Build Toward the Whole: davellm - #5
Merged
Merged
Conversation
PROJECT_SPEC section 8 states that the browser may persist only the allowlisted suggestion preferences and that prompt and response content is forbidden from persistent browser storage. The renderer still wrote the full conversation map to localStorage under dave_convos, wrote 200 characters of each rated response under dave_feedback, and silently restored the browser copy when the router was unreachable. That created a second, diverging conversation store beside dave_conversations.json. The renderer now treats the router as the only conversation source, leaves the list empty and logs the failure when the router cannot be reached, stops mirroring feedback content, and purges the two legacy keys at startup. The renderer contract test now asserts the absence of the browser mirror. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01656XvdqNAVojSPQBtLZAAt
The three conversation templates carried preferred_model values that were absolute llama.cpp GGUF paths on one personal desktop plus a relative ./models path. None of them can ever appear in an Ollama node inventory, and because the template value was consulted before the project's own setting, a project's preferred_model was never reported for a templated chat. Templates no longer carry a model preference and the from_template response reports only the project's preferred_model. The unused DEFAULT_MODEL_ID constant is removed with them. MODEL_CATALOG still holds the same legacy paths for the advisory routing and cost endpoints; that is reported separately because retiring or rewiring it is a product decision. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01656XvdqNAVojSPQBtLZAAt
PROJECT_SPEC listed two different requirements under FR-25, exact-call approval and responsive access. The second row is now FR-26 so each functional requirement has one identifier. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01656XvdqNAVojSPQBtLZAAt
|
You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard. |
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.
Applies the Build Toward the Whole patch series.
Commits
Gate
python -m pytest -q — 71 passed— passing locally on this branch.Not for merge yet.