GitHub: v17.3.0

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

Fixed

• Improved the manual /shake command to retain a small history of recent tool results, preventing the agent from losing its active working context.

@oh-my-pi/pi-ai

Breaking Changes

• Renamed withGeminiThinkingLoopGuard to withThinkingLoopGuard; the guard applies to Gemini, DeepSeek, and Grok model-id families.

Changed

• Updated OpenCode Go integration to use the official usage endpoint, removing hardcoded caps, enabling real-time credential validation, and routing multi-key pools based on rolling and weekly headroom.


• Optimized Anthropic prompt caching with rolling 5-minute breakpoints and idle refreshes to keep the prompt prefix warm.

Fixed

• Fixed Ollama chat adapter to correctly forward sampling parameters like temperature and topP to the provider.


• Fixed OpenAI agent turns ending prematurely after a web search with no visible answer, ensuring the agent continues processing the search results.


• Fixed a resource leak where completed model streams retained provider concurrency permits longer than necessary.


• Fixed image input support for qwen3.8-max and newer models when using DashScope compatible-mode.


• Fixed xAI usage reporting falling back to a stale cache when a new weekly cycle starts with 0% consumed credits.


• Fixed Together AI login validation failures by querying the authenticated models list instead of a hardcoded model.


• Fixed credential-health probes and usage fetches failing when using reference-stored API keys (such as environment variables or commands) by ensuring secrets are correctly resolved.


• Fixed Perplexity email-OTP login by preserving the session cookies required for verification.


• Fixed thinking configuration for OpenAI and Daybreak models to correctly send reasoning.effort: "none" when thinking is disabled.


• Fixed Grok runaway thinking streams bypassing the thinking-loop guard.

Removed

• Removed legacy local request-cost estimation machinery and database schemas previously used for OpenCode Go estimates.

@oh-my-pi/pi-catalog

Breaking Changes

• Removed OpenAICompat.enableGeminiThinkingLoopGuard; thinking-loop eligibility is derived solely from the model.id family.

Added

• Added first-party OpenAI Daybreak Blue, Daybreak Red, and GPT-5.6 Cyber models with full support for their documented API pricing (including long-context rates above 272K input), token limits, tools, and reasoning effort controls (off/low/medium/high/xhigh/max).


• Added calculateUncachedInputCost() to calculate prompt pricing against active context-length tiers without prompt caching.

Fixed

• Fixed Anthropic cache-write pricing to correctly honor mixed 5-minute and 1-hour TTL usage instead of incorrectly charging all writes at the 5-minute rate.


• Fixed Ollama Cloud DeepSeek V4 Flash and older reasoners to correctly apply the DeepSeek effort contract (e.g., low/high/max) instead of the generic effort ladder.


• Added a default request timeout to OpenAI-compatible model discovery to prevent stalled provider endpoints from hanging startup indefinitely.


• Fixed Anthropic cache-write pricing to honor mixed 5-minute and 1-hour TTL usage instead of charging every write at the 5-minute rate.


• Fixed Ollama Cloud DeepSeek V4 Flash (including dated/preview tags like deepseek-v4-flash:0731) exposing the generic minimal/low/medium/high/xhigh effort ladder without max; the ollama-chat transport now applies the DeepSeek effort contract (Flash → low/high/max, older reasoners → high/max), matching the direct API and every other host ().


• Bounded OpenAI-compatible model discovery with a default request timeout so a stalled provider /models endpoint can no longer hang startup indefinitely in resolveModelDiscoveryFallback ().

@oh-my-pi/hashline

Fixed

• Repaired mis-set replacement ranges using exact outside-row matches, indentation, tree-sitter structure, and a narrow pure-closer shape: opening comment fences and other syntax-essential edges are retained only when a parse-valid candidate satisfies those constraints; ambiguous placements are rejected.

@oh-my-pi/pi-natives

Fixed

• Fixed an issue where shell-internal background jobs (such as yes >/dev/null &) could survive a one-shot shell session and consume CPU indefinitely after the command returned.

@oh-my-pi/omptype

Added

• Added type.withJsonSchema(schema, json) to wrap a validation-only schema, ensuring JSON Schema emission yields the provided json verbatim even when nested inside objects, arrays, or unions. Schemas with defaults or output-changing morphs are rejected to prevent transformed outputs from being discarded.

@oh-my-pi/omp-stats

Added

• Added cost-weighted cacheSavings metric alongside cacheRate, accounting for cache-read discounts and write premiums against equivalent uncached prompt costs.

Fixed

• Ensured the embedded dashboard archive is byte-reproducible by sorting entries and zeroing tar and gzip timestamps during compilation.

@oh-my-pi/pi-tui

Fixed

• Fixed an issue where repeated pane-width adjustments or terminal resizing could corrupt native scrollback and soft-wrap behavior.


• Fixed an issue where scaled OSC 66 Markdown headings (such as "Large Headings" on Kitty) would render as invisible placeholders or get partially cleared after a redraw or terminal resize.

@oh-my-pi/pi-utils

Fixed

• Optimized performance of partial JSON parsing for long streaming tool-call arguments.


• Fixed Mermaid ASCII multi-word edge labels where routed lines would show through spaces.

What's Changed

• fix(tui): preserve scrollback across multiplexer width changes by


• fix(session): forward retry fallback events to extensions by


• fix(cli): surface actionable error when auth broker is unreachable by


• fix(utils): mask routed lines beneath edge labels by


• fix(discovery): support OpenCode JSONC configs by


• fix(launch): rearm broker idle shutdown on terminal settlement by


• fix(agent): reject cold revive that finishes after lifecycle dispose by


• fix(dap): drain runInTerminal debuggee stdout by


• fix(coding-agent): show scope in /ssh add hint by


• fix(coding-agent): ship omp:// docs to npm consumers by


• fix(coding-agent): interpret inline /skill in mode-command prompts by


• fix(extensions): preserve unsafe schemas during plugin install by


• fix(ai): preserve perplexity otp session cookies by


• fix(coding-agent): lowercase the hindsight project label by


• fix(coding-agent): restore is*ToolResult guards on legacy pi shim by


• docs(collab): clarify relay self-hosting availability by


• fix(rpc): strip snapcompact archive from compact result by


• fix(session): resolve wire-name aliases in hasBuiltInTool by


• feat(lsp): add Astral ty as built-in Python primary LSP server by


• fix(coding-agent): gate prompt tool mentions on session tool availability by


• fix(agent): support array model overrides in dashboard by


• fix(cli): handle standalone profile aliases by


• chore: force refresh provider api key command by


• fix(ai): continue after answerless hosted search by


• fix(omp): prevent false reset fireworks by


• fix(coding-agent): skip idle mid-turn persistence waits by


• fix(ai): release provider permit before stream completion by


• Fix open browser behaviour on Windows by


• fix(ai): stop stripping images from multimodal qwen3.8-max on DashScope by


• fix(coding-agent): suppress circular plan-yolo startup note by


• fix(mcp): show config source in startup failures by


• fix(catalog): bound openai-compatible model discovery with default timeout by


• fix(tui): keep scaled OSC 66 heading reserved rows intact on repaint by


• fix(ai): handle omitted creditUsagePercent in fresh xAI weekly periods by


• fix(ai): validated together login against models endpoint by


• fix(catalog): apply DeepSeek effort contract on Ollama Cloud by


• fix(usage): use authoritative OpenCode Go quotas by


• fix(coding-agent): normalize WebP for STB-backed models by


• fix(natives): stop detached internal shell jobs by


• fix(eval): allow awaiting Python workflow helpers by


• fix(mnemopi): contain lifecycle hook failures by


• fix(bash): resolve msys drive paths in utility builtins by


• docs: reconcile session dir layout with the 17.2.9 hashed-scheme revert by


• test(coding-agent): fix pre-existing session-manager legacy migration test failure by


• fix(tui,utils): remove O(N²) hot paths when streaming long tool-call args by


• fix(coding-agent): preserve ArkType command API compatibility by


• fix(compaction): manual /shake keeps a recent tail of tool results by


• fix(agent): fit-check retry fallback before switching models by


• fix(advisor): preserve advisor fallback role ownership by


• fix(build): set CMAKE_POLICY_VERSION_MINIMUM for audiopus_sys in cargo env by


• fix(mcp): close stale initial connections by


• fix(tui): keep large transcript rebuilds responsive by


• fix(lsp): correct workspace edit failure handling by


• fix(lsp): isolate document overlays across sessions by


• fix(lsp): preserve workspace resource options by


• fix(lsp): reject unsupported rust-analyzer snippet edits by


• fix(lsp): roll back rename_file edits when the move fails by


• fix(lsp): abort rename_file when willRenameFiles fails on a supporting server by


• fix(lsp): fail diagnostics when every applicable server fails by


• fix(lsp): synchronize applied workspace edits by


• fix(discovery): bound WSL host-home probe with a hard timeout by

New Contributors

Full Changelog: v17.2.15...v17.3.0