One command to the workbench - nanobot webui prepares the local channel, starts the gateway, opens the browser, and leads first-time users into guided setup.
A stronger browser workbench - Topic-style chats, composer model switching, quoted follow-ups, document attachments, native folder selection, responsive settings, and clearer fallback state.
Agent coordination without core sprawl - Inline subagents can consult inside the active task, authorized work can continue through verification, and typed runtime context keeps provider-owned state out of ad hoc loop logic.
Explicit long-running goals - Sustained execution is gated behind /goal, with clearer permission, cancellation, timeout, heartbeat, and local-trigger behavior.
Files and tool activity you can inspect - Syntax-highlighted previews, live file-edit diffs, better code-copy behavior, structured tool errors, richer MCP artifacts, and preserved multimodal tool output.
A more operational runtime - Live configuration reloads, bounded session and exec state, safer restart/shutdown, cleaner cancellation ownership, more reliable scheduled work, and faster CI.
Broader providers and search - OpenCode Zen/Go, Kimi Coding, Grok OAuth, provider-scoped proxies, Copilot Enterprise overrides, Parallel Search, Serper, and steadier authentication fallback.
Channels as maintainable extensions - Native Neonize WhatsApp, Mattermost, improved Feishu/Telegram/Discord/Matrix/QQ behavior, optional channel dependencies, and clearer setup flows.
Security tightened at the edges - Chained-command allowlist bypasses are blocked, SSRF checks pin validated DNS, credentials are redacted from MCP URLs, remote API binds require authentication, and attachment ingress is constrained.
Documentation and delivery caught up - Workflow-oriented docs, an automation guide, one-click Render deployment, stronger Docker controls, community-maintained project language, and a refreshed SVG identity.

Upgrade Notes

WhatsApp now uses Neonize instead of the old Node.js/Baileys bridge. Remove bridgeUrl and bridgeToken, run nanobot plugins enable whatsapp, and link the account again with nanobot channels login whatsapp. The old bridge authentication data is not reused. allowFrom entries should use the sender ID without a leading +.
Sustained goals are now explicit. Use /goal when a task should keep working across continuation turns. Normal chats no longer inherit long-running goal behavior implicitly.
Remote exposure requires authentication. Configurations that bind the API or WebUI gateway beyond loopback must provide the corresponding API or Web token. Localhost setup continues to use the guided short-lived token flow.

Community

Thank you to everyone who shaped v0.3.0: 260 merged PRs, 38 first-time contributors, and a month of careful review across the agent core, WebUI, providers, channels, security, documentation, and deployment. The Agency Release is not about making nanobot act without limits. It is about giving a small, inspectable agent the coordination, evidence, and operational discipline to finish more of the work you intentionally hand it.

What's Changed

docs: add v0.2.2 release news by @Re-bin in #4461
fix: skip sendRichMessage when streaming preview exists (#4470) by @axelray-dev in #4472
fix(providers): dedupe tool_use ids to prevent Anthropic 400s by @tedyyan in #4444
chore: bump to node 24 by @dvejmz in #4460
feat(providers): add OpenCode Zen and OpenCode Go providers by @zpljd258 in #4476
fix(webui): prevent iOS Safari composer zoom by @chengyongru in #4471
docs: document runtime environment variables by @chengyongru in #4462
fix(gateway): handle lifecycle edge cases by @chengyongru in #4447
fix(pairing): normalize sender IDs to str in the pairing store by @waelantar in #4433
feat(provider): add kimi_coding provider for Kimi Coding Plan by @zpljd258 in #4464
Fix raw tags in reasoning output by @ZhouJ-sh in #4466
fix(config): preserve dream cron when saving config by @yorkhellen in #4478
fix(web): pass proxy to DDGS client for DuckDuckGo search by @hyoukadev in #4484
fix: exclude archived keys in heartbeat & fallback missing session timestamps by @HengWeiBin in #4468
fix(webui): keep multi-file apply_patch edits by @chengyongru in #4487
fix(webui): restore code block copy fallback by @chengyongru in #4509
test: speed up test suite by @chengyongru in #4507
fix: add rich_messages config to disable sendRichMessage for Telegram Web (#4488) by @axelray-dev in #4489
fix(tools): gate MCP resource and prompt registration behind enabledTools by @michaelxer in #4436
fix(dingtalk): preserve richText formatting and set HTTP client timeout by @maxmilian in #4501
fix(cli): show search engines (incl. Keenable) in onboard wizard by @IlyaGusev in #4438
fix(webui): WebM→WAV conversion for Xiaomi MiMo ASR transcription by @zpljd258 in #4493
fix: advance dream cursor when Dream is disabled to prevent prompt bloat (#4242) by @axelray-dev in #4481
fix: allow custom provider to configure thinking style (#4429) by @axelray-dev in #4482
fix: make subagent fail_on_tool_error configurable (#4198) by @axelray-dev in #4485
docs: clarify heartbeat versus cron delivery by @chengyongru in #4543
test: harden webui and gateway checks by @chengyongru in #4535
fix: change exec login-shell default from true to false (#4518) by @axelray-dev in #4525
fix(session): remove message time replay prefixes by @chengyongru in #4540
fix(agent): gate microcompaction on context pressure by @chengyongru in #4238
refactor(whatsapp): replace bridge with neonize by @chengyongru in #4537
fix(exec): prevent allowPatterns bypass via chained commands by @axelray-dev in #4526
test: fix flaky test_keeps_n_most_recent due to identical mtimes by @primit1v0 in #4523
fix: deduplicate tool call IDs in non-stream parser (#4059) by @axelray-dev in #4530
fix: include _stream_id in stream delta coalescing key (#4063) by @axelray-dev in #4531
fix: validate content block type in Anthropic assistant blocks (#4060) by @axelray-dev in #4532
fix: prevent session key collision on disk (#4057) by @axelray-dev in #4533
fix(cron): guard public APIs against unavailable store by @yorkhellen in #4564
fix(webui): clear stuck streaming after reconnect and improve stop reliability by @axelray-dev in #4565
feat(mcp): deliver image content from MCP tools as artifacts by @codedragoncom in #4542
fix(session): repair corrupt legacy-stem files in list_sessions by @axelray-dev in #4566
fix(agent): harden tool-call path against malformed relay responses by @m11y in #4569
fix(context): make replay message cap internal by @chengyongru in #4582
refactor(session): return RetentionResult instead of bare tuple by @axelray-dev in #4574
feat(webui): refine prompt rail minimap by @Re-bin in #4600
fix(streaming): skip non-file-edit tools in apply_final_call_ids to prevent id corruption by @axelray-dev in #4596
fix(install): skip wizard without an interactive terminal by @chengyongru in #4602
fix(restart): add explicit restart mode by @chengyongru in #4607
feat(providers): support GitHub Copilot endpoint overrides for enterprise/GHE by @04cb in #4598
feat(whatsapp): send read receipts (blue double-check) for incoming messages by @franciscomaestre in #4601
feat(providers): support provider-scoped proxy config by @chengyongru in #4578
test(exec): cover bwrap sandbox mounts by @yu-xin-c in #4577
fix(weixin): stream LLM calls + buffer reply delivery to dodge non-stream relay bug by @m11y in #4567
fix(mcp): redact credentials from URLs before logging by @weijun-xia in #4584
fix(cli): allow oauth login to be/set main provider by @hamb1y in #4573
fix(webui): keep idle compaction out of session recency by @chengyongru in #4609
refactor(webui): derive provider model catalog kind by @chengyongru in #4613
refactor(tools): use structured tool error results by @chengyongru in #4610
feat(api): require api_key when binding to all interfaces (parity with WS gateway) by @dajiaohuang in #4548
feat(webui): add dollar skill shortcuts by @chengyongru in #4284
fix(cron): tolerate unsupported directory fsync by @chengyongru in #4617
refactor(bus): type outbound runtime events by @chengyongru in #4590
feat(trigger): add session-bound local triggers by @chengyongru in #4591
fix(trigger): cap local trigger audit records by @Re-bin in #4642
fix(exec): return early when session command exits by @chengyongru in #4643
test(cron): cover stale instance mutation consistency by @yu-xin-c in #4633
test: cover runner blocked tool-call finish reasons by @yu-xin-c in #4630
fix(webui): hide subagent backfill payloads by @chengyongru in #4641
fix(agent): avoid tool compaction echo loops by @chengyongru in #4647
fix(trigger): keep local worker alive on turn cancel by @chengyongru in #4644
feat(memory): add workspace Dream prompt override by @chengyongru in #4491
fix(providers): update Anthropic default model to claude-sonnet-4-6 by @bingqilinweimaotai in #4687
fix: omit temperature for sonnet 5 by @hamb1y in #4685
Add optional Nanobot plugin controls by @chengyongru in #4396
feat(cli): add safe WebUI first-run launcher by @Re-bin in #4688
fix(config): serialize model presets as camelCase by @Yuxin-Lou in #4692
fix(mcp): contain malformed tool results by @Yuxin-Lou in #4666
fix(copilot): guard token refresh with asyncio.Lock to prevent race condition by @axelray-dev in #4684
fix(pairing): restore durable atomic writes by @yorkhellen in #4653
fix(dingtalk): stop stream task on shutdown by @chengyongru in #4646
fix(gateway): handle Windows stop fallback by @Raccoon-njuse in #4690
fix(providers): standardize oauth_cli_kit error messages across CLI and WebUI by @axelray-dev in #4698
fix: normalize text tool call markup by @hamb1y in #4662
fix: isolate matrix stream buffers by @hamb1y in #4659
fix: resolve builtin skill reads by @hamb1y in #4658
fix(exec): default Windows commands to PowerShell and allow shell parameter by @dajiaohuang in #4545
feat(web-search): add Serper.dev (Google Search API) provider by @franciscomaestre in #4406
fix: limit long MCP-derived tool names by @thomya in #4700
fix(webui): keep chat viewport and composer inside narrow viewports, fixes #4693 by @hata33 in #4694
fix(dream): ground memory audit records in the real git diff by @goodtiding5 in #4673
feat: support canonical opencode provider by @hamb1y in #4686
feat(feishu): add new session divider by @chengyongru in #4763
feat: add Mattermost channel support by @goodtiding5 in #4459
fix(cli): print response text when streaming fails in interactive mode by @goodtiding5 in #4654
fix(gateway): self-heal state file PID on server startup by @dajiaohuang in #4547
fix(gateway): resolve config path for state refresh by @Re-bin in #4770
fix: pin validated dns for ssrf checks by @hamb1y in #4671
feat(cli): support multiline input via Alt+Enter by @m11y in #4614
chore: remove unused dead code by @chengyongru in #4824
fix(webui): show generic tool arguments in activity by @chengyongru in #4821
refactor(webui): drive slash commands from lifecycle metadata by @chengyongru in #4766
fix: require api key for serve by @hamb1y in #4669
Fix missing aiohttp slack dependency in pyproject.toml by @alekwo in #4830
fix(webui): keep prompt rail out of narrow chat columns by @chengyongru in #4831
Feature: non-interactive config refresh with 'nanobot onboard --refresh' by @alekwo in #4852
docs: improve search entry pages by @chengyongru in #4850
fix(webui): gate bootstrap API token issuance by @chengyongru in #4849
refactor(agent): extract turn hook assembly by @chengyongru in #4848
fix(webui): restore localhost bootstrap API tokens by @chengyongru in #4856
feat(webui): add file edit diff progress view by @chengyongru in #4828
fix(matrix): preserve mxc markdown image sources by @chengyongru in #4859
Add Dockerfile arg to override optional Python dependencies to install at build time by @dvejmz in #4857
refactor(agent): establish turn/runtime context foundation by @chengyongru in #4868
docs: add automation guide by @chengyongru in #4865
fix(webui): sync package-lock.json to resolve docker build failure by @SIDD-KIDD in #4863
fix(sandbox): add Red Hat certificate path support for Node by @luojiaaoo in #4845
fix(cli): handle CSI-u Shift+Enter instead of dumping raw escapes by @m11y in #4832
fix(webui): bind landing first message to created chat by @sidkang in #4836
fix(shell): reap zombie processes on all subprocess exit paths by @macroadster in #4840
feat(webui): highlight file previews and diffs by @chengyongru in #4877
feat(webui): guide queued prompt with second Enter by @chengyongru in #4876
fix(tools): enforce exact edit_file line hints by @chengyongru in #4635
fix(dream): skip no-op periodic commit attempts by @alekwo in #4873
fix(mcp): keep transport cleanup in owner tasks by @flyzstu in #4843
refactor(agent): gate sustained goals behind explicit /goal by @chengyongru in #4844
fix(webui): allow remote workspace access reduction by @Re-bin in #4892
fix(heartbeat): rewrite prompt to execute tasks instead of reporting by @wzrayyy in #4896
fix(discord): route unauthorized DMs to pairing by @chengyongru in #4899
fix(memory): prune encoded Dream sessions by @chengyongru in #4900
feat(webui): add guided setup flows by @Re-bin in #4855
fix(cli): restore enter before webui prompts by @Re-bin in #4903
fix(gateway): harden health endpoint exposure by @Re-bin in #4906
fix: align optional dependency contracts by @chengyongru in #4907
fix(dream): filter non-Dream history commits by @chengyongru in #4905
fix(codex): align OAuth defaults and setup docs by @chengyongru in #4910
docs: remove broken Star History embed by @chengyongru in #4912
docs: update recent changes through July 12 by @chengyongru in #4913
feat(webui): add Brazilian Portuguese (pt-BR) locale by @bill-kopp-ai-dev in #4914
fix(dream): ignore line-ending-only memory diffs by @bingqilinweimaotai in #4909
fix(telegram): HTML parse_mode for stream overflow chunks by @asif786ka in #4839
fix(shell): decode UTF-16 process output on Windows by @adabarbulescu in #4917
docs: reorganize documentation around user workflows by @chengyongru in #4916
feat(webui): support document attachments with ingress safeguards by @chengyongru in #4771
refactor(webui): centralize native runtime access by @chengyongru in #4769
fix(agent): add wall-clock timeout for streaming LLM requests by @wingkwong in #4902
fix: catch asyncio CancelledError in close_mcp shutdown by @bjoshuanoah in #4842
fix: install timezone data on Windows by @chengyongru in #4921
chore(codex): identify failing request stage by @chengyongru in #4929
feat(webui): add copy action to user messages by @chengyongru in #4930
fix(webui): sync package-lock.json for qrcode dependency by @3L1AS in #4927
fix: standardize --config help text across CLI commands by @rbankole in #4932
test: speed up CI and harden the suite by @chengyongru in #4936
feat(webui): highlight slash commands and app mentions by @chengyongru in #4933
fix(restart): deliver completion after channel reconnects by @chengyongru in #4931
fix(heartbeat): make response evaluation more configurable by @wzrayyy in #4915
fix(cli): point onboarding to the WebUI launcher by @chengyongru in #4938
fix(webui): validate inferred file paths before preview by @chengyongru in #4935
fix(webui): correct activity timer duration by @chengyongru in #4649
fix(providers): honor Codex proxy config consistently by @chengyongru in #4943
fix(gateway): stop channels before draining tasks by @chengyongru in #4944
docs(readme): reflect community maintenance by @Re-bin in #4950
feat(webui): support native folder picker bridges by @Re-bin in #4953
fix(providers): omit temperature for Moonshot Kimi K2.5/K2.6 by @bingqilinweimaotai in #4967
Improve zh-TW Traditional Chinese locale by @PeterDaveHello in #4958
fix(utils): handle empty commit messages in CommitInfo.format by @santhreal in #4973
fix(utils): coerce Tavily usage counters to int by @santhreal in #4972
fix(utils): avoid hang in split_message when max_len <= 0 by @santhreal in #4971
fix(exec): isolate exec session managers by @yu-xin-c in #4862
fix: preserve real cancellation in MCP paths by @adabarbulescu in #4960
fix(session): bound the in-memory session cache by @KDB-Wind in #4957
(fix docker) Harden default Docker Compose security by @Yuxin-Lou in #4955
feat: add Kimi K3 support by @bingqilinweimaotai in #4966
fix(cron): dual-case keys when loading jobs.json by @santhreal in #4974
feat: add one-click deploy to render support by @Ho1yShif in #4937
fix(agent): guide recovery from oversized tool results by @chengyongru in #4925
fix(triggers): coerce null ms fields when loading local triggers by @santhreal in #4986
fix(gitstore): resolve staged paths relative to workspace by @kuchazi-yy in #4979
fix(cli-apps): decode subprocess output as UTF-8 by @kuchazi-yy in #4976
fix(providers): fail over across provider failure domains by @chengyongru in #4904
fix(whatsapp): allow group ids in allowFrom by @chengyongru in #4834
fix(triggers): reject deliveries to disabled channels by @kuchazi-yy in #4990
refactor(channels): make built-in channels self-contained by @chengyongru in #4908
fix(webui): resolve Windows package manager shims by @chengyongru in #4994
fix(webui): show copy action on every assistant message by @chengyongru in #5001
style(webui): simplify Markdown code blocks by @chengyongru in #5002
fix(channels): complete dependency manifest migration by @chengyongru in #4995
docs(ollama): document tool prompt cache diagnostics by @chengyongru in #4998
fix(qq): add exponential backoff to WebSocket reconnect loop by @gola in #4768
refactor(agent): unify internal turn lifecycle by @chengyongru in #4993
fix(session): tolerate unsupported directory fsync by @amplifierplus in #5004
fix: stop masking runtime failures by @chengyongru in #5011
fix(cron): coerce null runHistory ms fields from jobs.json by @santhreal in #4985
fix(runner): narrow BaseException catch to Exception in tool execution by @axelray-dev in #4816
fix(session): cap messages at persistence boundary by @KDB-Wind in #4956
fix(exec): terminate active session process trees on shutdown by @KDB-Wind in #4978
fix(security): validate each shell segment against exec.allowPatterns by @michaelxer in #4562
fix(files): reject oversized reads before loading by @amplifierplus in #5014
fix(webui): keep Markdown table diffs inline by @chengyongru in #5015
fix(webui): prioritize skill names in autocomplete by @chengyongru in #5016
fix(config): write config.json atomically via temp+replace by @santhreal in #4984
fix(transcription): resolve ${VAR} env refs in transcription api_key/api_base by @benlenarts in #4989
feat(providers): support Codex fast mode by @chengyongru in #5019
fix(cron): coerce string schedule/state ms fields from jobs.json by @santhreal in #4983
fix(providers): sanitize UTF-16 surrogates at provider request boundary by @Krislu1221 in #4952
feat(webui): highlight skill references in sent messages by @chengyongru in #5020
Feat/modelscope provider support by @yrk111222 in #4965
docs(security): recommend env-var references over plaintext API keys by @cms19859230182-lang in #5010
fix: quarantine invalid tool results by @hamb1y in #4663
fix(providers): add Qwen model-level thinking style mapping by @cms19859230182-lang in #5023
feat(webui): show pin indicators for pinned chats by @chengyongru in #5025
feat(config): watch runtime configuration changes by @chengyongru in #5026
fix(webui): detect Chrome voice recording support by @chengyongru in #5027
style(webui): clarify surface hierarchy by @chengyongru in #5029
fix(webui): improve mobile composer layout by @chengyongru in #5030
fix(subagent): cascade exec session termination on /stop by @yorkhellen in #5021
fix(webui): avoid mobile welcome composer overlap by @chengyongru in #5031
fix(agent): preserve agent-owned state in project workspaces by @chengyongru in #4945
feat(webui): polish agent output and app discovery by @Re-bin in #4963
fix(webui): deliver late subagent results as new turns by @chengyongru in #4992
feat(agent): make model presets session-scoped by @chengyongru in #4866
feat(providers): add xAI Grok OAuth with capability-gated X Search by @chengyongru in #5035
feat(image): apply generation settings live by @Re-bin in #4964
fix(agent): deliver non-streamed finalization responses by @chengyongru in #5049
docs: explain slow optional dependency installs by @chengyongru in #5048
feat(xai): surface hosted X Search activity by @chengyongru in #5050
fix(feishu): keep fenced markdown tables out of card tables by @santhreal in #5046
fix(slack): keep fenced markdown tables intact in _to_mrkdwn by @santhreal in #5045
fix(pairing): treat null approved channel lists as empty by @santhreal in #5044
fix(cron): skip null runHistory elements when loading jobs.json by @santhreal in #5043
fix: add one second to retry after delays by @wzrayyy in #4959
fix(telegram): expose proxy setup in WebUI by @chengyongru in #5033
fix(providers): fall back on authentication errors by @chengyongru in #5052
fix(session): fall back to legacy paths in metadata reads by @axelray-dev in #4941
chore: pin migration TODOs to v0.2.4 by @chengyongru in #5053
feat(webui): indicate per-turn model fallback by @chengyongru in #5017
fix(documents): preserve DOCX table content by @Re-bin in #5039
style(webui): unify settings and dark mode surfaces by @chengyongru in #5058
fix(webui): polish responsive layouts and settings search by @chengyongru in #5060
fix(webui): keep composer model badge in sync by @Re-bin in #5067
fix(session): tolerate files removed during listing by @KDB-Wind in #5068
fix(exec): retain stale sessions after cleanup failure by @KDB-Wind in #5066
fix(telegram): advance markdown split on long single-line fences by @santhreal in #5055
fix(exec): extract absolute paths after equals sign in shell guard by @axelray-dev in #4594
fix(webui): allow media directory access when restrictToWorkspace is enabled by @cms19859230182-lang in #5065
feat(webui): simplify model preset settings by @chengyongru in #5061
test(agent): use python3 in ExecTool workspace scope tests by @flyzstu in #5064
feat(webui): present chats as topics by @chengyongru in #5070
feat(webui): add Parallel Search MCP preset by @georgeatparallel in #5047
fix: preserve pending message runtime context by @hamb1y in #4665
fix(webui): show quoted context after follow-up send by @chengyongru in #5071
Revert "fix: preserve pending message runtime context" by @chengyongru in #5072
feat(webui): switch model presets from the composer by @chengyongru in #5077
fix(webui): honor custom gateway port with Vite by @chengyongru in #5076
fix(providers): preserve multimodal tool outputs by @Re-bin in #5073
feat(agent): support inline subagent consultation by @Re-bin in #5074
feat(agent): carry authorized tasks through verification by @Re-bin in #5075
feat: launch first-time setup in webui by @chengyongru in #5078
Add nanobot logo (SVG) by @d1ago in #5079
feat(brand): migrate README and WebUI assets to SVG by @chengyongru in #5080
chore(release): prepare v0.3.0 by @Re-bin in #5081

New Contributors

@tedyyan made their first contribution in #4444
@dvejmz made their first contribution in #4460
@ZhouJ-sh made their first contribution in #4466
@hyoukadev made their first contribution in #4484
@maxmilian made their first contribution in #4501
@codedragoncom made their first contribution in #4542
@m11y made their first contribution in #4569
@weijun-xia made their first contribution in #4584
@dajiaohuang made their first contribution in #4548
@bingqilinweimaotai made their first contribution in #4687
@Raccoon-njuse made their first contribution in #4690
@thomya made their first contribution in #4700
@hata33 made their first contribution in #4694
@goodtiding5 made their first contribution in #4673
@SIDD-KIDD made their first contribution in #4863
@luojiaaoo made their first contribution in #4845
@sidkang made their first contribution in #4836
@flyzstu made their first contribution in #4843
@wzrayyy made their first contribution in #4896
@bill-kopp-ai-dev made their first contribution in #4914
@asif786ka made their first contribution in #4839
@adabarbulescu made their first contribution in #4917
@wingkwong made their first contribution in #4902
@bjoshuanoah made their first contribution in #4842
@3L1AS made their first contribution in #4927
@rbankole made their first contribution in #4932
@PeterDaveHello made their first contribution in #4958
@santhreal made their first contribution in #4973
@KDB-Wind made their first contribution in #4957
@Ho1yShif made their first contribution in #4937
@kuchazi-yy made their first contribution in #4979
@gola made their first contribution in #4768
@amplifierplus made their first contribution in #5004
@Krislu1221 made their first contribution in #4952
@yrk111222 made their first contribution in #4965
@cms19859230182-lang made their first contribution in #5010
@georgeatparallel made their first contribution in #5047
@d1ago made their first contribution in #5079

Full Changelog: v0.2.2...v0.3.0

详细ChangeLog

v0.2.2

2026年06月23日

🐈 nanobot v0.2.2 is here — 140 PRs merged, 21 new contributors. The agent got sturdier!

The headline is durability. WebUI conversations now survive more of real life: transcripts are segmented instead of living in one fragile file, forked chats preserve replies more reliably, active turns scroll and replay more predictably, startup paths block less, and gateway shutdown is much calmer. Long sessions, stale providers, slow routes, broken config files, malformed history, stream stalls, and empty provider responses all got less likely to derail the work.

The second story is nanobot becoming a real Python runtime. The SDK is no longer just a thin convenience layer around the agent loop: concurrent run() calls are isolated, hooks are cleaner, MCP lifecycle handling is safer, runtime controls are broader, and the docs now teach the SDK from first principles. If you want to embed nanobot inside your own application, v0.2.2 is the first release where that path feels intentional.

The third story is the workbench getting broader and easier to live in. The WebUI gained automation management, prompt navigation, token usage visibility, mobile polish, better update checks, richer activity timing, and a faster settings surface. The ecosystem expanded with Firecrawl as a keyless Web Data app, Exa / Bocha / Keenable / Volcengine search, more transcription providers, custom image generation, better Mistral and Kimi handling, and many channel fixes across Telegram, Feishu, WhatsApp, Slack, Email, QQ, DingTalk, and more.

Highlights

More durable WebUI sessions — Segmented transcript storage keeps large conversations readable without throwing away old turns, fork/replay paths preserve assistant replies more reliably, session deletion cleans up legacy files, refreshes no longer revive stale content, and active turns stay anchored while the model works. The WebUI also got prompt navigation, better mobile layout, clearer activity durations, token usage rendering, safer startup fetches, and on-demand version checks.
Python SDK as a first-class runtime — The SDK now has safer concurrent run() behavior, explicit runtime controls, cleaner per-run hook handling, better MCP cleanup, improved facade lifecycle behavior, and more beginner-friendly documentation. This makes nanobot easier to embed in scripts, services, evaluations, and custom agent products.
Gateway and onboarding polish — The gateway gained background/service controls, cleaner foreground shutdown, safer Ctrl+C behavior, and better MCP stdio cleanup. The onboarding flow was simplified around provider-first Quick Start, more neutral provider selection, safer WebUI setup, rollback on WebSocket failure, and better keyboard navigation.
Search, speech, and provider coverage — Web search now covers Firecrawl, Exa, Bocha, Keenable, and Volcengine paths; transcription expanded with shared voice input plus OpenRouter, StepFun, SiliconFlow, Xiaomi MiMo, and AssemblyAI support. Providers got better Mistral reasoning handling, Kimi K2.7 thinking, OpenAI-compatible query/body controls, custom image generation, OpenAI image edits, safer Anthropic tool IDs, and stronger retry/fallback behavior.
Reliability hardening across the agent core — Recent-history context is token-capped, idle auto-compact is on by default, Dream explains empty runs, malformed history is skipped, history cursors stay monotonic, tool schema estimates are cached, unknown builtin tool parameters are rejected, provider fallback logs the primary error, and stream stalls can retry or fall back without returning a truncated answer.
Channels that behave more like real apps — Telegram gained richer message support with safer fallback detection; Feishu got streaming recovery, WebSocket card reading, table extraction, lazy SDK loading, and QR login; WhatsApp got read receipts, forwarded-message handling, and LID mapping; Slack allowlisted channels can require mentions; Email gained attachments and IMAP post-actions; QQ / Napcat, DingTalk, Weixin, Matrix, and others received targeted fixes.
Security and workspace boundaries — Unsafe MCP HTTP URLs are rejected before probing, local provider endpoints bypass env proxies while cloud endpoints still respect them, workspace write policy is clearer, git commands work from workspace subdirectories without relaxing path guards, bwrap gets a sane HOME, and stripped image inputs no longer leak misleading local paths.

Community

Huge thanks to everyone who shipped v0.2.2 — 140 PRs, 21 first-time contributors, and a lot of careful review work. This release is less about one big switch and more about making nanobot dependable enough to keep open every day: steadier sessions, cleaner extension points, broader providers, and fewer sharp edges when real work gets long.

What's Changed

Refactor WebUI runtime state onto event bus by @chengyongru in #4135
feat(dingtalk): add group_user_isolation to separate sessions per use… by @lmzopq in #4016
feat(search): add Volcengine web search provider by @Re-bin in #4141
fix(webui): sort Chats group among projects by recency by @chengyongru in #4151
Fix WebUI refresh location routing by @chengyongru in #4150
fix: Support fallback copy for WebUI replies by @chengyongru in #4149
fix(memory): serialize cursor allocation in append_history (#4081) by @04cb in #4147
feat(channels): Add Napcat (QQ) channel by @chengyongru in #4146
feat(webui): add prompt rail and polish links by @Re-bin in #4156
fix(runner): prevent read_file offload loop by @jiehaoZ in #4155
refactor: split WebUI gateway dependencies by @chengyongru in #4115
fix(webui): bound startup fetch waits by @chengyongru in #4157
feat(email): add file attachment support to email channel by @chengyongru in #4162
refactor(dream): replace two-phase Dream class with simple cron + process_direct by @chengyongru in #3990
fix(session): reset out-of-range last_consolidated to recover hidden history (#4066) by @04cb in #4169
fix(email): skip progress messages to prevent empty emails after tool calls by @nblondiau in #4165
fix: restore top-level import order by @chengyongru in #4174
fix(qq): send pairing codes for unauthorized C2C users by @yorkhellen in #4180
fix(mcp): reconnect terminated sessions by @chengyongru in #4171
feat(webui): add new chat keyboard shortcut by @chengyongru in #4185
test: improve deterministic unit test coverage by @chengyongru in #4189
fix(cli): fall back to uv pip when pip is unavailable by @axelray-dev in #4164
Add run-level agent hook lifecycle by @chengyongru in #4176
feat(provider): Add support for Azure AAD based Auth for Azure OpenAI provider by @kunalk16 in #4126
fix(feishu): strip leading bot mention before commands by @Re-bin in #4184
feat(image): support custom image generation provider by @axelray-dev in #4187
Fix DM pairing for Weixin and Telegram by @chengyongru in #4197
fix(webui): persist user messages for refresh by @chengyongru in #4201
feat(command): add /skill slash command to list enabled skills by @Endeavour-Yuan in #3968
fix(sdk): close MCP connections from Nanobot facade by @axelray-dev in #4216
fix(providers): allow dropping default OpenAI image params via null extraBody by @04cb in #4209
feat(desktop): polish desktop shell and shared WebUI surfaces by @Re-bin in #4195
fix(whatsapp): handle LID group mentions by @danielphang in #2663
fix: preserve empty-string reasoning_content instead of coercing to None by @michaelxer in #4227
Fix token usage heatmap rendering by @chengyongru in #4248
docs: remove nightly branch guidance by @chengyongru in #4245
fix(mcp): reject unsafe HTTP URLs before probe by @yu-xin-c in #4123
feat(transcription): add shared voice input support by @Re-bin in #4232
feat(providers): add extra_query config for OpenAI-compatible providers by @axelray-dev in #4217
feat(transcription): configurable STT model + OpenRouter transcription provider by @breitburg in #4113
feat(transcription): add Xiaomi MiMo ASR provider (mimo-v2.5-asr) by @zpljd258 in #4175
feat(transcription): add AssemblyAI as transcription provider by @franciscomaestre in #4224
Improve tool call validation strictness by @chengyongru in #4190
fix(webui): render TeX math delimiters by @chengyongru in #4252
feat(email): add configurable IMAP post-actions for processed messages by @chengyongru in #4258
docs: make onboarding friendlier for beginners by @chengyongru in #4177
feat(webui): add assistant reply fork-from-here by @Bayern4ever-dot in #4208
fix(tools): keep apply_patch additions line-separated by @yu-xin-c in #4266
fix(providers): use max_completion_tokens for GPT-5/o-series models (#4261) by @04cb in #4268
fix(agent): finalize max-iteration turns without tools by @chengyongru in #4269
Add Exa web search provider by @erikmackinnon in #4213
feat(asr): add StepFun ASR SSE transcription provider by @morandot in #4260
fix(sandbox): set HOME inside bwrap by @primit1v0 in #4239
search: add Bocha web search provider by @morandot in #4182
fix(websocket): Fix bug in webui where session content is dropped by @Syoc in #4267
fix(feishu): lazy-load lark SDK during gateway startup by @chengyongru in #4277
Fail fast on invalid config files by @chengyongru in #4275
Scope prompt recent history by session by @chengyongru in #4274
feat(exec): add pathPrepend config by @chengyongru in #4273
fix(providers): allow retry and fallback on stream stalled timeout by @aiguozhi123456 in #4272
refactor(webui): on-demand version check in Settings > About by @JiajunBernoulli in #4255
feat(webui): segment transcript storage by @Re-bin in #4278
feat(transcription): add SiliconFlow as transcription provider by @morandot in #4281
fix(utils): make split_message fenced-code-block-aware by @axelray-dev in #4257
feat(slack): add groupRequireMention to scope allowlist channels to @mentions by @brendanlevy in #4289
feat: support multiple custom OpenAI-compatible providers by @JagoWang in #3239
fix(session): prevent orphaned tool results from being persisted to history (#4006) by @tangtaizong666 in #4306
feat(bridge): WhatsApp forwarded message detection, startup guard, and contact handling by @franciscomaestre in #4226
feat(cron): bind scheduled automations to sessions by @chengyongru in #4299
chore(repo): remove desktop app from core repo by @Re-bin in #4294
Break tool config schema import cycle by @chengyongru in #4314
Fix WebUI startup blocking on slow gateway routes by @chengyongru in #4327
fix(memory): summarize full session tail during idle compaction (#4264) by @tangtaizong666 in #4326
fix(cli): use configured bot_icon in agent interactive banner (#4262) by @04cb in #4335
fix(providers): widen omit_temperature to cover opus-4-8 and fable by @axelray-dev in #4334
Fix Codex image SSE handling by @cypggs in #4332
docs: add Kimi and MiniMax partner links by @oriengy in #4295
docs(readme): link Kimi partner banner by @Re-bin in #4338
fix(webui): localize update check copy by @chengyongru in #4331
docs(readme): add themed cover image by @Re-bin in #4341
Improve WebUI mobile responsiveness by @chengyongru in #4339
Add tools.file.enable to toggle built-in filesystem tools by @niradler in #4138
fix(runner): ignore empty injected payloads by @yu-xin-c in #4337
fix(memory): ignore malformed history entries by @yu-xin-c in #4315
fix(api): forward real LLM usage in /v1/chat/completions response by @michaelxer in #4310
fix(session): keep auto compact suffix on user turn by @chengyongru in #4348
fix(agent): refresh goal continuation context by @chengyongru in #4359
fix(webui): override wsUrl with local LAN IP when on dev server port 5173 by @HengWeiBin in #4364
chore: ignore bridge/node_modules by @franciscomaestre in #4355
fix(providers): enable thinking for Kimi K2.7 models by @Re-bin in #4361
fix(api): avoid duplicate user turn on empty-response retry (#4079) by @04cb in #4358
fix(providers): validate stream idle timeout config by @yu-xin-c in #4363
fix(context): cap recent-history digest by tokens, not characters by @waelantar in #4352
Explain empty Dream runs by @chengyongru in #4369
Enable idle auto-compact by default by @chengyongru in #4370
Fix macOS installer for externally managed Python by @chengyongru in #4368
docs: use pipe pattern for curl installer commands by @HaisamAbbas in #4365
feat(webui): add automation management view by @chengyongru in #4330
fix: silence unroutable cli progress noise by @chengyongru in #4386
fix: log primary model error before fallback by @chengyongru in #4385
fix: recover failed Feishu streaming updates by @chengyongru in #4381
fix: allow git commands in workspace subdirectories by @HaisamAbbas in #4380
fix(providers): disable proxy for local endpoints, respect env proxy for cloud by @michaelxer in #4367
fix(anthropic): sanitize tool_use/tool_result IDs to API pattern by @franciscomaestre in #4356
Fix my tool model preset switching by @chengyongru in #4347
fix(webui): correct activity duration display by @chengyongru in #4283
fix(session): preserve user turns in replay-window history by @Re-bin in #4349
Clarify filesystem workspace write policy by @chengyongru in #4202
feat(bridge): send read receipts (blue ticks) for incoming WhatsApp messages by @franciscomaestre in #4354
feat(providers): better Mistral support by @La-Volpe in #4351
feat(web): add Keenable search provider by @IlyaGusev in #4350
feat(feishu): add QR scan-to-create bot CLI login feishu command by @bllackhu in #4391
ci: skip docs-only changes by @chengyongru in #4400
feat(webui): make Firecrawl a keyless Web Data app by @Re-bin in #4403
fix(fallback): treat empty API choices as fallbackable error, 将 API 返回空 choices 视为可 fallback 的错误 (#4287) by @yonghuname in #4288
[codex] fix MCP malformed progress notifications by @yu-xin-c in #4372
fix(providers): use non-descriptive placeholder when stripping images by @michaelxer in #4401
fix(feishu): support reading WebSocket rendered card content by @JiajunBernoulli in #4342
fix: support OpenAI image reference edits by @sbyinin in #4394
fix(session): delete_session also removes legacy path files to prevent history revival by @yorkhellen in #4246
fix: set httpx timeout for streamableHttp transport by @lucndm in #4230
feat(whatsapp): seed LID->phone mappings on startup by @franciscomaestre in #4407
fix(memory): keep history cursor monotonic by @yu-xin-c in #4256
perf(tokens): cache tool schema estimates by @yu-xin-c in #4428
fix(telegram): narrow rich capability error detection and fix misleading log by @zpljd258 in #4423
fix(tools): reject unknown builtin parameters by @yu-xin-c in #4343
feat(web): allow Keenable search without an API key by @IlyaGusev in #4405
fix(sdk): isolate per-run hooks for concurrent run() calls by @michaelxer in #4425
feat(sdk): expand Python SDK runtime controls by @Re-bin in #4296
docs(readme): update news through 2026-06-20 by @Re-bin in #4432
Improve onboard wizard setup flow by @chengyongru in #4395
feat(gateway): add background and service controls by @xcosmosbox in #1854
fix(webui): avoid slow settings route refreshes by @chengyongru in #4398
chore(config): default context window to 200k by @chengyongru in #4448
fix: close MCP stdio transports from agent task by @Re-bin in #4450
fix(webui): stabilize sent turn layout and dev reloads by @Re-bin in #4451
chore(release): prepare v0.2.2 by @Re-bin in #4445
fix(webui): follow active turn output after send by @Re-bin in #4453
fix: stabilize gateway shutdown and webui fork replay by @Re-bin in #4454
fix(gateway): tolerate cancelled channel tasks during shutdown by @Re-bin in #4456

New Contributors

@lmzopq made their first contribution in #4016
@nblondiau made their first contribution in #4165
@michaelxer made their first contribution in #4227
@breitburg made their first contribution in #4113
@zpljd258 made their first contribution in #4175
@Bayern4ever-dot made their first contribution in #4208
@erikmackinnon made their first contribution in #4213
@primit1v0 made their first contribution in #4239
@Syoc made their first contribution in #4267
@brendanlevy made their first contribution in #4289
@JagoWang made their first contribution in #3239
@tangtaizong666 made their first contribution in #4306
@oriengy made their first contribution in #4295
@niradler made their first contribution in #4138
@waelantar made their first contribution in #4352
@La-Volpe made their first contribution in #4351
@IlyaGusev made their first contribution in #4350
@bllackhu made their first contribution in #4391
@yonghuname made their first contribution in #4288
@sbyinin made their first contribution in #4394
@lucndm made their first contribution in #4230

Full Changelog: v0.2.1...v0.2.2

详细ChangeLog

v0.2.1

2026年06月01日

🐈 nanobot v0.2.1 is here — 84 PRs merged, 17 new contributors. The agent got a real workbench.

The headline is the WebUI becoming the place where work actually happens. The chat surface is smoother, faster, and easier to trust: live file edits show up as activity, tool traces render more cleanly, source links get readable favicons, markdown and code blocks behave better, new chats survive refreshes, and Thought / response ordering now matches the model's real turn structure. Settings, sidebar controls, model switching, context-window control, slash commands, project workspaces, and access modes all moved closer to a single coherent control surface.

The second story is long-running work getting more durable. Sustained goals no longer trip the runner, goal iteration budget is higher, session locks prevent overlapping turns from stepping on each other, AutoCompact and consolidation races were fixed, heartbeat moved onto cron, and session archive retention got several data-loss fixes. In practice, this means fewer mysterious interruptions, fewer duplicate archives, and a much better chance that a long agent workflow keeps its thread of intent.

The third story is nanobot becoming easier to plug into real stacks. CLI Apps and MCP now share a more unified extension path; preset setup and capability mentions make tools easier to discover; the extension registry gives integrations a first-class home. Provider coverage expanded across Ant Ling, Skywork, Novita, Step Plan, StepFun, Zhipu image generation, OpenAI/Codex image generation, Ollama image generation, and richer OpenAI-compatible configuration. Channels also grew with Signal, Telegram webhook mode, Discord model slash commands, Matrix verification fixes, and safer Weixin / Teams / Matrix behavior.

Highlights

WebUI as a daily workbench — The WebUI is no longer just a packaged chat surface. It now has better activity rendering, live file edit visibility, cleaner source links, stronger markdown/code rendering, improved sidebar performance, project workspaces, access controls, context-window settings, model controls, slash command actions, and a more polished native-host feel. The final Thought / response ordering fix makes streamed agent work read in the order it actually happened. (#3877, #3899, #3906, #3951, #3953, #3987, #4007, #4045, #4108, #4121, #4137)
Long-running agent stability — Goal mode and multi-turn work got sturdier: sustained goals keep the runner alive, goal iteration budget is extended, process_direct now has per-session locking, streaming/session concurrency bugs were tightened, AutoCompact and consolidator races were fixed, and archive retention now avoids duplicate archives and message loss. (#3881, #3999, #4041, #4104, #4127, #4129)
CLI Apps, MCP, and extension workflows — CLI Apps landed as a way to connect CLI-native tools, then got unified with MCP concepts through preset setup, capability mentions, stale install recovery, registry logos, and an extension registry source. The result is a clearer path from "I have a useful local tool" to "nanobot can invoke it in a workflow." (#3963, #3979, #3991, #4046)
More providers, richer model routing — The provider surface widened with Ant Ling, Skywork, Novita, Step Plan, OpenAI API type selection, extraBody, and multiple image-generation providers including StepFun, OpenAI/Codex, Ollama, and Zhipu. Several follow-up fixes preserve tool-call IDs, improve quota/billing errors, handle provider transport edge cases, and keep thinking/reasoning controls honest across OpenAI-compatible routes. (#3900, #3910, #3916, #3927, #3946, #3954, #3971, #3974, #3984, #3988, #4048)
Channels and deployment polish — Signal support, Telegram webhook mode, Discord model slash commands, Docker/WebUI deployment fixes, and clearer secret/deployment docs make nanobot easier to run outside a local terminal. Gateway cold start also dropped dramatically, from seconds to sub-second territory. (#3872, #3918, #3935, #3996, #4031)
Security and reliability hardening — WebSocket token issuance now requires auth, redirect targets are validated before web fetches, IPv6-mapped IPv4 addresses are normalized in SSRF checks, Teams replies trust service URLs, Matrix inbound media downloads are bounded, and shell/exec behavior was tightened on Windows and URL-heavy commands. (#3928, #3933, #4051, #4086, #4103, #4106, #4047)
Internationalization and docs — The WebUI locale set was filled out across zh-TW, ja, and remaining keys, the README positioning and news section were refreshed, multi-language doc links were surfaced, local provider setup is easier to find, and AGENTS.md gives coding agents a clearer way into the repo. (#3930, #3962, #3964, #4131)

Community

Huge thanks to everyone who shipped v0.2.1 — 84 PRs, 29 contributors, and a warm welcome to 17 first-time contributors. This release feels less like one big feature drop and more like nanobot becoming something you can keep open all day: steadier, clearer, and much easier to extend.

What's Changed

fix(providers): recognize Chinese rate-limit marker '访问量过大' as transient error by @chengyongru in #3864
fix docker build and webui by @huanglei214 in #3872
docs(configuration): expand secrets section with more examples by @olgagaga in #3866
docs(deployment): match docker run gateway example to docker-compose.yml (refs #3873) by @voidborne-d in #3874
fix(agent): resolve race between AutoCompact and Consolidator by @chengyongru in #3881
fix(cli): buffer reasoning tokens to avoid one-token-per-line display by @li-yazhou in #3878
feat(webui+agent): optimize streaming, activity rendering, and runtime sync by @Re-bin in #3877
fix(webui): preserve single newlines in markdown rendering by @chengyongru in #3889
feat(cli): add Model Preset wizard to onboard by @chengyongru in #3890
feat(webui): add live file edit activity by @Re-bin in #3899
feat(providers): add Ant Ling support by @Re-bin in #3900
refactor(image-generation): introduce provider registry by @chengyongru in #3893
docs: surface local provider setup in README by @yanalialiuk in #3912
feat(webui): upgrade settings and sidebar controls by @Re-bin in #3906
fix(webui): accept end/error phases in tool trace rendering by @HengWeiBin in #3894
feat(image-generation): add StepFun (阶跃星辰) provider support by @morandot in #3910
feat(providers): add Skywork first-level support by @Re-bin in #3916
perf: optimize gateway cold start from ~4.6s to ~480ms by @chengyongru in #3918
fix(exec): detach stdin for shell commands by @Re-bin in #3922
fix(providers): update Skywork APIFree agent endpoint by @morandot in #3917
docs(readme): add multi-language doc site links by @chengyongru in #3930
feat(signal): add Signal channel support by @chengyongru in #3935
fix(provider): deduplicate streaming tool_call_ids for parallel calls by @chengyongru in #3943
fix(webui): keep new chat during session refresh by @boogieLing in #3944
fix(weixin): prevent silent message drops from poll exceptions, expired tokens, and ret=-2 by @chengyongru in #3684
fix(providers): inject OpenRouter reasoning.effort for thinking models (follow-up to #3851) by @olgagaga in #3867
Fix shell guard false positives on URL commands by @HaisamAbbas in #3933
feat(tools): optimize coding workflows by @Re-bin in #3923
feat: add Novita AI provider by @Alex-yang00 in #3927
feat(webui): refine collapsible sidebar by @Re-bin in #3951
feat(webui): improve sidebar performance by @Re-bin in #3953
fix: drop redundant reasoning_effort for Kimi thinking models by @agbocsardi in #3940
fix(webui): avoid misleading file edit counters by @Re-bin in #3957
refactor(apply_patch): remove deprecated patch mode, keep edits-only by @chengyongru in #3960
feat(image-generation): add OpenAI and Codex provider support by @ZegWe in #3954
Add Ollama image generation support by @HaisamAbbas in #3946
fix: dedupe Responses replay item ids by @Yuxin-Lou in #3961
Unify image provider HTTP handling and document Gemini image base URLs by @HaisamAbbas in #3929
chore: fill zh-TW and ja locale keys by @yu-xin-c in #3962
[security] fix(web): validate redirect targets before fetching by @Hinotoi-agent in #3928
chore: fill remaining WebUI locale keys by @yu-xin-c in #3964
feat(cli): add CLI Apps for CLI-Anything integrations by @Re-bin in #3963
test(cli): cover CLI Apps on Windows CI by @Re-bin in #3965
feat: Add Zhipu (智谱) image generation provider by @JiajunBernoulli in #3971
fix: uncap exec config timeout and normalize transcription apiBase (#3595, #3637) by @04cb in #3967
docs: use xiaomi_mimo provider for MiMo token plan by @honjiaxuan in #3972
feat(spawn): allow per-subagent sampling temperature (#3969) by @04cb in #3975
feat(mcp): add preset setup and capability mentions by @Re-bin in #3979
fix(provider): preserve OpenAI-compatible tool call ids by @Yuxin-Lou in #3984
feat(webui): improve slash command actions by @Re-bin in #3987
feat(providers): add OpenAI API type and extra body configuration by @outlook84 in #3974
fix(agent): propagate maxConcurrentSubagents config to SubagentManager by @Felix8568 in #3978
feat(providers): add Step Plan support by @morandot in #3988
feat(apps): unify CLI apps and MCP by @Re-bin in #3991
fix(agent): prevent runner from exiting while sustained goal is active by @chengyongru in #3999
fix(web): update Kagi search API integration by @agbocsardi in #4004
feat(telegram): add webhook mode by @outlook84 in #3996
chore: enable WebUI ESLint by @yu-xin-c in #3981
fix(provider): handle blank Codex transport errors by @ehs208 in #4009
fix(provider): honor NANOBOT_STREAM_IDLE_TIMEOUT_S in Codex provider by @yeounhyeok in #4018
feature: Add Discord model slash command by @hamb1y in #4031
refactor(heartbeat): migrate heartbeat service to cron-based auto-registration by @chengyongru in #4023
Fix session, goal, streaming, and context-budget bugs by @hamb1y in #4041
feat(webui): add project workspaces and access controls by @Re-bin in #4007
feat(webui): add context window setting by @Re-bin in #4045
feat(channels): add document extraction toggle by @boogieLing in #4049
fix(providers): surface clear arrearage warning to user on quota/billing errors (#3006) by @04cb in #4048
[security] fix(msteams): trust service URLs before replies by @Hinotoi-agent in #4047
feat(apps): add nanobot extension registry by @Re-bin in #4046
fix(exec): bypass cmd.exe for multi-line python -c commands on Windows by @chengyongru in #4051
[security] fix(matrix): bound inbound media downloads by @Hinotoi-agent in #4106
fix(security): normalize IPv6-mapped IPv4 addresses in SSRF checks by @yorkhellen in #4086
fix: coerce typeless Anthropic content blocks + add Dream enable toggle (#3993, #3885) by @04cb in #4054
feat(webui): refine output timeline and model controls by @Re-bin in #4108
fix(agent): acquire per-session lock in process_direct (#4080) by @04cb in #4104
fix(matrix): handle SAS device verification by @mytechdream in #4110
fix(heartbeat): skip empty HEARTBEAT.md and fail closed on delivery (#4111) by @04cb in #4114
Require auth for WebSocket token issuance by @hamb1y in #4103
fix(webui): handle undefined language in code blocks by @Flinn-X in #4117
feat(webui): polish chat rendering and host runtime by @Re-bin in #4121
fix(agent): extend sustained goal iteration budget by @Re-bin in #4127
fix(webui): preserve Thought/response ordering by @Re-bin in #4137
docs: add AGENTS.md for Codex by @jiehaoZ in #4131
fix(session): prevent duplicate archive and message loss in enforce_file_cap by @yorkhellen in #4129

New Contributors

@huanglei214 made their first contribution in #3872
@voidborne-d made their first contribution in #3874
@li-yazhou made their first contribution in #3878
@HengWeiBin made their first contribution in #3894
@HaisamAbbas made their first contribution in #3933
@Alex-yang00 made their first contribution in #3927
@agbocsardi made their first contribution in #3940
@ZegWe made their first contribution in #3954
@Yuxin-Lou made their first contribution in #3961
@yu-xin-c made their first contribution in #3962
@outlook84 made their first contribution in #3974
@Felix8568 made their first contribution in #3978
@ehs208 made their first contribution in #4009
@yeounhyeok made their first contribution in #4018
@hamb1y made their first contribution in #4031
@mytechdream made their first contribution in #4110
@jiehaoZ made their first contribution in #4131

Full Changelog: v0.2.0...v0.2.1

详细ChangeLog

v0.2.0

2026年05月16日

🐈 nanobot v0.2.0 is here 🎉 — 105 PRs merged, 20 new contributors. The agent learned to hold a goal.

The headline is /goal. Mark a thread as a sustained objective with long_task, and the active goal stays pinned in Runtime Context every turn — surviving compaction, surviving long tool chains, surviving the model's own forgetfulness — until you call complete_goal. The wall-clock timeout widens automatically while a goal is active; streaming requests fall back to an idle timeout instead of a hard wall, so a model that's still thinking doesn't get killed mid-thought.

The second story is the WebUI growing up. After several releases as a source-only preview, it now ships inside the wheel — pip install nanobot-ai and you have it. Settings and BYOK got a full redesign, the slash palette is localized, LAN access is gated by a token, reasoning streams live to the chat, and a brand-new image-generation tool turns "draw me X" into an inline preview without leaving the conversation.

The third story is the engine room. The agent loop got a real refactor — AgentLoop.from_config() for clean embedding, _process_message rewritten as a functional state machine, archived summary moved into the system prompt for KV cache stability, tools converted to a self-describing plugin architecture, ask_user and GlobTool retired in favor of cleaner replacements. Five new providers (AWS Bedrock Converse, NVIDIA NIM, LongCat, Atomic Chat, MiMo) join the lineup with fallback_models as a safety net so a single flaky endpoint can't take a turn down. Plus four [security] fixes — SSRF, media path confinement, softer workspace boundaries — and chat-native pairing so DM approvals finally happen in the chat instead of in a config file.

Highlights

/goal and long-running tasks — agent with a memory of why — The new long_task tool, paired with /goal and complete_goal, marks a thread as a sustained objective. The active goal is mirrored in Runtime Context every turn so the agent stays anchored even after compaction, the WebUI surfaces the goal in the chat header, and the LLM wall timeout is automatically widened while a goal is active so longer reasoning passes don't get killed mid-thought. Core agents and subagents both honor the longer budget; streaming requests fall back to an idle timeout instead of a hard wall clock so a model that's still emitting tokens won't be prematurely cut off. (#3788, #3855)
Image generation, end to end — A new image-generation tool plus a WebUI image mode let you go from prompt to picture without leaving the chat. Generated images render inline with rounded previews; replay-window and dedup paths were tightened so images don't double-deliver across long sessions, and the consolidation pass now respects the replay window when hiding history. (#3695, #3687)
WebUI shipped in the wheel + a year's worth of polish — pip install nanobot-ai now bundles the WebUI: enable the WebSocket channel, run nanobot gateway, open the browser. No cd webui && bun run build required. After several releases under a "preview" label, the WebUI is now a packaged surface. Inside it: redesigned settings and BYOK flow (including BYOK web search), localized slash palette, model preset badge that stays in sync across slash commands and config reloads, streamed reasoning rendered live, image previews, LAN access gated by tokenIssueSecret, default-to-new-chat on load, scroll preservation on settings return, a crypto.randomUUID shim for non-secure-context LAN use, and dropped eager markdown preload to cut first-paint cost. (#3653, #3661, #3703, #3709, #3656, #3658, #3733, #3759, #3782)
Five new providers and a fallback safety net — Native AWS Bedrock Converse lands as a first-class provider (#3574), with a follow-up that preserves Bedrock tool config across history (#3758). NVIDIA NIM (#3707), LongCat via OpenAI-compatible routing (#3114), Atomic Chat as a local OpenAI-compatible target (#3750), and MiMo with proper thinking-control wiring (#3734, #3851) round out the lineup. On top of the wider stack, fallback_models lets you list secondary models that take over when the primary fails (#3756), DeepSeek reasoning history is back-filled instead of dropped (#3616, #3560), Codex prompt cache keys stabilized (#3793), and Anthropic auto-falls back to streaming on long-request errors (#3579).
Model presets and runtime switching — ModelPresetConfig lets you name model + provider bundles in config and swap between them at runtime via /model (or the WebUI badge). Presets sync across slash commands, config reloads, and settings changes, so the model badge always matches what the next turn will hit. (#3714)
Core refactor — a cleaner agent loop, a smaller surface — AgentLoop.from_config() centralizes loop assembly so embedders stop reaching into private internals (#3708). _process_message was rewritten as a functional state machine with explicit transitions instead of nested branches (#3715). The archived conversation summary moved into the system prompt to keep KV caches stable across compactions (#3711). Tools became a self-describing plugin architecture (#3729). ask_user was removed in favor of structured message-tool choices (#3757), and GlobTool was retired in favor of read_file glob support (#3841). Vulture- and coverage-verified dead code was excised (#3755, #3719). Logging now preserves tracebacks and carries channel context (#3651, #3678). Ruff F rules are fully enforced in CI (#3672), and the agent test suite was expanded and restructured (#3766). New CLAUDE.md and .agent/ guides give AI contributors a stable on-ramp (#3534, #3860).
Pairing, DM approvals, and security hardening — Chat-native pairing (#3774) lets you approve DMs from inside chat instead of editing config. On the safety front: SSRF blocked in DingTalk outbound media (#3569), Feishu downloaded-media filenames confined to safe paths (#3789), local media attachments confined for the message tool (#3842), SSRF guard recovery softened so a transient miss doesn't poison subsequent turns (#3635), and workspace boundary violations get a retry-throttled soft warning instead of crashing the loop (#3614). Telegram silently ignores unauthorized senders instead of leaking error responses (#3629).
Memory, dream, and session durability — Cron jobs.json gained atomic writes with corrupt-store detection (#3606). Dream cursor only advances on completed batches (#3631) and restores correctly with memory state on resume (#3660). Replay-window hidden history is now properly consolidated (#3687). Workspace and tool-state changes survive restarts more reliably end-to-end.
Channel and platform fixes — Feishu group threads honor reply chains and topic isolation (#3547, #3704, #3747, #3775), Matrix skips pre-startup events and stops the sync loop on irrecoverable auth (#3575, #3578), WhatsApp voice messages download cleanly (#3607), Wecom preserves real filenames (#3751), Telegram quiets unauthorized senders (#3629), and Weixin raises on send failures so messages don't silently drop (#3659). On Windows: UNC path support in shell extraction (#3764). On the CLI: surrogate code points sanitized before the message bus (#3697), retry-wait messages no longer garble interactive output (#3705, #3609), and nanobot provider logout lands as a proper command (#3612).
Smaller things you'll feel — Configurable bot_name / bot_icon (#3730), configurable toolHintMaxLength (#3641), real SSE streaming restored on the OpenAI-compatible API (#3677), Whisper transcription retries on transient failures (#3646), sequential MCP server connects to stop CPU spin (#3640), MCP HTTP probe before connect (#3740), Brave search backoff under rate limits (#3840), sender_id in Runtime Context for user-aware responses (#3549), runtime context appended after user content for cache stability (#3844), origin_message_id outbound deduplication (#3561), and a Python SDK RunResult that finally exposes tools_used and messages (#3620).

Community

Heartfelt thanks to everyone who shipped v0.2.0 — 105 PRs, 33 contributors, and a huge welcome to 20 first-time contributors. Every review, patch, and bug report helped; this release is a shared win. 🎉

What's Changed

fix(feishu): streaming card and tool hint respect reply_to_message in groups by @04cb in #3543
Revert "fix(feishu): streaming card and tool hint respect reply_to_message in groups" by @Re-bin in #3548
fix(feishu): respect reply_to_message for group threads by @boogieLing in #3547
fix(agent): respect configured max iterations for subagents by @boogieLing in #3532
feat(provider): add native AWS Bedrock Converse support by @Re-bin in #3574
feat(skill): add nanobot upgrade wizard skill by @chengyongru in #3539
bugfix(#3751): ReadFileTool says "File unchanged since last read:" across different sessions by @LZDQ in #3576
refactor: replace try-except blocks with contextlib.suppress for cleaner error handling across multiple files by @JackLuguibin in #3566
fix(matrix): skip events received before bot startup by @coldxiangyu163 in #3575
fix(matrix): don't send empty room messages from blank progress callbacks by @halldorjanetzko in #3573
[security] fix(dingtalk): block SSRF in outbound media fetches by @Hinotoi-agent in #3569
fix(matrix): correct allow_room_mentions default type by @spinvettle in #3563
fix: API stream lifecycle for tool-backed requests by @boogieLing in #3555
feat(context): Add sender_id to LLM runtime context for user-aware responses by @yorkhellen in #3549
fix: origin_message_id support and outbound deduplication by @tongtianli03-code in #3561
fix: adjust DeepSeek reasoning mode check condition by @JiajunBernoulli in #3560
fix(web_fetch): sanitize URL to strip markdown backticks and quotes before validation by @XJPeng12 in #3528
fix: strip partial think tags in streaming output by @hongshunanhai in #3577
fix(matrix): stop sync loop on irrecoverable auth errors by @coldxiangyu163 in #3578
fix(anthropic): auto-fallback to stream on long-request error by @coldxiangyu163 in #3579
fix(helpers): restore tiktoken fallback in estimate_prompt_tokens_chain by @yorkhellen in #3582
feat(provider): add LongCat via OpenAI-compatible backend by @morandot in #3114
fix: allow_patterns take priority over deny_patterns in ExecTool by @chengyongru in #3594
Improve beta WebUI turn completion and chat isolation by @ramonpaolo in #3583
fix(cli): stop provider retry messages garbling interactive output by @04cb in #3609
fix(cron): atomic write for jobs.json + don't silently overwrite corrupt store by @hussein1362 in #3606
fix(runner): soft workspace boundary with retry throttle by @Re-bin in #3614
fix(agent): prevent safety guard false positives and streamed message drop by @chengyongru in #3613
fix(bridge): support WhatsApp voice message download by @yorkhellen in #3607
feat(cli): add provider logout command by @chengyongru in #3612
fix: backfill DeepSeek reasoning_content history instead of dropping it (#3554, #3584) by @04cb in #3616
feat(agent): limit concurrent subagent execution by @chengyongru in #3634
fix: only advance dream_cursor on completed batches to prevent silent loss by @JiajunBernoulli in #3631
fix: return absolute path for downloaded Feishu media files by @futurist in #3632
fix(telegram): ignore unauthorized users silently by @kaseru in #3629
fix(sdk): populate RunResult.tools_used and RunResult.messages by @chengyongru in #3620
fix(agent): soften SSRF guard recovery by @Re-bin in #3635
refactor(logging): preserve tracebacks and add channel context by @chengyongru in #3651
fix(agent): gate provider progress deltas for non-streaming channels by @boogieLing in #3645
feat(config): add toolHintMaxLength to control tool hint truncation by @chengyongru in #3641
fix: use sequential MCP server connections to prevent CPU spin by @chengyongru in #3640
fix(transcription): retry Whisper calls on transient failures by @chengyongru in #3646
feat(webui): polish chat layout and titles by @Re-bin in #3653
fix(webui): allow LAN access when host is 0.0.0.0 by @chengyongru in #3656
fix(webui): require token_issue_secret for LAN bootstrap with frontend auth by @chengyongru in #3658
fix(weixin): raise exceptions on message send failure to prevent silent loss by @chengyongru in #3659
feat(webui): polish chat UX and slash commands by @Re-bin in #3661
fix(dream): restore cursor with memory state by @Jefsky in #3660
refactor(logging): preserve tracebacks in remaining except blocks by @chengyongru in #3678
chore(ci): Enable full ruff -F (all F rules) checks and fix related errors by @yorkhellen in #3672
fix(api): remove enable_compression to restore real SSE streaming by @zhw415876999-prog in #3677
fix(onboard): allow empty strings and falsy values in input fields by @chengyongru in #3691
feat: add image generation tool and WebUI mode by @Re-bin in #3695
fix(memory): consolidate history hidden by replay window by @Re-bin in #3687
feat(webui): redesign settings and BYOK configuration by @Re-bin in #3703
fix(cli): sanitize surrogate code points before entering message bus by @chengyongru in #3697
fix(feishu): send all messages to topic when in thread by @yorkhellen in #3704
fix: log errors in silent exception handlers (matrix + weixin channels) by @vystartasv in #3664
fix(cli): handle retry-wait messages in interactive mode by @eugenechae in #3705
docs: add CLAUDE.md and .agent/ guides for AI contributors by @chengyongru in #3534
feat(webui): add BYOK web search settings by @Re-bin in #3709
fix(agent): persist _last_summary across restarts with used sentinel by @chengyongru in #3685
Revert "fix(agent): persist _last_summary across restarts with used sentinel" by @Re-bin in #3710
refactor: introduce AgentLoop.from_config() to centralize loop assembly by @chengyongru in #3708
refactor(loop): convert _process_message to functional state machine by @chengyongru in #3715
fix(utils): remove unreachable dead code in find_legal_message_start by @chengyongru in #3719
fix(agent): move archived summary into system prompt for KV cache stability by @chengyongru in #3711
feat: add NVIDIA NIM provider support by @barreler126 in #3707
feat(cli): make bot name and icon configurable (#3650) by @pixan-ai in #3730
fix(providers): wire MiMo to thinking_type to allow disabling reasoning (#3585) by @pixan-ai in #3734
fix(webui): shim crypto.randomUUID for non-secure contexts by @NearlCrews in #3733
fix(wecom): preserve real filename from SDK when payload omits name (#3737) by @04cb in #3751
refactor(tools): plugin architecture with self-describing tools by @chengyongru in #3729
fix(providers): set supports_max_completion_tokens for VolcEngine providers by @AlbertWang688 in #3738
feat(feishu): add topic_isolation config switch by @yorkhellen in #3747
feat(config): add ModelPresetConfig and runtime preset switching by @chengyongru in #3714
chore: remove dead code (vulture + coverage verified) by @chengyongru in #3755
fix(provider): preserve Bedrock tool config for history by @Re-bin in #3758
refactor(agent): remove ask_user tool by @chengyongru in #3757
fix(webui): default to new chat on load and preserve scroll on settings return by @XJPeng12 in #3759
test(agent): expand coverage and refactor test structure by @chengyongru in #3766
feat(reason): display model reasoning content during streaming by @Flinn-X in #3655
feat(runner): model failover with fallback_models by @chengyongru in #3756
fix(mcp): probe HTTP port before connecting to prevent event-loop crash by @chengyongru in #3740
fix(feishu): register no-op handlers for bot member events by @chengyongru in #3775
fix(agent): persist shortcut commands without polluting LLM context by @chengyongru in #3779
[security] fix(feishu): confine downloaded media filenames by @Hinotoi-agent in #3789
feat(pairing): chat-native DM sender approval by @chengyongru in #3774
fix(shell): support UNC paths in Windows path extraction by @JiajunBernoulli in #3764
fix: clear media_paths after successful voice transcription by @tamvicky in #3752
refactor(tools): remove GlobTool by @chengyongru in #3841
[security] fix(message): confine local media attachments by @Hinotoi-agent in #3842
perf(agent): append runtime context after user content for cache stability by @chengyongru in #3844
fix(web): back off Brave search rate limits by @boogieLing in #3840
fix(codex): stabilize prompt cache key by @boogieLing in #3793
feat(goal): /goal command & long-running tasks (long_task) by @Re-bin in #3788
fix(webui): remove eager markdown preload by @yorkhellen in #3782
feat: add Atomic Chat as OpenAI-compatible local LLM provider by @yanalialiuk in #3750
docs(contributing): warn that ruff format predates the codebase by @olgagaga in #3850
fix(agent): align LLM wall timeout with sustained goals for agents by @Re-bin in #3855
fix(exec): allow format in URL parameters while still blocking the format command by @Endeavour-Yuan in #3853
docs: update CLAUDE.md to reflect current codebase by @chengyongru in #3860
fix(agent): remove duplicate runtime context injection in mid-turn drain by @chengyongru in #3859
fix(providers): wire MiMo thinking control on gateway providers (#3845) by @olgagaga in #3851

New Contributors

@LZDQ made their first contribution in #3576
@halldorjanetzko made their first contribution in #3573
@Hinotoi-agent made their first contribution in #3569
@spinvettle made their first contribution in #3563
@tongtianli03-code made their first contribution in #3561
@hongshunanhai made their first contribution in #3577
@futurist made their first contribution in #3632
@kaseru made their first contribution in #3629
@Jefsky made their first contribution in #3660
@zhw415876999-prog made their first contribution in #3677
@vystartasv made their first contribution in #3664
@eugenechae made their first contribution in #3705
@barreler126 made their first contribution in #3707
@NearlCrews made their first contribution in #3733
@AlbertWang688 made their first contribution in #3738
@Flinn-X made their first contribution in #3655
@tamvicky made their first contribution in #3752
@yanalialiuk made their first contribution in #3750
@olgagaga made their first contribution in #3850
@Endeavour-Yuan made their first contribution in #3853

Full Changelog: v0.1.5.post3...v0.2.0

详细ChangeLog

v0.1.5.post3

2026年04月29日

🐈 nanobot v0.1.5.post3 is here 🎉 — 57 PRs merged, 12 new contributors. The agent learned to talk in threads.

If v0.1.5.post2 was about reach and polish, v0.1.5.post3 is about conversations becoming first-class citizens of their platform. Feishu group topics get isolated sessions. Discord threads inherit parent allowlists and keep their own context. Telegram can render inline keyboard choices. MSTeams prunes stale conversation references so outbound messages stop failing silently. And across all channels, sendProgress and sendToolHints can now be overridden per channel — quiet the noisy ones, keep the verbose ones. Underneath, DeepSeek-V4 is supported end to end: thinking mode and legacy session compatibility ship together, with follow-up fixes for incomplete reasoning history and non-string message content so long threads stay stable. A new ask_user tool lets the agent pause and ask you to choose mid-task. Olostep and Hugging Face joined the provider lineup, and a pair of timeout env vars (NANOBOT_LLM_TIMEOUT_S and NANOBOT_OPENAI_COMPAT_TIMEOUT_S) keep hung requests from holding your session hostage. The WebUI continued to evolve — image uploads, video rendering, ask-user choices, model settings — but remains source-preview only, not bundled into the wheel.

Highlights

Threads everywhere — Feishu, Discord, Slack, MSTeams — Each channel grew up this release. Feishu group topics now isolate sessions so messages in one topic don't leak into another; streaming cards and tool hints follow the original topic. Discord threads inherit their parent channel's allowChannels and get session isolation, which also means slash commands respect the allowlist. Slack stopped losing thread context on proactive replies. MSTeams conversation references gained TTL-based pruning (refTtlDays), auto-cleanup for Web Chat refs, and a touch interval to keep active refs alive. The theme is consistent: conversations belong to their thread, not to the channel at large. (#3449, #3397, #3440, #3462, #3475, #3447, #3487)
Per-channel progress and interaction controls — sendProgress and sendToolHints used to be global on-or-off switches. Now you can place them inside any individual channel config to override the global default — keep Telegram quiet while WebSocket stays verbose. The agent also learned to ask users structured questions mid-task via the new ask_user tool: in WebUI these render as buttons, in other channels they fall back to text. Telegram got inline keyboards (inline_keyboards: true) for rendering message tool button choices. The /history [n] command lets you review recent messages without scrolling. (#3487, #2791, #3398, #3454, #3466)
DeepSeek-V4 and the wider provider stack — This release makes DeepSeek-V4 a first-class target: thinking mode and legacy session compatibility land in one go (#3420), so you can point the agent at V4 without abandoning older conversations. Real-world transcripts exposed two gaps that got dedicated follow-ups — truncated or incomplete reasoning history (#3453) and heterogeneous (non-string) message content (#3458) — so tool-heavy sessions don’t fall over mid-run. On top of that, Hugging Face Inference Providers arrived as a first-class provider (#3496), Olostep joined web search (#3505), OpenAI-compatible endpoints gained extraBody for vLLM guided decoding and friends (#3491), and the timeout pair NANOBOT_LLM_TIMEOUT_S / NANOBOT_OPENAI_COMPAT_TIMEOUT_S split outer turn limits from inner HTTP bounds (#3428, #3478). GitHub Copilot routes GPT-5 and o-series models correctly (#3380); Gemini routing picks up reasoning_effort="none" and Gemma (#3515).
Memory and session hardening — consolidationRatio (0.1–0.95) lets you tune how aggressively token-triggered consolidation compresses context. maxMessages (default 120) caps the replay window without touching persistence. History.jsonl gained atomic writes with fsync and directory sync, closing the last data-loss window on unexpected shutdowns. A raw_archive bloat path and several stuck-consolidation edges were sealed. Sessions now fsync on graceful shutdown. The result: memory is both more tunable and more durable. (#3285, #3482, #3508, #3369, #3412, #3415, #3459)
macOS LaunchAgent and deployment — A new docs/deployment.md section walks through deploying nanobot gateway as a macOS LaunchAgent — plist, launchctl bootstrap/enable/kickstart, log paths, and the inevitable port-conflict gotcha when you forget to stop a manual gateway. Useful for anyone who wants the agent online at login without keeping a terminal open. (#3441)
Security and reliability fixes — A shell injection vector via path_append on non-Windows platforms was closed. Workspace directory violations now stop the agent loop instead of logging a warning. resolve_config_env_vars stopped stripping excluded fields. Anthropic image_url blocks inside tool_result content get converted correctly. MCP capability names are sanitized for model API compatibility. Windows MCP stdio launchers avoid WinError 193. Structured tool-event payloads give channels richer progress data. Document parsers lazy-import to cut cold-start time. Twenty-odd smaller fixes across providers, channels, and the agent loop round out the release. (#3366, #3493, #3383, #3387, #3470, #3379, #3399, #3423)

Community

Heartfelt thanks to everyone who shipped v0.1.5.post3 — 57 PRs, 27 contributors, and a huge welcome to 12 first-time contributors. Every review, patch, and bug report helped; this release is a shared win. 🎉

What's Changed

feat(transcription): add language parameter for Whisper STT by @chengyongru in #3375
fix: normalize DashScope reasoning_effort (minimal vs minimum) by @hlgone in #3374
fix(cli): respect sys.stdout.isatty() in commands.py by @knightconnorp in #3370
fix(session): fsync sessions on graceful shutdown to prevent data loss by @hussein1362 in #3369
fix(providers): support GPT-5 models on GitHub Copilot backend by @gongpx20069 in #3380
fix(mcp): avoid WinError 193 for Windows stdio launchers by @lahuman in #3379
fix(agent): prevent duplicate responses when sub-agents complete concurrently by @chengyongru in #3385
fix(anthropic): convert image_url blocks inside tool_result content by @tetratorus in #3387
fix(config): preserve excluded fields in resolve_config_env_vars by @saimonventura in #3383
feat(webui): image attachments — composer + signed media pipeline by @Re-bin in #3393
feat(telegram): add inline keyboard buttons by @gthieleb in #3398
feat(agent): emit structured tool-event payloads via on_progress by @pblocz in #3399
fix(agent): prevent history.jsonl bloat from raw_archive and stuck consolidation by @chengyongru in #3412
fix(agent): bound remaining memory/history pollution paths by @Re-bin in #3415
fix(provider): support DeepSeek V4 thinking mode and legacy session compatibility by @Re-bin in #3420
fix(anthropic): omit temperature for opus-4-7 (#3417) by @04cb in #3418
perf(document): lazy-import heavy document parsers by @mvanhorn in #3423
feat(channels): add video support for Telegram and WebSocket by @Re-bin in #3429
feat(webui): render video media attachments by @Re-bin in #3430
fix(agent): add LLM request timeout to prevent session lock starvation by @yorkhellen in #3428
docs: add macOS LaunchAgent setup for gateway by @choiking in #3441
feat(agent): add ask user tool by @lzmjlrt in #2791
fix(msteams): send threaded replies via replyToId by @chengyongru in #3447
feat(feishu): thread-scoped sessions, reply_in_thread, non-blocking reaction by @chengyongru in #3449
fix(providers): disable HTTP keepalive for local/LAN endpoints by @hussein1362 in #3444
fix(heartbeat): inject delivered messages into channel session for reply continuity by @hussein1362 in #3391
fix(provider): gate reasoning-to-content fallback behind spec flag by @chengyongru in #3446
feat(memory): make consolidate ratio configurable by @chengyongru in #3285
fix(security): prevent shell injection via path_append on non-Windows platforms by @yorkhellen in #3366
fix(provider): handle incomplete DeepSeek reasoning history by @Re-bin in #3453
feat(webui): add ask-user choices and model settings by @Re-bin in #3454
fix(slack): preserve thread context for proactive replies by @Re-bin in #3462
fix(agent): expose session timestamps in model context by @Re-bin in #3463
fix(mcp): sanitize MCP capability names for model API compatibility by @chengyongru in #3470
fix(slack): polish threaded replies and proactive delivery by @Re-bin in #3475
fix(agent): resolve relative media paths in MessageTool by @chengyongru in #3471
fix(agent): subagent announces from threaded callers route to channel session, not the originating thread by @mt-huerta in #3465
fix(provider): normalize DeepSeek non-string message content by @boogieLing in #3458
修复：自动清理未支持或已过期的 MSTeams 会话引用，避免通知发送失败 Fixes: #3433 by @zhuzhh in #3440
feat(session): enforce replay/file-cap invariants for history lifecycle by @boogieLing in #3459
fix(discord): full thread support with session isolation and allowlist enforcement by @Lbin91 in #3397
fix(provider): bound OpenAI-compatible request timeouts by @boogieLing in #3478
fix(heartbeat): prevent internal reasoning leaks and finalization fallback in delivery by @hussein1362 in #3389
feat(command): add /history command to review recent session messages by @LeoFYH in #3466
fix(codex): stream progress deltas to channels by @boogieLing in #3480
feat(config): wire max_messages into session history replay by @hussein1362 in #3482
feat(providers): add Hugging Face inference provider by @chengyongru in #3496
The agent loop should be stopped when workspace directory restrictions are violated by @lvqiushi in #3493
fix(channels): send telegram attachments with named file path by @Seym0n in #3489
feat(web-tools): Improve to allow bypassing Cloudflare captchas by @Mizarka in #3382
feat(providers): add extra_body config for OpenAI-compatible endpoints by @hussein1362 in #3491
fix(feishu): Fix done emoji addition and on-it emoji removal before task actually ends by @BarclayII in #3502
feat(web_search): add olostep provider by @chengyongru in #3505
Fix reasoning_effort="none" handling and add gemma to Gemini routing by @masterlyj in #3515
fix: sanitize Matrix user_id for Windows-safe store file names by @JiajunBernoulli in #3510
feat(channels): support per-channel progress controls by @boogieLing in #3487
fix(memory): ensure atomic write for history.jsonl by @yorkhellen in #3508

New Contributors

@knightconnorp made their first contribution in #3370
@tetratorus made their first contribution in #3387
@saimonventura made their first contribution in #3383
@gthieleb made their first contribution in #3398
@pblocz made their first contribution in #3399
@mvanhorn made their first contribution in #3423
@choiking made their first contribution in #3441
@mt-huerta made their first contribution in #3465
@zhuzhh made their first contribution in #3440
@Seym0n made their first contribution in #3489
@Mizarka made their first contribution in #3382
@BarclayII made their first contribution in #3502

Full Changelog: v0.1.5.post2...v0.1.5.post3

详细ChangeLog

v0.1.5.post2

2026年04月22日

🐈 nanobot v0.1.5.post2 is here 🎉 — 67 PRs merged, 12 new contributors. The agent's world got bigger and steadier.

If v0.1.5.post1 was about the agent learning to manage itself, v0.1.5.post2 is about reach and polish. Windows and Python 3.14 joined the supported matrix. The read_file tool learned to understand DOCX, XLSX, and PPTX. Microsoft Teams arrived as a channel. The OpenAI-compatible API started streaming via SSE. And beneath all of that, ~50 smaller fixes across cron, memory, retry, session files, and provider quirks kept turning "it works" into "it's solid." A dedicated browser UI also started taking shape in the repo — source preview for now.

Highlights

Windows + Python 3.14 — first-class support — A full CI matrix covering Windows runners and Python 3.14 landed, along with install markers and runtime fixes for the quirks those platforms expose. If you've been running nanobot on WSL because "Windows didn't quite work," you can stop. (#3194)
Office documents, natively readable — The read_file tool now extracts text from DOCX, XLSX, and PPTX — tables and grouped shapes included, workbook handles closed safely. Combined with the earlier PDF support, the agent can open whatever format your colleague just emailed you without bouncing through a converter. (#3336, #3269, #3353)
OpenAI-compatible API — SSE streaming — /v1/chat/completions now emits SSE chunks when stream=true, wiring up the existing on_stream / on_stream_end callbacks. Any client built for the OpenAI API — LangChain, LlamaIndex, your own frontend — gets live deltas from nanobot instead of waiting for the whole response. The endpoint also stopped terminating streams with a success marker after a backend failure, so errors surface honestly. (#3222, #3262)
Microsoft Teams, MiniMax thinking, LM Studio, MyTool — Microsoft Teams joined the channel roster. MiniMax got a dedicated Anthropic-style thinking endpoint plus a reasoning_effort → reasoning_split mapping fix. LM Studio is now supported via nullable API keys for local servers that don't expect one. The new MyTool lets the agent introspect its own runtime configuration — and hides sensitive nested config fields in check output so self-inspection doesn't leak secrets. (#3197, #3160, #3363, #3186, #3177, #3261)
Reliability — the unglamorous half of a release — Session files now use atomic writes with corrupt-file repair, so a bad shutdown no longer eats your history. Memory cursor recovery handles non-integer corruption. Auto-compact skips sessions with active tasks and unifies summary injection across consolidation paths. Providers gain a circuit breaker for Responses API fallback and recognize ZhiPu 1302 rate limits. Cron stops leaking intermediate progress, its tool schema works with OpenAI Codex/Responses, and retry heartbeats no longer spill into user channels. Subagent follow-ups persist in session history. Half of these you'll never notice — which is exactly the point. (#3312, #3340, #3081, #3304, #3302, #3356, #3320, #3295, #3229, #3242)
Channels — quieter and sharper — Telegram gained mid-stream splitting for long replies and better markdown rendering for modern LLM output. Discord stopped treating bot-to-bot messages as self-loops and added channel-based allow-lists. Email deduplicates SPF/DKIM-rejected messages to stop log spam and ignores self-sent mailbox messages. WeCom parses mixed inbound messages correctly. Each individually small; together they mean fewer "why did my bot do that" moments. (#3329, #3355, #3280, #3171, #3325, #3228, #3161)
WebUI — early preview, source only — A dedicated webui/ has landed in the repo with a WebSocket chat flow, i18n locale switcher, Apple-inspired typography with CJK support, and live dark-mode code-block theming. The underlying WebSocket channel also learned to multiplex multiple chat_ids over a single connection. Heads up: this is source-preview only — the WebUI is intentionally not bundled into the published wheel yet. If you want to try it, clone the repo and run it from webui/. A packaged release will follow once the UX settles. (#3310, #3272, #3314, #3306)

Community

v0.1.5.post2 is what a release looks like when the foundation is done and people start finishing things. A Windows CI matrix from @JiajunBernoulli. Native Office document extraction from @aiguozhi123456. Session atomic writes from the same author, catching a real data-loss edge case. A Telegram mid-stream split that makes long replies actually readable. Twelve new contributors, and a lot of returning ones quietly landing the things that were on everyone's wish list. The agent runs on Windows. It reads your documents. It keeps its history even when the power blinks. And there's a UI taking shape in webui/ for whoever wants to peek. That's a post release doing post-release work — and then some.

What's Changed

fix(agent): skip auto-compact for sessions with active agent tasks by @chengyongru in #3085
fix(provider): recover trailing assistant as user to prevent Zhipu 1214 by @chengyongru in #3086
fix(log): remove noisy no-op logs from auto-compact by @chengyongru in #3094
fix(log): only log auto-compact when messages are actually archived by @chengyongru in #3099
refactor(context): deduplicate system prompt by @chengyongru in #3162
fix(channel.wecom): inbound mixed msg parse by @dzydzydzy7 in #3161
fix(providers): guard chat_with_retry against explicit None max_tokens (#3102) by @04cb in #3157
fix(cron): respect deliver flag when agent produces output by @chengyongru in #3168
feat(provider): add MiniMax Anthropic endpoint for thinking mode 添加minimax的思考模式 by @Aisht669 in #3160
fix(discord): remove duplicate channel_id assignment in message handler by @LeoFYH in #3178
Add support for nullable API keys and LM Studio by @sohamb117 in #3186
fix(memory): handle missing cursor key in history entries by @JiajunBernoulli in #3195
feat(msteams): add Microsoft Teams channel by @chengyongru in #3197
fix(skills): use yaml.safe_load for frontmatter parsing to handle multiline descriptions by @yanghan-cyber in #3141
fix(status): correct context percentage and sync consolidator by @chengyongru in #3209
fix(api): prevent upload filename collisions and reject unsupported image URLs by @mohamed-elkholy95 in #3187
perf(tools): cache ToolRegistry.get_definitions() between mutations by @chengyongru in #3210
feat(agent): add MyTool for runtime self-inspection by @chengyongru in #3177
feat(api): afeat(api): add SSE streaming for /v1/chat/completions by @wanghesong2019 in #3222
feat: add channel-based filtering for Discord by @Lbin91 in #3171
feat(dream): git-based section age annotations for memory staleness by @chengyongru in #3212
fix: pass apiBase from config to transcription providers (Groq & OpenAI) by @chengyongru in #3237
feat(windows): Windows + Python 3.14 support — CI matrix, install markers, runtime fixes by @JiajunBernoulli in #3194
fix(agent): preserve user message to prevent GLM error 1214 by @chengyongru in #3233
fix(email): ignore self-sent mailbox messages by @yorkhellen in #3228
fix(exec): pass allowed_env_keys to exec tool calls in subagents by @mcampo in #3238
fix(docs): update channel plugin build backend to hatchling by @JiajunBernoulli in #3192
fix(memory): fall back to raw_archive on LLM error response by @chengyongru in #3248
fix: guard tool execution against non-compliant API gateway injection #3220 by @subalkum in #3225
fix: make cron tool schema require message for add action by @sicnuyudidi in #3163
fix(api): avoid success-style SSE termination after backend failure by @shaun0927 in #3262
fix(my-tool): hide sensitive nested config fields in check output by @shaun0927 in #3261
fix(utils): extract PPTX table cells and grouped shape text (#3250) by @04cb in #3269
fix(loop): persist subagent follow-up events in session history by @xzq-xu in #3242
fix(agent): stop leaking provider retry heartbeats to user channels by @SamZhu19921116 in #3229
feat(websocket): multiplex multiple chat_ids over a single connection by @Re-bin in #3272
refactor(templates): separate identity and SOUL responsibilities by @chengyongru in #3275
feat(wizard): add Channel Common, API Server menus and constraint validation by @chengyongru in #3273
feat: add issue templates by @chengyongru in #3287
fix: prevent GitStore from creating nested repos and overwriting .gitignore by @longle325 in #3289
fix: harden cron tool contract by @yeyitech in #3125
fix(config): return provider default api base in config resolution by @morandot in #3112
fix(cli): respect sys.stdout.isatty() in stream renderer (#3265) by @pixan-ai in #3271
docs: refactor README into a docs-first landing page by @Re-bin in #3306
fix: unify summary injection strategy between token consolidation and auto-compact by @JiajunBernoulli in #3304
fix(providers): add circuit breaker for Responses API fallback by @chengyongru in #3302
feat(webui): add initial browser UI with websocket chat and i18n by @Re-bin in #3310
fix(cron): drop top-level oneOf so OpenAI Codex/Responses accept tool schema by @coldxiangyu163 in #3295
fix(discord): allow bot-to-bot messaging, only drop self-loops (#3217) by @pixan-ai in #3280
fix(session): prevent data loss with atomic writes and corrupt-file repair by @aiguozhi123456 in #3312
style(webui): improve typography and code block rendering by @chengyongru in #3314
fix: suppress intermediate progress output in cron jobs by @chengyongru in #3320
fix(agent): align subagent result session key with main agent for mid-turn injection by @chengyongru in #3321
fix(email): deduplicate SPF/DKIM-rejected emails to stop log spam by @chengyongru in #3325
feat(telegram): mid-stream split in send_delta by @chengyongru in #3329
fix(utils): strip malformed think tags and harmony channel markers by @hlgone in #3327
fix(loop): preserve partial context when /stop cancels a task by @hussein1362 in #3299
fix(anthropic): strip trailing assistant messages to prevent prefill error by @hussein1362 in #3297
fix(mcp): retry once on transient connection errors by @hussein1362 in #3338
agent: use ContextVar for tool routing context by @chengyongru in #3345
fix(memory): harden cursor recovery against non-integer corruption by @MuataSr in #3340
fix(retry): recognize ZhiPu 1302 rate-limit error for retry by @chengyongru in #3356
fix(telegram): improve markdown rendering for modern LLM output by @hussein1362 in #3355
fix(commands): intercept non-priority commands during active turn by @chengyongru in #3359
fix(utils/document): use try/finally in _extract_xlsx to ensure workbook is always closed by @XJPeng12 in #3353
feat(read_file): add DOCX, XLSX, PPTX office document support by @aiguozhi123456 in #3336
Fix/minimax reasoning split by @lahuman in #3363

New Contributors

@dzydzydzy7 made their first contribution in #3161
@Aisht669 made their first contribution in #3160
@sohamb117 made their first contribution in #3186
@Lbin91 made their first contribution in #3171
@mcampo made their first contribution in #3238
@sicnuyudidi made their first contribution in #3163
@SamZhu19921116 made their first contribution in #3229
@longle325 made their first contribution in #3289
@hlgone made their first contribution in #3327
@hussein1362 made their first contribution in #3299
@MuataSr made their first contribution in #3340
@lahuman made their first contribution in #3363

Full Changelog: v0.1.5.post1...v0.1.5.post2

详细ChangeLog

v0.1.5.post1

2026年04月15日

🐈 nanobot v0.1.5.post1 is here 🎉 — 80 PRs merged, 25 new contributors. The agent learned to manage itself.

If v0.1.5 was about making the building livable, v0.1.5.post1 is about the building learning to take care of itself. The agent now compresses its own context before it gets too long, injects follow-up messages mid-turn instead of making you wait, discovers reusable skills from its own workflows, and opens a WebSocket so anything can talk to it. Meanwhile, 40+ bug fixes across cron, memory, retry, and channels turned "it works most of the time" into "it works."

Highlights

Mid-turn injection — follow-ups don't wait in line — If you send another message while the agent is still working, it no longer queues behind a lock. The follow-up gets injected into the active turn, and on streaming channels the reply continues in the same live response. This makes long tool-call chains feel interactive instead of one-way. Edge-case draining on error paths was hardened in a follow-up pass. (#3042, #3110)
Dream learns skills, not just facts — Dream's consolidation flow can now recognize repeated workflows and promote them into standalone workspace skills under skills/. Combined with disabledSkills config for excluding skills you don't want, the agent's skill surface is now something that grows organically and stays manageable. (#3048, #2959)
Auto compact — the agent manages its own context — Sessions no longer grow until they hit the wall. Auto compact watches for idle periods, then proactively summarizes older context while preserving recent live messages — so when you come back, the agent remembers what matters without dragging along everything that doesn't. This isn't the old "nuke the session" approach; it's surgical compression that keeps the conversation feeling continuous. Pair it with idleCompactAfterMinutes in config for fine-grained control. (#3007, #3081, #3093)
WebSocket channel — connect anything — A new websocket channel runs a WebSocket server with streaming (delta + stream_end events), token-based auth (static or issued), per-connection sessions, and TLS support. Web apps, CLIs, Chrome extensions, scripts — anything that can open a socket can now talk to the agent in real time. (#2964)
Channels got deeper — Telegram gained location sharing. Discord got streaming replies and proxy support. Feishu added done-emoji lifecycle, inline tool hints, and Lark global domain config. QQ and WeCom received full media support. Slack's message tool now resolves #channel_name and @user to real IDs. The API endpoint accepts file uploads via JSON base64 and multipart, with automatic document extraction (PDF, DOCX, XLSX, PPTX) across all channels. And retry amplification — where a failed send would trigger cascading retries — was fixed across every channel. (#2910, #2939, #2960, #2993, #3046, #3044, #3138, #2938, #3053)
Providers — adaptive thinking and Kimi — Anthropic's adaptive reasoning mode landed, letting Claude decide when and how much to think. Kimi thinking-capable models (kimi-k2.5, k2.6-code-preview) now get automatic extra_body.thinking injection via reasoningEffort. StepFun Plan API reasoning fields fall back correctly. Non-Claude providers get proper role alternation enforcement. And tool-call arguments are normalized for strict providers that reject malformed JSON. (#2882, #3124, #2903, #2637, #3154)
MCP, tools, and search — MCP resources and prompts are now exposed as read-only tools — the agent can query them directly. Multiple MCP servers connect in isolated tasks instead of racing each other. The notebook editing tool arrived. Kagi joined the web search provider lineup. And the exec tool got tighter: Windows support landed, allowed_env_keys lets you selectively forward env vars, internal state files are write-protected, and working_dir outside the workspace is rejected. (#2907, #3019, #3017, #2945, #2893, #2962, #3061)
Cron stopped dropping jobs — Four separate cron fixes addressed reentrant store reloads during job execution, fixed-interval tasks duplicating due to concurrent store replacement, job config not reloading, and manual run state not being preserved. If you rely on scheduled tasks, this release is the one where they become boring. (#3038, #3034, #2895, #2930)

Community

Welcome to our 25 new contributors who made their first contribution in this release: @Bahtya, @LeoFYH, @xwind, @Xerxes-cn, @BalorLC3, @invictus-z, @zijiefang, @kronk307, @stutiredboy, @SHLE1, @RohitDayanand, @justforyoudear, @XJPeng12, @linziyanleo, @chenyahui, @JonasGao, @weitongtong, @danielphang, @mterhar, @ramonpaolo, @nikube, @yeyitech, @ravs-cyberrock, @samyzhh, and @razzh7.

v0.1.5.post1 reflects something we keep seeing in the commit log: the best contributions aren't always the flashiest ones. A cron race condition caught by @weitongtong. A retry amplification loop spotted by @Bahtya. A channel error path that silently swallowed messages, fixed by @yanghan-cyber. These are the changes that make an agent trustworthy — not because it can do more, but because it stops doing things wrong. 80 PRs later, nanobot is quieter, steadier, and a little more grown-up. That's worth celebrating.

Full Changelog: v0.1.5...v0.1.5.post1

What's Changed

fix(matrix): correct e2eeEnabled camelCase alias mapping by @Bahtya in #2877
fix(filesystem): correct write success message from bytes to characters by @LeoFYH in #2865
fix: Matrix e2eeEnabled config alias and cron job name parameter (#2851, #2680) by @04cb in #2855
ci: add ruff lint check for unused imports and variables by @JiajunBernoulli in #2847
fix(docker): Windows CRLF breaks entrypoint.sh by @flobo3 in #2883
fix(cli): sanitize surrogate characters in prompt history by @Bahtya in #2869
fix(feishu): resolve mentions data and ensure access token initializationDev by @xwind in #2885
fix(runner): silent retry on empty response before finalization by @Re-bin in #2889
feat(agent): tool hint enhancement by @chengyongru in #2884
feat(memory):dream enhancement (#2887) by @chengyongru in #2891
fix(cron): fix not reload job config by @Xerxes-cn in #2895
feat(anthropic): add adaptive thinking mode by @BalorLC3 in #2882
docs: fix channel plugin guide — require Pydantic config model by @invictus-z in #2850
fix(memory): prevent potential loss of compressed session history by @LingaoM in #2890
fix(memory): add timestamp and cap to recent history injection by @Re-bin in #2906
feat(mcp): expose MCP resources and prompts as read-only tools by @Re-bin in #2907
chore: update .gitignore to include additional project-specific, build, test, and environment files by @JackLuguibin in #2862
fix(provider): fallback to reasoning field for StepFun Plan API by @zijiefang in #2903
fix(exec): add Windows support for shell command execution by @Re-bin in #2893
feat(agent): prompt behavior directives, tool descriptions, and loop robustness by @Re-bin in #2912
feat(telegram): add location/geo support by @kronk307 in #2910
feat: telegram support stream edit interval by @stutiredboy in #2919
fix(tool-hint): fold paths in exec commands and deduplicate by formatted string by @chengyongru in #2926
fix(cron): Concurrency issues by @Xerxes-cn in #2930
refactor(hook): add reraise flag to AgentHook and remove _LoopHookChain by @LingaoM in #2918
Fix version mismatch: use importlib.metadata as single source of truth by @Bahtya in #2860
fix(discord): enable streaming replies to avoid empty final response by @SHLE1 in #2939
fix(status): use consistent divisor for token count display by @LeoFYH in #2951
fix(dingtalk): #2696 by @RohitDayanand in #2948
fix(exec): forward complete Windows env to subprocesses by @justforyoudear in #2941
feat: unified session across channels via config toggle (closes #2798) by @wanghesong2019 in #2900
fix(helpers): ensure assistant message content is never None by @pixan-ai in #2748
fix(cli): remove default green style from Enabled column in tables by @XJPeng12 in #2936
fix(providers): enforce role alternation for non-Claude providers by @linziyanleo in #2637
feat(channels): add WebSocket server channel by @chengyongru in #2964
fix(agent): deliver LLM errors to streaming channels and avoid polluting session context by @yanghan-cyber in #2963
feat(exec): support allowed_env_keys to pass specified env vars to su… by @chenyahui in #2962
feat(channel): add proxy support for Discord channel by @JonasGao in #2960
fix: strip blocks from Gemma 4 and similar models by @chengyongru in #2991
feat(feishu): streaming resuming, inline tool hints, and done emoji by @chengyongru in #2993
fix(memory): harden consolidation with try/except on token estimation and chunk size cap by @franciscomaestre in #2978
fix(agent): Avoid truncate_text name shadowing by @yorkhellen in #2997
feat(cron): 添加 CronService.update_job 方法 by @weitongtong in #3005
fix(utils): anchor unclosed think-tag regex to string start (#3004) by @04cb in #3020
feat(agent): auto compact — proactive session compression by @chengyongru in #3007
fix(cron): 修复固定间隔任务因 store 并发替换导致的重复执行 by @weitongtong in #3034
fix(cron): guard _load_store against reentrant reload during job execution by @danielphang in #3038
feat: Add Kagi search by @mterhar in #2945
fix(mcp): support multiple MCP servers by connecting each in isolated… by @Qinnnnnn in #3019
feat(tool): improve file editing and add notebook tool by @Re-bin in #3017
fix(feishu): improve voice message download with detailed logging by @chengyongru in #3041
feat(agent): mid-turn message injection for responsive follow-ups by @chengyongru in #3042
feat(channels): Add full media support for QQ and WeCom channels by @chengyongru in #3044
fix(agent): preserve tool results on fatal error to prevent orphan tool_calls (#2943) by @04cb in #3045
feat(channels/feishu): add domain config for Lark global support by @chengyongru in #3046
feat(skills): add disabled_skills config to exclude skills from loading by @chenyahui in #2959
fix(shell): tighten exec safety guards (#2989, #2826) by @04cb in #3061
feat(agent): integrate skill discovery into Dream by @chengyongru in #3048
fix(retry): strip images in-place to prevent repeated error-retry cycles by @yanghan-cyber in #3060
fix(channels): prevent retry amplification and silent message loss across channels by @Bahtya in #3053
fix(provider): clarify local 502 recovery hints by @haosenwang1018 in #3075
fix(mcp): hint on stdio protocol pollution by @haosenwang1018 in #3079
fix: improve tool call parameter validation and error messages by @ramonpaolo in #2859
fix(agent): persist user message before running turn loop by @nikube in #3076
fix(agent): skip auto-compact for sessions with active agent tasks by @chengyongru in #3081
fix(provider): recover trailing assistant as user to prevent Zhipu 1214 by @chengyongru in #3082
docs(provider): clarify responses api routing by @haosenwang1018 in #3089
fix(log): remove noisy no-op logs from auto-compact by @chengyongru in #3093
fix(agent): drain injection queue on error/edge-case exit paths by @chengyongru in #3110
fix(web): serialize duckduckgo search calls by @yeyitech in #3128
test(loop): cover /stop checkpoint recovery by @yeyitech in #3130
feat: add HTTP health endpoint on gateway port by @ravs-cyberrock in #2625
fix(feishu): remove resuming and add streaming card fallback by @chengyongru in #3133
feat(slack): resolve named message targets by @yeyitech in #3138
feat(api): support file uploads via JSON base64 and multipart/form-data by @dividduang in #2938
fix: handle dict config in is_allowed() and _validate_allow_from() by @samyzhh in #3153
fix: normalize tool-call arguments for strict providers by @Michael-lhh in #3154
feat: show active task count in /status output by @aiguozhi123456 in #3149
fix: add retry termination notification to interaction channel by @aiguozhi123456 in #3150
feat(provider): enable Kimi thinking via extra_body for k2.5 and k2.6 by @razzh7 in #3124

New Contributors

@Bahtya made their first contribution in #2877
@LeoFYH made their first contribution in #2865
@xwind made their first contribution in #2885
@Xerxes-cn made their first contribution in #2895
@BalorLC3 made their first contribution in #2882
@invictus-z made their first contribution in #2850
@zijiefang made their first contribution in #2903
@kronk307 made their first contribution in #2910
@stutiredboy made their first contribution in #2919
@SHLE1 made their first contribution in #2939
@RohitDayanand made their first contribution in #2948
@justforyoudear made their first contribution in #2941
@XJPeng12 made their first contribution in #2936
@linziyanleo made their first contribution in #2637
@chenyahui made their first contribution in #2962
@JonasGao made their first contribution in #2960
@weitongtong made their first contribution in #3005
@danielphang made their first contribution in #3038
@mterhar made their first contribution in #2945
@ramonpaolo made their first contribution in #2859
@nikube made their first contribution in #3076
@yeyitech made their first contribution in #3128
@ravs-cyberrock made their first contribution in #2625
@samyzhh made their first contribution in #3153
@razzh7 made their first contribution in #3124

Full Changelog: v0.1.5...v0.1.5.post1

详细ChangeLog

v0.1.5

2026年04月06日

🐈 nanobot v0.1.5 is here 🎉 — 66 PRs merged, 27 new contributors, and the first release with its own home.

We're excited to announce that nanobot now has an official website at nanobot.wiki, with multilingual documentation in English, Chinese, Japanese, Korean, Spanish, and French. Building it reminded us why we do this: nanobot has always belonged to the open-source community, and a proper home — one that speaks your language — felt overdue. Every doc page, every translation, every example is open and contribution-ready. That's not going to change.

Now, about the release itself. If v0.1.4.post6 was about decomposing the foundation, v0.1.5 is about making the building livable. The agent can now run for hours without losing its mind. Memory got a proper architecture. And running nanobot in production went from "possible" to "comfortable." This is the release where nanobot stops being a prototype and starts being infrastructure.

Highlights

Long-running tasks got more reliable — Long-running tasks received a ground-up reliability pass. The runtime now handles CancelledError without orphaning subprocesses, retry classification uses structured error metadata instead of regex-on-error-text (so a 429 quota exhaustion stops immediately while a rate limit waits and retries), SDK-level auto-retries were disabled to prevent request amplification, and Azure retries no longer double-dip. If your agent runs cron jobs, orchestrates tools overnight, or handles bursty traffic — this is the release that makes those sessions stick. (#2733, #2762, #2759, #2761, #2765)
Memory got an architecture — meet Dream — The new two-stage memory system separates live conversation history from consolidated long-term knowledge. Dream runs as a background consolidation pass — think of it as the agent sleeping on what it learned — backed by git-versioned storage so every memory state is recoverable. Legacy HISTORY.md files migrate automatically. Jinja2 templating arrived alongside Dream, giving you control over how the agent shapes its responses and memory summaries. This isn't a feature bolted on — it's the memory system nanobot should have had from day one. (#2717, #2779, and 10+ follow-up hardening commits)
Running nanobot in production got real — exec calls are now sandboxed via bwrap and containers run as non-root by default. The exec tool no longer leaks host environment variables to the LLM. API port binds to localhost by default. Config secrets support ${VAR} interpolation so you never have to hardcode a key again. A new nanobot-api Docker service gives you an isolated OpenAI-compatible endpoint out of the box. WhatsApp bridge gained automatic local auth. These aren't glamorous changes — they're the reason you'll sleep through the night after deploying. (#1940, #2831, #2830, #2841, #2715)
Three new providers, and GPT-5 is ready — GPT-5 model family support landed with proper temperature handling. Xiaomi MiMo joined for on-device inference fans. Baidu Qianfan arrived for the Chinese ecosystem. Dashscope and ModelArk got proper thinking parameter control. And reasoning_content (chain-of-thought from DeepSeek-R1, Kimi, MiMo) is now visible and preserved through the full message pipeline. nanobot keeps meeting users wherever their models are. (#2788, #2495, #2811, #2840, #2770)
Channels kept getting better — Email now extracts attachments with MIME filtering and filename sanitization. WhatsApp gained voice transcription via Groq/OpenAI Whisper. Feishu auto-removes reactions after processing and supports video downloads. Telegram renders tool hints as collapsible blockquotes, supports DM threads, and splits oversized streamed replies. WeChat multimodal alignment continued. Langfuse integration landed for production observability. And /status now shows web search provider usage alongside cache hit rates. (#2815, #2530, #2812, #2810, #2793, #2520, #2659, #2832, #2703)
Developer experience, quietly — Built-in grep and glob tools give the agent native code search. The Tool class was refactored with proper JSON Schema for parameters. The Python SDK facade enables programmatic per-session isolation. The CLI gained --config for multi-instance setups. Web search was unified under WebToolsConfig with toggle controls. And the test suite grew to 1,142 tests, all green. (#2754, #2780, #2653, #2740, #2643)

Community

Welcome to our 27 new contributors who made their first contribution in this release.

v0.1.5 is shaped by a simple conviction: an AI agent framework earns trust not by adding features, but by being the kind of software you'd run unattended on a Friday night. Memory that doesn't forget. Retries that don't amplify. Sandboxes that don't leak. Every contributor who hardened a boundary, caught a race condition, or added a test — you made nanobot more trustworthy today than it was yesterday. That's the only metric that matters.

Full Changelog: v0.1.4.post6...v0.1.5

What's Changed

fix(skill-creator): Fix grammar in SKILL.md: 'another the agent' by @quanmou in #2586
feat: add OpenAI-compatible API by @goxofy in #1362
feat(agent): add CompositeHook for composable lifecycle hooks by @sontianye in #2615
feat: add Python SDK facade and per-session isolation by @Re-bin in #2653
fix: three minor user-facing fixes (#2651, #2566, #2579) by @04cb in #2656
fix: Prevent ExecTool registration in Subagent when exec_config.enable is False by @yorkhellen in #2648
feat(channel): matrix/discord enhancement by @chengyongru in #2673
Feat(WeiXin): WeXin multimodal capabilities and align with version 2.1.1 by @xcosmosbox in #2614
fix(test): fix flaky test_fixed_session_requests_are_serialized by @chengyongru in #2676
fix: restore GitHub Copilot auth flow by @RongLei-intel in #2668
fix(agent): message tool incorrectly replies to original chat when targeting different chat_id by @WormW in #2474
fix: ExecTool to block root directory paths when restrict_to_workspace is enabled by @yorkhellen in #2683
fix(providers): only apply cache_control for Claude models on OpenRouter by @Tejas1Koli in #2687
feat(provider): show cache hit rate in /status (#2645) by @chengyongru in #2703
feat(cron): add deliver parameter to support silent jobs by @xgzlucario in #2718
chore(provider): Use OpenAI Responses API for Azure OpenAI Provider by @kunalk16 in #2661
test(matrix): skip cleanly when optional deps are missing by @haosenwang1018 in #2741
feat(cli): add --config option to channels login and status commands by @masterlyj in #2740
feat: harden agent runtime for long-running tasks by @Re-bin in #2733
feat(channel): channel enhancement by @chengyongru in #2769
fix: restore Weixin typing indicator by @cypggs in #2646
feat(provider): add Xiaomi MiMo LLM support by @LingaoM in #2495
feat(provider): support reasoning_content in OpenAI compat provider by @LingaoM in #2770
fix(restart): send completion notice after channel is ready and unify… by @imfondof in #2745
feat: unify web tool config under WebToolsConfig + add web tool toggle controls by @Shiniese in #2643
fix: Support media directory access when restrict_to_workspace is enabled by @Shiniese in #2743
fix: Retry-After was ignored, causing premature retries (now honors header/json hints) by @pikaxinge in #2761
fix: stop retry amplification (12→4 requests) by disabling SDK auto-retries by @pikaxinge in #2759
feat(memory): two-stage memory system with Dream consolidation by @chengyongru in #2717
feat: integrate Jinja2 templating for agent responses and memory cons… by @JackLuguibin in #2779
fix(security): add ssrfWhitelist config to unblock Tailscale/CGNAT (#2669) by @04cb in #2715
refactor: streamline Tool class methods and improve type handling by @JackLuguibin in #2780
fix(provider): restore reasoning_content and extra_content in message… by @LingaoM in #2786
feat(providers): add GPT-5 model family support by @friday-james in #2788
perf(cache): stabilize tool prefix caching under MCP tool churn by @pikaxinge in #2722
fix(docker): rewrite github ssh git deps to https for npm build by @Wenzhang-Chen in #1700
feat(agent): add built-in grep and glob search tools by @Re-bin in #2754
fix(cli): prevent spinner ANSI escape codes from being printed verbatim by @chengyongru in #2809
feat(telegram): render tool hints as expandable blockquotes by @chengyongru in #2810
feat(provider): add Qianfan provider support by @chengyongru in #2811
feat(feishu): auto-remove reaction after processing and support video download by @chengyongru in #2812
fix: stop leaking reasoning_content to stream output by @chengyongru in #2817
fix(dream): allow LLM to retry on tool errors by @chengyongru in #2824
fix(web-search): fix Jina search request format and restore DuckDuckGo fallback by @KimGLee in #2808
Fix: add asyncio timeout guard for DuckDuckGo search by @hoaresky in #2805
fix(telegram): support threads in DMs by @IlyaSemenov in #2793
refactor(agent): streamline hook method calls and enhance error logging by @JackLuguibin in #2794
feat: sandbox exec calls with bwrap and run container as non-root (minimally fixes #1873) by @kinchahoy in #1940
chore: add codespell support (config, workflow to detect/not fix) and make it fix a few typos by @yarikoptic in #121
security: prevent exec tool from leaking process env vars by @benlenarts in #2831
docs: another two places for renaming assitant to agent by @qixinbo in #2835
expand /status to show web search provider usage limits (#2820) by @wanghesong2019 in #2832
security: support ${VAR} env var interpolation for config secrets by @benlenarts in #2830
fix(shell): kill subprocess on CancelledError to prevent orphan proce… by @LingaoM in #2765
fix(feishu): match bot's own open_id in _is_bot_mentioned to prevent … by @yq612 in #2719
feat(provider): 添加 Langfuse 观测平台的集成支持 by @lang07123 in #2659
fix(matrix): fix e2ee authentication by @limdingwen in #2596
feat(whatsapp): add voice message transcription via OpenAI/Groq Whisper by @franciscomaestre in #2530
fix(whatsapp): detect phone vs LID by JID suffix, not field name by @franciscomaestre in #2531
Fix cron reminder notifications being suppressed by @mrbob-git in #2449
fix(telegram): split oversized final streamed replies by @Michael-lhh in #2520
feat(email): add attachment extraction support by @benlenarts in #2815
feat(agent): Adjust thinking method for Dashscope and Modelark by @power88 in #2840
feat(docker): add nanobot-api service with isolated workspace by @dividduang in #2841
fix: make app-layer retry classification structured (408/409/timeout/connection) by @pikaxinge in #2762
fix(status): use correct AgentLoop attribute for web search config by @yanghan-cyber in #2844

New Contributors

@quanmou made their first contribution in #2586
@goxofy made their first contribution in #1362
@sontianye made their first contribution in #2615
@RongLei-intel made their first contribution in #2668
@WormW made their first contribution in #2474
@Tejas1Koli made their first contribution in #2687
@masterlyj made their first contribution in #2740
@cypggs made their first contribution in #2646
@LingaoM made their first contribution in #2495
@imfondof made their first contribution in #2745
@Shiniese made their first contribution in #2643
@friday-james made their first contribution in #2788
@Wenzhang-Chen made their first contribution in #1700
@hoaresky made their first contribution in #2805
@IlyaSemenov made their first contribution in #2793
@kinchahoy made their first contribution in #1940
@yarikoptic made their first contribution in #121
@qixinbo made their first contribution in #2835
@wanghesong2019 made their first contribution in #2832
@yq612 made their first contribution in #2719
@lang07123 made their first contribution in #2659
@limdingwen made their first contribution in #2596
@franciscomaestre made their first contribution in #2530
@mrbob-git made their first contribution in #2449
@power88 made their first contribution in #2840
@dividduang made their first contribution in #2841
@yanghan-cyber made their first contribution in #2844

Full Changelog: v0.1.4.post6...v0.1.5

详细ChangeLog

v0.1.4.post6

2026年03月27日

🐈 nanobot v0.1.4.post6 is here — 57 PRs merged, 27 new contributors, and a release that's less about adding surface area than about rethinking what's underneath.

Some releases are about what you can do. This one is about how cleanly you can do it. The agent runtime got formally decomposed, a major dependency was removed, streaming went end-to-end, and a security vulnerability was closed. Beneath the feature work, v0.1.4.post6 is a structural turning point — the kind of release that makes the next release possible.

Highlights

The agent runtime was decomposed into composable pieces — A shared AgentRunner was extracted, lifecycle hooks were unified into a formal HookContext, and subagent progress is now preserved even on failure. Command routing was refactored into a plugin-friendly structure, and process_direct was unified to return OutboundMessage consistently. This isn't just cleanup — it's the foundation for pluggable agent behaviors, custom execution strategies, and third-party lifecycle integrations that are coming next. (#2524, #2541, #2388, #2338)
litellm was replaced with native OpenAI + Anthropic SDKs — The entire provider layer was rewritten to talk directly to upstream SDKs instead of routing through litellm. Prompt cache optimization for Anthropic, proper max_completion_tokens handling for OpenAI o1, and Gemini thought signature preservation all came along for the ride. If you've ever debugged a litellm traceback at 2am, you understand why this matters. (#2448, #1109, #2468, #2550, #2453)
Streaming went end-to-end — From provider to channel to CLI, streaming output now flows as a first-class path. Feishu gained CardKit streaming support, queued stream deltas are coalesced to reduce API calls, and the channel manager handles stream boundaries correctly. This is the difference between "the bot is typing..." and actually watching it think. (#2365, #2545, #2497)
A security vulnerability was patched — Email injection and spoofing via missing authentication verification has been fixed. Inbound emails now verify SPF/DKIM through Authentication-Results headers, with verify_dkim and verify_spf enabled by default. Email content is tagged with [EMAIL-CONTEXT] to prevent LLM prompt injection from email bodies. See the advisory for details. (GHSA-4gmr-2vc8-7qh3)
WeChat support landed as a full channel — WeChat (Weixin) joined the channel family with HTTP long-poll, QR code login, and plugin 1.0.3 compatibility. Alongside it, Telegram, QQ, WhatsApp, and Feishu all received cross-channel enhancements including retry mechanisms with exponential backoff. (#2412, #2428, #2386, #2478)
Provider coverage kept expanding — Mistral and OVMS providers arrived, Step Fun (阶跃星辰) joined the ecosystem, and custom provider error reporting got much more honest — raw API errors instead of opaque JSONDecodeError. nanobot continues to meet users wherever their models live. (#2199, #2472, #2289, #2139)
The agent got smarter about resources — Per-session concurrent dispatch landed, native multimodal sensory capabilities were added, token estimation now counts all message fields, and memory consolidation properly reserves completion headroom. The agent loop also handles CancelledError gracefully and records subagent results with correct roles. (#2393, #2304, #2344, #2378, #2239, #2104)
Feishu and Telegram both leveled up — Feishu gained streaming cards, code block parsing in post messages, and fixes for markdown rendering and media types. Telegram got HTTP(S) URL media support, separated connection pools to prevent pool exhaustion, and quieter network error logging. Small individually, substantial together. (#2545, #2246, #1814, #1755, #1793, #2247, #2272)
CLI and onboarding became more capable — A full-featured onboard wizard arrived, --dir enables multiple instances, /status shows runtime info, -h works everywhere, and timezone is now configurable. The kind of polish that makes first-run experience feel intentional. (#2101, #1763, #1985, #2123, #2477, #1136, #2266)
Infrastructure hardened across the board — Zombie processes are reaped on shell timeout, cron job stores are scoped to workspaces, MCP tool schemas handle nullable params correctly, Docker builds include openssh-client, and the test suite was reorganized into a cleaner structure. The kind of work that prevents the bug report you'd otherwise file next month. (#2362, #2204, #2230, #2287, #1911, #2427, #2367)

Community

A warm welcome to our 27 new contributors in this release.

v0.1.4.post6 is shaped by a belief that the most important work in open source isn't always the most visible. Replacing a core dependency, decomposing a runtime, closing a security hole — none of these make for flashy demos, but all of them make nanobot a project you can build on with more confidence tomorrow than yesterday. Thank you to everyone who contributed code, fixes, docs, and ideas. The foundation is getting stronger.

Full Changelog: v0.1.4.post5...v0.1.4.post6

What's Changed

fix：Workspace path in onboard command ignores config setting by @danielyangfei in #1136
feat: add --dir option to onboard command for Multiple Instances by @skiyo in #1763
fix(providers): handle empty choices in custom provider response by @JiajunBernoulli in #2139
feat(slack): update reaction emoji on task completion by @sihyeonn in #1852
fix(feishu): fix markdown rendering issues in headings and tables by @xgzlucario in #1814
fix(feishu): use correct msg_type for audio/video files by @weipengOO98 in #1755
fix: preserve image paths in fallback and session history by @Re-bin in #2165
docs(readme): fix broken link to Channel Plugin Guide by @angleyanalbedo in #2040
fix:subagent result messages incorrectly recorded as user role by @yorkhellen in #2104
fix(cron): show schedule details and run state in _list_jobs() output by @pjhoberman in #2107
logo: transparent background by @vivganes in #1647
fix: When using custom_provider, a prompt "LiteLLM:WARNING" will still appear during conversation by @JavisPeng in #2191
feat(telegram): support HTTP(S) URLs for media in TelegramChannel by @h4nz4 in #1793
feat: parse feishu code block content in post message by @mamamiyear in #2246
fix: separate Telegram connection pools and add timeout retry to prevent pool exhaustion by @Re-bin in #2247
Fix TypeError for MCP tools with nullable JSON Schema params by @rreben in #2230
fix: nanobot onboard update config crash by @mamamiyear in #2266
docs: add subagent workspace assignment hint to spawn tool description by @JilunSun7274 in #2248
Full-featured onboard wizard![from nightly] by @chengyongru in #2101
fix(custom_provider): show raw API error instead of JSONDecodeError by @asdf17128 in #2289
fix(agent): handle asyncio.CancelledError in message loop by @cdkey85 in #2239
feat(tools): enhance ExecTool with enable flag and custom deny_patterns by @angleyanalbedo in #1824
feat(cron): add run history tracking for cron jobs by @xzq-xu in #1838
Add support for -h in the CLI by @JamesWrigley in #2123
fix: add openssh-client and use HTTPS for GitHub in Docker build by @KEEPSLAMDUNK in #1911
Harden email IMAP polling retries by @jr551 in #2122
docs: add github copilot oauth setup and exclude from generated config by @Harvey-Mackie in #2310
feat(agent): implement native multimodal autonomous sensory capabilities by @vandazia in #2304
fix: normalize MCP tool schema for OpenAI-compatible providers by @haosenwang1018 in #2287
feat: add /status command to show runtime info by @robbyczgw-cla in #1985
refactor(agent): unify process_direct to return OutboundMessage by @Re-bin in #2338
fix(agent): count all message fields in token estimation by @Re-bin in #2344
perf: optimize prompt cache hit rate for Anthropic models by @coldxiangyu163 in #1109
feat: end-to-end streaming output for providers, channels, and CLI by @Re-bin in #2365
feat(provider): add mistral/ovms provider by @chengyongru in #2199
fix(memory): reserve completion headroom before token consolidation by @Re-bin in #2378
Refactor command routing for a plugin-friendly structure by @Re-bin in #2388
feat(agent): enable per-session concurrent dispatch by @Re-bin in #2393
fix(shell): reap zombie processes when command timeout kills subprocess by @macroadster in #2362
fix(heartbeat): retain bounded legal session suffix by @Re-bin in #2413
feat(wechat): support wechat channel by @chengyongru in #2412
fix(cron): scope cron job store to workspace directory by @MiguelPF in #2204
feat: telegram/qq/whatsapp/feishu enhancement by @chengyongru in #2386
proposal to adopt mypy some e.g. interfaces problems by @19emtuck in #2367
refactor(tests): optimize unit test structure by @chengyongru in #2427
refactor: replace litellm with native openai + anthropic SDKs by @Re-bin in #2448
Fix/Feat(WeiXin): Adapt to WeChat plugin 1.0.3 by @xcosmosbox in #2428
Unintended Discord behaviour with Threads by @Seeratul in #2452
fix: preserve Gemini thought signatures in tool calls by @yoheinishikubo in #2453
fix(providers): add max_completion_tokens for openai o1 compatibility (backport to main) by @flobo3 in #2468
feat(config): add configurable timezone for runtime context by @Re-bin in #2477
feat(channel): add message send retry mechanism with exponential backoff by @chengyongru in #2478
feat(provider): add Step Fun (阶跃星辰) provider support by @ZouR-Ma in #2472
refactor: extract shared agent runner and preserve subagent progress on failure by @Re-bin in #2524
refactor: unify agent runner lifecycle hooks by @Re-bin in #2541
fix(providers): make max_tokens and max_completion_tokens mutually exclusive (#2491) by @chengyongru in #2550
fix(channel): coalesce queued stream deltas to reduce API calls by @chengyongru in #2497
feat(feishu): support stream output (cardkit) (#2382) by @chengyongru in #2545
fix(telegram): log network errors as warnings without stacktrace by @flobo3 in #2272

New Contributors

@danielyangfei made their first contribution in #1136
@skiyo made their first contribution in #1763
@sihyeonn made their first contribution in #1852
@xgzlucario made their first contribution in #1814
@weipengOO98 made their first contribution in #1755
@angleyanalbedo made their first contribution in #2040
@pjhoberman made their first contribution in #2107
@JavisPeng made their first contribution in #2191
@h4nz4 made their first contribution in #1793
@mamamiyear made their first contribution in #2246
@rreben made their first contribution in #2230
@JilunSun7274 made their first contribution in #2248
@cdkey85 made their first contribution in #2239
@JamesWrigley made their first contribution in #2123
@KEEPSLAMDUNK made their first contribution in #1911
@jr551 made their first contribution in #2122
@Harvey-Mackie made their first contribution in #2310
@vandazia made their first contribution in #2304
@robbyczgw-cla made their first contribution in #1985
@macroadster made their first contribution in #2362
@MiguelPF made their first contribution in #2204
@19emtuck made their first contribution in #2367
@xcosmosbox made their first contribution in #2428
@Seeratul made their first contribution in #2452
@yoheinishikubo made their first contribution in #2453
@ZouR-Ma made their first contribution in #2472

Full Changelog: v0.1.4.post5...v0.1.4.post6

详细ChangeLog

v0.1.4.post5

2026年03月16日

🐈 nanobot v0.1.4.post5 is here — 57 PRs merged, 29 new contributors, and a release cycle shaped less by spectacle than by something quieter: careful refinement where it matters most.

This is the kind of release that makes a project feel more trustworthy in daily use. The edges got smoother, the failure modes got softer, and the platform got broader. Across channels, providers, memory, MCP, CLI, and infrastructure, nanobot is becoming not just more capable, but more dependable — more like a tool you can actually live with.

Highlights

Reliability took center stage — A lot of this release is about making nanobot fail more gracefully. Agent loops are less likely to crash, MCP connections now handle cancellation better, orphaned tool results are preserved correctly, and async CLI/subagent output behaves more cleanly. (#1999, #1953, #2075, #1930, #2039)
Memory became more practical — Async background consolidation landed, consolidation inputs are passed through more faithfully, payloads are validated before persistence, and save_memory is enforced more consistently. This is a meaningful step toward memory that feels less magical and more reliable. (#1961, #1962, #1868, #1810, #1909)
The channel layer keeps maturing — Channel plugin architecture arrived, channel discovery is now automatic, and built-in channel/config boundaries are cleaner. That kind of structural work matters: it makes growth easier without making the system brittle. (#1982, #1888)
Provider support keeps expanding outward — Ollama support landed for local models, VolcEngine and BytePlus joined the ecosystem, openrouter/* models are supported, and web search providers are now configurable with fallback behavior. nanobot is increasingly meeting users where they already are. (#1863, #1608, #2026, #398)
Observability and tooling got stronger — Langsmith integration brings better conversation tracking, built-in skill packaging got fixed up, and smarter filesystem/shell tooling improves pagination, fallback matching, and output behavior. The system is becoming easier to inspect and easier to trust. (#1920, #1416, #1895)
Feishu saw major polish — Reply/quote support landed, tool calls can now render in code blocks, group mention behavior improved, Groq Whisper audio compatibility was fixed, and broader multimedia handling got much better. Feishu support feels substantially more complete after this cycle. (#1963, #1966, #1768, #1741, #2034)
Telegram got meaningfully better in groups and media workflows — Group response behavior is now configurable, reply-to-message context works across text and media, and media filename collision bugs were cleaned up. These are small details individually, but together they make conversations feel much more natural. (#1389, #1900, #1796)
Enterprise and collaboration channels improved too — WeCom channel support landed, Slack thread behavior was clarified, QQ legacy plain-text replies were restored, and DingTalk gained both voice recognition text retrieval and multimedia improvements. (#1327, #1784, #1941, #1859, #2034)
CLI and runtime behavior are more predictable — Gateway port defaults now respect config, restart flows are more portable, Windows compatibility got attention, and shell/workspace guards became stricter around home-expanded and tilde-based paths. This is the kind of work users only notice when it’s missing — which is exactly why it matters. (#1797, #1785, #1958, #1479, #1827, #1845)
A lot of sharp edges disappeared — Hidden files are no longer synced by accident, non-vision models won’t receive image_url, heartbeat and cron got less noisy, and version IDs now show up in logs. These aren’t flashy changes, but they make nanobot feel more settled, more deliberate, and more production-ready. (#1856, #1901, #1973, #2058)

Community

A huge welcome to our 29 new contributors in this release.

Open source grows in two ways: through bold new ideas, and through the patient work of noticing rough edges and smoothing them out. v0.1.4.post5 has plenty of both. Thank you to everyone who contributed features, fixes, refactors, docs, and infrastructure improvements — nanobot is becoming stronger not all at once, but through many careful hands moving it forward together.

Full Changelog: v0.1.4.post4...v0.1.4.post5

What's Next

Looking ahead, we’ll continue moving nanobot toward a more modular, plugin-oriented ecosystem. As a first step, we plan to experiment and iterate in the channel layer first — using channels as the proving ground for a more extensible architecture before expanding that approach further across the project.

We’ll also keep using the nightly branch for faster testing, earlier feedback, and quicker iteration on new ideas. If you’re interested in helping shape that future, we’d warmly welcome contributions there. You can find the contribution workflow and guidelines in CONTRIBUTING.md.

And one more small note: v0.1.4.post5 will likely be the last release in the 0.1.4 line. It closes out this cycle with a lot of polish and hard-earned stability — and also makes room for what comes next.

The next main version is already taking shape, and we think it will be worth the wait. 😉

What's Changed

fix: ensure feishu audio file has .opus extension for Groq Whisper compatibility by @chengyongru in #1741
fix(slack): define thread usage in send() by @ailuntz in #1784
fix(cli): let gateway use config port by default by @Protocol-zero-0 in #1797
fix(cli): respect config.gateway.port in gateway command by @ailuntz in #1785
fix(telegram): add group_policy to control bot response behavior in groups by @haosenwang1018 in #1389
Add missing scripts to built-in skill skill-creator by @yankeguo in #1416
feat: add LLM retry with exponential backoff for transient errors by @kiplangatkorir in #1512
refactor: implement token-based context compression mechanism by @VITOHJL in #1704
fix: bump litellm version to 1.82.1 for Moonshot provider support by @greyishsong in #1855
feat: support retrieving DingTalk voice recognition text by @dingyanyi2019 in #1859
fix(subagent): preserve reasoning_content in assistant messages by @lailoo in #1848
fix: exclude hidden files when syncing workspace templates by @yapex in #1856
Add WeChat Work (WeCom) channel support by @chengyongru in #1327
feat: add Ollama as a local LLM provider by @letzdoo-js in #1863
fix(memory): pass temperature, max_tokens and reasoning_effort to memory consolidation by @ethanclaw in #1868
refactor: auto-discover channels via pkgutil, eliminate hardcoded registry by @Re-bin in #1888
feat: allow direct references in hatch metadata for wecom dep by @for13to1 in #1885
Fix Gemini thought_signature loss in tool-call replay by @WhalerO in #1874
fix(exec): enforce workspace guard for home-expanded paths by @suger-m in #1827
enhance: improve filesystem & shell tools with pagination, fallback matching, and smarter output by @Re-bin in #1895
fix: detect tilde paths in restrictToWorkspace shell guard by @nikolasdehor in #1845
fix: wecom-aibot-sdk-python should use pypi version by @chengyongru in #1897
fix: force save_memory in consolidation by @Re-bin in #1909
feat(channels): add "restart" command by @groudas in #1751
feat(feishu): add global group mention policy by @Zeknes in #1768
feat(telegram): support reply-to-message context (text and media) by @Schokobecher in #1900
feat: Add VolcEngine and BytePlus (Pay-per-use & Coding Plan) support by @Maaannnn in #1608
fix: preserve interactive CLI formatting for async subagent output by @ducheng121 in #1930
fix: catch BaseException in MCP connection to handle CancelledError by @chengyongru in #1953
fix(qq): restore plain text replies for legacy clients by @tsubasakong in #1941
[紧急]修复we_chat在pyproject.toml配置的问题 by @ALIZE126 in #1919
fix(restart): use -m nanobot for Windows compatibility by @chengyongru in #1958
fix(memory): validate save_memory payload before persisting by @shenchengtsi in #1810
feat(ci): add GitHub Actions workflow for test directory by @JiajunBernoulli in #1916
docs: correct BaiLian dashscope apiBase endpoint by @tsubasakong in #1949
Integrate Langsmith for conversation tracking by @korruz in #1920
feat(web): add configurable web search providers with key-missing fallback by @chris-alexander in #398
chore: bump wecom-aibot-sdk-python to >=0.1.5 by @chengyongru in #1981
feat: channel plugin architecture with decoupled configs by @Re-bin in #1982
fix(channels login): add shell=True for npm subprocess calls on Windows by @gongpx20069 in #1479
fix(cron, heartbeat): prevent notification spam from cron and heartbeat tasks by @SJK-py in #1973
feat:在MCP注册时指定启用工具以便让agent识别更准确并且减少token消耗 by @lvqiushi in #1965
fix: add exception handling to prevent agent loop crash by @chengyongru in #1999
fix(telegram): avoid media filename collisions by @Protocol-zero-0 in #1796
feat(feishu): implement message reply/quote support by @mru4913 in #1963
feat(feishu): display tool calls in code block messages + fix empty by @nne998 in #1966
Support openrouter/* models by @rick2047 in #2026
fix: filter image_url for non-vision models at provider layer by @coldxiangyu163 in #1901
Fix builtin skills inaccessible when restrictToWorkspace is enabled by @benlenarts in #2037
Feat/dingtalk multimedia enhance by @chengyongru in #2034
fix(heartbeat): inject current datetime into Phase 1 prompt by @who96 in #2038
docs: add branching strategy and CONTRIBUTING guide by @chengyongru in #2021
fix(loop): restore /new immediate return with safe background consolidation by @chengyongru in #1962
feat: implement async memory background consolidation by @nne998 in #1961
Fix orphan tool results in truncated session history by @xx2689 in #2075
fix(cli): stop spinner before printing tool progress lines by @who96 in #2039
qol: add version id to log output by @pve in #2058

New Contributors

@ailuntz made their first contribution in #1784
@Protocol-zero-0 made their first contribution in #1797
@greyishsong made their first contribution in #1855
@dingyanyi2019 made their first contribution in #1859
@lailoo made their first contribution in #1848
@yapex made their first contribution in #1856
@letzdoo-js made their first contribution in #1863
@ethanclaw made their first contribution in #1868
@for13to1 made their first contribution in #1885
@WhalerO made their first contribution in #1874
@groudas made their first contribution in #1751
@Zeknes made their first contribution in #1768
@Schokobecher made their first contribution in #1900
@Maaannnn made their first contribution in #1608
@ducheng121 made their first contribution in #1930
@tsubasakong made their first contribution in #1941
@ALIZE126 made their first contribution in #1919
@JiajunBernoulli made their first contribution in #1916
@korruz made their first contribution in #1920
@SJK-py made their first contribution in #1973
@lvqiushi made their first contribution in #1965
@mru4913 made their first contribution in #1963
@nne998 made their first contribution in #1966
@rick2047 made their first contribution in #2026
@benlenarts made their first contribution in #2037
@who96 made their first contribution in #2038
@xx2689 made their first contribution in #2075

Full Changelog: v0.1.4.post4...v0.1.4.post5

详细ChangeLog

欢迎回来

nanobot 超轻量个人 AI 智能体

nanobot 超轻量个人 AI 智能体

为nanobot打分

收藏到合集

相关产品

DeepTutor

Vibe-Trading

用户评论 (0)

#215.飞书无法建立长连接

#4867.Preserve exact prompt prefix to enable caching in Ollama and others

#218.feat(whatsapp): 支持"发给自己"功能 - 删除 fromMe 消息过滤

#336.DeepSeek provider not working - LLM Provider NOT provided error

#2133.关于在任务执行期间用户消息入列的一些想法

#75.How Do I content the Ollama

#2.Feature Request: Native Support for Z.AI (Zhipu AI) API & Latest GLM Models

#2880.[BUG] 无论发什么消息都回复报错

#176.feishu配置不成功

#52.question: access whatsapp not response

#5494.Why docs on nanobot.wiki does not support search?

#5423.Design check: split gateway liveness and readiness probes?

#5394.Idea: Optional follow-up suggestions after each LLM response

#5365.VOKO：面向 AI 智能体的本地通信与协作运行时

#5363.Question: signed receipts for selected nanobot tool / automation / handoff events?

#5188.Nanobot needs a voice!!!

#5037.Hindsight intergration

#5024.Kimi K3 Plan Support

#5012.Brand new docker install, web interface returns 'Connection reset by peer' despite no errors in the gateway

#4970.How to add Nous Research as a provider in nanobot

v0.3.0

Highlights

Upgrade Notes

Community

What's Changed

New Contributors

v0.2.2

Highlights

Community

What's Changed

New Contributors

v0.2.1

Highlights

Community

What's Changed

New Contributors

v0.2.0

Highlights

Community

What's Changed

New Contributors

v0.1.5.post3

Highlights

Community

What's Changed

New Contributors

v0.1.5.post2

Highlights

Community

What's Changed

New Contributors

v0.1.5.post1

Highlights

Community

What's Changed

New Contributors

v0.1.5

Highlights

Community

What's Changed

New Contributors

v0.1.4.post6

Highlights

Community

What's Changed

New Contributors

v0.1.4.post5

Highlights

Community

What's Next

What's Changed