Retained complete native web-search call/result pairs through leaked-thinking projection at their original source anchors.
Kept opaque server-tool blocks atomic during persistence, stripped them on reparent, and covered custom continuations plus compaction retention.
Fixes#6703
- Detect bun crash exits (signals 132-139) and retry up to MAX_CHUNK_ATTEMPTS in a fresh heap.
- Add `retries` field to ChunkOutcome and surface crash retries in progress output.
- Fix test assertion expecting `stopReason: "aborted"` to use `toolUse` (aborted turns are dropped from context).
- Replaced leaf-to-root unshift path assembly with push plus one reverse in buildSessionContext and SessionEntryIndex.pathTo.
- Added regression coverage that keeps deep linear context and branch paths root-to-leaf without Array.unshift work.
Fixes#3961
fix(compaction): cap snapcompact frame payloads (#3866)
Bound rebuilt snapcompact image payloads by a per-request base64 byte
budget so long sessions stop re-sending multi-megabyte standing image
archives on every provider request; auto-compaction falls back to
context-full summaries when snapcompact output is too large.
Resolved snapcompact.ts conflict against the main font-rendering refactor
by keeping both renderabilityProbeText and the frame-budget helpers.
Fixed historyBlocks to emit the omitted-frame notice before the kept
(newer) images, since the byte budget drops the oldest frames — keeping
reconstructed blocks oldest-to-newest (addresses Codex P2 review).
Fixes#3792
When legacy snapcompact archives exceed the per-request byte budget, retain frames from the newest end of the archived middle and restore oldest-to-newest order for the kept subset.
Bounded persisted snapcompact image archives by base64 byte size so large sessions stop re-sending multi-megabyte frame walls on every provider request.
Auto snapcompact now falls back to context-full summaries when rendered frame payloads exceed the byte budget, and legacy oversized archives omit over-budget frames during LLM context rebuilds.
Fixes#3792
Commit 3bcbf1515 (fix#3258) moved the compaction summary to position 0
(top of transcript) as a side-effect of collapsing compacted history for
performance. This caused the divider to scroll into native scrollback where
Ctrl+O could no longer expand it — users got no visible feedback after /compact.
In collapsed transcript mode (display), emit kept messages first, then the
compaction summary, then post-compaction messages — restoring the chronological
position. Agent context (non-transcript) keeps summary-first ordering unchanged.
- Added session-domain modules and exports for session-entries, context, listing, loader, and migrations.
- Changed persistence to async append writes plus writeTextAtomic, removing sync line APIs.
- Added compaction-aware session context rebuild with dangling tool-call cleanup.
- Added resumable session resolution with status inference, id/stem/suffix matching, and backup recovery.
- Removed `<turn-aborted>` guidance injection from `transformMessages`, deleted `turn-aborted-guidance.md`, and dropped the synthetic abort note path for aborted/error turns.
- Updated `c`/`.` continue shortcuts to submit `manual-continue.md` as a hidden synthetic `developer` message via `session.prompt(..., { synthetic: true })` instead of sending an empty user turn.
- Updated tests and changelog notes in AI and coding-agent to reflect the revised abort-context and continue behavior.
- Previously only stripped dangling tool_use blocks from the trailing assistant turn; now scans all assistant turns on the resolved path.
- Builds a set of paired tool result IDs upfront to identify dangling calls anywhere in the message list.
- Adds a test covering a mid-path dangling turn alongside a correctly paired turn that must be preserved.
- Stripped `redactedThinking` blocks (encrypted, no downgradeable plaintext) from trailing assistant turns during context rebuild.
- Cleared `thinkingSignature` on `thinking` blocks so the encoder downgrades them to plain text, avoiding Anthropic's "modified latest assistant message" rejection.
- Extended existing test to cover signed/redacted thinking alongside dangling tool calls.
- Removed todo spinner interval state and rendering hooks from InteractiveMode, and in-progress or active-matched todos now use the static running glyph.
- Removed spinner-driven matcher caching and render updates from todo list generation so running state is based on direct content matching.
- Added build-session context tests that remove dangling assistant `toolCall` entries and drop trailing assistant turns that contain only tool calls.
buildSessionContext walked the entry path and unconditionally overwrote
models.default from every assistant message's reported model. Temporary
fallbacks (retry fallback, context promotion) and codex-side model
downgrades both produce assistant messages tagged with a different model
id, which clobbered the user's explicit /model pick on resume and made
the session silently revert to the older model.
Treat assistant-message inference as a legacy fallback that only fills
in models.default when no explicit `model_change` with role="default"
has been seen on the path.
Fixes#849
- Added serviceTier option to OpenAI providers for controlling processing priority and cost across agent, completions, responses, and codex APIs.
- Added providerPayload field to messages for transport-native history reconstruction in OpenAI Responses and Codex APIs.
- Added /fast slash command and serviceTier setting to coding-agent for toggling OpenAI priority mode with fast mode indicator.
- Added remote compaction support with encrypted reasoning preservation for OpenAI models in coding-agent.
- Removed usage caching layer across all providers and refactored UsageFetchContext to eliminate cache and now dependencies.
- Fixed OpenAI Codex streaming service_tier inclusion, provider retry logic with exponential backoff, and email-based credential deduplication.
- Removed Prettier configuration files (.prettierignore and .prettierrc) and migrated formatting to Biome.
- Updated Biome configuration from version 2.3.11 to 2.3.12 and changed arrowParentheses rule from 'always' to 'asNeeded'.
- Pinned @biomejs/biome dependency to exact version 2.3.12 in package.json and bun.lock.
- Applied consistent arrow function formatting across 489 files by removing unnecessary parentheses around single parameters.
- Removed blank lines after comment blocks and reorganized imports for consistency across the codebase.
- Added tsconfig.publish.json files to all packages with optimized publish-time configuration.
- Updated all package.json scripts with prepublishOnly hooks for correct type checking during publish.
- Added @oh-my-pi/omp-stats path mappings to root tsconfig.json for consistent imports.
- Added WASM generation script for photon module and integrated into install:dev script.
- converted relative imports to path aliases ($c/*, $ai/*, $tui/*, etc.) across all packages
- added per-package tsconfig.json with complete path mappings for runtime resolution
- set importModuleSpecifier to non-relative for IDE auto-import preferences
- updated dev script to run from monorepo root for consistent path resolution
- Settings now use modelRoles map (e.g., { default: 'anthropic/claude-sonnet-4-5', small: 'anthropic/claude-haiku-4-5' })
- Session persistence uses 'provider/modelId' string format with optional role field
- Model selector: Enter sets default, S sets small, Escape closes
- Added role markers in selector: checkmark for default, lightning bolt for small
- Task tool supports pi/<role> aliases (e.g., model: pi/small, haiku, flash, mini)
- Title generation uses configured small model with auto-discovery fallback
- Explore agent now uses pi/small as primary model preference
Major changes:
- Replace monolithic SessionEvent with reason discriminator with individual
event types: session_start, session_before_switch, session_switch,
session_before_new, session_new, session_before_branch, session_branch,
session_before_compact, session_compact, session_shutdown
- Each event has dedicated result type (SessionBeforeSwitchResult, etc.)
- HookHandler type now allows bare return statements (void in return type)
- HookAPI.on() has proper overloads for each event with correct typing
Additional fixes:
- AgentSession now always subscribes to agent in constructor (was only
subscribing when external subscribe() called, breaking internal handlers)
- Standardize on undefined over null throughout codebase
- HookUIContext methods return undefined instead of null
- SessionManager methods return undefined instead of null
- Simplify hook exports to 'export type * from types.js'
- Add detailed JSDoc for skipConversationRestore vs cancel
- Fix createBranchedSession to rebuild index in persist mode
- newSession() now returns the session file path
Updated all example hooks, tests, and emission sites to use new event types.
- addMessageToChat: exhaustive switch for all AgentMessage roles
- renderSessionContext: delegates to addMessageToChat, special handling for assistant tool calls and tool results
- export-html formatMessage: exhaustive switch for all AgentMessage roles
- Removed isHookMessage, isBashExecutionMessage type guards in favor of role checks
- Fixed imports and removed unused getLatestCompactionEntry
roboomp