fix(deps): update all non-major dependencies - #113

v0.84.4

Compare Source

Breaking Changes

• Changed prepareNextTurn and prepareNextTurnWithContext to run only after shouldStopAfterTurn and queued-message checks determine that the agent loop will start another assistant turn. They no longer run after final or terminating turns; move end-of-run work to agent_end handling (#​6879).

Fixed

• Fixed Windows NodeExecutionEnv aborts crashing when taskkill.exe is unavailable on PATH (#​6596).

v0.84.4

Compare Source

Added

• Added the experimental vision-capable deepseek-v4-flash-vision-exp model to the DeepSeek catalog.

Fixed

• Fixed OpenAI-compatible Chat Completions ignoring an explicitly requested toolChoice when no tools are defined.
• Fixed thinking signature serialization to run once after the signature is complete (#​8671).
• Fixed fragmented Mistral tool calls splitting when continuation chunks omit the tool-call ID (#​8387).
• Fixed OpenAI-compatible reasoning replay to merge consecutive streamed text and summary reasoning_details deltas.
• Fixed the Cloudflare AI Gateway catalog to include supported workers-ai/* passthrough models omitted by models.dev.
• Fixed OpenRouter reasoning controls by deriving off support and available effort levels from OpenRouter's model metadata, preventing reasoning-mandatory models from receiving effort: "none" (#​8614 by @​davidbrai).

v0.84.4

Compare Source

New Features

• Terminal capability overrides — Override detected terminal hyperlink, image, and truecolor support. See Capability Overrides.
• Extension UI prompt events — Integrations can distinguish active agent work from time spent waiting for ctx.ui prompts. See Extension UI prompt events.
• RPC queue clearing — Retrieve and clear queued steering and follow-up messages with clear_queue. See RPC clear_queue.
• Fullscreen selection copy controls — Disable automatic selection copying in fullscreen mode and use Ctrl+X to copy the active selection. See UI & Display.
• DeepSeek V4 Flash Vision (experimental) — Use the vision-capable model through the built-in DeepSeek provider. See API Keys.

Added

• Added ui_prompt_start and ui_prompt_end extension events so host integrations can distinguish active agent work from waiting on user-facing ctx.ui prompts (#​8355 by @​cristinaponcela).
• Added detectSupportedImageMimeTypeFromFile() to the public library exports (#​8600 by @​xl0).
• Added inherited experimental vision-capable deepseek-v4-flash-vision-exp model support.
• Added transcript usage notices for compaction and branch summaries when cache miss notices are enabled.
• Added RPC clear_queue to retrieve and remove queued steering and follow-up messages (#​8432).
• Added environment variables and advanced settings for overriding auto-detected terminal hyperlink, image, and truecolor capabilities (#​8665).
• Added fullscreenCopyOnSelect to disable automatic fullscreen selection copy; when disabled, Ctrl+X copies the active text selection before falling back to the last assistant message, while /tree still copies the selected message (#​7720).

Fixed

• Fixed toggling thinking visibility clearing partial output from running Bash tools (#​8611).
• Fixed Windows shell aborts crashing Pi when taskkill.exe is unavailable on PATH (#​6596).
• Fixed resumed sessions corrupting the next appended entry when their JSONL file lacks a trailing newline (#​8345).
• Fixed extension messages sent with triggerTurn: false while the agent is running being inserted between a tool call and its result, which made providers that validate message order reject the replayed history. They are now appended once the turn's tool results are in (#​8537).
• Fixed compaction and branch summaries forcing toolChoice: "none" (#​8649, #​8638).
• Fixed large tool results crossing the auto-compaction threshold being sent to the provider before compaction. Pi now compacts between tool execution and the next assistant response in the same run, and restores interactive progress when that run resumes (#​6879).
• Fixed Google Vertex requests failing with HttpsProxyAgent is not a constructor when the bundled Node.js runtime uses an HTTP(S) proxy (#​8610).
• Fixed saving a default model from a non-empty model scope so it remains available in that scope.
• Fixed inherited @ file autocomplete ranking to prefer direct and shallower matches over similarly ranked nested paths (#​8669).
• Fixed inherited OpenAI-compatible streams serializing thinking signatures repeatedly during streaming (#​8671).
• Fixed inherited main-screen rendering crashing when image-heavy output exceeded V8's string length limit (#​8028).
• Fixed inherited fullscreen double-click word selection splitting paths and kebab-case tokens on / and - (#​8676).
• Fixed inherited Cloudflare AI Gateway catalogs omitting supported workers-ai/* passthrough models.
• Fixed inherited OpenAI-compatible reasoning replay to merge consecutive streamed text and summary reasoning_details deltas.
• Fixed inherited OpenRouter reasoning controls so reasoning-mandatory models do not receive effort: "none" (#​8614 by @​davidbrai).
• Fixed inherited OpenAI-compatible Chat Completions ignoring an explicitly requested toolChoice when no tools are defined.
• Fixed inherited fragmented Mistral tool calls splitting when continuation chunks omit the tool-call ID (#​8387).

v0.84.4

Compare Source

Added

• Added environment and programmatic overrides for OSC 8 hyperlinks, inline image protocols, and truecolor terminal capabilities (#​8665).
• Added a TuiAltScreen copyOnSelect option plus helpers to detect and copy the active fullscreen text selection programmatically (#​7720).

Fixed

• Fixed main-screen rendering crashing when image-heavy output exceeded V8's string length limit (#​8028).
• Fixed autocomplete ordering for nested results (#​8669).
• Fixed fullscreen double-click word selection splitting paths and kebab-case tokens on / and - (#​7746).

v2.8.0

Compare Source

v2.8.0

Compare Source

v2.8.0

Compare Source

v3.9.1

Compare Source

What's Changed

• fix: persist abort/fail agent status and run cause by @​QuintinShaw in #​172

Full Changelog: QuintinShaw/pi-dynamic-workflows@v3.9.0...v3.9.1

v2.31.0

Compare Source

Highlights

• MCP Apps-aware servers can now recognize Pi as a UI-capable host and expose interactive resources.
• UI capability advertising works consistently across legacy and modern MCP protocol negotiation.
• Manual OAuth callback completion now supports HTTPS redirect URLs for pre-registered clients.

Added

• Pi now advertises MCP Apps UI support with the io.modelcontextprotocol/ui extension capability, so compatible servers can expose UI resources. Thanks to @​VikashLoomba for #​465.

Fixed

• Pre-registered OAuth clients can use HTTPS callback URLs through manual callback completion instead of being rejected as non-local redirects. Thanks to @​jluisrojas for PR #​464.

v0.59.0

Compare Source

Highlights

• Run host commands from workflow scripts with safer saved output and clearer command results.
• Build sequential parallel workflows with runs.lanes(...), launch preflight labels, and better retained-resume behavior.
• See cleaner async status, child labels, and worktree handoff details without extra setup.
• Recover more reliably from stale contexts, provider aborts, missing outputs, malformed MCP metadata, and Windows file locks.
• Control live workflow children from more places, including non-TUI and RPC hosts.

Added

• Add runs.host(...) command steps to workflowScript, with required timeouts, saved output, and status and receipt evidence (#​1648).
• Add CI and gate monitor rows that record monitor kind, terminal verdict, freshness, and report pointers in workflow status and receipts.
• Persist workflow lane metadata in child status, receipts, and existing worktree handoff manifests, including display-only worktree paths and branches.
• Add runs.lanes(...) for parallel sequential workflow stages with per-lane results and retained-resume support (#​1633).
• Add display-only preflight lane metadata for workflowScript launches, with coverage warnings and planned-lane rendering in launch, status, and live-card views.
• Add a plan-only worktree.cleanup management action that records a cleanup plan without removing worktrees or branches.
• Give every subagent child session a human-readable display name, and include it in result, progress, status, workflow, nested, and intercom payloads. Thanks to @​yanqianglu for #​1615.
• Add /subagents-steer <run-id> [--child <child-id>] <message> so non-TUI sessions and RPC hosts can steer live async runs. Thanks to @​yanqianglu for #​1608.
• Add explicit allowNestedSubagents agent authorization for nested fanout without replacing inherited tools or extensions. Thanks to @​tutu359 for #​1587.
• Accept a child id on /subagents-stop <run-id> <child-id> so one child of a multi-child async run can be stopped without stopping the whole run. Thanks to @​yanqianglu for #​1603.

Changed

• Reduce noisy launch, status, output, settings, and worktree cleanup messages without changing behavior.
• Include a direct resumable child id in missing workflow receipt guidance when retained status proves it is safe.
• Clarify workflowScript contracts for retained resume keys and durable child output paths.
• Record merge or supersession evidence in existing worktree handoff manifests and show cleanup eligibility without removing anything.
• Show optional lane and work-item context in async status rows, including phase, gate, next action, output, run reference, and stale or blocked state.
• Show workflow child labels and phases in async status progress while preserving stable workflow keys.
• Remove assistant turn budgets, including hard termination, wrap-up prompt injection, and launch configuration.
• Split internal launch, status, settlement, evidence, and direct-MCP planning code into smaller modules without changing public behavior.

Fixed

• Match detached workflow completion by exact child identity, keep host gate rows in snapshots, and report missing host verdicts as inconclusive.
• Replace explicit runs.host(...) output files atomically inside their verified directory, and retry transient Windows destination locks.
• Reject malformed MCP direct-tool server and metadata-cache fields when JSON is loaded.
• Preserve live composite child tool-call ids for cursor-native, so Cursor MCP results keep matching pending execs. Thanks to @​moofone for #​1677 and #​1678.
• Ignore stale cached UI contexts during background status refresh and session lifecycle cleanup (#​1670).
• Compact workflow preflight status in default TUI and status views while keeping full details available when expanded (#​1668).
• Give runs.lanes(...) stage-0 retained-resume validation actionable runs.run(...) guidance instead of a generic error (#​1657).
• Remove the remaining lane: prefix from operator-facing async status rows in the TUI (#​1658).
• Allow scheduled project roots shared through a registered Git worktree's .pi symlink while rejecting unrelated or unproven Git-layout escapes. Thanks to @​sususu98 for #​1656.
• Include delegated child usage in subagent tool results and /subagent-cost, including completed async workflow children and parent compaction usage with persisted workflow-receipt recovery when needed (#​1662, #​1666). Thanks to @​Geraldo-Morais for #​1662 and @​jf88888 for #​1666.
• Avoid false preflight mismatch warnings for generated runs.lanes(...) stage keys (#​1649).
• Accept long host tool-call ids in workflow child summaries, matching the existing 4,096-byte session id bound. Thanks to @​SudoKillMe for #​1653.
• Keep an async workflowScript continuation live while an awaited child coordinates with its supervisor, so later sequential steps still run (#​1634).
• Stop stale extension and slash-command contexts from escaping during reload or session replacement.
• Include saved workflow child output paths and inline previews in completion notices (#​1629).
• Format million-scale context limits as 1M instead of 1000k in live status displays.
• Restore active workflow children under their workflow parent in Fleet Status after reload, while keeping unmatched shell rows visible.
• Prefer loaded workspace context over repeated internal workflow keys in async TUI lane rows (#​1619).
• Accept path-like Pi session ids up to 4,096 characters when snapshotting background work. Thanks to @​dvishoot for #​1616.
• Accept bare leaf model ids reported by provider drivers when verifying provider-qualified launch candidates. Thanks to @​lallenlowe for #​1609.
• Resume compaction-induced child aborts once when retained state is safe, and report the exact recovery blocker otherwise.
• Report aborted or signalled no-output child runs with their terminal stop, stderr, or process signal before missing-output handoff diagnostics.
• Apply globalConcurrencyLimit to workflowScript children launched through runs.run and runs.all, not only legacy multi-child runners. Thanks to @​mateominato for #​1600.
• Ignore nested .pi and sync-backups directories during agent discovery so stale backup definitions cannot become executable agents. Thanks to @​arlishansenn for #​1596.
• Let projects layer agent overrides by the active parent model provider without duplicating agent definitions. Thanks to @​arichiardi for #​1597.
• Let operators configure the default subagent_wait window and report window expiry as non-error active work while preserving strict headless draining. Thanks to @​Shujakuinkuraudo for #​1591.
• Degrade run status to the stored fan-out budget snapshot when persisted state is unavailable, instead of failing the entire run list. Thanks to @​qsgy-edge for #​1595.
• Enforce MCP server includeTools and excludeTools policies for child direct-tool grants, including adapter-compatible glob matching. Thanks to @​Shujakuinkuraudo for #​1590.
• Prevent Fleet prompt audit rendering from crashing on malformed non-string task payloads. Thanks to @​bengidev for #​1586.
• Resume a retained child session once after a provider or transport abort follows useful progress, without restarting the task or involving the parent model.
• Retry unused fallback models after a provider reports a plain-text 500 or internal server error. Thanks to @​rafafortes for #​1642.
• Mark missing required child handoffs with useful mutation evidence as partial needs-attention results.

v1.3.22

Compare Source

v1.3.21

Compare Source