deps(deps-dev): bump the npm-development-dependencies group with 4 updates

[dependabot]

Bumps the npm-development-dependencies group with 4 updates: @earendil-works/pi-ai, @earendil-works/pi-coding-agent, eslint and typescript.

Updates @earendil-works/pi-ai from 0.80.3 to 0.80.6

Release notes

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

v0.80.6

New Features

• max thinking level - New opt-in thinking level above xhigh, natively supported on GPT-5.6 and adaptive Claude models, available across CLI (--thinking max), SDK, RPC, and model selection. Custom themes can define thinkingMax. See CLI Reference.
• Input-based pricing tiers - Request-wide input-token pricing tiers for accurate long-context cost accounting (e.g. GPT-5.4/5.5/5.6 long-context rates), also configurable for custom models in models.json and modelOverrides. See Model Configuration.

Added

• Added the opt-in max thinking level across CLI, SDK, RPC, model selection, and themes. Custom themes can define thinkingMax; existing themes fall back to thinkingXhigh.
• Added request-wide input-token pricing tiers to custom model costs in models.json, modelOverrides, and extension-registered providers.
• Added ~ (home directory) expansion for the shellPath setting (#6470 by @​aaronkyriesenbach).

Fixed

• Fixed inherited post-compaction output-token budgeting to ignore stale assistant usage from before the compaction boundary (#6464).
• Fixed inherited GPT-5.4 and GPT-5.5 long-context cost accounting while retaining the intentional 272K default context limit for models that require an explicit override.
• Fixed inherited GPT-5.6 metadata to keep direct OpenAI requests in the 272K short-context tier while exposing the Codex backend's 372K context window with long-context pricing, and removed the nonexistent bare gpt-5.6 alias.
• Fixed inherited Anthropic message conversion to preserve thinking blocks with empty thinking text but a valid signature instead of dropping them, avoiding thinking-block errors on newer Claude models (#6457 by @​davidbrai).

v0.80.5

Release 0.80.5

Changelog

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

[0.80.6] - 2026-07-09

Added

• Added a separate opt-in max thinking level, including native xhigh and max support for GPT-5.6 and Anthropic adaptive-thinking effort metadata matching Anthropic's documentation: max on all adaptive Claude models, native xhigh on Opus 4.7/4.8, Sonnet 5, and Fable 5 only.
• Added request-wide input-token pricing tiers to model cost metadata and usage cost calculation.

Fixed

• Fixed post-compaction output-token budgeting to ignore stale assistant usage from before the compaction boundary (#6464).
• Fixed GPT-5.4 and GPT-5.5 long-context cost accounting while retaining the intentional 272K default context limit for models that require an explicit override.
• Fixed GPT-5.6 metadata to keep direct OpenAI requests in the 272K short-context tier while exposing the Codex backend's 372K context window with long-context pricing, and removed the nonexistent bare gpt-5.6 alias from the OpenAI and Azure OpenAI Responses catalogs.
• Fixed Anthropic message conversion to preserve thinking blocks with empty thinking text but a valid signature instead of dropping them, avoiding thinking-block errors on newer Claude models (#6457 by @​davidbrai).

[0.80.5] - 2026-07-09

[0.80.4] - 2026-07-09

Fixed

• Fixed retry classification for gRPC ResourceExhausted provider errors such as NVIDIA NIM transient exhaustion responses (#6449 by @​davidbrai).
• Fixed low-level message transformation to normalize null message content before provider conversion, avoiding crashes on lax imported transcripts (#6343).
• Fixed Xiaomi Token Plan model metadata to follow the upstream models.dev token-plan catalogs, removing unsupported mimo-v2-omni variants (#6204).
• Fixed GitHub Copilot device-code login polling to wait before the first token poll, avoiding incorrect device-code failures for some users after browser authorization (#6187).
• Fixed OAuth device-code polling to honor the server-provided slow_down interval instead of only applying the RFC 8628 5-second increment, so GitHub Copilot login recovers instead of appearing to hang when polls arrive early (e.g. WSL/VM clock drift) (#6187).
• Fixed OpenAI Codex user-agent construction to synchronously load Node OS metadata, avoiding a startup race that could report pi (browser) in Node/Bun.
• Fixed Fireworks GLM 5.2 Fast to use the OpenAI-compatible endpoint and thinkingLevelMap, aligning it with GLM 5.2 (#6195).
• Fixed Amazon Bedrock prompt-cache points for Claude Fable 5 and Claude Sonnet 5 (#6235).
• Fixed Amazon Bedrock Claude 5 prompt-cache pricing metadata by removing stale fallback overrides.
• Fixed DS4 server context overflow detection for Prompt has ... tokens, but the configured context size is ... tokens errors (#6262).
• Fixed OpenAI Codex WebSocket sessions to rotate cached connections before the backend's 60-minute limit, avoiding connection-limit failures on long sessions (#6268).
• Fixed Cloudflare Workers AI / AI Gateway auth to fall back to the ambient CLOUDFLARE_ACCOUNT_ID (and CLOUDFLARE_GATEWAY_ID) when the stored credential carries only the API key, so /login-style key-only credentials no longer leave the {CLOUDFLARE_ACCOUNT_ID} placeholder unresolved and return 404 (#6021).
• Fixed OpenAI Completions and Responses providers to send (no tool output) instead of (see attached image) when a tool result has empty text and no image content, preventing the model from hallucinating image attachments.
• Fixed OpenAI Responses and Azure OpenAI Responses requests to avoid sending max_output_tokens values below the provider minimum (#6265).
• Fixed retry classification for Cloudflare 524 timeout responses (#6239).
• Fixed retry classification for Bun fetch socket-drop errors such as socket connection was closed, so transient stream disconnects retry automatically (#6431).
• Fixed GitHub Copilot extended context window models (Claude Opus 4.7/4.8, Claude Opus 4.6, Claude Sonnet 4.6/5, Claude Fable 5, GPT-5.3 Codex, GPT-5.4, GPT-5.5) to use contextWindow: 1000000, preventing premature compaction and under-budgeting (#6439).

Added

• Added OpenAI GPT-5.6 model metadata for gpt-5.6, gpt-5.6-sol, gpt-5.6-terra, and gpt-5.6-luna, plus verified openai-codex support for gpt-5.6-sol, gpt-5.6-terra, and gpt-5.6-luna.
• Refreshed generated model catalogs from models.dev, adding newly listed models including Kimi K2.7 Code for GitHub Copilot and Fable 5 to several providers (#6256).
• Added Claude Sonnet 5 to the GitHub Copilot model catalog (#6200).
• Added zstd request-body compression for the OpenAI Codex Responses SSE transport. Requests are sent with Content-Encoding: zstd when Node/Bun zstd support is available; the WebSocket transport is unchanged.

Commits

• 2b3fda9 Release v0.80.6
• 5b4bda3 fix(ai): refresh generated model catalogs
• 1775fe4 docs: audit unreleased changelogs
• 3387465 fix(ai): isolate service-tier pricing test
• 6731a0b fix: send anthropic thinking blocks also when thinking text is empty (#6457)
• 3664806 fix(ai): add GPT-5.4 and GPT-5.5 long-context pricing
• a9ecf30 feat(ai): add input-based pricing tiers
• 6c735db fix(ai): exclude nonexistent GPT-5.6 alias
• fbdd463 feat(ai): add max thinking level
• 8973ae2 fix(ai): ignore stale usage after compaction
• Additional commits viewable in compare view

Updates @earendil-works/pi-coding-agent from 0.80.3 to 0.80.6

Release notes

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

v0.80.6

New Features

• max thinking level - New opt-in thinking level above xhigh, natively supported on GPT-5.6 and adaptive Claude models, available across CLI (--thinking max), SDK, RPC, and model selection. Custom themes can define thinkingMax. See CLI Reference.
• Input-based pricing tiers - Request-wide input-token pricing tiers for accurate long-context cost accounting (e.g. GPT-5.4/5.5/5.6 long-context rates), also configurable for custom models in models.json and modelOverrides. See Model Configuration.

Added

• Added the opt-in max thinking level across CLI, SDK, RPC, model selection, and themes. Custom themes can define thinkingMax; existing themes fall back to thinkingXhigh.
• Added request-wide input-token pricing tiers to custom model costs in models.json, modelOverrides, and extension-registered providers.
• Added ~ (home directory) expansion for the shellPath setting (#6470 by @​aaronkyriesenbach).

Fixed

• Fixed inherited post-compaction output-token budgeting to ignore stale assistant usage from before the compaction boundary (#6464).
• Fixed inherited GPT-5.4 and GPT-5.5 long-context cost accounting while retaining the intentional 272K default context limit for models that require an explicit override.
• Fixed inherited GPT-5.6 metadata to keep direct OpenAI requests in the 272K short-context tier while exposing the Codex backend's 372K context window with long-context pricing, and removed the nonexistent bare gpt-5.6 alias.
• Fixed inherited Anthropic message conversion to preserve thinking blocks with empty thinking text but a valid signature instead of dropping them, avoiding thinking-block errors on newer Claude models (#6457 by @​davidbrai).

v0.80.5

Release 0.80.5

Changelog

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

[0.80.6] - 2026-07-09

New Features

• max thinking level - New opt-in thinking level above xhigh, natively supported on GPT-5.6 and adaptive Claude models, available across CLI (--thinking max), SDK, RPC, and model selection. Custom themes can define thinkingMax. See CLI Reference.
• Input-based pricing tiers - Request-wide input-token pricing tiers for accurate long-context cost accounting (e.g. GPT-5.4/5.5/5.6 long-context rates), also configurable for custom models in models.json and modelOverrides. See Model Configuration.

Added

• Added the opt-in max thinking level across CLI, SDK, RPC, model selection, and themes. Custom themes can define thinkingMax; existing themes fall back to thinkingXhigh.
• Added request-wide input-token pricing tiers to custom model costs in models.json, modelOverrides, and extension-registered providers.
• Added ~ (home directory) expansion for the shellPath setting (#6470 by @​aaronkyriesenbach).

Fixed

• Fixed inherited post-compaction output-token budgeting to ignore stale assistant usage from before the compaction boundary (#6464).
• Fixed inherited GPT-5.4 and GPT-5.5 long-context cost accounting while retaining the intentional 272K default context limit for models that require an explicit override.
• Fixed inherited GPT-5.6 metadata to keep direct OpenAI requests in the 272K short-context tier while exposing the Codex backend's 372K context window with long-context pricing, and removed the nonexistent bare gpt-5.6 alias.
• Fixed inherited Anthropic message conversion to preserve thinking blocks with empty thinking text but a valid signature instead of dropping them, avoiding thinking-block errors on newer Claude models (#6457 by @​davidbrai).

[0.80.5] - 2026-07-09

[0.80.4] - 2026-07-09

New Features

• Prompt cache miss visibility - Significant cache misses can be shown in transcripts via showCacheMissNotices. See Model & Thinking.
• Project-local resource configuration - pi config -l and Tab switching manage global vs project-local package resources. See Enable and Disable Resources.
• Extension lifecycle and provider hooks - Extensions get agent_settled, before_provider_headers, entry renderers, and InlineExtension. See agent_start / agent_end / agent_settled, before_provider_headers, and InlineExtension.
• New inherited model and transport support - GPT-5.6 metadata, Copilot Claude Sonnet 5, and zstd Codex SSE transport are available through inherited provider support. See Providers and Model Options.

Added

• Added inherited OpenAI GPT-5.6 model metadata for gpt-5.6, gpt-5.6-sol, gpt-5.6-terra, and gpt-5.6-luna, plus verified openai-codex support for gpt-5.6-sol, gpt-5.6-terra, and gpt-5.6-luna.
• Added inherited Claude Sonnet 5 to the GitHub Copilot model catalog (#6200).
• Added inherited zstd request-body compression for the OpenAI Codex Responses SSE transport.
• Added /login <provider> support with provider autocomplete.
• Added public SDK exports for CLI-equivalent model and scoped-model resolution (#6201).
• Added extension and RPC agent_settled events plus session-level idle waiting for fully settled agent runs (#6363).
• Added before_provider_headers extension hook support for injecting provider request headers (#6350 by @​pmateusz).
• Added an InlineExtension type for named inline extension factories (#6267 by @​any-victor).
• Added extension entry renderers for persisted display-only session entries that are rendered in interactive mode without being sent to the model context.
• Added project-local resource override management to pi config, including project mode startup with pi config -l and Tab switching between global and project scopes (#6309).
• Added inherited InMemorySessionStorage and JsonlSessionStorage exports from the agent harness (#6435).
• Added inherited custom metadata support in JSONL session headers (#6417 by @​ArcadiaLin).
• Added a showCacheMissNotices setting and /settings toggle for significant prompt-cache miss transcript notices.

Fixed

• Fixed inherited retry classification for gRPC ResourceExhausted provider errors such as NVIDIA NIM transient exhaustion responses (#6449 by @​davidbrai).

... (truncated)

Commits

• 2b3fda9 Release v0.80.6
• 1775fe4 docs: audit unreleased changelogs
• 1a2542b feat(coding-agent): expand ~ in shellPath setting (#6470)
• a9ecf30 feat(ai): add input-based pricing tiers
• fbdd463 feat(ai): add max thinking level
• e351319 Add [Unreleased] section for next cycle
• cc62baa Release v0.80.5
• a98778e test(coding-agent): fix interactive mode fixture
• ef793a9 Add [Unreleased] section for next cycle
• 912d095 Release v0.80.4
• Additional commits viewable in compare view

Updates eslint from 10.6.0 to 10.7.0

Release notes

Sourced from eslint's releases.

v10.7.0

Features

• cf2a9bf feat: add errorClassNames option to preserve-caught-error rule (#21032) (sethamus)
• f8b873a feat: max-nested-callbacks option for constructor callbacks (#21063) (fnx)
• 557fde8 feat: support computed Number.parseInt member access in radix rule (#21041) (Pixel)
• 0b4a73b feat: add suggestions to no-compare-neg-zero (#21034) (den$)
• 96cdd42 feat: report invalid signed numeric radix values in radix rule (#21030) (Pixel)

Bug Fixes

• 3e7bf15 fix: apply ignoreClassesWithImplements to class expressions (#21069) (Pixel)
• 0d7d70c fix: insert cause outside wrapping parens in preserve-caught-error (#21062) (Mahin Anowar)
• 75ec753 fix: handle static template literals in eqeqeq rule (#21058) (Pixel)
• b717a22 fix: prevent eqeqeq null option from reporting non-equality operators (#21057) (Pixel)
• e35b05f fix: avoid no-invalid-regexp false positive for shadowed RegExp (#21051) (Pixel)
• a3172b6 fix: avoid no-control-regex false positive for shadowed RegExp (#21050) (Pixel)
• d1f637e fix: parenthesize sequence expression operands in no-implicit-coercion (#21045) (spokodev)
• 8859baf fix: avoid prefer-numeric-literals false positive for shadowed globals (#21047) (한국)
• a9e5961 fix: use-isnan false positive on shadowed NaN/Number (#20958) (sethamus)
• 8a240a7 fix: avoid false positives in radix rule for spread arguments (#21044) (Pixel)

Documentation

• c30d808 docs: Update README (GitHub Actions Bot)
• 5139800 docs: document ESLint migration codemods in v9 and v10 guides (#20980) (Alex Bit)
• 04174cb docs: Update README (GitHub Actions Bot)
• 026e130 docs: update semver policy for bug fixes (#21048) (Milos Djermanovic)
• 9d42fef docs: Update README (GitHub Actions Bot)
• b230159 docs: Update README (GitHub Actions Bot)
• 0129972 docs: correct **/.js glob to **/*.js in config files guide (#21036) (EduardF1)

Chores

• 9489379 chore: update dependency @​eslint/eslintrc to ^3.3.6 (#21076) (renovate[bot])
• 81a4774 chore: updates for v9.39.5 release (Jenkins)
• 9835414 chore: enable $ExpectType annotations in all TypeScript files (#21071) (Francesco Trotta)
• 72adf6b chore: restrict markdownlint-cli2 updates in renovate (#21067) (lumir)
• 833ec10 chore: update dependency prettier to v3.9.4 (#21061) (renovate[bot])
• 7ea106d chore: update ecosystem plugins (#21059) (ESLint Bot)
• 8fb550e chore: add prettier update commit to .git-blame-ignore-revs (#21056) (lumir)
• e4e1166 chore: update dependency prettier to v3.9.1 (#21055) (renovate[bot])
• 0493f53 chore: update prettier to v3.9.0 (#21054) (Pixel)
• 1056a99 chore: update dependency prettier to v3.8.5 (#21049) (renovate[bot])
• 4d4155d ci: run ecosystem tests on pull requests (#21027) (sethamus)
• 993539f chore: update dependency @​eslint/json to ^2.0.1 (#21042) (renovate[bot])
• 53f8b69 test: add error locations to no-constant-binary-expression (#21039) (lumir)
• 5ab71d5 refactor: clean up radix rule internals (#21015) (Pixel)
• a80a9a4 chore: update ecosystem plugins (#21035) (ESLint Bot)
• 7c9a029 ci: add Node.js 26 to CI (#20847) (lumir)

Commits

• fabd99b 10.7.0
• 37c5e75 Build: changelog update for 10.7.0
• 9489379 chore: update dependency @​eslint/eslintrc to ^3.3.6 (#21076)
• 81a4774 chore: updates for v9.39.5 release
• 3e7bf15 fix: apply ignoreClassesWithImplements to class expressions (#21069)
• 9835414 chore: enable $ExpectType annotations in all TypeScript files (#21071)
• cf2a9bf feat: add errorClassNames option to preserve-caught-error rule (#21032)
• c30d808 docs: Update README
• f8b873a feat: max-nested-callbacks option for constructor callbacks (#21063)
• 72adf6b chore: restrict markdownlint-cli2 updates in renovate (#21067)
• Additional commits viewable in compare view

Updates typescript from 6.0.3 to 7.0.2

Commits

• See full diff in compare view

Maintainer changes

This version was pushed to npm by microsoft1es, a new releaser for typescript since your current version.

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually 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 <dependency name> major version will close this group update PR and stop Dependabot creating any more for the specific dependency's major version (unless you unignore this specific dependency's major version or upgrade to it yourself)
• @dependabot ignore <dependency name> minor version will close this group update PR and stop Dependabot creating any more for the specific dependency's minor version (unless you unignore this specific dependency's minor version or upgrade to it yourself)
• @dependabot ignore <dependency name> will close this group update PR and stop Dependabot creating any more for the specific dependency (unless you unignore this specific dependency or upgrade to it yourself)
• @dependabot unignore <dependency name> will remove all of the ignore conditions of the specified dependency
• @dependabot unignore <dependency name> <ignore condition> will remove the ignore condition of the specified dependency and ignore conditions

[dependabot]

Labels

The following labels could not be found: dependencies, npm. Please create them before Dependabot can add them to a pull request.

Please fix the above issues or remove invalid values from dependabot.yml.