Skip to content

v17.1.0

Choose a tag to compare

View all tags
@github-actions github-actions released this 24 Jul 02:05
v17.1.0
4e5cb4d
This commit was signed with the committer’s verified signature.
can1357 Can Bölük
GPG key ID: 78CE190854FB4A0A
Verified
Learn about vigilant mode.

@oh-my-pi/pi-agent-core

Added

  • Added support for tracking Cloudflare AI Gateway cache status (hit, miss, bypass, unknown) on chat spans.

Changed

  • Improved tool execution steering behavior: queued steering now cooperatively signals long-running, non-interruptible tools (via ToolCallContext.steeringSignal) to allow graceful early termination or backgrounding, rather than hard-aborting them.

Fixed

  • Fixed an out-of-memory (OOM) crash caused by an infinite loop when a steer or follow-up message was queued on an agent session with an empty transcript.
  • Fixed an issue where switching providers or models on a session could lose compacted history; the agent now correctly falls back to a portable local summary if the new model cannot replay the prior provider's remote-compaction payload.
  • Fixed a compaction failure with Anthropic models where serializing prior assistant reasoning inside tags triggered reasoning_extraction refusals.

@oh-my-pi/pi-ai

Added

  • Added support for caller-owned cachedContent on Google Generative AI and Google Vertex AI GenerateContent options, allowing passing of opaque cache resource names.
  • Added Anthropic extra-usage reporting across CLI, interactive, and ACP usage endpoints, normalizing the authoritative spend payload into a 'Claude Extra Usage' USD row with accurate limit, remaining, and status details.
  • Added process-scoped OAuth account pools for trusted auth-broker clients via OMP_AUTH_BROKER_ACCOUNT_POOL_FILE to filter snapshots, updates, refreshes, and usage reports to selected OAuth identities.
  • Added opt-in Vercel AI Gateway automatic prompt caching for OpenAI Chat Completions, including support for cache anchors and cache lifetimes.
  • Added opt-in explicit prompt-cache controls for OpenAI GPT-5.6+ Responses and Chat Completions, supporting stable boundary selection, stateful Responses markers, and future GPT-5.x/6.x models.
  • Added support for forwarding statefulResponses through streamSimple to allow diagnostic callers to explicitly disable OpenAI Responses previous_response_id chaining.
  • Added native QwenCloud Token Plan support, including API-key login, model discovery, and an optional interactive console-Cookie prompt for quota reporting.
  • Added interactive Meta Model API key login and support for MODEL_API_KEY and META_API_KEY environment variables.
  • Added model-scoped usage health tracking and same-provider reselection for native coding-plan credential pools.

Fixed

  • Fixed AWS Bedrock cache checkpoints to use resolved model compatibility, falling back to the provider-default 5-minute cache for unsupported 1-hour retentions, emitting AWS-recommended explicit checkpoints for Nova models (Lite, Micro, Pro, Premier, Nova 2 Lite), and honoring configured checkpoint maxima.
  • Fixed Pi-native and compatibility-wrapper requests dropping cache controls required by omp bench --cache to preserve explicit prompt-cache affinity and allow disabling OpenAI Responses chaining.
  • Fixed outbound credential-pattern redaction running unconditionally; it is now opt-in via configureCredentialRedaction and disabled by default.
  • Fixed SuperGrok (xai-oauth) /usage reporting for unified-billing accounts by falling back to the default monthly limit and usage payload when credit usage percentages are absent.
  • Fixed sessions wedging with a 400 Invalid signature in thinking block error when switching Anthropic-compatible providers by stripping signatures whose issuing provider differs from the target.
  • Fixed OAuth callback servers aborting login on premature invalid callbacks, and restricted localhost callback listeners to the IPv4 loopback interface.
  • Fixed Google Gemini CLI and Antigravity OAuth login hanging indefinitely during Cloud Code Assist project provisioning by introducing request timeouts, cancellation checks, and bounded polling.

@oh-my-pi/pi-catalog

Added

  • Added Bedrock Converse prompt-cache compatibility limits, including 5-minute checkpoint support for Nova models (Lite, Micro, Pro, Premier, Nova 2 Lite) and 1-hour Claude retention.
  • Added native Meta Model API provider and Muse Spark 1.1 support, featuring Responses API reasoning replay, image input, and reasoning-effort controls.
  • Added Vercel AI Gateway integration features, including opt-in automatic prompt-cache compatibility, provider routing preferences, and Responses cache-anchor and cache-lifetime controls.
  • Added prompt-cache breakpoint capability metadata for OpenAI GPT-5.6, with opt-in support for older models and compatible endpoints.
  • Added native alibaba-token-plan provider with QwenCloud Token Plan Individual discovery and a curated chat-model fallback catalog.

@oh-my-pi/pi-coding-agent

Breaking Changes

  • Replaced the providers.webSearch and providers.image single-preference configuration options with providers.webSearchOrder and providers.imageOrder priority lists. Existing configurations migrate automatically on startup.

Added

  • Added dynamic multi-root workspace context support, allowing users to manage multiple workspace directories mid-session via /add-dir, /remove-dir, and /dirs slash commands, or seed them at launch using the --add-dir CLI flag.
  • Added /live, a Codex-authenticated real-time voice interface that streams microphone audio over WebRTC and routes coding tasks through the active agent session.
  • Added opt-in usage-aware model fallback for rationed coding plans, including a /usage command to view live quantitative usage data and automatic fallback chain traversal.
  • Added error.notify configuration to allow failed model turns to trigger distinct terminal or desktop notifications.
  • Added auto-following light and dark themes to HTML session exports, with a /export --themes option to bundle selected TUI themes.
  • Added owner-routed asynchronous job delivery, ensuring background bash and task results are injected directly into the owning subagent or agent session rather than the top-level session.
  • Added background-on-steer capability for auto-backgrounded bash commands, allowing incoming user or peer messages to immediately background running commands.
  • Added friendlyName support for hidden secrets, allowing model-visible placeholders to carry sanitized semantic labels, hashes, and case hints.
  • Added support for Jujutsu (jj) repositories in the statusline git segment, displaying the nearest bookmark or change ID and retrieving working-copy change counts.
  • Added block and unblock operations for tasks, introducing a blocked status for tasks waiting on external input to exclude them from incomplete-todo reminders.
  • Added a toggle-list editor in /settings for managing array-of-enum settings like search and image provider orders.
  • Added models.yml Bedrock Converse prompt-cache capability overrides for bundled and opaque inference profiles.
  • Added getServiceTiers() and setServiceTier() extension APIs to read and modify the live per-family service tier for session requests.
  • Added opt-in omp bench --cache for independent cold/warm prompt-cache benchmarking with stable-prefix controls.
  • Added tools.xdevDocs prompt-doc modes and the tools.xdevInlineDevices glob allowlist to control which mounted device documentation is inlined into the system prompt.
  • Added the opt-in read.renderMarkdown setting for formatted Markdown read previews.

Changed

  • Updated subagent behavior to inherit async.enabled and bash.autoBackground.enabled from parent sessions, and refined subagent run completion to wait for background jobs to settle.
  • Added ordered bash.patterns command approval rules to allow, prompt, or deny bash commands by pattern.
  • Updated Markdown file handling so all Markdown flavors (.markdown, .mdx, .mdc, etc.) respect the read.summarize.prose setting.
  • Upgraded xAI web search to use grok-4.5 at low reasoning effort instead of grok-4.3.
  • Improved search provider resilience by cascading and falling back through other configured search providers when the preferred provider fails.
  • Extended the bash tool's direnv and devenv auto-loading to all backends (including the ACP client terminal and interactive PTY) while honoring direnv's local allow list.

Fixed

  • Fixed a path traversal vulnerability in blob reference resolution by rejecting non-canonical hashes in parseBlobRef.
  • Fixed multiple edge cases in the secret obfuscation and redaction engine, including handling of context-sensitive regexes, placeholder key requirements in unwritable directories, friendly-name forgery vulnerabilities, and regex match boundaries straddling existing placeholders.
  • Fixed a first-use race condition in ArtifactManager where concurrent callers could allocate duplicate artifact IDs.
  • Fixed Vibe-mode session stability, resolving issues with workers disappearing across restarts, hanging during teardown, clobbering target tools during session switches, and resolving against incorrect models.
  • Fixed concurrent MCP configuration mutations losing updates by serializing read-modify-write operations under a per-file lock with atomic writes.
  • Fixed legacy extensions failing to load on npm/source-link installs due to transitive CommonJS dependency graph clobbering.
  • Fixed omp auth-gateway commands bypassing the process-scoped OAuth account pool configured via environment variables.
  • Fixed terminal transcript rendering issues where displaceable snapshots (like waiting polls and todo lists) spammed native scrollback.
  • Fixed the terminal title to reflect the active agent run state (working, waiting, or blocked) when tui.titleState is enabled.
  • Fixed the browser tool's open action ignoring timeouts during browser acquisition and leaking orphaned browser instances.
  • Fixed the write tool silently creating empty files when a read-tool selector was mis-dispatched as a write.
  • Fixed snapcompact archiving reproducing assistant reasoning (¶think: sections) into replayed frames for Anthropic-dialect models.
  • Fixed Linux socket-mode DAP launches hanging indefinitely on connection failures.
  • Fixed Plan Review annotations being discarded on dismissal and limited to headings.
  • Fixed Assistant-mode TTS playback aborting prematurely when an agent continued after a tool call.
  • Fixed absolute usage amounts rendering inconsistently across CLI, TUI, and ACP output surfaces.
  • Fixed MCP sessions dropping tools from servers that finished connecting after the initial startup window.

@oh-my-pi/collab-web

Fixed

  • Fixed action metadata loss on xd://resolve, xd://reject, and xd://propose cards to ensure correct action badges are rendered.
  • Added proper rendering support for reject, propose, and hub-family aliases (irc, job, await, poll, cancel_job) to prevent them from falling back to generic JSON.

@oh-my-pi/snapcompact

Added

  • Added an includeThinking serialization option (defaulting to true) to allow excluding assistant reasoning (¶think: sections) from archived transcripts.

@oh-my-pi/omp-stats

Fixed

  • Fixed an issue where malformed persisted content blocks could abort stats ingestion for subsequent projects, and ensured pending full-session migrations are properly settled after successful backfills.

@oh-my-pi/pi-tui

Added

  • Added Text.setStyleFn() to apply foreground stylers at render time, allowing components to dynamically re-resolve colors after invalidation instead of baking in the palette active at construction.

Fixed

  • Fixed an issue where exiting or tearing down the TUI left the terminal in cursor-key/keypad application mode (DECCKM), which broke arrow keys in the parent shell. Both stop() and emergencyTerminalRestore() now correctly emit standard rmkx resets.

What's Changed

  • feat(ai): report Anthropic extra usage in omp usage by @LunarECL in #6382
  • fix: preserve oauth links across wrapped rows by @ondrejsojka in #6383
  • feat(providers): browser OAuth sign-in for Z.AI (GLM Coding Plan) by @cefege in #6385
  • feat(catalog): add native Meta Model API provider by @eggpeat in #6386
  • feat(coding-agent): opt-in Markdown read previews by @oldschoola in #4001
  • fix(bash): bound interactive bash live display write queue by @metaphorics in #4269
  • fix(bash): bound ACP terminal lifecycle with abort/timeout by @metaphorics in #4270
  • perf(hindsight): cache full-session retention transcript incrementally by @metaphorics in #4275
  • feat(todo): add blocked status with block/unblock ops by @mattwilkinsonn in #4448
  • feat(statusline): make git segment jj-aware by @mattwilkinsonn in #4450
  • feat(coding-agent): reflect agent run state in terminal title by @mattwilkinsonn in #4451
  • feat(coding-agent): auto-load direnv environment into the bash session by @mattwilkinsonn in #4455
  • feat(secrets): add friendly names to secret placeholders by @Mathews-Tom in #4636
  • feat(notifications): add error turn notifications by @Mathews-Tom in #4637
  • feat(coding-agent): use Grok 4.5 for xAI web search by @metaphorics in #4890
  • fix(coding-agent): persist vibe sessions across restarts by @roboomp in #5464
  • feat(omp): configure web search provider order by @riverpilot in #6029
  • feat: lift subagent async/auto-background limits via owner-routed delivery and quiescence by @korri123 in #6119
  • Add dynamic multi-root workspace context (#2569) by @maatheusgois-dd in #6255
  • Support light, dark, and system themes in HTML exports by @anatoli-tsinovoy in #6349
  • fix(compaction): rescue snapcompact archives stuck past the maintenance threshold (#4786 gap) by @HugoLopes45 in #6362
  • feat(coding-agent): support per-command bash approval rules by @WahidinAji in #6363
  • fix(ai): strip foreign thinking signatures on the latest assistant turn by @LunarECL in #6380
  • fix(edit): align relative path resolution by @roboomp in #6417
  • fix(tui): re-resolve transient status colors on theme swap by @roboomp in #6420
  • fix(tts): play buffered audio when streaming backend exits nonzero by @roboomp in #6421
  • fix(mcp): serialize mcp.json config writes and use unique temp path by @roboomp in #6424
  • fix(session): serialize ArtifactManager first-use init by @roboomp in #6426
  • fix(memory): synchronize live backend lifecycle by @roboomp in #6428
  • fix(session): resume resolved tool stalls by @roboomp in #6435
  • docs: document /vibe mode and /fresh command by @roboomp in #6441
  • fix(tui): reset cursor-key and keypad mode on terminal teardown by @roboomp in #6398
  • fix(stats): prevent malformed entries from stalling sync by @roboomp in #6400
  • fix(coding-agent): make PDF image cache content-aware by @roboomp in #6404
  • fix(eval): coalesce dead Python kernel replacement by @roboomp in #6405
  • fix(agent): deliver queued steer on empty transcript instead of looping by @roboomp in #6406
  • fix(browser): bound open timeout and lease browser across tab acquisition by @roboomp in #6407
  • fix(compaction): judge remote-preserve reuse against the active model by @roboomp in #6415
  • fix(tool): expand internal urls inside backtick substitutions by @roboomp in #6418
  • fix(robomp): route issues.reopened to admission-gated re-triage by @roboomp in #6419
  • fix(collab-web): restore resolve/reject/propose cards after xdev unwrap by @roboomp in #6422
  • fix(ai): prevent invalid callbacks from aborting oauth by @roboomp in #6423
  • fix(session): validate blob refs before path join by @roboomp in #6427
  • fix(compaction): stop feeding reasoning back to Claude summarizer by @roboomp in #6439
  • feat(ai): add process-scoped OAuth account pools by @atyrode in #6416
  • fix(session): preserve compaction data for rewinds by @roboomp in #6429
  • fix(dap): reject and bound the unix socket connect on Linux by @roboomp in #6430
  • fix(acp): pick up MCP tools that connect after the startup race by @barisdemirdelen in #6437
  • fix(plan): preserve and line-anchor review annotations by @anatoli-tsinovoy in #6444
  • feat(extensions): expose session service tiers by @atyrode in #6445
  • fix(extensibility): guard legacy-pi-compat commonjs registration first-wins by @roboomp in #6450
  • fix(tts): preserve playback across internal turns by @roboomp in #6396
  • fix(write): reject local read-selector-shaped write targets by @roboomp in #6397
  • feat(google): reference caller-owned cached content by @riverpilot in #6408
  • feat(gateway): map Vercel prompt cache controls by @riverpilot in #6410
  • feat(agent): classify Cloudflare response cache status by @riverpilot in #6411
  • feat(openai): add explicit prompt cache policy by @riverpilot in #6412
  • feat(cli): benchmark prompt cache reuse by @riverpilot in #6413
  • fix(agent): commit plan-reference flag on delivery, not construction by @roboomp in #6431
  • fix(oauth): bound and cancel Google Cloud Code Assist provisioning poll by @roboomp in #6433
  • fix(coding-agent): return from cancelled /omfg amendments by @anatoli-tsinovoy in #6442
  • fix(coding-agent): make mixed-agent task batches atomic and inspectable by @TechDufus in #6443

New Contributors

Full Changelog: v17.0.9...v17.1.0

Contributors

cefege, barisdemirdelen, and 16 other contributors
Assets 9
Loading