chore(deps): update docker

[bootc-bot]

This PR contains the following updates:

Package	Update	Change
astral-sh/uv	patch	0.12.5 → 0.12.9
block/goose	minor	v1.47.0 → v1.48.0
rust-nightly	patch	nightly-2026-08-24 → nightly-2026-09-01

---

Release Notes

astral-sh/uv (astral-sh/uv)

v0.12.9

Compare Source

Released on 2026-09-01.

Python

• Add CPython 3.15.0rc2 (#​21413, #​21415)

Enhancements

• Add --no-locked and --no-frozen to disable lock modes enabled by UV_LOCKED and UV_FROZEN for a single invocation (#​21408)
• Report the exact command-line lock-mode flag in warnings and errors (#​21402)

Performance

• Speed up cold wheel installs by extracting each streaming ZIP archive in a single blocking task and reusing buffers across files (#​21372)

Bug fixes

• Update async_http_range_reader to 0.11.1 to address a potential memory-safety issue when reading metadata ranges from untrusted wheels (#​21401)
• Remove sensitive headers when redirects cross authentication realms, including same-host redirects that change URL schemes (#​21382)
• Redact secrets in signed URLs from retry diagnostics, including nested request errors (#​21381)
• Give --locked, --frozen, --check, and --check-exists precedence over conflicting UV_LOCKED and UV_FROZEN values (#​21396)
• Prevent concurrent uv processes from redundantly extracting the same local or source-built wheel (#​21400)

v0.12.8

Compare Source

Released on 2026-08-31.

Enhancements

• Warn about invalid tool directories and continue upgrading valid tools with uv tool upgrade --all (#​21368)

Preview features

• Deduplicate identical files within and across cached wheels with the content-addressed-cache preview feature (#​21327)
• Reduce allocations while extracting content-addressed wheels by reusing the hashing buffer across files (#​21340)
• Speed up content-addressed cache cleanup on macOS by reading hard-link counts in bulk (#​21344)

Performance

• Prevent concurrent uv processes from downloading and extracting the same remote wheel more than once (#​21379)
• Speed up dependency graph construction from large lockfiles by indexing packages during traversal (#​21373)
• Extend indexed lockfile traversal to exports, dependency trees, audits, and freshness checks (#​21377)
• Speed up warm resolutions by reducing repeated marker interner work (#​21300)

Bug fixes

• Do not trust hashes from direct URLs discovered only in wheel metadata when installing with --require-hashes (#​21348)
• Use a compatible Azure Storage API version for anonymous and authenticated requests, allowing credential retries when public access is disabled (#​21366)
• Redact Azure shared access signature (sig) query parameters from displayed URLs (#​21360)
• Treat projects below one-level workspace member globs as standalone instead of aborting workspace discovery (#​21341)

Other changes

• Update astral-tokio-tar to 0.7.0 and use effective sizes when tracking extracted hard links (#​21346)

v0.12.7

Compare Source

Released on 2026-08-27.

Python

• Replace managed Python installations when upgrading to a newer build of the same version (#​21323)

Enhancements

• Support Linux s390x, ppc64le, and loongarch64 targets for cross-platform dependency resolution (#​21313)
• Retry downloads with configured credentials when Azure Storage denies anonymous access to an endpoint configured via UV_AZURE_ENDPOINT_URL (#​21318)

Preview features

• Use content-based directory hashes to deduplicate extracted wheels in the cache with the content-addressed-cache preview feature (#​19693)

Bug fixes

• Reject source archives with hash mismatches before persisting their extracted contents to the cache (#​21248)

Other changes

• remove pyx specific features (#​21182, #​21183, #​21184, #​21185, #​21186)

v0.12.6

Compare Source

Released on 2026-08-25.

Python

• Update CPython to use OpenSSL 3.5.8 and libffi 3.4.8 #​21295)

Enhancements

• Report cache-cleaning space savings from filesystem block allocation and avoid double-counting hard links (#​21261)
• Limit warnings about unbounded uv_build requirements to source-distribution builds (#​21078)
• Display byte counts below 1 KiB without a fractional part (#​21237)

Preview features

• Add uv workspace metadata --sync --exact to remove packages outside the selected resolution (#​21117)
• Add the artifact-hash-filtering preview feature to make uv pip compile --generate-hashes honor --only-binary and --no-binary (#​21235)
• Respect package-specific exclude-newer cutoffs when uv check selects its ty executable (#​21227)
• Preserve virtual-environment hints from tar-codec source-distribution errors when the base interpreter is outside a bin directory (#​21146)

Performance

• Enable profile-guided optimization for Linux x86-64 release binaries (#​21001)
• Enable profile-guided optimization for Windows x86-64 release binaries (#​21003)
• Enable profile-guided optimization for macOS ARM64 release binaries (#​21002)
• Enable profile-guided optimization for Linux ARM64 release binaries (#​21004)
• Speed up syncing projects with many activated conflict items by reusing their encoded representation (#​21148)

Bug fixes

• Allow explicit uv build and non-editable first-party workspace packages when no-build is enabled (#​21294)
• Reuse configured index credentials during uv tool upgrade when the tool receipt references the same index (#​21275)
• Ensure full 40-character Git commit pins resolve to the requested object instead of a SHA-named branch (#​21224)
• Prevent TLS segfaults in riscv64 musl release binaries (#​21158)
• Preserve dependencies selected by recursive extras when markers mix production and extra conditions (#​21181)
• Preserve version constraints from transitively referenced recursive extras (#​21209)
• Resolve repository-relative Git archive dependencies inside the checkout during the initial uv sync (#​21264)
• Return an error instead of panicking when a bearer token cannot be encoded as an HTTP header (#​21282)
• Do not misclassify package URLs ending in .py as local script paths (#​21144)
• Use directory creation times consistently across libc implementations for directory cache-keys entries (#​21137)
• Promote human-readable sizes to the next unit at rounding boundaries (#​21136)

Other changes

• Add Python 3.15 release-candidate Docker images (#​21293)
• Raise the minimum supported Rust version to 1.96 and update the repository toolchain to Rust 1.98 (#​21258)

block/goose (block/goose)

v1.48.0

Compare Source

✨ Features

Providers

• TrustedRouter declarative provider #​11422
• OpenCode Zen gateway as a declarative provider #​10939
• Gondola as declarative OpenAI-compatible provider #​11421
• SayGM as declarative OpenAI-compatible provider #​11267
• Lynkr as a declarative OpenAI-compatible provider #​11372
• PleumRouter declarative provider #​10479
• Z.ai GLM-5.2 replaced with GLM-5.3 #​11226
• Custom provider cost fields drive cost tracking #​11220
• Model-native audio transcription provider #​10589
• OpenAI GPT-5.6 (sol/terra/luna) routing via AWS Bedrock #​10502
• GPT-5.6 follow-up support for Codex and Responses API #​10460

Hooks

• on_failure block for PreToolUse hooks #​11449
• PreToolUseResult event and stable tool_call_id across tool lifecycle #​11120

Desktop & UI

• Select saved recipes when creating a schedule #​10892
• Sort configured providers to the top of the provider list #​11409
• Collapse scheduled job sessions into accordion in chat history #​11265
• Auto-focus chat input when user starts typing #​11184
• Interactive git branch indicator in chat bottom bar #​11290
• Show recent used models in chat footer model picker #​11097

CLI

• --with-extension can now name its extension #​11127
• /new command to start a fresh session without restarting #​10767

Skills & Extensions

• Web-search and browser-use built-in skills #​11233
• Support pre-registered OAuth clients for streamable_http extensions #​11182

ACP

• Derive and forward thinking effort from the ACP harness #​10949
• Title new sessions from _meta.sessionTitle #​10712
• _goose/unstable/session/extensions/apply method #​11081

Observability

• OpenTelemetry request params, response metadata, tool call parity, and agent identification #​11261
• OpenRouter session_id forwarding and app category header #​10868

Other

• Blox run target for the ACP server #​11423
• Linux ARM64 desktop release packages #​11518
• Roaming as opt-in goose-cli feature #​11516
• MCP conformance tests in CI #​10940

🐛 Bug Fixes

Security

• Recognize Windows package runners #​11466
• Fail closed on malformed tool visibility #​11474
• Permission denies take precedence #​11477
• Clear custom provider transition secrets #​11467
• Require fresh file parameter input #​11455
• Escape OAuth callback content #​11479
• Sanitize Unicode tags in MCP prompts #​11453
• Honor plugin enablement for skills #​11439
• Honor MCP tool model visibility in Code Mode #​11425
• Suppress sensitive OTLP traces #​11381
• Fail closed on invalid default GCP credentials #​11363
• Bound call graph traversal #​11193
• Fail closed on invalid Codex ACP mode #​11362
• Validate memory categories #​11191
• Bound recursive mention scans #​11228
• Avoid predictable editor symlink #​11188
• Fail closed on malformed app visibility #​11341
• Encode session navigation parameters #​11232
• Redact URLs in provider errors #​11230
• Validate recipe parameter values #​11234
• Bind Foundry API keys to request origin #​11347

Providers

• Stop provider save from overwriting stored config with defaults #​11517
• Sanitize hidden Unicode in Bedrock tools #​11121
• Bound non-streaming JSON responses #​11109
• Inform user of clipboard copy and remove copilot auth retry on timeout #​11160
• Escape Gemini tool response ref keys in OpenRouter #​11276
• Estimate cost for Azure Foundry models via inferred catalog pricing #​11264
• Coalesce consecutive Thinking blocks in collect_stream #​11317
• Replace flat model list with routing table, add Gemma 4 Mantle support #​10297
• Include thinking tokens in Google usage output_tokens #​10354
• Send explicit thinking disabled to adaptive Claude models #​11177
• Include required annotations field on replayed output_text items #​11263
• Deprecated Gemini OAuth provider #​11223
• Stop paying the prompt-cache write premium on one-shot fast-model calls #​11179
• Classify byte-size request limit errors as context-length-exceeded #​11173
• Bound local image reads #​11114
• Map kimi_code provider name and pass correct provider to create_request #​11130
• Handle error code for context length exceeded #​11283
• DeepSeek and Alibaba compatibility with OpenAI responses API #​11298

Desktop & UI

• Honor remote working directory for new chats and allow typed paths #​11322
• Scope app events by extension #​11486
• Pin renderer ACP certificates #​11485
• Bind ACP permissions to request generations #​11415
• Chat input freeze after opening model picker #​11525
• Gate external URL protocols centrally #​11311
• Stop stale microphone test streams #​11309
• Prevent recipe parameter form from reloading the app on Enter #​10522
• Suppress extension loading toast when all extensions succeed #​11016

CLI & Shell

• Reject cmd.exe commands containing newlines #​11537
• Refuse symlink diagnostics outputs #​11398
• Deduplicate enabled builtins #​11340
• Avoid reading file params in recipe explain #​11119
• Honor provider overrides on session resume #​10810

Core

• Deduplicate parallel tool-pair summaries #​11195
• Exclude Git metadata from project hints #​11148
• Avoid sending images to non-vision capable models #​11496
• Keep recalled history agent-visible #​11490
• Honest compaction failure message and fast-fail when no tool responses exist #​10500
• Pass complete response to stop hooks #​11366
• Contain and bound skill supporting file reads #​11342
• Compact with the main session model, not the fast model #​11255
• Make Gemini plugin installs transactional #​11303
• Include working directory in stop hook context #​11112
• Re-enable minijinja builtins so documented recipe filters work #​11310
• Show tool inputs before approval #​10932
• Reject context commands for context-owning providers #​11094
• Bind deeplink recipe parameters to startup session #​11123

ACP

• Restrict project updates to visible sessions #​11487
• Seed provider handoff history #​8941
• Preserve tool result audience metadata #​11375
• Bound the handoff memo so long sessions stay resumable #​11204
• Return auth error for ACP provider from goose ACP server #​11202
• Ignore ACP provider generated title and use goose generated title #​11197
• Prevent large-session disconnects #​11159

Recipes

• Confine library writes #​11482
• Reject non-object response schemas #​11478
• Confine temporary extraction cleanup #​11125

Extensions & MCP

• Reject symlinked check sources #​11489
• Reject socket-backed MCP extensions for Codex #​11304
• Keep stdio extensions alive across worker exits #​10364
• Preserve extensions when adding MCP servers #​11339
• Preserve platform tool allowlists #​11369

Other

• Claude-Code: protect system prompt transport #​11441
• Fail fast when a recipe's structured response can't reach an ACP-bridged provider #​11307
• Fetch attestation bundles from bundle_url #​10557
• Contain REVIEW.md discovery #​11367
• Sanitize Pi imported output #​10990
• Honor RUST_LOG directives for OTEL logs #​11360
• Give GOOSE_SUBAGENT_PROVIDER/MODEL priority over LLM-injected params #​9650
• Respect ACP audience in bang-shell shortcut #​11150
• Redact Telegram tokens from request errors #​11343
• Isolate concurrent subagent notifications #​10772
• Serialize secret mutations #​11388
• Enforce secure OAuth token transport #​11183
• Skip local extension spawn when provider manages own context #​11203
• Decouple source file and tool response limits #​11391
• Bound action-required stream admission #​11113
• Bound partial thinking tags #​11108
• Enforce review check tool policy #​11128
• Secure Copilot API endpoint transport #​11129
• Remove goose tui command #​11484
• Update SQLite to 3.51.3 #​11157
• Narrow desktop file read IPC #​11149
• Render visualizer data as text #​11186
• Bound XLSX range reads #​11190

🔧 Improvements

• Session listing performance: limit sessions before counting messages #​11521
• Keep turn-context out of the OpenAI-compatible prefix cache #​10937
• Parallelize provider resolution and eagerly init SQLite pool #​8899
• Deduplicate _goose/providers/list RPC call at startup #​8873
• ACP provider setup and unified setup metadata #​11100
• Disable thinking for tool call labels #​11207
• Canonicalize mangled tool names before permission inspection #​10285
• Gate clear_thinking behind an opt-in flag (Z.AI-only) #​10439
• Scan uvx from selectors for malware #​10988
• Aura dark theme for Goose #​10283
• Unrolled agent loop state machine #​11216
• Generic unrolled loop state machine #​11139
• Retry ACP handoff context after failed prompts #​10660
• Use rmcp ContentBlock in goose-sdk UniFFI #​11210
• Upgrade ACP SDK to 1.3.0 #​11218
• Mergeable configs and cleanup #​8378
• Move mlx deps under macOS for goose-local-inference #​11328
• Share axum-server via workspace.dependencies #​11326
• Remove automation_script, web_scrape, and cache tools from computercontroller #​11198
• Agent provider using explicit type states #​8879

📚 Documentation

• SDK API reference for Rust, Python, and Kotlin #​11251
• Correct Telegram gateway setup #​11527
• Keep GitHub comments concise #​11447
• Improve readability in AGENTS.md #​8979

---

Configuration

📅 Schedule: (in timezone UTC)

• Branch creation
  • "on sunday"
• Automerge
  • At any time (no schedule defined)

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.

👻 Immortal: This PR will be recreated if closed unmerged. Get config help if that's undesired.

---

• If you want to rebase/retry this PR, check this box

---

This PR has been generated by Mend Renovate CLI.