agent/pi - pi - Penguin

Skills standard compliance

Implement Agent Skills standard (https://agentskills.io/specification):
- Validate name (must match parent dir, lowercase, max 64 chars)
- Validate description (required, max 1024 chars)
- Warn on unknown frontmatter fields
- Warn on name collisions (keep first)
- Change prompt format to XML structure
- Remove {baseDir} placeholder (use relative paths)
- Add tests and update documentation

fixes #231

Mario Zechner · 2025-12-19 00:11:39 +01:00

05b7b81338

Add intra-line diff highlighting for edit tool

- Extract diff rendering to dedicated diff.ts component
- Show word-level changes with inverse highlighting when a single line is modified
- Use diffWords for cleaner token grouping (includes adjacent whitespace)
- Only apply intra-line diff when exactly 1 removed and 1 added line (true modification)
- Multi-line changes show all removed then all added without incorrect pairing
- Add theme.inverse() method for inverse text styling

Mario Zechner · 2025-12-18 16:49:44 +01:00

5117187362

Syntax highlighting improvements

- Fix cli-highlight import (use static import instead of dynamic require)
- Add syntax highlighting to read/write tool output
- Update dark/light themes with VS Code default syntax colors
- Add highlightCode and getLanguageFromPath exports
- Upgrade @google/genai to 1.34.0 for IMAGE_RECITATION/IMAGE_OTHER FinishReason
- Add AGENTS.md rule: never downgrade code to fix type errors from outdated deps

Mario Zechner · 2025-12-18 16:01:01 +01:00

1a944f50f9

Add syntax highlighting to markdown code blocks

Sergii Kozak · 2025-12-17 20:15:44 -08:00

f8e6d62db7

Fix TUI performance regression: add caching to Box, use Text directly for built-in tools

Mario Zechner · 2025-12-17 16:39:23 +01:00

909989066a

Custom tools with session lifecycle, examples for hooks and tools

- Custom tools: TypeScript modules that extend pi with new tools
  - Custom TUI rendering via renderCall/renderResult
  - User interaction via pi.ui (select, confirm, input, notify)
  - Session lifecycle via onSession callback for state reconstruction
  - Examples: todo.ts, question.ts, hello.ts

- Hook examples: permission-gate, git-checkpoint, protected-paths

- Session lifecycle centralized in AgentSession
  - Works across all modes (interactive, print, RPC)
  - Unified session event for hooks (replaces session_start/session_switch)

- Box component added to pi-tui

- Examples bundled in npm and binary releases

Fixes #190

Mario Zechner · 2025-12-17 16:03:23 +01:00

e7097d911a

Fix image limits test to use realistic payload sizes

Previous test used compressed 8k images (0.01MB) which was meaningless.
Now tests with actual large noise images that don't compress.

Realistic payload limits discovered:
- Anthropic: 6 x 3MB = ~18MB total (not 32MB as documented)
- OpenAI: 2 x 15MB = ~30MB total
- Gemini: 10 x 20MB = ~200MB total (very permissive)
- Mistral: 4 x 10MB = ~40MB total
- xAI: 1 x 20MB (strict request size limit)
- Groq: 5 x 5760px images (5 image + pixel limit)
- zAI: 2 x 15MB = ~30MB (50MB request limit)
- OpenRouter: 2 x 5MB = ~10MB total

Also fixed GEMINI_API_KEY env var (was GOOGLE_API_KEY).

Related to #120

Mario Zechner · 2025-12-16 23:48:59 +01:00

e1ce9c1f49

Fix editor text clearing during compaction, fixes #179

Mario Zechner · 2025-12-16 15:15:37 +01:00

871188219b

Add tool result streaming

- Add AgentToolUpdateCallback type and optional onUpdate callback to AgentTool.execute()
- Add tool_execution_update event with toolCallId, toolName, args, partialResult
- Normalize tool_execution_end to always use AgentToolResult (no more string fallback)
- Bash tool streams truncated rolling buffer output during execution
- ToolExecutionComponent shows last N lines when collapsed (not first N)
- Interactive mode handles tool_execution_update events
- Update RPC docs and ai/agent READMEs

fixes #44

Mario Zechner · 2025-12-16 14:53:17 +01:00

7ac832586f

Fix RGB to 256-color mapping for non-truecolor terminals

Mario Zechner · 2025-12-15 22:32:23 +01:00

82dceb22e1

GitHub Copilot: auto-enable models, fix gpt-5 API, normalize tool call IDs

- Auto-enable all models after /login via POST /models/{model}/policy
- Use openai-responses API for gpt-5/o3/o4 models (not accessible via completions)
- Normalize tool call IDs when switching between github-copilot models with different APIs
  (fixes #198: openai-responses generates 450+ char IDs with special chars that break other models)
- Update README with streamlined GitHub Copilot docs

Mario Zechner · 2025-12-15 20:06:11 +01:00

c5543f7586

Merge branch 'main' into pr-191-github-copilot-auth

Mario Zechner · 2025-12-15 18:10:15 +01:00

ce4ba70d33

Fix model selector fuzzy search to match provider and support multi-token queries

Mario Zechner · 2025-12-15 18:05:32 +01:00

3de8e0757d

feat: initial impl

- add GitHub Copilot model discovery (env token fallback, headers,
compat) plus fallback list and quoted provider keys in generated map
- surface Copilot provider end-to-end (KnownProvider/default, env+OAuth
token refresh/save, enterprise base URL swap, available only when
creds/env exist)
- tweak interactive OAuth UI to render instruction text and prompt
placeholders

gpt-5.2-high took about 35 minutes. It had a lot of trouble with `npm
check`  and went off on a "let's adjust every tsconfig" side quest.
Device code flow works, but the ai/scripts/generate-models.ts impl is
wrong as models from months ago are missing and only those deprecated
are accessible in the /models picker.

cau1k · 2025-12-14 17:18:13 -05:00

ccae7a4e0e

Fix image rendering artifacts and improve show-images selector

- Image component returns correct number of lines (rows) for TUI accounting
- Empty lines rendered first, then cursor moves up and image is drawn
- This clears the space the image occupies before rendering
- Add spacer before inline images in tool output
- Create ShowImagesSelectorComponent with borders like other selectors
- Use showSelector pattern for /show-images command

Mario Zechner · 2025-12-13 23:53:28 +01:00

e4e234ecff

Update existing tool components when toggling show-images setting

Mario Zechner · 2025-12-13 23:15:56 +01:00

53794d78f2

Add /show-images command to toggle inline image display

- Add terminal.showImages setting to settings-manager.ts
- Add /show-images slash command (only visible if terminal supports images)
- ToolExecutionComponent checks both terminal support and user setting
- Shows text fallback when inline images are disabled

Mario Zechner · 2025-12-13 23:14:46 +01:00

f68a933d2c

add inline image rendering for terminals with graphics support

Nico Bailon · 2025-12-12 19:30:50 -08:00

9e9d5c94ed

Display loaded skills on startup in interactive mode

Mario Zechner · 2025-12-12 21:28:31 +01:00

03c404c15f

Auto-retry on transient provider errors (overloaded, rate limit, 5xx)

- Add retry logic with exponential backoff (2s, 4s, 8s) in AgentSession
- Disable Anthropic SDK built-in retries (maxRetries: 0) to allow app-level handling
- TUI shows retry status with Escape to cancel
- RPC mode: add set_auto_retry, abort_retry commands and auto_retry_start/end events
- Configurable via settings.json: retry.enabled, retry.maxRetries, retry.baseDelayMs
- Exclude context overflow errors from retry (handled by compaction)

fixes #157

Mario Zechner · 2025-12-10 23:36:46 +01:00

bb445d24f1

Fix git branch indicator in subdirectories

Walk up directory hierarchy to find .git/HEAD instead of only checking cwd.

fixes #156

Mario Zechner · 2025-12-10 22:52:19 +01:00

79f5c6d22e

Fix branch selector for single message and --no-session mode

- Allow branch selector to open with single user message (changed <= 1 to === 0 check)
- Support in-memory branching for --no-session mode (no files created)
- Add isEnabled() getter to SessionManager
- Update sessionFile getter to return null when sessions disabled
- Update SessionSwitchEvent types to allow null session files
- Add branching tests for single message and --no-session scenarios

fixes #163

Mario Zechner · 2025-12-10 22:41:32 +01:00

3d35e7c469

fixes #161 : disable theme watcher in print mode

The theme file watcher was keeping the Node.js process alive indefinitely
even in print mode where hot-reload is unnecessary. This fix adds an
enableWatcher parameter to initTheme() and setTheme() functions, and only
enables watchers in interactive mode.

- Modified initTheme() to accept enableWatcher parameter (default: false)
- Modified setTheme() to accept enableWatcher parameter (default: false)
- Updated main.ts to only enable watchers in interactive mode
- Updated InteractiveMode to enable watchers when changing themes

Mario Zechner · 2025-12-10 21:16:47 +01:00

9516424cae

Add hooks system with pi.send() for external message injection

- Hook discovery from ~/.pi/agent/hooks/, .pi/hooks/, --hook flag
- Events: session_start, session_switch, agent_start/end, turn_start/end, tool_call, tool_result, branch
- tool_call can block execution, tool_result can modify results
- pi.send(text, attachments?) to inject messages from external sources
- UI primitives: ctx.ui.select/confirm/input/notify
- Context: ctx.exec(), ctx.cwd, ctx.sessionFile, ctx.hasUI
- Docs shipped with npm package and binary builds
- System prompt references docs folder

Mario Zechner · 2025-12-10 00:50:30 +01:00

7c553acd1e

fix(coding-agent): skip hook init when no hooks configured

Mario Zechner · 2025-12-09 22:24:17 +01:00

86c2a33df4

feat(coding-agent): implement hooks system

- Add hooks infrastructure in core/hooks/ (loader, runner, types)
- HookUIContext interface with mode-specific implementations
- Interactive mode: TUI-based selector/input/confirm dialogs
- RPC mode: JSON protocol for hook UI requests/responses
- Print mode: no-op UI context (hooks run but can't prompt)
- AgentSession.branch() now async, returns { selectedText, skipped }
- Settings: hooks[] and hookTimeout configuration
- Export hook types from package for hook authors

Based on PR #147 proposal, adapted for new architecture.

Mario Zechner · 2025-12-09 22:17:12 +01:00

04d59f31ea

Simplify compaction: remove proactive abort, use Agent.continue() for retry

- Add agentLoopContinue() to pi-ai for resuming from existing context
- Add Agent.continue() method and transport.continue() interface
- Simplify AgentSession compaction to two cases: overflow (auto-retry) and threshold (no retry)
- Remove proactive mid-turn compaction abort
- Merge turn prefix summary into main summary
- Add isCompacting property to AgentSession and RPC state
- Block input during compaction in interactive mode
- Show compaction count on session resume
- Rename RPC.md to rpc.md for consistency

Related to #128

Mario Zechner · 2025-12-09 21:43:49 +01:00

5a9d844f9a

Fix bash execution component to limit by visual lines instead of logical lines

Mario Zechner · 2025-12-09 21:16:25 +01:00

d67c69c6e9

feat(coding-agent): implement new compaction system with overflow recovery

Phase 1: Updated compaction.ts
- findCutPoint now returns CutPointResult with isSplitTurn and turnStartIndex
- Can cut at user, assistant, or bashExecution messages (never tool results)
- Added turnPrefixSummary support for split turns (parallel summarization)
- estimateTokens helper for context size estimation

Phase 2: Updated session-manager.ts
- CompactionEntry now has optional turnPrefixSummary field
- loadSessionFromEntries injects both summaries when turn was split

Phase 3: Updated agent-session.ts
- Overflow detection via isContextOverflow after agent_end
- Proactive compaction check on turn_end before next LLM call
- _abortingForCompaction flag to skip saving aborted messages
- Auto-retry after overflow recovery or proactive compaction
- New event fields: reason (overflow/threshold), willRetry

Phase 4: Updated interactive-mode.ts
- Shows reason in compaction status (Context overflow detected...)
- Shows retry status after compaction

Tests updated for new CutPointResult return type.

Mario Zechner · 2025-12-09 17:18:53 +01:00

a38e619095

Fix hardcoded truncation limits in tool output display

- Add maxLines and maxBytes fields to TruncationResult to track actual limits used
- Update tool-execution.ts to use actual limits from truncation result
- Add fallbacks to DEFAULT_MAX_* for backward compatibility with old sessions
- Fix outdated comments that said 30KB when default is 50KB

Mario Zechner · 2025-12-09 17:06:29 +01:00

ee9acdb49d

Fix auto-compaction TUI integration and cut point logic

- Trigger auto-compaction after agent_end instead of during message_end
- Show CompactionComponent after auto-compaction (same as manual /compact)
- Fix cut point to include bash executions before kept user message
- Stop backward scan at compaction, assistant, user, or toolResult boundaries

Mario Zechner · 2025-12-09 02:45:24 +01:00

4227fd5996

Add auto-compaction events to AgentSession

- Add AgentSessionEvent type extending AgentEvent with auto_compaction_start/end
- Emit events when auto-compaction starts and completes
- TUI shows loader during auto-compaction with escape to cancel
- Rebuilds chat UI when auto-compaction succeeds

Mario Zechner · 2025-12-09 01:51:51 +01:00

91b89578c1

Show pending bash executions in pending area, move to chat on user submit

Mario Zechner · 2025-12-09 01:39:40 +01:00

803d4b65ee

Move config.ts from utils/ to src/

Mario Zechner · 2025-12-09 01:28:06 +01:00

14d99b5f86

Deduplicate interactive-mode: consolidate message rendering, add showStatus helper

Mario Zechner · 2025-12-09 01:12:19 +01:00

109a30b265

Refactor selectors: replace show/hide pairs with single showSelector helper