v0.32.1

v0.32.1#

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

Contributors#

Thanks to everyone who contributed to this release:

@erikbjare, @TimeToBuildBob

Changelog#

Changes since v0.32.0:

📦 gptme#

✨ Features (27)#

  • feat(webui): warn on server API incompatibility (#3271) (6c5c979b7)

  • feat(context): expose initial prompt to context_cmd (#3270) (47c30c14c)

  • 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 (35)#

Click to expand

  • fix(acp): advertise authMethods in initialize response for ACP registry (#3274) (5d16f2dce)

  • fix(llm): capture usage tokens from subscription response.done events (#3273) (a3ea7fdc5)

  • fix(test): kill the leaked-thread teardown race class (moving “dictionary changed size during iteration” flake) (#3257) (0c8a90891)

  • fix(security): replace last bare ‘git’ subprocess call in tasks_api.py with GIT_CMD (#3269) (3e5147f4a)

  • fix(security): extend GIT_CMD hardening to all remaining bare git subprocess call sites (#3267) (36ce99eb0)

  • fix(logmanager): don’t merge adjacent tool-result system messages (#3268) (5be4ccf03)

  • 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 (e196475ee)

  • 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: https://github.com/gptme/gptme/compare/v0.32.0…v0.32.1

Contents