build(deps-dev): bump @earendil-works/pi-ai from 0.74.0 to 0.75.3

[dependabot]

Bumps @earendil-works/pi-ai from 0.74.0 to 0.75.3.

Release notes

Sourced from @​earendil-works/pi-ai's releases.

v0.75.3

Fixed

• Fixed undici 8 HTTP/2 destroyed-session races crashing the Node CLI by preserving the previous HTTP/1.1-only fetch dispatcher behavior (#4681).

v0.75.2

Fixed

• Fixed Bun-compiled release binaries failing to start when Bun's built-in undici shim lacks npm undici's install export (#4661 by @​dmasiero).
• Fixed Xiaomi MiMo generated model metadata to replay assistant tool-call messages with reasoning_content for thinking-mode multi-turn requests, inherited from @earendil-works/pi-ai (#4678).
• Fixed Windows external editor handoff so vim/nvim can receive input after opening from the TUI (#4612).
• Fixed Windows npm self-updates to move loaded native dependency packages out of the active install before reinstalling pi (#4157).
• Fixed pi update --self detection for pnpm v11 global installs whose package path resolves through the pnpm store (#4647).
• Fixed Windows pnpm self-updates to resolve pnpm command shims and run through pnpm instead of requiring manual updates (#4157).
• Fixed Windows npm-family command execution to use cross-spawn instead of parsing .cmd shim internals (#4665).

v0.75.1

Fixed

• Fixed config selectors to scale their visible row count to terminal height (#4243 by @​samjonester).
• Fixed Anthropic-compatible API-key requests to ignore unrelated ANTHROPIC_AUTH_TOKEN environment values, avoiding invalid bearer credentials for providers such as Xiaomi MiMo inherited from @earendil-works/pi-ai (#4342).
• Fixed Amazon Bedrock message conversion to skip unknown content blocks instead of failing the stream, inherited from @earendil-works/pi-ai (#4223).
• Fixed Azure OpenAI Responses and OpenAI Responses error formatting to prefix HTTP status codes onto errorMessage, so transient 5xx and 429 errors are correctly matched by the agent-level auto-retry classifier inherited from @earendil-works/pi-ai (#4232).
• Fixed OpenCode Go Kimi reasoning replay by normalizing streamed reasoning fields back to reasoning_content for OpenCode Go only, inherited from @earendil-works/pi-ai (#4251).
• Fixed Xiaomi MiMo model metadata to use the OpenAI-compatible endpoints and openai-completions API, restoring multi-turn thinking/tool-call sessions inherited from @earendil-works/pi-ai (#4505).
• Fixed JSON parse failures for compressed fetch responses under Node 26.0 by installing undici fetch globals alongside pi's global dispatcher (#4650, #4652, #4653).
• Fixed npm-family package commands on Windows to avoid shell argument splitting when install prefixes contain spaces (#4623).

Removed

• Removed non-working OpenAI Codex fast model variants inherited from @earendil-works/pi-ai.

v0.75.0

Breaking Changes

• Raised the minimum supported Node.js version to 22.19.0.

Fixed

• Fixed compaction summary calls to use custom agent stream functions, preserving proxy-backed LLM routing (#4484).
• Fixed system prompt and context file boundaries to use explicit XML tags instead of Markdown headings, reducing inconsistent boundary ingestion by models (#4541 by @​herrnel).
• Fixed OpenAI Codex generated model metadata to use the current upstream model list inherited from @earendil-works/pi-ai (#4603 by @​mattiacerutti).
• Fixed GitHub Copilot GPT model thinking metadata inherited from @earendil-works/pi-ai to map unsupported minimal thinking to low (#4622 by @​mattiacerutti).
• Fixed user-scoped npm pi packages to install under ~/.pi/agent/npm/ instead of npm's global package root, avoiding permission errors with system-managed Node installs (#4587).
• Fixed Mistral requests failing after the global fetch proxy/timeout workaround by removing the custom fetch override and using undici 8 dispatcher support instead (#4619).
• Fixed default output token requests for models whose advertised output limit is effectively their full context window, avoiding impossible provider requests inherited from @earendil-works/pi-ai (#4614).

... (truncated)

Changelog

Sourced from @​earendil-works/pi-ai's changelog.

[0.75.3] - 2026-05-18

[0.75.2] - 2026-05-18

Fixed

• Fixed Xiaomi MiMo generated model metadata to replay assistant tool-call messages with reasoning_content for thinking-mode multi-turn requests (#4678).

[0.75.1] - 2026-05-18

Fixed

• Fixed Anthropic-compatible API-key requests to ignore unrelated ANTHROPIC_AUTH_TOKEN environment values, avoiding invalid bearer credentials for providers such as Xiaomi MiMo (#4342).
• Fixed Amazon Bedrock message conversion to skip unknown content blocks instead of failing the stream (#4223).
• Fixed Azure OpenAI Responses and OpenAI Responses error formatting to prefix HTTP status codes onto errorMessage, so transient 5xx and 429 errors are correctly matched by the agent-level auto-retry classifier (#4232).
• Fixed Xiaomi MiMo model metadata to use the OpenAI-compatible endpoints and openai-completions API, restoring multi-turn thinking/tool-call sessions (#4505).
• Fixed OpenCode Go Kimi reasoning replay by normalizing streamed reasoning fields back to reasoning_content for OpenCode Go only (#4251).

Removed

• Removed non-working OpenAI Codex fast model variants.

[0.75.0] - 2026-05-17

Breaking Changes

• Raised the minimum supported Node.js version to 22.19.0.

Fixed

• Fixed OpenAI Codex generated model metadata to use the current upstream model list (#4603 by @​mattiacerutti).
• Fixed GitHub Copilot GPT model thinking metadata to map unsupported minimal thinking to low (#4622 by @​mattiacerutti).
• Fixed streamSimple() defaults for models whose advertised output limit is effectively their full context window to avoid impossible default requests (#4614).

[0.74.1] - 2026-05-16

Added

• Added image generation APIs, image model metadata, and built-in OpenRouter image generation support (#3887 by @​cristinaponcela).
• Added Together AI as a built-in OpenAI-compatible provider with generated model metadata and TOGETHER_API_KEY authentication (#3624 by @​Nutlope).

Fixed

• Fixed GitHub Copilot model availability to ignore generic GH_TOKEN and GITHUB_TOKEN environment variables, requiring OAuth login or COPILOT_GITHUB_TOKEN instead (#4485).
• Fixed openai-completions streams to surface an error when the stream ends before any terminal finish_reason, so truncated responses can retry instead of being accepted as success (#4345).
• Fixed Fireworks provider caching compatibility by adding session affinity headers and model metadata compat settings (#4358 by @​yanirz).
• Fixed OpenAI Codex WebSocket transport to respect proxy environment variables under Bun (#4354 by @​haoqixu).
• Fixed OpenRouter cache usage normalization to preserve cached-token semantics without treating cached tokens as cache writes.
• Fixed Bedrock proxy handling to preserve NO_PROXY exclusions while using HTTP(S)-only proxy agents.
• Fixed compiled Bun binaries failing to start outside the repo when Bedrock proxy support tried to resolve proxy-from-env from external node_modules (#4513).

... (truncated)

Commits

• a7d8dd3 Release v0.75.3
• 0c4d704 Add [Unreleased] section for next cycle
• ea713ba Release v0.75.2
• b8f5195 fix(ai): add Xiaomi reasoning replay compat
• 93b2e7f Add [Unreleased] section for next cycle
• 73a6165 Release v0.75.1
• f1218fa chore: audit unreleased changelogs
• 9e2bfc7 fix(ai): skip unknown bedrock content blocks
• 52e1387 fix(ai): prefix HTTP status codes onto Azure OpenAI and OpenAI Responses erro...
• 21d80de fix(ai): normalize opencode go reasoning replay
• Additional commits viewable in compare view

You can trigger a rebase of this PR by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

Note
Automatic rebases have been disabled on this pull request as it has been open for over 30 days.