Michael Freno
087c64ff18
- Cap commit diffs in review/commit prompts at 50KB to prevent context window overflow on follow-up sessions - Skip skills catalog (noSkills) in commit/review follow-up sessions for leaner context - Wire Pi's SettingsManager into runAgentSession so Pi's built-in retry (exponential backoff, provider retry) applies to ralpi sessions — removes ralpi's duplicate manual retry loop - Remove maxRetries/retryDelayMs from ralpi config; rely on Pi's retry.* settings (with manual override support) - Remove retries field from progress.json and incrementRetry() from ProgressTracker - Add model failover to follow-up sessions (commit/review cycle through the model pool on connection errors) - Namespace reflection files by PRD key under .ralpi/reflections/<prdKey>/ so task sets don't overwrite each other - Skip loop-startup prompts for config fields explicitly set in YAML - Remove (default) annotations from loop options prompts - Default commitTimeoutMs/reviewTimeoutMs to 0 (inherit Pi defaults)
3.2 KiB
AGENTS.md
What this is
A Pi coding agent extension that registers the /ralpi slash command. Not a standalone app — it runs inside Pi's extension host.
Type checking
npm run typecheck # tsc --noEmit
No build step needed — Pi loads extensions via jiti, which compiles TypeScript at runtime. index.ts is the entry point directly.
Entry point
index.ts at repo root (not src/). Exports a default function receiving ExtensionAPI.
External dependencies
The extension imports from Pi SDK packages (not in package.json — provided by the host):
@earendil-works/pi-coding-agent—ExtensionAPI,ExtensionContext,createAgentSession, etc.@earendil-works/pi-tui—Box,Textfor custom message renderer
The only real npm dependency is yaml (^2.4.0).
Source structure
index.ts— extension entry, command routing, UI registration, reload detectionsrc/— all logic modules:parser.ts— task file parsing (Fio, checkbox, YAML formats)dag.ts— Kahn's algorithm dependency resolution, batch planningexecutor.ts— task execution, retry, parallel/sequential modesprogress.ts—.ralpi/progress.jsonstate managementprompts.ts— prompt generation for spawned agent sessionsreflection.ts— reflection extraction from agent outpututils.ts— config loading, progress discovery,runAgentSession()types.ts— all interfaces andDEFAULT_CONFIGwidget-batcher.ts— debounced widget updates for parallel tasksconstants.ts— static constants
skills/ralpi-use.md— Pi skill definition for task executionprompts/task-manager.md— Pi prompt for task planning
Runtime state
All runtime state lives in .ralpi/ in the project directory (not this extension directory):
.ralpi/progress.json— execution progress, supports multiple PRDs.ralpi/reflections/— per-task reflection JSON files.ralpi/prompts/— generated prompts (timestamped, for debugging).ralpi/sessions/— full session transcripts
Task ID convention
Task IDs are zero-padded strings ("01", "02", etc.). The parser prepends 0 to parsed digits. Never use raw numeric IDs.
Command routing
/ralpi with no args → plan. First token looks like a path (@path, ./path, .md, etc.) → run. Otherwise dispatches to subcommand (run, plan, resume, reset).
Config
Read from .ralpi/config.yaml in project directory (and global ~/.pi/ralpi/config.yaml). Falls back to DEFAULT_CONFIG in src/types.ts when files are missing. Config is loaded at projectDir level, not extension level.
Key config fields in execution:
autoCommit/autoReview— toggle follow-up commit and review agent sessions (also selectable at loop startup viaselectLoopOptions)models— round-robin model list for parallel modeimplModel/commitModel/reviewModel—<provider>/<model>strings resolved viaresolveModelSpecinutils.tscommitTimeoutMs/reviewTimeoutMs— timeouts for follow-up sessionsloopTimeoutMs— max total loop duration in ms (0 = no limit; checked between batches inexecutePlanBatches)timeoutMs— per-task execution timeout