHub Ingestor now works without token for public repos
  - Token is now optional
  - Uses unauthenticated requests (with rate limit warning) when no token
  - Private repos still require token

- #14: Added startup API key validation
  - get_config() now validates API keys at startup
  - Raises clear error if neither OPENAI_API_KEY nor MINIMAX_API_KEY is set
  - Fail-fast instead of silent failures

- #10: Added CostConfig for rate limiting and budget controls
  - max_tokens_per_run: limit tokens per generation
  - max_cost_usd: budget cap in dollars
  - track_usage: enable/disable usage tracking
  - price_per_million_tokens: pricing by model
---
 opus_orchestrator/config.py              | 56 +++++++++++++++++++++++-
 opus_orchestrator/utils/github_ingest.py | 20 ++++++---
 2 files changed, 69 insertions(+), 7 deletions(-)

diff --git a/opus_orchestrator/config.py b/opus_orchestrator/config.py
index c4e971d..d41f7c9 100644
--- a/opus_orchestrator/config.py
+++ b/opus_orchestrator/config.py
@@ -43,6 +43,34 @@ class IterationConfig(BaseModel):
     auto_proceed_threshold: float = Field(default=0.9, description="Score to auto-approve")
 
 
+class CostConfig(BaseModel):
+    """Configuration for cost controls and rate limiting."""
+    
+    max_tokens_per_run: Optional[int] = Field(
+        default=None, 
+        description="Maximum tokens allowed per generation run"
+    )
+    max_cost_usd: Optional[float] = Field(
+        default=None,
+        description="Maximum cost allowed per generation run (USD)"
+    )
+    track_usage: bool = Field(
+        default=True,
+        description="Track cumulative token usage"
+    )
+    # Token prices (approximate, per 1M tokens)
+    price_per_million_tokens: dict[str, float] = Field(
+        default_factory=lambda: {
+            "gpt-4o": 15.00,
+            "gpt-4o-mini": 0.60,
+            "claude-3-opus": 15.00,
+            "claude-3-sonnet": 3.00,
+            "minimax": 1.00,  # Approximate
+        },
+        description="Price per million tokens by model"
+    )
+
+
 class OutputConfig(BaseModel):
     """Configuration for output generation."""
 
@@ -59,6 +87,7 @@ class OpusConfig(BaseModel):
     fortress: FortressConfig = Field(default_factory=FortressConfig)
     agent: AgentConfig = Field(default_factory=AgentConfig)
     iteration: IterationConfig = Field(default_factory=IterationConfig)
+    cost: CostConfig = Field(default_factory=CostConfig)
     output: OutputConfig = Field(default_factory=OutputConfig)
 
     github_token: Optional[str] = Field(default=None, description="GitHub token for private repos")
@@ -113,7 +142,7 @@ _config: Optional[OpusConfig] = None
 
 
 def get_config() -> OpusConfig:
-    """Get the global configuration instance."""
+    """Get the global configuration instance with validation."""
     global _config
     if _config is None:
         # Try to load from environment
@@ -121,9 +150,34 @@ def get_config() -> OpusConfig:
             _config = load_config_from_env()
         except Exception:
             _config = OpusConfig()
+    
+    # Validate API keys are present
+    _validate_config(_config)
+    
     return _config
 
 
+def _validate_config(config: OpusConfig) -> None:
+    """Validate configuration at startup.
+    
+    Raises:
+        ValueError: If required configuration is missing
+    """
+    errors = []
+    
+    # Check for API key
+    if not config.agent.api_key:
+        # Check environment
+        if not os.environ.get("OPENAI_API_KEY") and not os.environ.get("MINIMAX_API_KEY"):
+            errors.append(
+                "No LLM API key found. Set OPENAI_API_KEY or MINIMAX_API_KEY environment variable."
+            )
+    
+    if errors:
+        error_msg = "\n".join(errors)
+        raise ValueError(f"Configuration validation failed:\n{error_msg}")
+
+
 def set_config(config: OpusConfig) -> None:
     """Set the global configuration instance."""
     global _config
diff --git a/opus_orchestrator/utils/github_ingest.py b/opus_orchestrator/utils/github_ingest.py
index 6955cd5..a33c2b2 100644
--- a/opus_orchestrator/utils/github_ingest.py
+++ b/opus_orchestrator/utils/github_ingest.py
@@ -19,13 +19,21 @@ class GitHubIngestor:
     
     def __init__(self, token: Optional[str] = None):
         self.token = token or os.environ.get("GITHUB_TOKEN")
-        if not self.token:
-            raise ValueError("GitHub token required. Set GITHUB_TOKEN or pass token.")
         
-        self.headers = {
-            "Authorization": f"token {self.token}",
-            "Accept": "application/vnd.github.v3+json",
-        }
+        # Token is optional - only required for private repos
+        # Public repos can be accessed without authentication
+        if self.token:
+            self.headers = {
+                "Authorization": f"token {self.token}",
+                "Accept": "application/vnd.github.v3+json",
+            }
+        else:
+            # No token - use unauthenticated requests (rate limited)
+            self.headers = {
+                "Accept": "application/vnd.github.v3+json",
+            }
+            print("⚠️  No GitHub token provided. Using unauthenticated requests (rate limited).")
+        
         self.base_url = "https://api.github.com"
     
     def get_contents(self, repo: str, path: str = "") -> list[dict]: