agent/pi
1
0
Fork 0
mirror of https://github.com/earendil-works/pi.git synced 2026-06-18 15:54:04 +08:00
Code Issues Packages Projects Releases Wiki Activity
799 Commits 32 Branches 288 Tags
652ac0fa366d93ee15c201f86a2d71eaf831981e
Commit Graph

25 Commits

  • 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
  • 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
  • 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
  • Update RPC example to use RpcClient
    Mario Zechner · 2025-12-09 14:44:13 +01:00
    70b84532bb
  • Fix agent event ordering: update state before emitting events 
    Previously, Agent.emit() was called before state was updated (e.g., appendMessage).
This meant event handlers saw stale state - when message_end fired,
agent.state.messages didn't include the message yet.

Now state is updated first, then events are emitted, so handlers see
consistent state that matches the event.
    Mario Zechner · 2025-12-09 14:33:39 +01:00
    2b0aa5ed8e
  • Rewrite RPC mode with typed protocol and client 
    - Move RPC files to modes/rpc/ directory
- Add properly typed RpcCommand and RpcResponse types
- Expose full AgentSession API via RPC commands:
  - State: get_state
  - Model: set_model, cycle_model, get_available_models
  - Thinking: set_thinking_level, cycle_thinking_level
  - Queue: set_queue_mode
  - Compaction: compact, set_auto_compaction
  - Bash: bash, abort_bash
  - Session: get_session_stats, export_html, switch_session, branch, etc.
- Add RpcClient class for programmatic access
- Rewrite tests to use RpcClient instead of raw process spawning
- All commands support optional correlation ID for request/response matching
    Mario Zechner · 2025-12-09 14:13:28 +01:00
    3559a43ba0
  • Add test fixture for auto-compaction testing 
    Session at ~98% context usage, triggers auto-compaction with single prompt
    Mario Zechner · 2025-12-09 02:49:47 +01:00
    66ba63050d
  • Reorganize file structure: core/, utils/, modes/interactive/components/, modes/interactive/theme/
    Mario Zechner · 2025-12-09 00:51:33 +01:00
    83a6c26969
  • Add bash mode for executing shell commands 
    - Add ! prefix in TUI editor to execute shell commands directly
- Output streams in real-time and is added to LLM context
- Supports multiline commands, cancellation (Escape), truncation
- Preview mode shows last 20 lines, Ctrl+O expands full output
- Commands persist in session history as bashExecution messages
- Add bash command to RPC mode via {type:'bash',command:'...'}
- Add RPC tests for bash command execution and context inclusion
- Update docs: rpc.md, session.md, README.md, CHANGELOG.md

Closes #112

Co-authored-by: Markus Ylisiurunen <markus.ylisiurunen@gmail.com>
    Mario Zechner · 2025-12-08 22:40:32 +01:00
    bd0d0676d4
  • Fix truncation test assertions to match new message format (#136)
    Nico Bailon · 2025-12-07 12:07:15 +01:00
    2e3ff4a15a
  • Add totalTokens field to Usage type 
    - Added totalTokens field to Usage interface in pi-ai
- Anthropic: computed as input + output + cacheRead + cacheWrite
- OpenAI/Google: uses native total_tokens/totalTokenCount
- Fixed openai-completions to compute totalTokens when reasoning tokens present
- Updated calculateContextTokens() to use totalTokens field
- Added comprehensive test covering 13 providers

fixes #130
    Mario Zechner · 2025-12-06 22:46:02 +01:00
    86e5a70ec4
  • fix: TUI crash with Unicode characters in branch selector 
    - Use truncateToWidth instead of substring in user-message-selector.ts
- Fix truncateToWidth to use Intl.Segmenter for proper grapheme handling
- Add tests for Unicode truncation behavior
    Mario Zechner · 2025-12-05 11:59:39 +01:00
    240064eec3
  • fix(coding-agent): update compaction test to match actual summary prefix
    Mario Zechner · 2025-12-04 12:29:14 +01:00
    547dcf0e4a
  • feat(coding-agent): add auto-compaction to RPC mode, add RPC compaction test 
    - RPC mode now auto-compacts when context exceeds threshold (same as TUI)
- Add RPC test for manual compaction via compact command
- Auto-compaction emits compaction event with auto: true flag
    Mario Zechner · 2025-12-04 02:49:22 +01:00
    c3f63dd243
  • WIP: Context compaction core logic (#92) 
    - Add CompactionEntry type with firstKeptEntryIndex
- Add loadSessionFromEntries() for compaction-aware loading
- Add compact() function that returns CompactionEntry
- Add token calculation and cut point detection
- Add tests with real session fixture and LLM integration

Still TODO: settings, /compact and /autocompact commands, auto-trigger in TUI, /branch rework
    Mario Zechner · 2025-12-04 00:07:53 +01:00
    6c2360af28
  • fix(coding-agent): use describe.skipIf for RPC test with explicit model 
    - Use describe.skipIf pattern matching other tests
- Skip when ANTHROPIC_API_KEY and ANTHROPIC_OAUTH_TOKEN are missing
- Use explicit --provider anthropic --model claude-sonnet-4-5
    Mario Zechner · 2025-12-02 14:50:29 +01:00
    bc4aa4aaa1
  • Add CI workflow and fix workspace tests
    Peter Steinberger · 2025-12-02 12:53:53 +00:00
    c43f1d307c
  • fix: RPC mode session management not saving sessions 
    Since version 0.9.0, RPC mode (--mode rpc) was not saving messages to
session files. The agent.subscribe() call with session management logic
was only present in the TUI renderer after it was refactored.

RPC mode now properly saves sessions just like interactive mode.

Added test for RPC mode session management to prevent regression.

Fixes #83

Thanks @kiliman for reporting this issue!
    Mario Zechner · 2025-12-01 01:19:17 +01:00
    d2b60f11eb
  • feat(coding-agent): add read-only exploration tools (grep, find, ls) and --tools flag 
    Add grep, find, and ls tools for safe code exploration without modification risk.
These tools are available via the new --tools CLI flag.

- grep: Uses ripgrep (auto-downloaded) for fast regex searching. Respects .gitignore,
  supports glob filtering, context lines, and hidden files.
- find: Uses fd (auto-downloaded) for fast file finding. Respects .gitignore, supports
  glob patterns, and hidden files.
- ls: Lists directory contents with proper sorting and directory indicators.
- --tools flag: Specify available tools (e.g., --tools read,grep,find,ls for read-only mode)
- Dynamic system prompt adapts to selected tools with relevant guidelines

Closes #74
    Mario Zechner · 2025-11-29 00:59:23 +01:00
    186169a820
  • Release v0.8.0
    Mario Zechner · 2025-11-21 03:12:42 +01:00
    85adcf22bf
  • Add session export to HTML, improve tool error handling, and enhance RPC mode documentation
    Mario Zechner · 2025-11-12 21:55:10 +01:00
    9e3e319f1a
  • Improve edit tool diff display with context-aware rendering 
    - Add generateDiffString() function in edit tool to create unified diffs with line numbers and 4 lines of context
- Store only the formatted diff string in tool result details instead of full file contents
- Update tool-execution renderer to parse and colorize the diff string
- Filter out message_update events from session saving to prevent verbose session files
- Add markdown nested list and table rendering tests
    Mario Zechner · 2025-11-12 20:09:11 +01:00
    c75f53f6f2
  • Add proper truncation notices and comprehensive tests for read tool 
    **Improved output messages:**
1. File fits within limits: Just outputs content (no notices)
2. Lines get truncated: Shows "Some lines were truncated to 2000 characters for display"
3. File doesn't fit limit: Shows "N more lines not shown. Use offset=X to continue reading"
4. Offset beyond file: Shows "Error: Offset X is beyond end of file (N lines total)"
5. Both truncations: Combines both notices with ". " separator

**Comprehensive test coverage:**
- Files within limits (no notices)
- Large files (line truncation)
- Long lines (character truncation)
- Offset parameter
- Limit parameter
- Offset + limit together
- Invalid offset (out of bounds)
- Combined truncations (both notices)

All 17 tests passing ✓
    Mario Zechner · 2025-11-12 17:13:03 +01:00
    2f0f0a913e
  • Add image support in tool results across all providers 
    Tool results now use content blocks and can include both text and images.
All providers (Anthropic, Google, OpenAI Completions, OpenAI Responses)
correctly pass images from tool results to LLMs.

- Update ToolResultMessage type to use content blocks
- Add placeholder text for image-only tool results in Google/Anthropic
- OpenAI providers send tool result + follow-up user message with images
- Fix Anthropic JSON parsing for empty tool arguments
- Add comprehensive tests for image-only and text+image tool results
- Update README with tool result content blocks API
    Mario Zechner · 2025-11-12 10:45:56 +01:00
    84dcab219b
  • Agent package + coding agent WIP, refactored web-ui prompts
    Mario Zechner · 2025-10-17 11:47:01 +02:00
    ffc9be8867