github gptme/gptme v0.32.1.dev20260716

pre-release3 hours ago

These are the release notes for gptme version v0.32.1.dev20260716.

Contributors

Thanks to everyone who contributed to this release:

@ErikBjare, @TimeToBuildBob

Changelog

Changes since v0.32.0:

📦 gptme

✨ Features (25)

  • feat(webui): add BranchMapPanel to right sidebar (#3264) (ab4ae0950)
  • feat(subagent): cooperative cancel checkpoint — make cancel actually stop thread-mode subagents (#3261) (9acd22a61)
  • feat(subagent): stop thread agents at control checkpoints (#3262) (808c1af76)
  • feat(subagent): add max_concurrent fleet cap to subagent_parallel() (#3222) (6eda8b7d4)
  • feat(anti-slop): add LLM-slop detector and quality gate CLI (#3245) (55bc30398)
  • feat(llm): stream idle-timeout retry + env overrides for subscription streaming (#3248) (6ee57a509)
  • feat(skills): surface reputation badges in webui (#3241) (9c3649e19)
  • feat(profiles): add dynamic web interaction functions to computer-use and browser-use profiles (#3237) (d988b3053)
  • feat(security): add --injection-hygiene CLI flag; screen local file reads (#3218) (bda4c1a3f)
  • feat(prompts): add brief response mode (#3230) (d9be279cf)
  • feat(subagent): add SubagentBudget for fleet-wide token budget coordination (#3198) (42e53289d)
  • feat(tauri): add GPTME_SERVER_PORT env var to override default port (#3220) (7cd71f406)
  • feat(gptme-util): add chats fork for point-in-time session forking (#3209) (8903a783d)
  • feat(context): proactive context-window summarization before hard limit (#3203) (75bd94ae7)
  • feat(webui): show external sessions in chat sidebar (#3219) (c20cd200f)
  • feat(security): extend injection screening — shell/mcp coverage, block mode, JSONL logging (#3215) (e47142bca)
  • feat(subagent): worktree isolation string API + smart cleanup (#3200) (1541032f3)
  • feat(tauri): add auto-updater for desktop app (#3197) (7969b1cd4)
  • feat(computer): add triple_click action and fill_native helper for native field filling (#3201) (434167ef0)
  • feat(ci): weekly check for stale OpenRouter model IDs (#3204) (b16c492ad)
  • feat(subagent): cancel_on_failure — cancel the fleet when a sibling fails (#3199) (214ecfdd9)
  • feat(cli): compact log output for user-facing CLIs (#3195) (94122d68d)
  • feat(tui): add Textual-based TUI (gptme-tui) (#3188) (c0abe9c67)
  • feat(ci): add mypy type coverage reporting to Codecov (#3189) (ac1515739)
  • feat(cli): add gear autonomy presets (#3180) (bfdcef7db)

🐛 Fixes (29)

Click to expand

  • fix(security): harden bare git subprocess resolution on native Windows (#3266) (eb4be1ad1)
  • fix(subagent): eliminate cancel status race — set result before writing control file (#3263) (39881fba8)
  • fix(webui): latch demo mode so SPA URL rewrites can't split demo state (#3252) (16d29171c)
  • fix(subagent): stop orphaned subagents at parent session end via SESSION_END hook (#3260) (3e13dd38e)
  • fix(test): suppress pytest-retry StashKey teardown errors (#3256) (e4642b529)
  • fix(test): stop ACP health-monitor thread leaks and SessionManager dict-mutation races (#3254) (4018ea10d)
  • fix(webui): keep offline demo active across navigation (#3249) (dd2ebcf1e)
  • fix(test): replace slow_stream timing hack with deterministic gate in TUI queue test (#3255) (d8744f3fb)
  • fix(security): redact secrets in GET /api/v2/user/config-file response (#3246) (f743b340a)
  • fix(llm): increase subscription stream timeout for reasoning models (#3247) (1424aa62f)
  • fix(models): add gpt-5.6-sol to the openai-subscription registry (#3243) (a11e48f38)
  • fix(webui): degrade gracefully when older gptme-server returns 404 for newer api/v2 routes (#3235) (731e3d0bc)
  • fix(webui): use dvh units for mobile browser URL bar compatibility (#3240) (77b145e87)
  • fix(chats): copy files/attachments dirs on fork + validate at-turn range (cf1987415)
  • fix(webui): hide Local preset server in embedded/hosted mode (#3231) (8c0610d81)
  • fix(deps): update code for acp 0.11.0 and openai 2.45.0 breaking changes (#3228) (ce90c0e8e)
  • fix(computer): capture pre-action baseline on native xdotool path in act_and_observe (#3221) (1494b7dbc)
  • fix: resolve cache_tokens test failures for openai 2.45.0 and acp 0.11.0 (#3229) (fc47d6b41)
  • fix(ci): add overwrite: true to tauri release artifact uploads (#3227) (03d497dc3)
  • fix(tauri): sync webui to managed server port (#3223) (a8c795bd8)
  • fix(tokens): graceful tiktoken fallback for local/airgapped endpoints (#3205) (b9a2a135b)
  • fix(tauri): bundle matching libgpg-error in AppImage (#3211) (98675dfe6)
  • fix(tests): replace duckduckgo.com URL in test_fill_element with local fixture (#3214) (f3ae0573e)
  • fix(computer): lower wait_for_change threshold to 0.2% to detect small screen changes (#3210) (bf1b29e8e)
  • fix(tauri): add GPTME_DISABLE_AUTO_UPDATE env var to opt out of update check (#3208) (46002270e)
  • fix(test): mock _monitor_subprocess in subprocess tests to fix flaky is_alive assertion (#3196) (6ae6ec759)
  • fix(release): drop duplicate version heading from GitHub release bodies (#3185) (0c3af2ed3)
  • fix(ci): name Android release assets like desktop bundles (#3186) (e2a8113f2)
  • fix(ci): stop tauri-action overwriting release changelogs (#3184) (e6831ece4)

🔨 Misc (10)

Click to expand

  • chore: bump version to 0.32.1.dev20260716 (8ca37f82d)
  • docs(subagent): document SubagentBudget and max_concurrent in tool instructions (#3251) (ed3b6b336)
  • test(computer): add missing error-path coverage for _measure_terminal_startup (#3244) (25b2537cf)
  • test(computer): add --terminal flag coverage for latency cmd (#3242) (c1fdd6c30)
  • revert(prompts): revert brief response mode (#3230) (#3234) (a4074c0d0)
  • docs(computer): add Background section linking to origin conversation (#216) (#3207) (330fbc5e6)
  • chore(deps): bump rich to 14.x and textual to 8.x (#3202) (55a7cc712)
  • docs: add local-models guide (Ollama, Groq, vLLM) (#3178) (104dec4fb)
  • chore: update changelog_contributors caches (386a33b1a)
  • perf: cut startup time ~6x by deferring heavy imports (#3193) (613fed71b)

(excluded 4 less relevant commits)

Full Changelog: v0.32.0...v0.32.1.dev20260716

Don't miss a new gptme release

NewReleases is sending notifications on new releases.