Conversation
…ctions)
MODULE_OVERVIEW_PROMPT and REPO_OVERVIEW_PROMPT (module-parent and repo-root
overview generation) have no {custom_instructions} slot, unlike
SYSTEM_PROMPT/LEAF_SYSTEM_PROMPT — so --instructions (language, audience,
forbidden diagram styles, link format) never reaches these two prompts.
Confirmed empirically on a real run (voll-intelligence): every affected
overview page came back in English with the tool's default developer-oriented
structure ("Purpose / Architecture / Core component documentation") and, in
one case, a broken local-filesystem link — regardless of a detailed
Portuguese business-audience --instructions file being passed on the CLI.
Appending the instructions as trailing text to the single user-role prompt
(the obvious first fix) measurably failed to change model output. The actual
fix: thread an optional system_prompt through call_llm/_call_llm_via_litellm/
_call_llm_via_azure/LLMBackend.complete/PydanticAIBackend.complete/
CawBackend.complete, and have generate_parent_module_docs pass
config.get_prompt_addition() as a system-role message — the same mechanism
SYSTEM_PROMPT/LEAF_SYSTEM_PROMPT already use successfully, just not
previously wired to the bare-completion overview path.
…gnature The previous commit added an optional system_prompt kwarg to LLMBackend.complete() (and a get_prompt_addition() call on the config passed into generate_parent_module_docs), but two test doubles didn't get updated to match: - FakeBackend.complete() in test_processing_order_update.py and test_updater_orchestrator.py didn't accept system_prompt, so generate_parent_module_docs's `backend.complete(prompt, system_prompt=...)` call raised TypeError. - The SimpleNamespace fake config in test_processing_order_update.py had no get_prompt_addition(), so the AttributeError below. CI: 3 failed (AttributeError: 'SimpleNamespace' object has no attribute 'get_prompt_addition'; TypeError: FakeBackend.complete() got an unexpected keyword argument 'system_prompt').
This was referenced Sep 29, 2026
Collaborator
|
fixed at #121 |
pull Bot
pushed a commit
to soitun/CodeWiki
that referenced
this pull request
Sep 29, 2026
…ons, ship updater - 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. (FSoft-AI4Code#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`. (FSoft-AI4Code#115, FSoft-AI4Code#118) - Fallback: FallbackModel now also falls back on UnexpectedModelBehavior (a 200 response whose body does not parse), keeping ModelAPIError. (FSoft-AI4Code#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. (FSoft-AI4Code#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 FSoft-AI4Code#115, FSoft-AI4Code#116, FSoft-AI4Code#117, FSoft-AI4Code#118, FSoft-AI4Code#119.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Problem
MODULE_OVERVIEW_PROMPTandREPO_OVERVIEW_PROMPT(module-parent and repo-root overview generation) have no{custom_instructions}slot, unlikeSYSTEM_PROMPT/LEAF_SYSTEM_PROMPT— so--instructions(language, audience, forbidden diagram styles, link format) never reaches these two prompts.Confirmed empirically on a real run (
voll-intelligence, business documentation in Portuguese for a PM/PO audience): every affected overview page came back in English with the tool's default developer-oriented structure ("Purpose / Architecture / Core component documentation") and, in one case, a broken local-filesystem link (file:///home/.../docs/...) — regardless of a detailed Portuguese business-audience--instructionsfile being passed on the CLI.What didn't work
Appending the instructions as trailing text to the single user-role prompt (the obvious first fix) measurably failed to change model output — still English, still the default structure.
Fix
Thread an optional
system_promptthroughcall_llm/_call_llm_via_litellm/_call_llm_via_azure/LLMBackend.complete/PydanticAIBackend.complete/CawBackend.complete, and havegenerate_parent_module_docspassconfig.get_prompt_addition()as a system-role message. This is the same mechanismSYSTEM_PROMPT/LEAF_SYSTEM_PROMPTalready use successfully (via the Agent'ssystem_prompt=) — it just wasn't wired to the bare-completion overview path.Validation
Isolated test call with the fix (same model, same instructions, synthetic minimal
repo_structure) produced fully Portuguese, correctly-structured, correctly-hedged output. Applied to the realvoll-intelligencerun: all previously-broken overview pages (including the repo root) came back in the correct language/structure after the fix.🤖 Generated with Claude Code