agent run limits, fallback on malformed responses, overview instruction

.gitignore

@@ -47,6 +47,7 @@ tests/*
 !tests/test_branding.py
 !tests/test_artifact_analyzer.py
 !tests/test_scala_analyzer.py
+!tests/test_agent_limits.py
 
 # Jupyter
 *.ipynb

codewiki/cli/adapters/doc_generator.py

@@ -145,6 +145,8 @@ def generate(self) -> DocumentationJob:
                 max_token_per_leaf_module=self.config.get("max_token_per_leaf_module", 16000),
                 max_leaf_nodes_per_cluster=self.config.get("max_leaf_nodes_per_cluster", 600),
                 max_depth=self.config.get("max_depth", 2),
+                request_limit=self.config.get("request_limit", 100),
+                agent_retries=self.config.get("agent_retries", 3),
                 agent_instructions=self.config.get("agent_instructions"),
                 use_gitignore=self.config.get("use_gitignore", True),
                 prompt_caching=self.config.get("prompt_caching", True),

codewiki/cli/commands/config.py

@@ -51,6 +51,12 @@ def config_group():
 @click.option(
     "--max-depth", type=int, help="Maximum depth for hierarchical decomposition (default: 2)"
 )
+@click.option(
+    "--request-limit", type=int, help="Maximum model requests per agent run (default: 100)"
+)
+@click.option(
+    "--agent-retries", type=int, help="Retries for a failing agent tool call (default: 3)"
+)
 @click.option(
     "--provider",
     type=click.Choice(
@@ -97,6 +103,8 @@ def config_set(
     max_token_per_module: Optional[int],
     max_token_per_leaf_module: Optional[int],
     max_depth: Optional[int],
+    request_limit: Optional[int] = None,
+    agent_retries: Optional[int] = None,
     provider: Optional[str] = None,
     aws_region: Optional[str] = None,
     api_version: Optional[str] = None,
@@ -166,6 +174,8 @@ def config_set(
                 max_token_per_module,
                 max_token_per_leaf_module,
                 max_depth,
+                request_limit is not None,
+                agent_retries is not None,
                 provider,
                 aws_region,
                 api_version,
@@ -226,6 +236,16 @@ def config_set(
                 raise ConfigurationError("max_depth must be a positive integer")
             validated_data["max_depth"] = max_depth
 
+        if request_limit is not None:
+            if request_limit < 1:
+                raise ConfigurationError("request_limit must be a positive integer")
+            validated_data["request_limit"] = request_limit
+
+        if agent_retries is not None:
+            if agent_retries < 0:
+                raise ConfigurationError("agent_retries must be zero or a positive integer")
+            validated_data["agent_retries"] = agent_retries
+
         if provider is not None:
             validated_data["provider"] = provider
 
@@ -258,6 +278,8 @@ def config_set(
             max_token_per_module=validated_data.get("max_token_per_module"),
             max_token_per_leaf_module=validated_data.get("max_token_per_leaf_module"),
             max_depth=validated_data.get("max_depth"),
+            request_limit=validated_data.get("request_limit"),
+            agent_retries=validated_data.get("agent_retries"),
             provider=validated_data.get("provider"),
             aws_region=validated_data.get("aws_region"),
             api_version=validated_data.get("api_version"),
@@ -311,6 +333,12 @@ def config_set(
         if max_depth:
             click.secho(f"✓ Max depth: {max_depth}", fg="green")
 
+        if request_limit:
+            click.secho(f"✓ Request limit: {request_limit}", fg="green")
+
+        if agent_retries is not None:
+            click.secho(f"✓ Agent retries: {agent_retries}", fg="green")
+
         if provider:
             click.secho(f"✓ Provider: {provider}", fg="green")
 
@@ -384,6 +412,8 @@ def config_show(output_json: bool):
                 "max_token_per_module": config.max_token_per_module if config else 36369,
                 "max_token_per_leaf_module": config.max_token_per_leaf_module if config else 16000,
                 "max_depth": config.max_depth if config else 2,
+                "request_limit": config.request_limit if config else 100,
+                "agent_retries": config.agent_retries if config else 3,
                 "use_gitignore": config.use_gitignore if config else True,
                 "prompt_caching": config.prompt_caching if config else True,
                 "agent_instructions": config.agent_instructions.to_dict()
@@ -450,6 +480,8 @@ def config_show(output_json: bool):
             click.secho("Decomposition Settings", fg="cyan", bold=True)
             if config:
                 click.echo(f"  Max Depth:               {config.max_depth}")
+                click.echo(f"  Request Limit:           {config.request_limit}")
+                click.echo(f"  Agent Retries:           {config.agent_retries}")
                 click.echo(f"  Use Gitignore:           {config.use_gitignore}")
 
             click.echo()

codewiki/cli/commands/generate.py

@@ -296,6 +296,18 @@ def _find_affected(tree, parent_names=None):
     default=None,
     help="Maximum depth for hierarchical decomposition (overrides config)",
 )
+@click.option(
+    "--request-limit",
+    type=click.IntRange(min=1),
+    default=None,
+    help="Maximum model requests per agent run (overrides config)",
+)
+@click.option(
+    "--agent-retries",
+    type=click.IntRange(min=0),
+    default=None,
+    help="Retries for a failing agent tool call (overrides config)",
+)
 @click.option(
     "--prompt-caching/--no-prompt-caching",
     default=None,
@@ -398,6 +410,8 @@ def generate_command(
     max_token_per_module: int | None,
     max_token_per_leaf_module: int | None,
     max_depth: int | None,
+    request_limit: int | None,
+    agent_retries: int | None,
     prompt_caching: bool | None,
     artifacts: bool = True,
     artifact_token_budget: int = 200_000,
@@ -717,6 +731,13 @@ def generate_command(
                 else config.max_token_per_leaf_module,
                 # Max depth setting (runtime override takes precedence)
                 "max_depth": max_depth if max_depth is not None else config.max_depth,
+                # Agent run limits (runtime override takes precedence)
+                "request_limit": request_limit
+                if request_limit is not None
+                else config.request_limit,
+                "agent_retries": agent_retries
+                if agent_retries is not None
+                else config.agent_retries,
                 # Gitignore setting (runtime override takes precedence)
                 "use_gitignore": use_gitignore
                 if use_gitignore is not None

codewiki/cli/config_manager.py

@@ -136,6 +136,8 @@ def save(
         max_token_per_module: Optional[int] = None,
         max_token_per_leaf_module: Optional[int] = None,
         max_depth: Optional[int] = None,
+        request_limit: Optional[int] = None,
+        agent_retries: Optional[int] = None,
         provider: Optional[str] = None,
         aws_region: Optional[str] = None,
         api_version: Optional[str] = None,
@@ -157,6 +159,8 @@ def save(
             max_token_per_module: Maximum tokens per module for clustering
             max_token_per_leaf_module: Maximum tokens per leaf module
             max_depth: Maximum depth for hierarchical decomposition
+            request_limit: Maximum model requests per agent run
+            agent_retries: Retries for a failing tool call
             provider: LLM provider type (openai-compatible, anthropic, bedrock, azure-openai)
             aws_region: AWS region for Bedrock provider
             api_version: Azure OpenAI API version
@@ -205,6 +209,10 @@ def save(
             self._config.max_token_per_leaf_module = max_token_per_leaf_module
         if max_depth is not None:
             self._config.max_depth = max_depth
+        if request_limit is not None:
+            self._config.request_limit = request_limit
+        if agent_retries is not None:
+            self._config.agent_retries = agent_retries
         if provider is not None:
             self._config.provider = provider
         if aws_region is not None:

codewiki/cli/models/config.py

@@ -130,6 +130,8 @@ class Configuration:
         max_token_per_module: Maximum tokens per module for clustering (default: 36369)
         max_token_per_leaf_module: Maximum tokens per leaf module (default: 16000)
         max_depth: Maximum depth for hierarchical decomposition (default: 2)
+        request_limit: Maximum model requests per agent run (default: 100)
+        agent_retries: Retries for a failing tool call (default: 3)
         use_gitignore: Apply Git ignore rules during repository analysis
         prompt_caching: Add prompt-cache breakpoints to agentic LLM calls (default: True)
         agent_instructions: Custom agent instructions for documentation generation
@@ -148,6 +150,8 @@ class Configuration:
     max_token_per_module: int = 36369
     max_token_per_leaf_module: int = 16000
     max_depth: int = 2
+    request_limit: int = 100
+    agent_retries: int = 3
     use_gitignore: bool = True
     prompt_caching: bool = True
     agent_instructions: AgentInstructions = field(default_factory=AgentInstructions)
@@ -187,6 +191,8 @@ def to_dict(self) -> dict:
             "max_token_per_module": self.max_token_per_module,
             "max_token_per_leaf_module": self.max_token_per_leaf_module,
             "max_depth": self.max_depth,
+            "request_limit": self.request_limit,
+            "agent_retries": self.agent_retries,
             "use_gitignore": self.use_gitignore,
             "prompt_caching": self.prompt_caching,
             "fallback_model": self.fallback_model,
@@ -224,6 +230,8 @@ def from_dict(cls, data: dict) -> "Configuration":
             max_token_per_module=data.get("max_token_per_module", 36369),
             max_token_per_leaf_module=data.get("max_token_per_leaf_module", 16000),
             max_depth=data.get("max_depth", 2),
+            request_limit=data.get("request_limit", 100),
+            agent_retries=data.get("agent_retries", 3),
             use_gitignore=data.get("use_gitignore", True),
             prompt_caching=data.get("prompt_caching", True),
             agent_instructions=agent_instructions,
@@ -300,6 +308,8 @@ def to_backend_config(
             max_token_per_module=self.max_token_per_module,
             max_token_per_leaf_module=self.max_token_per_leaf_module,
             max_depth=self.max_depth,
+            request_limit=self.request_limit,
+            agent_retries=self.agent_retries,
             agent_instructions=final_instructions.to_dict() if final_instructions else None,
             use_gitignore=self.use_gitignore,
             prompt_caching=self.prompt_caching,

codewiki/src/be/agent_tools/generate_sub_module_documentations.py

@@ -1,13 +1,18 @@
 import os
 
 from pydantic_ai import RunContext, Tool, Agent
+from pydantic_ai.usage import UsageLimits
 
 from codewiki.src.be.agent_tools.deps import CodeWikiDeps
 from codewiki.src.be.module_naming import plan_sub_module_specs
 from codewiki.src.be.agent_tools.read_code_components import read_code_components_tool
 from codewiki.src.be.agent_tools.str_replace_editor import str_replace_editor_tool
 from codewiki.src.be.llm_services import create_fallback_models
-from codewiki.src.be.prompt_template import SYSTEM_PROMPT, LEAF_SYSTEM_PROMPT, format_user_prompt
+from codewiki.src.be.prompt_template import (
+    format_leaf_system_prompt,
+    format_system_prompt,
+    format_user_prompt,
+)
 from codewiki.src.be.utils import is_complex_module, count_tokens
 from codewiki.src.be.cluster_modules import format_potential_core_components
 
@@ -83,9 +88,8 @@ async def generate_sub_module_documentation(
                 model=fallback_models,
                 name=sub_module_name,
                 deps_type=CodeWikiDeps,
-                system_prompt=SYSTEM_PROMPT.format(
-                    module_name=sub_module_name, custom_instructions=ctx.deps.custom_instructions
-                ),
+                system_prompt=format_system_prompt(sub_module_name, ctx.deps.custom_instructions),
+                retries=ctx.deps.config.agent_retries,
                 tools=[
                     read_code_components_tool,
                     str_replace_editor_tool,
@@ -97,9 +101,10 @@ async def generate_sub_module_documentation(
                 model=fallback_models,
                 name=sub_module_name,
                 deps_type=CodeWikiDeps,
-                system_prompt=LEAF_SYSTEM_PROMPT.format(
-                    module_name=sub_module_name, custom_instructions=ctx.deps.custom_instructions
+                system_prompt=format_leaf_system_prompt(
+                    sub_module_name, ctx.deps.custom_instructions
                 ),
+                retries=ctx.deps.config.agent_retries,
                 tools=[read_code_components_tool, str_replace_editor_tool],
             )
 
@@ -117,6 +122,7 @@ async def generate_sub_module_documentation(
                 module_tree=ctx.deps.module_tree,
             ),
             deps=ctx.deps,
+            usage_limits=UsageLimits(request_limit=ctx.deps.config.request_limit),
         )
 
         # remove the sub-module name from the path to current module and the module tree

codewiki/src/be/backend.py

@@ -89,8 +89,9 @@ def complete(
         prompt: str,
         *,
         model: str | None = None,
+        system_prompt: str | None = None,
     ) -> str:
-        """Single-shot text completion."""
+        """Single-shot text completion, with an optional system message."""
 
     @abc.abstractmethod
     async def run_module_agent(

codewiki/src/be/caw_backend.py

@@ -246,6 +246,7 @@ def complete(
         prompt: str,
         *,
         model: str | None = None,
+        system_prompt: str | None = None,
     ) -> str:
         # Blocks the calling thread for the lifetime of the claude/codex
         # subprocess.  Callers running this from an async context (e.g. the
@@ -256,6 +257,7 @@ def complete(
             provider=self._caw_provider,
             model=effective_model,
             tools=ToolGroup.READER,
+            system_prompt=system_prompt,
         )
         traj = agent.completion(prompt)
         self.last_usage = usage_to_dict(getattr(traj, "total_usage", None))

codewiki/src/be/documentation_generator.py

@@ -24,6 +24,7 @@
     MODULE_OVERVIEW_PROMPT,
     REPO_OVERVIEW_ARTIFACT_ADDENDUM,
     REPO_OVERVIEW_PROMPT,
+    format_overview_system_prompt,
 )
 from codewiki.src.config import (
     FIRST_MODULE_TREE_FILENAME,
@@ -354,7 +355,10 @@ async def generate_parent_module_docs(
         logger.debug(f"Overview prompt for {module_name}: {len(prompt)} chars")
 
         try:
-            parent_docs = self.backend.complete(prompt)
+            parent_docs = self.backend.complete(
+                prompt,
+                system_prompt=format_overview_system_prompt(self.config.get_prompt_addition()),
+            )
             if not parent_docs:
                 raise RuntimeError(
                     f"LLM returned empty content for {module_name} overview "