- Enforced tool decision in plan mode--agent now requires calling either `ask` or `exit_plan_mode` when a turn ends without a required tool call.
- Fixed cancellation behavior of `ask` tool to abort the current turn instead of returning a normal cancelled selection, while timeout-driven auto-cancel still returns without aborting.
- Added plan-mode-tool-decision-reminder system prompt to guide agent when required tools are not called.
- Improved agent_end event handling to use fallback assistant message when #lastAssistantMessage is unavailable.
- Added checkpoint and rewind tools to create context checkpoints before exploratory work and rewind to replace exploration messages with concise reports.
- Added checkpoint.enabled setting to control availability of checkpoint and rewind tools in agent sessions.
- Added getCheckpointState() and setCheckpointState() methods to agent session API for checkpoint state management.
- Implemented checkpoint state tracking with message count, entry ID, and timestamp to enable context cost optimization during investigations.
- Removed normativeRewrite setting and buildNormativeUpdateInput() function from public API.
- Removed $normative property and TNormative generic parameter from ToolResultMessage and AgentToolResult interfaces.
- Deleted normative.ts patch normalization module and related helper functions for diff anchor processing.
- Removed rewriteAssistantToolCallArgs() and #rewriteToolCallArgs() methods that modified tool call arguments.
## New: schema compatibility validation API
Add `validateSchemaCompatibility(schema, provider)` in
`packages/ai/src/utils/schema/compatibility.ts` that performs a static
audit of a JSON Schema against three provider targets:
- `openai-strict`: checks forbidden keys, required/properties symmetry,
additionalProperties constraint, and that every node declares a type,
combinator, or $ref
- `google`: checks unsupported keyword set and array-valued type
- `cloud-code-assist-claude`: checks forbidden keywords, array type,
null type, nullable keyword, and combiner presence; also validates via
AJV 2020 draft
Add `validateStrictSchemaEnforcement(original, result)` to assert the
fail-open contract: when strict enforcement succeeds the output must pass
openai-strict validation; when it fails the output must be the original
schema object (same reference).
Export both functions and their types from `./utils/schema/index.ts`.
## New: shared constants in fields.ts
Extract `COMBINATOR_KEYS` (`anyOf`, `allOf`, `oneOf`) and add
`CCA_UNSUPPORTED_SCHEMA_FIELDS` as exported constants, eliminating the
local duplicate in `strict-mode.ts` and providing a canonical field set
for Cloud Code Assist (much narrower than the Google set — CCA supports
validation keywords like `additionalProperties`, `minLength`,
`pattern`, etc.).
## Fix: cycle detection in all recursive schema traversals
All recursive walkers now carry a `WeakSet<object>` guard. Previously any
schema with a reference cycle (or a schema object that appears at two
nodes in the tree) would cause an infinite loop or a stack overflow:
- `sanitizeSchemaForStrictMode` / `enforceStrictSchema`
- `normalizeSchemaForCloudCodeAssistClaude`
- `normalizeNullablePropertiesForCloudCodeAssist`
- `stripResidualCombiners`
- `sanitizeSchemaImpl` (Google sanitizer)
- `hasResidualCloudCodeAssistIncompatibilities`
`hasResidualCloudCodeAssistIncompatibilities` previously returned `true`
for already-visited nodes, producing false positives that forced the CCA
fallback schema on valid (but multiply-referenced) schemas. It now
correctly returns `false`.
## Fix: stripResidualCombiners iterates to fixpoint
The previous single-pass approach missed chained combiner reductions
where one collapsed variant exposed another reducible combiner. The
rewriter now loops until no further reduction occurs.
## Fix: mergeObjectCombinerVariants required-field computation
The merged object schema now takes the intersection of all variants'
`required` arrays, then unions in own-level required properties that
exist in the merged schema. Previously the `required` field was silently
dropped from the flattened schema, making all properties effectively
optional.
## Fix: sanitizeSchemaForGoogle improvements
- Type inference for const-collapsed enums: type is derived from all
variants (must unanimously agree), falling back to inference from enum
values; mixed null/non-null infers the non-null scalar type and sets
`nullable: true`
- Const→enum deduplication now uses deep structural equality instead of
`Object.is`
- Recursion spreads the full options object so new fields (`unsupportedFields`,
`seen`) are not silently dropped when descending into sub-schemas
- Array-valued `type` is filtered to strings before processing
- Removed incorrect stripping of `additionalProperties: false` (the
field is valid and should be preserved)
- Parameterized `unsupportedFields` in `SanitizeSchemaOptions` enables
code reuse between the Google and CCA sanitizers
## Fix: sanitizeSchemaForStrictMode / enforceStrictSchema
- `nullable: true` is now stripped during sanitization and expanded into
`anyOf: [schema, {type: "null"}]` in the enforcer output, matching
what OpenAI strict mode requires
- Type inference: `type: "array"` is inferred when `items` is present;
a scalar type is inferred from uniform `enum` values
- Const→enum merge uses deep equality to avoid duplicate entries when
both `const` and `enum` exist with the same value
- `additionalProperties` is now dropped unconditionally in sanitization
(previously only object-valued `additionalProperties` was recursed;
non-object values were passed through)
- `enforceStrictSchema` recurses into `$defs` and `definitions` blocks
- `enforceStrictSchema` handles tuple-style `items` arrays
- `enforceStrictSchema` skips double-wrapping: optional properties
already expressed as `anyOf: [..., {type: "null"}]` are not wrapped again
- `tryEnforceStrictSchema` now caches results in a `WeakMap` keyed on
the input schema object to avoid redundant work on repeated calls
## Fix: mergeCompatibleEnumSchemas deep equality
Uses `areJsonValuesEqual` instead of `Object.is` when deduplicating
enum members, so structurally equal objects are not duplicated.
## New: test coverage
- `packages/ai/test/schema-normalization.test.ts`: comprehensive unit
tests for strict mode, Google, and Cloud Code Assist normalization
- `packages/ai/test/schema-compatibility.test.ts`: unit tests for all
three provider targets in the new compatibility validator
- `packages/coding-agent/test/tools/provider-schema-compatibility.test.ts`:
integration test that instantiates every builtin and hidden tool, runs
their parameter schemas through all three provider pipelines, and
asserts zero compatibility violations
- Added public `waitForIdle()` and `getLastAssistantMessage()` APIs to AgentSession for deterministic session state access.
- Refactored deferred continuation scheduling from raw `setTimeout()` to centralized post-prompt task tracking system for concurrent recovery operations.
- Fixed race conditions between deferred TTSR/context-promotion continuations and `prompt()` completion via shared recovery orchestrator.
- Replaced `#waitForRetry()` with `#waitForPostPromptRecovery()` to unify retry and TTSR resume gate handling.
- Fixed TTSR violations during subagent execution aborting the entire subagent run; `#waitForPostPromptRecovery()` now awaits agent idle after TTSR/retry gates resolve, preventing `prompt()` from returning while fire-and-forget `agent.continue()` is still streaming.
- Added comprehensive test case verifying `prompt()` blocks until TTSR continuation with tool calls completes, preventing premature session disposal.
- Implemented TTSR resume gate to ensure `prompt()` blocks until TTSR interrupt continuations complete, preventing race conditions between TTSR injections and subsequent prompts.
- Replaced `#waitForRetry()` with `#waitForPostPromptRecovery()` to handle both retry and TTSR resume gates, ensuring prompt completion waits for all post-prompt recovery operations.
- Added comprehensive test coverage for TTSR resume gate behavior under interrupt and deferred injection modes.
- Consolidated @oh-my-pi/pi-utils subpath imports into single package root import across 100+ files.
- Moved tryParseJson utility from local web scrapers module to @oh-my-pi/pi-utils package for centralized JSON parsing.
- Renamed loadSkillsFromDir to scanSkillsFromDir and refactored skill discovery to use fs.promises.readdir instead of glob-based approach.
- Replaced custom parseJSON with tryParseJson across discovery modules for consistent error handling.
- Removed emitCustomToolSessionEvent method and cleanupSshResources function, consolidating shutdown logic into dispose method.
- Updated glob pattern construction to use GlobBuilder with literal_separator(true) for improved path handling.
- Added getTodoPhases() and setTodoPhases() methods to ToolSession API for in-memory todo phase management.
- Added getLatestTodoPhasesFromEntries() export to retrieve todo phases from session history entries.
- Changed todo state management from file-based (todos.json) to in-memory session cache with automatic persistence.
- Changed todo phases to sync from session branch history during branching and rewriting operations.
- Removed file-based todo loading logic and replaced with session-based todo phase retrieval throughout codebase.
- Renamed the `notes://` protocol to `local://` for better clarity.
- Updated all internal references, prompts, and tool documentation.
- Migrated plan storage paths to use the new `local://` scheme.
- Renamed XML tags from underscore to kebab-case format for consistency across prompts and system messages.
- Updated context tag from `swarm_context` to `context` in render logic and test assertions.
- Consolidated conditional logic in subagent user prompt by removing duplicate assignment blocks.
- Updated system prompt documentation to reflect kebab-case naming convention for XML tags.
- Replaced plan:// protocol with notes:// for session-scoped artifact storage and plan finalization.
- Added title parameter to exit_plan_mode tool to enable plan file renaming during approval workflow.
- Implemented NotesProtocolHandler for notes:// URL scheme with path traversal protection and session fallback.
- Added renameApprovedPlanFile function to handle plan artifact finalization with validation and error handling.
- Updated system prompt documentation to reference notes:// protocol and internal URL schemes for artifact access.
- Standardized XML tag naming from snake_case to kebab-case across 50+ prompt files for consistency.
- Replaced imperative language with RFC 2119 keywords (MUST/SHOULD/MAY/MUST NOT) throughout system and tool prompts for clarity.
- Removed artifactsDir parameter from Python executor and simplified environment variable handling to use PI_SESSION_FILE only.
- Renamed read_path.md to read-path.md and updated memory guidance with hierarchy rules and conflict resolution workflow.
- Added noEscape option to bash URL expansion and extracted cwd parameter from leading cd commands for improved path handling.
- Exported NO_PAGER_ENV constant from bash-interactive module for centralized environment variable management.
- Added stripInternalArgs() utility function to filter harness-internal keys from tool arguments.
- Hidden agent__intent parameter from UI and log displays across agent, session, MCP, and tool-execution components.
- Implemented HIDDEN_ARG_KEYS constant to centrally manage internal argument filtering.
- Updated formatArgsInline() to exclude internal keys when rendering tool arguments.
- Added async background job execution for bash and task tools with configurable concurrency limits and automatic result delivery.
- Added cancel_job tool and /jobs slash command to manage and inspect running background jobs with status display.
- Added jobs:// internal protocol handler for querying job status and retrieving job execution details.
- Added async.enabled and async.maxJobs settings to control background job execution behavior.
- Enhanced status line to display count of running background jobs with visual indicator.
- Implemented AsyncJobManager with exponential backoff retry delivery, job lifecycle tracking, and automatic eviction.
Fixes#56.
- Extracted credential storage to shared @oh-my-pi/pi-ai package with AuthCredentialStore and AuthStorage classes.
- Consolidated UI formatting logic from ToolUIKit class into standalone utility functions across render-utils and output-meta modules.
- Moved utility functions (parseCommandArgs, substituteArgs, expandPath, normalizeUnicode) to dedicated modules for improved code reuse.
- Extracted JTD type definitions and type guards to jtd-utils module for shared use across schema conversion tools.
- Updated Claude model pricing and added cache read costs in models.json for accurate billing calculations.
- Refactored agent-storage to delegate credential management to AuthCredentialStore instead of direct SQLite operations.
- Added streamed tool intent display in working message to show real-time intent tracking during agent execution.
- Changed intent tracing field name from `$intent` to `_intent` across tool schemas and agent core for consistency.
- Added support for file deletion and renaming operations in hashline edit mode.
- Renamed hashline edit operation fields: `set` to `target`/`new_content`, `set_range` to `first`/`last`/`new_content`, `insert` to `inserted_lines`.
- Added 'unable to connect' to transient error patterns in retry logic to properly handle connection failures.
- Updated retry error detection in coding-agent to match ai package pattern for consistency.
- Reorganized import statements in openai-compat.ts for consistency.
- Consolidated multi-line ternary expression into single line in openai-compat.ts.
- Simplified AgentBusyError instantiation to use default message.
- Updated test assertion to check error type instead of message content.
- Added AgentBusyError exception class for concurrent operation handling across agent packages.
- Added automatic retry logic with 30-second timeout for agent prompts when agent is busy.
- Changed concurrent operation errors from generic Error to AgentBusyError for better error handling.
- Fixed model discovery to use default refresh mode instead of explicit 'online' parameter.
- Added TTSR injection tracking with per-turn recording and deduplication to prevent repeated rule injections within the same turn.
- Changed TTSR message format to use custom message type with metadata fields for improved injection tracking and session persistence.
- Fixed TTSR repeat-after-gap mode to correctly restore injected rules from previous sessions and recalculate gap thresholds.
- Added test suite with 6 test cases covering TTSR repeat modes (once, after-gap, restored) and injection deduplication behavior.
- Added scoped TTSR rule matching with condition and scope fields supporting file globs and tool-specific filtering.
- Added ttsr.interruptMode setting to control when TTSR rules interrupt agent responses (never/prose-only/tool-only/always).
- Added support for loading rules, prompts, and commands from ~/.agent/ directory with fallback to ~/.agents/.
- Refactored rule discovery across all providers to use unified buildRuleFromMarkdown helper and per-stream-key buffering.
- Enhanced TTSR pattern matching to respect tool-specific scope filters and normalize file paths in glob matching.
- Changed context promotion to trigger on context overflow errors instead of a configurable threshold percentage.
- Removed the contextPromotion.thresholdPercent configuration setting.
- Updated context promotion to retry immediately on the promoted model without requiring compaction.
- Refactored context promotion logic to attempt promotion before compaction in the overflow handling flow.
- Updated agent session to merge context promotion checks into the compaction method for unified overflow handling.
- Updated tests to reflect overflow-based promotion triggering instead of threshold-based promotion.
- Added contextPromotionTarget model property to specify preferred fallback model when context promotion is triggered.
- Added automatic context promotion target assignment for Spark models to their base model equivalents.
- Updated Qwen model context window and max token limits for improved accuracy.
- Updated o1 model context window from 256000 to 262144 tokens and max tokens from 64000 to 65536 tokens.
- Implemented context promotion logic to use configured contextPromotionTarget when available instead of role-based model resolution.
- Added automatic context promotion feature that switches to larger-context models when approaching context limits.
- Added 'contextPromotion.enabled' setting to control automatic model promotion with default value of enabled.
- Added 'contextPromotion.thresholdPercent' setting to configure context usage threshold for triggering promotion with default value of 90%.
- Implemented context promotion logic in AgentSession that monitors token usage and automatically switches models when threshold is exceeded.
- Added provider session cleanup during model switches to properly handle session state transitions.
- Added comprehensive test coverage for context promotion functionality including threshold-based promotion and non-promotion scenarios.
Hashline prefixes (LINE:HASH|content) in read/grep output exist solely to
support the hashline edit mode. Agents that don't have the edit tool
(e.g. explore, plan, reviewer) gain nothing from them — they just waste
tokens and add noise.
resolveFileDisplayMode now takes a session-like object with an optional
hasEditTool flag. When false, hashlines are suppressed regardless of
settings. ToolSession gains hasEditTool (set from toolNames in the SDK),
and AgentSession exposes it as a getter over the tool registry.
Replace single `theme` setting with `theme.dark` and `theme.light`.
Auto-detection is always on — COLORFGBG determines which slot to use.
On SIGWINCH, re-check COLORFGBG and switch themes if background changed.
Old `theme` setting auto-migrated using luminance detection.
Fixes#65
can1357