@oh-my-pi/pi-coding-agent 17.1.0 → 17.1.2

package/CHANGELOG.md

@@ -2,6 +2,61 @@
 
 ## [Unreleased]
 
+## [17.1.2] - 2026-07-24
+
+### Added
+
+- Added in-process moreutils-style shell builtins to the bash tool's embedded shell: `ts` (timestamp lines; `-i`/`-s` elapsed modes, `-m` monotonic clock, `-r` relative rewriting of RFC3339/syslog timestamps, `%.S`/`%.s`/`%.T` subsecond extensions), `sponge` (soak stdin fully before atomically writing the target, so `foo file | ... | sponge file` works; `-a` appends), `ifne` (run a command only when stdin is non-empty; `-n` inverts and passes non-empty stdin through), `isutf8` (streaming UTF-8 validation with line/char/byte diagnostics; `-q`, `-l`, `-i`), `combine` (boolean `and`/`not`/`or`/`xor` on the lines of two files, `-` for stdin), and `errno` (errno name/number/description lookup with `-l` list and `-s` search; unix only). Like the uutils-backed builtins, they run in-process against the command's own stdio, resolve paths against the shell working directory, honor cancellation, and are disabled by `PI_DISABLE_UUTILS_BUILTINS`.
+- The bash tool prompt now lists the available shell builtins (`mkdir` through `jq`, `rm`/`mv`/`ln`, and the moreutils set) so the model relies on them without existence checks; the line is dropped when `PI_DISABLE_UUTILS_BUILTINS` disables the builtins and omits unix-only `errno` on Windows.
+- Sessions using a broker-backed auth store now report each completed request's token usage and cost to the auth broker (batched, 10s cadence) so the broker can track actual token burn per client install
+- Added a per-spawn `effort` parameter to the `task` tool (`"lo"` | `"med"` | `"hi"`): each selector maps onto the resolved model's supported thinking range (lowest, middle, and highest level — whatever the model tops out at, e.g. `high`, `xhigh`, or `max`) and overrides the agent's default selector, including `auto`. Omitting `effort` keeps the existing automatic per-prompt thinking classification.
+- Added `searxng.engines` setting for the SearXNG web search provider: a comma-separated list of engine names or bang shortcuts (e.g. `ddg, br, startpage`) sent as the API's `engines=` parameter. Shortcuts are resolved to canonical engine names via the instance's `/config` endpoint (cached per endpoint; entries pass through verbatim if `/config` is unreachable). Bang syntax in queries (`!ddg foo`) continues to pass through to the instance, and external bangs (`!!g`) are now stripped client-side since SearXNG answers them with an HTTP redirect even for JSON requests.
+- Web search queries now understand Google-style directives on every provider: `site:`/`-site:` (plus `domain:`/`host:` aliases), `after:`/`before:`/`since:`/`until:` date bounds, `inurl:`/`intitle:`/`intext:`/`allin*:`, `filetype:`/`ext:`, `lang:`, quoted phrases (including smart quotes), `+term`, `-`/`NOT` exclusions, and `OR`/`|` groups. A shared parser (`web/search/query.ts`) structures the query once per request; each provider maps constraints onto native API filters where the upstream supports them (Perplexity domain/date/language filters on both the API-key and ask paths, Tavily `include_domains`/`exclude_domains` + `start_date`/`end_date`, Exa domain lists + published-date bounds on API and MCP paths, Anthropic `allowed_domains`/`blocked_domains`, xAI `filters.allowed_domains`/`excluded_domains`, Parallel `source_policy`, Brave absolute `freshness` ranges, Firecrawl `tbs=cdr` date ranges, Jina `X-Site`, SearXNG `language`) and otherwise re-emits only the operator syntax its engine parses (full Google syntax for Gemini grounding, OpenAI, Kagi, and the credential-free scrapers — with scraper-hostile path-`site:`/`inurl:` operators demoted to plain keywords; conservative subsets for DuckDuckGo, Mojeek, Kimi, Z.AI, TinyFish, and Synthetic). The pipeline then applies a lenient post-filter to every response: constraints the engine ignored are enforced on the returned sources, and any constraint dimension that would eliminate every result is relaxed and reported to the model (`Note: no results matched \`site:...\`; the constraint was relaxed`) instead of returning nothing. Directive-free queries are passed through byte-identical everywhere.
+- Eval and browser `run` code previews are now prettified for display: minified/compact agent-written cells are expanded by conservative streaming formatters (Python, JavaScript, Ruby, Julia) that indent block structure, split statements, normalize operator spacing (JS), and expand object literals wider than 100 columns onto one property per line — purely for rendering, the executed source is untouched. The formatters handle in-flight prefixes (unterminated strings/comments/blocks) without inventing closers, and layout decisions are prefix-stable so already-rendered lines never reflow while a call streams.
+
+### Changed
+
+- Large pastes saved via the large-paste menu now insert `local://paste-N.md` references (previously `local://attachment-N`), so the saved paste carries a markdown extension and a clearer name.
+- Raw SSE debug capture now trims over-budget events smartly instead of chopping off the tail: tool definitions inside `data:` payloads are compacted first (name kept, schema/description elided — often enough to keep the whole payload as valid JSON), and anything still over the 64k cap keeps its head and tail with a `: omp-debug-elided chars=N` comment marking the removed middle, so trailing fields like `usage` stay visible.
+- The `web_search` tool prompt now tells the model to never search for content that is programmatically accessible or has a known URL (GitHub, known arXiv papers, Wikipedia pages, official docs) and to `read` the URL directly instead.
+
+### Fixed
+
+- Fixed `todo` calls that omit `op` hard-failing validation ("op must be operation to apply (was missing)"): the tool now validates leniently and infers the op for unambiguous payloads (`list` → `init`, `phase`+`items` → `append`, bare `items` on an empty list → `init`); `op` stays required in the schema, and ambiguous op-less calls surface the schema error as a retryable tool error.
+- Fixed credential-free web search engines (SearXNG, DuckDuckGo, Google, Startpage, Ecosia, Mojeek, and the Public Web fan-out) returning zero results for queries with `site:` paths (e.g. `site:github.com/owner/repo`) or `inurl:` operators: scraper engines only match `site:` against a bare domain and DuckDuckGo ignores `inurl:` entirely, so such queries silently emptied the result set and fell through to the next provider in the chain. A shared `formatScraperQuery` formatter now structurally demotes path-carrying `site:` and all `inurl:` values to plain search terms (covering OR-grouped and quoted directives) while preserving bare-domain `site:` filters, negated operators, and each engine's supported syntax; the pipeline post-filter still enforces the demoted constraints on returned sources.
+- Fixed `ast_edit` previews reading like applied edits to the model: the `⟨proposed⟩` badge was TUI-only, so the model-visible result (hashline header + `-`/`+` rows, identical to applied edit output) carried no staged-proposal signal. The preview result now leads with a "Staged as a proposal — files NOT modified yet" notice naming `xd://resolve`/`xd://reject`, the injected resolve reminder names the source tool, and the `ast_edit` tool prompt documents the two-phase flow.
+- Fixed the `hub` launch `ps`/`list` response burying the active process behind every exited one and growing without bound in long-lived projects: the broker now lists non-terminal daemons first (oldest to newest) and caps exited/failed history at the 10 most recently exited, so the active launch is immediately visible and the response stays bounded. Broker recovery also preserves each already-terminal daemon's real exit time instead of overwriting it with the restart timestamp, so the history cap keeps the genuinely most-recently-exited processes after an idle-broker restart ([#6517](https://github.com/can1357/oh-my-pi/issues/6517)).
+- Fixed a tool call rendering twice in the transcript. A mid-stream `rebuildChatFromMessages` (from `/shake`, auto-compaction, or a settings toggle) preserves the live `pendingTools` components across the clear+replay, but that preservation assumed every pending-tool component was still dangling. When a tool's result had already landed in the session entries while its component still lingered in `pendingTools`, the replay reconstructed the completed block *and* the preserved live component was re-appended, so the same block appeared twice; resolved components are now dropped from preservation and owned by the replay ([#6516](https://github.com/can1357/oh-my-pi/issues/6516)).
+- Fixed `--model default` (and other bare role names) resolving to the bundled `cursor/default` catalog model instead of the configured `modelRoles.default` role. `resolveCliModel`'s exact-match phase ran its unauthenticated catalog fallback before role resolution, so a bundled id colliding with a reserved role name shadowed a configured, runnable role — failing with `No API key found for cursor` on machines without Cursor credentials. The catalog fallback is now deferred so an authenticated exact model still wins, a configured role beats an unauthenticated catalog-only id, and the catalog id is still recovered when no role matches ([#6508](https://github.com/can1357/oh-my-pi/issues/6508)).
+
+### Removed
+
+- Removed the `model` parameter from `task` and `agent()`: explicit per-spawn model selectors and fallback chains are no longer supported; spawns always use the agent's configured model
+
+## [17.1.1] - 2026-07-24
+
+### Added
+
+- Added the `/session pin` subcommand and account picker to pin provider OAuth accounts for the current session
+- Added the disabled-by-default `computer` essential tool with configurable enablement, backend, display, and maximum width/height settings. Native desktop execution runs through a `DesktopSession` worker; observation uses read approval, input uses exec approval, and provider checks always prompt and fail closed.
+- Added the `/computer` slash command (`on`/`off`/`status`/toggle) to enable or disable the computer tool for the current session without persisting settings.
+- Exposed `computer` to models without native OpenAI computer-use support as a regular function tool with a typed GA action schema; the same native desktop backend and approval policy apply on both paths.
+- Hardened computer action ingress: action-specific fields, modifier/key arrays, coordinates, drag points, and scroll deltas fail closed before native input; numeric fields must be signed 32-bit integers and coordinates must be non-negative.
+
+### Changed
+
+- Replaced Chromium-backed `/live` media and external speech recorder/player subprocesses with the cross-platform native microphone, speaker, Opus, and WebRTC stack from `@oh-my-pi/pi-natives`.
+
+### Fixed
+
+- Fixed live-call attestation depending on the ChatGPT desktop app being installed: `generateLiveAttestation` now mints DeviceCheck tokens in-process through the `@oh-my-pi/pi-natives` `deviceCheckGenerateToken` binding instead of probing `/Applications` for the app's `devicecheck.node` addon, so the `x-oai-attestation` header works on hosts without the desktop app and drops the `createRequire` addon probing; the attestation provider is now wired up to `@oh-my-pi/pi-ai` for ChatGPT-OAuth Codex requests.
+- Fixed `xd://` device execution failures rendering as `write` errors instead of using the mounted tool's own error renderer.
+- Fixed custom tools without bespoke renderers losing the default state-tinted card when mounted under `xd://`; dispatched calls now keep their label, arguments, status, output preview, and expansion affordance instead of dumping a bare result line into the transcript.
+- Fixed the clipboard image-paste keybind mangling copied URL text into a bogus path error on macOS (e.g. `Image not found at /https/::i.can.ac:CE4Ek3.png` for a copied `https://i.can.ac/CE4Ek3.png`). AppleScript's `the clipboard as «class furl»` coerces plain *text* into a file URL by treating the string as an HFS path (`:`↔`/` swap), so `readMacFileUrlsFromClipboard` returned a garbage path that dead-ended in `handleImagePathPaste` instead of falling through to the text paste. The script now bails early via `clipboard info for «class furl»` unless the pasteboard actually carries a `public.file-url` representation, so URL/text clipboards paste as text.
+- Fixed spilled tool-output artifact descriptors leaking on error/abort paths. `OutputSink.dump()` was the only path that closed the spill `Bun.FileSink`, but the bash and Python executors re-throw on failure and their `finally` blocks never closed the sink, so a large-output command that errored leaked the artifact descriptor until an unrelated read (e.g. a `SKILL.md` load) hit `EMFILE`. `OutputSink` now exposes an idempotent `dispose()` that closes the sink exactly once, wired into every executor's `finally` ([#6463](https://github.com/can1357/oh-my-pi/issues/6463)).
+- Fixed the first submitted prompt stalling while the local tiny-title worker started: the interactive submit handler now paints the pending user row before starting title generation, and startup prewarms an idle, unref'd worker so the first submit reuses a live subprocess instead of paying spawn latency ahead of the first frame ([#6462](https://github.com/can1357/oh-my-pi/issues/6462)).
+- Fixed legacy Pi extensions failing validation when importing the upstream `keyText` keybinding helper ([#6470](https://github.com/can1357/oh-my-pi/issues/6470)).
+
 ## [17.1.0] - 2026-07-24
 
 ### Breaking Changes