Breaking changes:
- Agent class moved to @mariozechner/pi-agent-core
- Transport abstraction removed (ProviderTransport, AppTransport)
- AppMessage renamed to AgentMessage
- UserMessageWithAttachments now has role: 'user-with-attachments'
- CustomMessages interface replaced with CustomAgentMessages
- agent.appendMessage() removed (use queueMessage())
- New agent event types from pi-agent-core
Added:
- defaultConvertToLlm, convertAttachments utilities
- isUserMessageWithAttachments, isArtifactMessage type guards
- createStreamFn for CORS proxy support
- Default streamFn and getApiKey on AgentInterface
- Proxy utilities exported
README completely rewritten to reflect new architecture.
- Export wrapTextWithAnsi from tui package
- Add 'Handling Input' section to README with key detection example
- Document wrapTextWithAnsi in utilities section
- Add selectedBg theme color for active line highlight
- Fix filter modes:
- no-tools: default minus tool results (still hides label/custom)
- user-only: just user messages
- labeled-only: just labeled entries
- all: everything
- Update theme.md with new color tokens (50 total)
- Add GoogleThinkingLevel type mirroring Google's ThinkingLevel enum
- Update GoogleGeminiCliOptions and GoogleOptions to use our type
- Cast to any when assigning to Google SDK's ThinkingConfig
- New utils.ts with shared functions:
- FileOperations type and createFileOps()
- extractFileOpsFromMessage()
- computeFileLists()
- formatFileOperations()
- serializeConversation()
- SUMMARIZATION_SYSTEM_PROMPT
- branch-summarization.ts now uses:
- Serialization approach (conversation as text, not LLM messages)
- completeSimple with system prompt
- Shared utility functions
- serializeConversation now takes Message[] (after convertToLlm)
- Handles all custom message types via convertToLlm
- Includes thinking blocks as [Assistant thinking]
- Removes truncation of tool args and results (already token-budgeted)
Instead of passing conversation as LLM messages (which makes the model
try to continue it), serialize to text wrapped in <conversation> tags.
- serializeConversation() formats messages as [User]/[Assistant]/[Tool result]
- Tool calls shown as function(args) format
- Tool results truncated to prevent bloat
- Conversation wrapped in <conversation> tags in the prompt
- SUMMARIZATION_SYSTEM_PROMPT explains the task clearly
- Tells model to NOT continue conversation, ONLY output summary
- Updated prompts to reference 'messages above' for clarity
- Pass systemPrompt to completeSimple
- CompactionDetails type with readFiles/modifiedFiles
- extractFileOperations collects from tool calls and previous compaction details
- UPDATE_SUMMARIZATION_PROMPT for merging with previous summary
- generateSummary now accepts previousSummary for iterative updates
- compact() extracts files, passes previousSummary, returns details
- Only merges from !fromHook compaction entries (backward compatible)
Both auto_compaction_end and executeCompaction were manually adding
CompactionSummaryMessageComponent instead of using addMessageToChat,
which caused missing spacers. Now both use addMessageToChat for
consistent spacing and expansion state handling.
Prepends: 'The user explored a different conversation branch before
returning here. Summary of that exploration:'
This helps the LLM understand the summary is background context from
a different path, not the current thread being continued.
The old messagesToText only extracted text content, losing all tool calls.
Now uses convertToLlm like compaction does, preserving the full conversation
including tool calls, which is essential for generating useful summaries.
getHookPaths(), getCustomToolPaths(), and getSkillsSettings() now return
copies of arrays instead of references to internal state. This prevents
callers from accidentally mutating settings without going through setters.
Fixes#361
Both now use consistent sections:
- Goal
- Constraints & Preferences
- Progress (Done/In Progress/Blocked)
- Key Decisions
- Next Steps
- Critical Context (compaction only)
Prompts instruct LLM to use EXACT format and preserve file paths/function names.
- BranchPreparation now uses AgentMessage[] instead of custom type
- Reuse getMessageFromEntry pattern from compaction.ts
- Add BranchSummarySettings with reserveFraction to settings.json
- Add getBranchSummarySettings() to SettingsManager
- Use settings for reserveFraction instead of hardcoded value
