agent run limits, fallback on malformed responses, overview instruction

[anhnh2002]

• Package: add codewiki.src.be.updater to [tool.setuptools] packages; a non-editable install had no updater, so every --update failed on import. New test checks every package directory is listed. (fix: include updater package in pyproject configuration #119)
• Agent limits: pass UsageLimits(request_limit=...) to every agent run and retries=... to every Agent. pydantic-ai defaults are 50 requests per run and 1 retry per failing tool call, which complex modules and generate_sub_module_documentation hit. New settings request_limit (default 100) and agent_retries (default 3), in codewiki config set, config show and as per-run overrides on codewiki generate. (fix: raise pydantic-ai request_limit for complex modules and make it configurable #115, feat: add max_retries config for PydanticAI agent retries #118)
• Fallback: FallbackModel now also falls back on UnexpectedModelBehavior (a 200 response whose body does not parse), keeping ModelAPIError. (fix: fallback model never triggers on a malformed provider response #117)
• Overview pages: MODULE_OVERVIEW_PROMPT / REPO_OVERVIEW_PROMPT had no slot for the user's instructions. complete() takes an optional system_prompt (OpenAI- compatible, litellm, Azure, and caw via CawAgent(system_prompt=...)), and parent/repo overviews send the instructions as a system message. (fix: overview generation never receives --instructions (custom_instructions) #116)
• Sub-module agents built their system prompt with a raw .format(), so with no instructions the prompt ended in the literal text "None"; they now use format_system_prompt / format_leaf_system_prompt like the top-level agents.

Reported in #115, #116, #117, #118, #119.