fix: raise pydantic-ai request_limit for complex modules and make it configurable

[fabceolin]

Problem

pydantic-ai's own default (UsageLimits(request_limit=50)) is too low for "complex" modules whose agent loop reads several code components and/or spins off sub-module docs via generate_sub_module_documentation_tool.

On a real-world run (voll-intelligence, a 5,381-file TypeScript monorepo, 16,720 functions), 4 modules hit UsageLimitExceeded mid-run and were skipped outright:

ERROR    Failed to process module app_integration_bff/app_integration_travel_search: The next request would exceed the request_limit of 50.

No retry, no fallback to the configured fallback-model, and no CLI flag to raise the limit.

Fix

1. Raise the default limit to 100 via UsageLimits(request_limit=100), passed explicitly to both agent.run(...) call sites in pydantic_ai_backend.py (run_update_agent and run_module_agent).
2. Make the limit a real, first-class configuration knob instead of a hardcoded constant — some repos/modules need more than 100 requests per agent run. request_limit now follows the exact same pattern as the other generation knobs (max_tokens, max_token_per_module, ...):
   • Config.request_limit in the backend (codewiki/src/config.py), default DEFAULT_REQUEST_LIMIT = 100
   • --request-limit on codewiki generate and codewiki config set
   • persisted in ~/.codewiki/config.json, shown in codewiki config show (text and --json)

Usage

# One-off override for this run
codewiki generate --request-limit 200

# Persist a higher default
codewiki config set --request-limit 200
codewiki config show

Validation

• All 4 modules that previously failed with request_limit=50 succeeded on the exact same input once the limit was raised to 100, with no other change.
• Config.from_cli(...) with and without a request_limit override; PydanticAIBackend._agent_usage_limits picks up the configured value.
• Configuration.to_dict/from_dict/to_backend_config round-trip for request_limit.
• codewiki config set --request-limit N + codewiki config show end-to-end (isolated HOME).
• codewiki generate --help shows the new flag; invalid (< 1) values are rejected the same way as the sibling max_* options.

🤖 Generated with Claude Code