docs: Phase 11 (Settings v2) task plan + CP-L design exploration - #183
Merged
Conversation
Expand Phase 11 (Settings v2) into a full design-gated, human-in-the-loop task breakdown (T-11.1-T-11.10, CP-L-CP-P) modeled on the Phase 10 doc, and record the approved CP-L design exploration with the Claude Design captures. - docs/tasks/phase-11-settings-v2.md: decisions, codebase-verified hard data facts, checkpoint map, and T-11.1-T-11.10. Locked stance: cost is estimated, never stored (cost_usd stays NULL; USD derived from a versioned in-repo price table; unknown model -> "—", never $0). No schema/mcp/engine change this phase (re-freeze after Phase 10). Fixes scoped: D14 (label the threshold) and B1 (approval queue gates on the user's confidence threshold, not a hard-coded 0.7). - docs/design/explorations/settings-v2.md: CP-L exploration (every section + state) with all eight decisions resolved. Provider set = OpenAI / Anthropic / Ollama only (no Google/Gemini this phase). Palette is re-skinned to toolbox-v2 at build (mockup colors are disposable). - 16 Claude Design state captures for Provider & keys, Local model, Spend, Processing, and Pipeline health. Co-authored-by: Cursor <cursoragent@cursor.com>
✅ Deploy Preview for velvety-moxie-c6d22b canceled.
|
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Expands Phase 11 — Settings v2 into a full, design-gated, human-in-the-loop task breakdown (modeled on the Phase 10 doc) and records the CP-L–approved design exploration with the Claude Design captures. Docs + design assets only — no code changes.
docs/tasks/phase-11-settings-v2.md— intro, locked decisions, codebase-verified Hard data facts, checkpoint map (CP-L…CP-P), and tasks T-11.1–T-11.10 in the standard shape (Goal / Files / Task execution / Refining loop / HITL / Acceptance) + a dependency graph.docs/design/explorations/settings-v2.md— the CP-L exploration: every section (Provider & keys · Local model · Spend · Processing · Pipeline health) and every state, with all eight decisions resolved.settings-v2-*.png).Decisions locked
cost_usdstaysNULL; USD is derived from a versioned in-repo price table, version-stamped, and an unknown model renders—(never$0).mcp/enginechange this phase — re-freeze after Phase 10; thellm_runscolumns already exist, the price data is in-repo.llm.confidenceThreshold, not a hard-coded0.7).Test plan
phase-11-settings-v2.mdfor scope/decision accuracy (esp. the estimated-not-stored stance and the B1 root-cause).settings-v2.mdmatches the approved design and that the embedded captures render.Docs-only; no build/test impact.
Made with Cursor