- Added a Python `analyze.py` CLI with `tools`, `edits`, and `followups` session-stats subcommands.
- Added `sync.py` ingestion with `~/.omp/stats.db`, migration SQL, and incremental JSONL resume logic.
- Replaced `stats:run` in `package.json` with `stats:sync` and new `stats:edits`, `stats:tools`, and `stats:followups` scripts.
- Removed the Rust session-stats crate files (`Cargo.toml`, `main.rs`, `common.rs`, `cmd_*.rs`) and their old command logic.
- Removed `.gitignore` ignores for `scripts/session-stats/Cargo.lock` and `scripts/session-stats/edit-analysis.csv`.
- Updated eval tool guidance to show Python `asyncio.run(...)` usage.
MiniMax descriptors carried thinkingFormat: "zai", which made
openai-completions emit thinking: { type: "enabled" } in plan mode.
MiniMax's OpenAI-compatible endpoint rejects that field with
`400 invalid params, invalid chat setting (2013)`. Drop thinkingFormat
from both minimax-coding-plan descriptors and add
supportsReasoningEffort: false (MiniMax also ignores reasoning_effort).
Normalize bundled minimax-code/minimax-code-cn entries inside
applyGeneratedModelPolicy so a regenerated models.json cannot
reintroduce the bad flag.
Fixes#955
Some extensions/plugins still import the legacy @mariozechner/pi-* package names (pi-agent-core, pi-ai, pi-coding-agent, pi-tui) instead of @oh-my-pi/pi-*. Register a single Bun.plugin on first plugin/extension load that rewrites those specifiers to the current @oh-my-pi/pi-* equivalents, including the @mariozechner/pi-coding-agent/extensibility/{extensions,hooks} sub-exports. No filesystem mutation, no symlinks, no proxy files.
Fixes#973
Add an explicit openai-models-list discovery type for custom providers while keeping lm-studio as a compatible alias. Custom providers can now point baseUrl at an OpenAI-compatible /v1 endpoint, provide an api key, and auto-populate models via GET {baseUrl}/models.
Discovered models merge cleanly with user-defined models from models.yml/models.json, so YAML entries still win for display name and token limits. The provider picker now explains when discovery succeeds but returns zero models, and when the configured /models endpoint responds with 404.
Fixes#970
normalizeSystemPrompts assumed context.systemPrompt was always an array
and called .map directly, crashing on legacy single-string values.
Accept string, string[], null, and undefined; normalize a single string
into a one-element prompt block list.
Fixes#976
Interactive /mcp test only consulted getMCPConfigPath("user"|"project")
configs and missed servers defined in standalone .mcp.json. /mcp reauth
already resolved through #findConfiguredServer, which includes that
fallback path. Route /mcp test through the same resolver so both
commands enumerate the same set of servers.
Fixes#956
The custom status line rendered cache_read with the input icon and
cache_write with the output icon — backwards relative to Anthropic's
cache_creation_input_tokens (write) / cache_read_input_tokens (read)
semantics. Swap the icon pairings in status-line/segments.ts and the
labels in status-line-segment-editor.ts to match.
Fixes#953
Kimi Code OAuth stored the access-token expiry at the exact server
cutoff, and AuthStorage only refreshes when now >= expires. The Kimi
request path has no 401-driven refresh, so near-cutoff tokens were
being sent and rejected as the 24h window rolled over. Apply the same
5-minute expiry skew the other OAuth providers use so refresh fires
before the server boundary.
Fixes#957
RenderMermaid is disabled by default and emits terminal text rather
than SVG/PNG; complex sequence diagrams with alt/else blocks become
hard to read at default widths. Add docs/render-mermaid.md covering
enablement (renderMermaid.enabled), config knobs (useAscii, paddingX,
paddingY, boxBorderPadding), output expectations, and limitations.
Link the new guide from the coding-agent README.
Fixes#961
runSplitCommit reset the index and then re-staged each split via
git.stage.hunks, but stage.hunks builds its file map from the current
diff. After the reset, newly created files were untracked again and
absent from that map, throwing "No diff found for <path>" mid-split.
Preserve the original staged diff so new files remain locatable
through every split iteration.
Fixes#966
DeepSeek streams leak chat-template markers (e.g. <｜Assistant｜>)
into delta.content, but the marker-stripping logic in
openai-completions.ts was gated on model.provider === "nvidia" and
so bypassed the native deepseek provider. Multibyte markers split
across chunk boundaries also surfaced as garbled "<瘻" sequences.
Apply the marker stripping for deepseek as well, hold partial
markers across chunks, and clean up surrounding whitespace when a
standalone marker is removed.
Fixes#959
getSupportedEfforts() intersected explicit model.thinking metadata
with heuristic capability inference from known model IDs. For custom
OpenAI-compatible proxy models that intentionally override thinking
levels in models.yml, that intersection dropped xhigh, so request
construction stopped treating xhigh as supported and the outgoing
payload lost the high-effort marker. Trust the explicit metadata when
it is present and fall back to inference only otherwise.
Fixes#969
- Added an intent function to EvalTool that generated a label from provided input.
- Parsed input with parseEvalInput and joined each cell title or language fallback into a newline string.
- Returned "evaluating" when input was missing or could not be parsed.
- Added an instruction in the Python eval prompt explaining that notebook cells run in an IPython kernel with a live event loop.
- Documented that users should use top-level `await` directly and avoid `asyncio.run(...)` due to the running event loop.
- Kept the existing failure-handling guidance unchanged while clarifying async execution behavior for Python cells.
- Updated system prompts to require every active turn to end with a tool call and clarified that reminders should default to resuming work unless the task was complete or genuinely blocked.
- Reworked the yield-reminder text to disallow fake blocker reasons and to permit continued tool-calling instead of forced immediate yields.
- In `runSubprocess`, applied `toolChoice` only on the final yield retry by adding an `isFinalRetry` check before sending the reminder.
- BuildWorkspaceTree now attempts to list files via `git ls-files` and builds a child index for tree rendering, avoiding native recursion when git output is available.
- `buildDirectoryTree` gained an optional `childIndex` path map, `tryListGitFiles` now applies a 3s timeout and falls back to existing native scan on failure or timeout.
- Added a workspace-tree test that verifies git-backed listing skips gitignored entries while including tracked workspace files.
- Added a 5-second `Promise.race` deadline around `buildAgentsMdSearch` and `buildWorkspaceTree` in `createAgentSession` to prevent startup blocking on slow scans.
- Changed startup handling to forward `undefined` to `ToolSession` when scans time out so `buildSystemPromptInternal` can re-run them through its existing `withDeadline` path.
- Added a static-import rewriter that converts common import clauses into dynamic `await import(...)` expressions before VM wrapping.
- Provided `require` and `createRequire` globals in the JS VM context using a cwd-based resolver.
- Added executor tests confirming rewritten imports run correctly and that `require`/`createRequire` are exposed with expected behavior.
Subagents previously re-ran buildAgentsMdSearch and buildWorkspaceTree on
every spawn, repeating the slowest part of system-prompt construction for
each task tool invocation. On large/pathological repos those scans
exceeded the 5s preparation deadline and tripped the per-subagent
'system prompt preparation timed out' warning.
Forward the parent's already-resolved AgentsMdSearch and WorkspaceTree
through createAgentSession (alongside the existing contextFiles, skills,
and promptTemplates inheritance):
- Add agentsMdSearch and workspaceTree to CreateAgentSessionOptions;
createAgentSession short-circuits the parallel scan promises when
these are provided.
- Resolve them with contextFiles before constructing ToolSession; expose
on ToolSession so the task tool can read the parent's values.
- Thread them through ExecutorOptions (task/executor.ts) into the
subagent's createAgentSession call, and pass them from the task tool
(task/index.ts) on both the worktree-isolated and non-isolated paths.
- Added hideThinkingSummary options across stream, agent, and session payload paths.
- Routed Coding-Agent hideThinkingBlock toggles to agent hideThinkingSummary during session updates.
- Updated OpenAI, Azure OpenAI, and Codex requests to omit reasoning.summary when hide/ summary is null.
- Reworked system-prompt preparation with per-step timeouts, fallback defaults, and step-level warnings.
- Updated the read tool docs to define URL selectors as `:50`, `:50-100`, and `:50+150` and to document the `https://host/:port` form for URLs with explicit ports.
- Changed URL selector parsing to use the file-style numeric range format, treated `raw` as a separate token, and updated the invalid zero-line message to direct users to `:1`.
- Refined embedded URL selector extraction to validate the base URL first and then match selectors against the new numeric range regex.
- Added `supportsMultipleSystemMessages?: boolean` to `OpenAICompat` for configurable multi-system handling.
- Added OpenAI-compat host detection, allowing per-host multiple-system defaults and explicit override control.
- Updated `convertMessages` to merge system prompts when disabled, while preserving separate system messages when enabled.
- Added tests for merged-vs-split system prompts, MiniMax/Qwen strict-template behavior, and override defaults.
- Added a new `scrubProcessEnv` helper in `procmgr` to remove macOS malloc logging variables from `process.env` before spawning.
- Invoked the helper at coding-agent CLI startup so bun sub-processes no longer inherit the problematic environment.
- This prevented the recurring `MallocStackLogging` warning from appearing in child process stderr output.
- Added optional `/loop` `count|duration` command arguments and wired `command.args` into loop handling.
- Implemented `loop-limit` parsing and runtime types/helpers for iteration and duration budget limits with validation.
- Updated interactive mode to enforce loop limits per iteration, check duration expiry, and clear budget state on disable.
- Added loop-limit parse/runtime tests and fixed `/loop` arg errors plus macOS `MallocStackLogging` environment leakage.
- Rendered diff content before the truncation notice instead of after.
- Updated hidden lines label to show count with "+" prefix.
- Added fallback label when no lines are hidden.
- Removed the read CLI argument and tool schema field so read requests no longer accept custom timeouts.
- Updated URL read handling to stop forwarding timeout values and execute URL reads without a timeout parameter.
- Standardized URL read fetching to a fixed 30-second timeout and dropped timeout metadata from URL call rendering.
- Removed [blocked]-focused instructions from failure handling and pre-yield checks in the system prompt.
- Eliminated the separate completion-honesty block and folded stronger end-to-end-completion language into the contract sections.
- Reworded output and critical-response guidance to focus on continuous progress and completion-only yielding.
- Added a readonly intent property to the write tool implementation.
- The intent now returned a contextual message using `args.path` when available, otherwise a generic "writing" label.
- Exported hashline section interfaces and helpers, including a new section-diff API for external callers.
- Refactored `computeHashlineDiff` to split input sections, propagate split errors, and delegate each section via helper.
- Added context-highlight caching and batched highlighting for unchanged lines, with `replaceTabs` fallback on unknown files.
- Fixed hashline streaming preview so completed sections stay visible when a new `@PATH` header appears mid-stream.
- Added hashline streaming tests for section persistence, malformed trailing `+ 7`, and dual sections.
- Adjusted streaming preview formatting to render the tail section using a computed start index and hidden-line count.
- Passed language into streaming formatting to syntax-highlight visible lines and include aligned line-number gutters.
- Updated the hidden-lines notice to handle singular vs plural earlier-line counts correctly.
- Added a new `orchestrate.md` prompt under `src/prompts/commands` defining an orchestrator workflow, verification gates, and anti-patterns.
- Imported and rendered the prompt in `src/task/commands.ts` as `orchestrateMd`.
- Appended the new prompt to `EMBEDDED_COMMANDS` so it is registered with existing embedded command templates.
- Updated the hashline prompt to require replacement ranges to cover entire statements or expressions, preventing broken syntax when applying changes.
- This clarified how replacement anchors should be chosen for function calls, literals, blocks, and control-flow branches.
- Added a boundary normalizer that validated tool output shape and replaced malformed responses with a fallback text-only result.
- Updated tool execution to coerce both streaming partial updates and final tool results through that normalizer.
- Set the tool call error state when a malformed result was detected by the coercer.
- Updated the write tool preview renderer to syntax-highlight visible lines and annotate them with line-number gutters.
- Changed the file metadata output to an inline line-count suffix on the header and removed the separate metadata row.
- Adjusted preview truncation to show the first lines first while preserving hidden-line hints for collapsed output.
- Added a new completion-honesty section to the coding-agent system prompt with stricter delivery constraints.
- The prompt now requires all acceptance criteria to be met before completion, prohibits scope reduction without approval, and forbids delivering stubs, placeholders, or fake implementations as finished work.
- Verification language was tightened so completion claims must reflect actual verification and not be inflated by partial checks.
- Added `.ipynb` detection and editable-cell conversion utilities, including merge/serialize helpers in `edit/notebook`.
- Rerouted hashline, patch, and replace edit flows, plus read/write paths, through notebook-aware helpers before persistence.
- Removed the dedicated `notebook` tool, its schema flags, renderer, and built-in registration/settings checks.
- Updated notebook read behavior, docs, and tests so `.ipynb` reads return editable `# %%` cells and edits reserialize to JSON.
- Removed persona preambles ("You are an expert...") in favor of direct imperatives.
- Stripped redundant MUST/SHOULD modals where plain prose suffices.
- Condensed multi-sentence instructions into tighter single-line equivalents.
- Updated the `init` operation to require a `list: [{phase, items: string[]}]` payload and to replace any existing list.
- Updated the `append` operation description to state tasks are appended to a given `phase` and that the phase is lazily created.
- Added `readSseEvents` and `ServerSentEvent` exports in utils for reusable SSE stream parsing.
- Replaced Anthropic's local SSE parser with shared `readSseEvents(response.body, signal)` decoding.
- Updated abort handling in agent stream loop to race an `ABORTED` sentinel with `responseIterator.next()`.
- Expanded stream tests for `readSseEvents` parsing of CRLF, comments, split UTF-8 chunks, and trailing events.
can1357