v0.2.1

🐈 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 A...

v0.2.0

🐈 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 https://...

v0.1.5.post3

🐈 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 https://github.com/HK...

v0.1.5.post2

🐈 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 an...

v0.1.5.post1

🐈 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 prox...

v0.1.5

🐈 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 ...

v0.1.4.post6

🐈 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
• fi...

v0.1.4.post5

🐈 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 ht...

v0.1.4.post4

🐈 nanobot v0.1.4.post4 is here — 58 PRs merged, 29 new contributors, and a lot of real-world polish from the community.

This release is a big one: safer defaults, better multi-instance support, stronger MCP/tool reliability, and major improvements across Telegram, Feishu, QQ, DingTalk, Discord, WhatsApp, Matrix, and more. A ton of sharp edge cases got cleaned up in this cycle — the kind of fixes that make nanobot feel much more solid day to day.

Highlights

• Safer by default — Access control is tighter now. This release includes a real authorization-bypass fix and stronger default handling around allowFrom, making deployments much safer out of the box. (#1403, #1677)

• Multi-instance support is finally real — --config support landed, runtime path handling got cleaned up, and the CLI agent now supports --workspace / --config too. Running separate bots, tenants, or environments is much easier now. (#1581, #1635)

• MCP got tougher — SSE transport support is in, auto-detection is smarter, and MCP tool calls are much less likely to take down the process when cancellations or weird failures happen. (#1488, #1728)

• Tooling got more forgiving — Auto-casting tool params, safer validation, graceful datetime handling, and read_file size limits all help nanobot fail less badly when tools or inputs get weird. (#1610, #1507, #1508, #1511)

• Provider support keeps growing — Azure OpenAI support is here, Alibaba Cloud Coding Plan API support landed, prompt-caching affinity headers were added, and GitHub Copilot / Codex compatibility keeps improving. (#1618, #1563, #1428, #1555, #1637, #1525)

• Cron got much sturdier — External jobs.json changes are respected, job context handling is better, and cron jobs are no longer allowed to recursively schedule more cron jobs forever. (#1371, #1375, #1399, #1458)

• Context got cleaner — Consecutive user messages are merged to avoid provider-side errors, internal reasoning is hidden from user-facing progress updates, image MIME detection is more reliable, and prompt/platform guidance is more polished. (#1456, #1655, #1573, #1579)

• Telegram got a lot of love — Proxy handling was fixed, group topics are supported, /stop works better, streaming messages landed, and generic documents now keep the right file extensions. (#1535, #1476, #1482, #1660, #1522, #436)

• Feishu keeps getting better — Rich text parsing, table/card splitting, smarter format selection, Groq Whisper transcription, audio/video compatibility fixes, and cleaner event handling all landed in this release. (#1361, #1384, #1648, #1605, #1531, #1594, #332, #1568)

• More channels, more polish — DingTalk group chat support, QQ group handling and markdown sending, Discord group policy + attachments, WhatsApp media support, Slack fallback fixes, and Matrix media normalization all made it in. (#1467, #532, #1727, #553, #1613, #1638, #673, #1406)

• Cross-platform stability improved — Better Windows signal handling, fewer missing imports/dependencies, cleaner tests, and overall more confidence that nanobot behaves well across different environments. (#1598, #1485, #1533, #1546, #1339, #1521)

Community

A huge welcome to our 29 new contributors in this release — thank you all for jumping in and improving nanobot across channels, providers, tooling, docs, and infrastructure. This project keeps getting better because of contributions like these.

What's Changed

• fix(cron): auto-reload jobs.json when modified externally by @Re-bin in #1371
• style: unify code formatting and import order by @JackLuguibin in #1339
• fix(feishu): parse post wrapper payload for rich text messages by @cyzlmh in #1361
• feat(cron): improve cron job context handling by @VITOHJL in #1375
• feat(tool): add web search proxy by @chengyongru in #1370
• security: deny by default in is_allowed for all channels by @chengyongru in #1403
• fix(matrix): normalize media metadata and keyword-call attachment upload by @wenjielei1990 in #1406
• cron: honor external jobs.json updates during timer ticks by @cyzlmh in #1399
• fix: merge consecutive user messages to prevent API errors by @nikolasdehor in #1456
• fix: prevent cron job from scheduling new jobs (feedback loop) by @nikolasdehor in #1458
• fix: add missed openai dependency by @cocolato in #1485
• fix(codex): pass reasoning_effort to Codex API by @danielemden in #1525
• test: fix test failures from refactored cron and context builder by @chengyongru in #1521
• fix: handle invalid ISO datetime in CronTool gracefully by @kiplangatkorir in #1508
• fix: guard validate_params against non-dict input by @kiplangatkorir in #1507
• fix(feishu): convert audio type to file for API compatibility by @bendusy in #1531
• fix: add size limit to ReadFileTool to prevent OOM by @kiplangatkorir in #1511
• fix(tests): resolve failing tests by @SergioSV96 in #1533
• fix(qq): add msg_seq to prevent message deduplication error by @Liwx1014 in #1499
• fix(feishu): isolate lark ws Client event loop from main asyncio loop by @coldxiangyu163 in #1568
• feat(custom-provider): add x-session-affinity header for prompt caching by @dmarkey in #1428
• feat(discord): add group policy to control group respond behaviour by @joel611 in #553
• feat(mcp): add SSE transport support with auto-detection by @Qinnnnnn in #1488
• feat(gateway): support multiple instances by @chengyongru in #1435
• fix: add SIGTERM, SIGHUP handling and ignore SIGPIPE by @chengyongru in #1400
• feat(telegram): add streaming messages by @SergioSV96 in #1522
• fix(feishu): split card messages when content has multiple tables by @zerone0x in #1384
• fix(feishu): use msg_type "media" for mp4 video files by @pikaqqqqqq in #1594
• fix(cli): add Windows compatibility for signal handlers (PR #1400) by @Wangshixiong in #1598
• fix(memory): handle list type tool call arguments for Bailian Qwen by @Wangshixiong in #1603
• fix(feishu): smart message format selection (fixes #1548) by @pikaqqqqqq in #1605
• fix(context): detect image MIME type from magic bytes instead of file extension by @coldxiangyu163 in #1573
• refactor(channels): extract split_message utility to reduce code dupl… by @suger-m in #1567
• feat: Add Alibaba Cloud Coding Plan API support by @Mrart in #1563
• fix(github copilot tool calls): GitHub Copilot tool_calls not working (multi-choice response) by @gongpx20069 in #1555
• fix: not imported when LiteLLMProvider is not used by @hcanyz in #1546
• feat(whatsapp): Media support, incl. image, docs, video by @fat-operator in #1638
• Fix tool_call_id length error for GitHub Copilot provider by @04cb in #1637
• feat(provider): support azure openai provider by @kunalk16 in #1618
• feat: enhance message sending to include file attachments in Discord API by @lzmjlrt in #1613
• feat(tools): auto-cast parameter types to match tool schema by @wb213 in #1610
• fix(telegram): added "stop" command handler, fixed stop command by @hlibr in #1660
• feat(feishu): add audio transcription support using Groq Whisper by @chengyongru in #1648
• fix: hide reasoning_content from user progress updates by @VITOHJL in #1655
• fix(feishu): Prevent error logs from unhandled reaction and read events by @huhu-tiger in #332
• Fix: Telegram channel crash when proxy is configured by @dsxyy in #1535
• feat(telegram): add Telegram group topic support by @WufeiHalf in #1482
• fix problem with proxy for Telegram by @noki1928 in #1476
• fix(telegram): preserve file extension for generic documents by @ZXGERIC in #436
• feat(dingtalk): add support for group chat messages by @shawnWXN in #1467
• feat: enable QQ group message handling and dynamic reply dispatch by @zhenghan3852 in #532
• fix(auth): prevent allowlist bypass via sender_id token splitting by @Re-bin in #1677
• Update Slack message text fallback response by @alekwo in #673
• feat: multi-instance support with --config parameter by @shenchengtsi in https://git...

v0.1.4.post3

🐈 nanobot v0.1.4.post3 just dropped — 33 PRs merged, 16 new contributors! You guys are unstoppable 🔥

This release is all about making the agent smarter by seeing less junk: cleaner context, hardened session history, and fewer ghost messages. Less noise in → less hallucination out. Plus a shiny new Matrix channel and experimental thinking mode.

Highlights

• Agent Loop Hardening — Empty assistant messages (no content, no tool calls) are now filtered instead of poisoning context; LLM error responses are no longer saved to history, preventing permanent 400-error loops; message tool suppression scoped to same-channel only (#1314, #1198, #1206)
• Context Noise Reduction — Runtime metadata (time, channel, chat ID) separated into an untrusted layer and excluded from session history, so the agent sees only what matters — fewer tokens, less confusion, less hallucination (#1126, #1222)
• Session Safety — Base64 images stripped from history to prevent context overflow; null responses no longer corrupt future turns (#1191, #1314)
• Matrix Channel — Full Matrix (Element) chat channel support with E2EE, media uploads, and typing indicators (#420, #1239)
• Provider Compatibility — Short alphanumeric tool_call_id for Mistral; list-type tool arguments handled gracefully; explicit provider selection in config (#1293, #1294, #1214, #1316)
• Thinking Mode (experimental) — New reasoning_effort config enables LLM reasoning for supported models; session history preserves reasoning_content and thinking_blocks across turns (#1351, #1330, #1074)
• Subagent Improvements — /stop cancels spawned subagents; streamlined prompt eliminates dead code and reuses ContextBuilder (#1180, #1347)
• Feishu — Interactive card text extraction fix, configurable reaction emoji, corrected bot permissions (#1323, #1257, #1317, #1348)
• DingTalk — Images and media sent as proper message types instead of plain-text links (#1337)
• Telegram — Media groups aggregated into a single inbound message (#1258)
• QQ — Fixed C2C reply permissions, disabled file log on read-only filesystems (#1307, #1346)
• WhatsApp — Message deduplication prevents redundant agent processing (#1325)
• Shell & Security — Full Windows path parsing in workspace guard; configurable path_append for subprocess PATH (#1286, #1083)
• Memory & Concurrency — WeakValueDictionary for consolidation locks eliminates race conditions and manual cleanup (#1326)
• Workspace — Automatic template synchronization restores critical files on startup (#1253)

What's Changed

• fix: preserve reasoning_content in messages for thinking-enabled models by @haosenwang1018 in #1074
• feat/fix(exec): add path_append config to extend PATH for subprocess by @aiguozhi123456 in #1083
• feat: add stable system layer + untrusted runtime context layer by @pikaxinge in #1126
• feat: /stop cancels spawned subagents via session tracking by @coldxiangyu163 in #1180
• feat: support explicit provider selection in config by @Re-bin in #1214
• Fix assistant messages without tool calls not being saved to session history by @VITOHJL in #1198
• Fix: The base64 images are stored in the session history, causing context overflow. by @dxtime in #1191
• feat: add Matrix (Element) chat channel support by @tanishra in #420
• fix(agent): only suppress final reply when message tool sends to same… by @chengyongru in #1206
• fix(web): use self.api_key instead of undefined api_key by @yongPhone in #1228
• fix(telegram): aggregate media groups into a single inbound message by @KimGLee in #1258
• feat(feishu): make reaction emoji configurable by @kimkitsuragi26 in #1257
• feat: automatic workspace template synchronization by @honjiaxuan in #1253
• Fix Matrix channel initialization and configuration by @tanishra in #1239
• fix(agent): avoid persisting runtime context metadata into history by @KimGLee in #1222
• fix: update heartbeat tests to match two-phase tool-call architecture by @intelliot in #1200
• Fix(prompt): guide llm grep using timestamp by @aiguozhi123456 in #1278
• fix: generate short alphanumeric tool_call_id for Mistral compatibility by @Re-bin in #1293
• fix: remove overly broad "codex" keyword from openai_codex provider by @nikolasdehor in #1316
• fix: prevent session poisoning from null/error LLM responses by @nikolasdehor in #1314
• fix the feishu interactive message text cannot be extracted by @azhengzz in #1323
• Modify Feishu bot permissions in README by @yankeguo in #1317
• fix: pass msg_id in QQ C2C reply to avoid proactive message permissio… by @GabrielWithTina in #1307
• fix: handle list-type tool arguments in _tool_hint by @Michael-lhh in #1294
• fix(shell): parse full Windows absolute paths in workspace guard by @fengxiaohu in #1286
• refactor: use WeakValueDictionary for consolidation locks by @Re-bin in #1326
• fix: add message deduplication to WhatsApp channel by @spartan077 in #1325
• feat(dingtalk): send images as image messages, keep files as attachments by @asdf17128 in #1337
• refactor: streamline subagent prompt by reusing ContextBuilder and SkillsLoader by @Re-bin in #1347
• fix(qq): disable botpy file log to fix read-only filesystem error by @zerone0x in #1346
• feat: add reasoning_effort config to enable LLM thinking mode by @Re-bin in #1351
• fix(lark): Remove non-existent stop() call on Lark ws.Client when enable lark channel by @yorkhellen in #1348
• fix(providers): allow reasoning_content in message history by @fengxiaohu in #1330

New Contributors

• @aiguozhi123456 made their first contribution in #1083
• @VITOHJL made their first contribution in #1198
• @tanishra made their first contribution in #420
• @yongPhone made their first contribution in #1228
• @kimkitsuragi26 made their first contribution in #1257
• @honjiaxuan made their first contribution in #1253
• @intelliot made their first contribution in #1200
• @azhengzz made their first contribution in #1323
• @yankeguo made their first contribution in #1317
• @GabrielWithTina made their first contribution in #1307
• @Michael-lhh made their first contribution in #1294
• @fengxiaohu made their first contribution in #1286
• @spartan077 made their first contribution in #1325
• @asdf17128 made their first contribution in #1337
• @zerone0x made their first contribution in #1346
• @yorkhellen made their first contribution in #1348

Full Changelog: v0.1.4.post2...v0.1.4.post3