Phase D: TUI + AI Assistant - #39
Merged
Merged
Conversation
…l/go/node detectors
…e B) - internal/runner/: pipeline resolution, Kahn's scheduler, parallel batch executor (B5-B8) - internal/cache/: content-addressable SHA256 hasher, local store, manifest with replay (B1-B3) - internal/graph/affected.go: git diff -> affected project set + transitive expansion (B4) - cmd/workspace/run: topological task execution with cache (B10) - cmd/workspace/affected: list affected projects (B11) - cmd/workspace/cache: status/clear commands (B12) - Full integration test: cache miss -> hit workflow (B15) - 272 tests passing (was 247), 23 files, +3325 lines
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Phase D: Workspace TUI + AI Assistant
Adds a terminal UI (bubbletea) with dashboard and AI chat views, plus an offline command interpreter for chat input.
New packages
apps/cli/internal/ai/— Provider abstraction, OpenAI streaming, Tool Registry, Chat loop, Cost tracking, Config, System promptapps/cli/internal/tui/— bubbletea Model, Dashboard, Chat view, :command parser, Help overlay, Entry pointNew commands
radas(no args + TTY) → TUI dashboardradas workspace generate <template>(Phase C carryover)radas workspace template list|add|createFeatures
ai:in radas.yml)ai.cost_ceiling, default $0.10)run api test→:run api test) when no AI provider configuredTest count
Phase history
Notes
go vetclean,go build ./...cleanAdd()is wired but only updates from manual cost entries (not auto-computed from API usage) — known limitationapi_key: $resolution returns explicit error on missing env var