diff --git a/CHANGELOG.md b/CHANGELOG.md index 5909c9899..f3998d892 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -13,6 +13,7 @@ Status: beta. - Branding: update launchd labels, mobile bundle IDs, and logging subsystems to bot.molt (legacy com.clawdbot migrations). Thanks @thewilloftheshadow. - Tools: add per-sender group tool policies and fix precedence. (#1757) Thanks @adam91holt. - Agents: summarize dropped messages during compaction safeguard pruning. (#2509) Thanks @jogi47. +- Memory Search: allow extra paths for memory indexing (ignores symlinks). (#3600) Thanks @kira-ariaki. - Skills: add multi-image input support to Nano Banana Pro skill. (#1958) Thanks @tyler6204. - Agents: honor tools.exec.safeBins in exec allowlist checks. (#2281) - Matrix: switch plugin SDK to @vector-im/matrix-bot-sdk. @@ -72,11 +73,15 @@ Status: beta. - **BREAKING:** Gateway auth mode "none" is removed; gateway now requires token/password (Tailscale Serve identity still allowed). ### Fixes +- Mentions: honor mentionPatterns even when explicit mentions are present. (#3303) Thanks @HirokiKobayashi-R. - Discord: restore username directory lookup in target resolution. (#3131) Thanks @bonald. - Agents: align MiniMax base URL test expectation with default provider config. (#3131) Thanks @bonald. - Agents: prevent retries on oversized image errors and surface size limits. (#2871) Thanks @Suksham-sharma. - Agents: inherit provider baseUrl/api for inline models. (#2740) Thanks @lploc94. - Memory Search: keep auto provider model defaults and only include remote when configured. (#2576) Thanks @papago2355. +- Telegram: include AccountId in native command context for multi-agent routing. (#2942) Thanks @Chloe-VP. +- Telegram: handle video note attachments in media extraction. (#2905) Thanks @mylukin. +- TTS: read OPENAI_TTS_BASE_URL at runtime instead of module load to honor config.env. (#3341) Thanks @hclsys. - macOS: auto-scroll to bottom when sending a new message while scrolled up. (#2471) Thanks @kennyklee. - Web UI: auto-expand the chat compose textarea while typing (with sensible max height). (#2950) Thanks @shivamraut101. - Gateway: prevent crashes on transient network errors (fetch failures, timeouts, DNS). Added fatal error detection to only exit on truly critical errors. Fixes #2895, #2879, #2873. (#2980) Thanks @elliotsecops. @@ -106,6 +111,7 @@ Status: beta. - Telegram: centralize API error logging for delivery and bot calls. (#2492) Thanks @altryne. - Voice Call: enforce Twilio webhook signature verification for ngrok URLs; disable ngrok free tier bypass by default. - Security: harden Tailscale Serve auth by validating identity via local tailscaled before trusting headers. +- Media: fix text attachment MIME misclassification with CSV/TSV inference and UTF-16 detection; add XML attribute escaping for file output. (#3628) Thanks @frankekn. - Build: align memory-core peer dependency with lockfile. - Security: add mDNS discovery mode with minimal default to reduce information disclosure. (#1882) Thanks @orlyjamie. - Security: harden URL fetches with DNS pinning to reduce rebinding risk. Thanks Chris Zheng. diff --git a/README.md b/README.md index 7e884be33..70ca70157 100644 --- a/README.md +++ b/README.md @@ -479,36 +479,38 @@ Thanks to all clawtributors:

steipete plum-dawg bohdanpodvirnyi iHildy jaydenfyi joaohlisboa mneves75 MatthieuBizien MaudeBot Glucksberg - rahthakor vrknetha radek-paclt Tobias Bischoff joshp123 vignesh07 czekaj mukhtharcm sebslight maxsumrall - xadenryan rodrigouroz juanpablodlc hsrvc magimetal zerone0x meaningfool tyler6204 patelhiren NicholasSpisak - jonisjongithub abhisekbasu1 jamesgroat claude JustYannicc Hyaxia dantelex SocialNerd42069 daveonkels google-labs-jules[bot] - lc0rp mousberg adam91holt hougangdev gumadeiras mteam88 hirefrank joeynyc orlyjamie dbhurley - Mariano Belinky Eng. Juan Combetto TSavo julianengel bradleypriest benithors rohannagpal timolins f-trycua benostein - nachx639 shakkernerd pvoo sreekaransrinath gupsammy cristip73 stefangalescu nachoiacovino Vasanth Rao Naik Sabavat petter-b - cpojer scald thewilloftheshadow andranik-sahakyan davidguttman sleontenko denysvitali sircrumpet peschee rafaelreis-r - dominicnunez ratulsarna lutr0 danielz1z AdeboyeDN Alg0rix papago2355 emanuelst KristijanJovanovski rdev - rhuanssauro joshrad-dev kiranjd osolmaz adityashaw2 CashWilliams sheeek artuskg Takhoffman onutc - pauloportella neooriginal manuelhettich minghinmatthewlam myfunc travisirby buddyh connorshea kyleok obviyus - mcinteerj dependabot[bot] John-Rood timkrase uos-status gerardward2007 roshanasingh4 tosh-hamburg azade-c dlauer - JonUleis bjesuiter cheeeee robbyczgw-cla Josh Phillips YuriNachos pookNast Whoaa512 chriseidhof ngutman - ysqander aj47 kennyklee superman32432432 Yurii Chukhlib grp06 antons austinm911 blacksmith-sh[bot] damoahdominic - dan-dr HeimdallStrategy imfing jalehman jarvis-medmatic kkarimi mahmoudashraf93 pkrmf RandyVentures Ryan Lisse - dougvk erikpr1994 fal3 Ghost jonasjancarik Keith the Silly Goose L36 Server Marc mitschabaude-bot mkbehr - neist sibbl chrisrodz Friederike Seiler gabriel-trigo iamadig Jonathan D. Rhyne (DJ-D) Joshua Mitchell Kit koala73 - manmal ogulcancelik pasogott petradonka rubyrunsstuff siddhantjain suminhthanh svkozak VACInc wes-davis - zats 24601 ameno- Chris Taylor dguido Django Navarro evalexpr henrino3 humanwritten larlyssa - odysseus0 oswalpalash pcty-nextgen-service-account rmorse Syhids Aaron Konyer aaronveklabs andreabadesso Andrii cash-echo-bot - Clawd ClawdFx EnzeD erik-agens Evizero fcatuhe itsjaydesu ivancasco ivanrvpereira jayhickey - jeffersonwarrior jeffersonwarrior jverdi longmaba mickahouan mjrussell odnxe p6l-richard philipp-spiess Pocket Clawd - robaxelsen Sash Catanzarite T5-AndyML travisp VAC william arzt zknicker 0oAstro abhaymundhara alejandro maza - Alex-Alaniz alexstyl andrewting19 anpoirier arthyn Asleep123 bolismauro chenyuan99 Clawdbot Maintainers conhecendoia - dasilva333 David-Marsh-Photo Developer Dimitrios Ploutarchos Drake Thomsen Felix Krause foeken ganghyun kim grrowl gtsifrikas - HazAT hrdwdmrbl hugobarauna Jamie Openshaw Jane Jarvis Jefferson Nunn jogi47 kentaro Kevin Lin - kitze Kiwitwitter levifig Lloyd longjos loukotal louzhixian martinpucik Matt mini mertcicekci0 - Miles mrdbstn MSch Mustafa Tag Eldeen ndraiman nexty5870 Noctivoro ppamment prathamdby ptn1411 - reeltimeapps RLTCmpe Rolf Fredheim Rony Kelner Samrat Jha senoldogann Seredeep sergical shiv19 shiyuanhai - siraht snopoke Suksham-sharma techboss testingabc321 The Admiral thesash Ubuntu voidserf Vultr-Clawd Admin - Wimmie wolfred wstock yazinsai YiWang24 ymat19 Zach Knickerbocker 0xJonHoldsCrypto aaronn Alphonse-arianee - atalovesyou Azade carlulsoe ddyo Erik latitudeki5223 Manuel Maly Mourad Boustani odrobnik pcty-nextgen-ios-builder - Quentin Randy Torres rhjoh ronak-guliani William Stock + rahthakor vrknetha radek-paclt vignesh07 Tobias Bischoff joshp123 czekaj mukhtharcm sebslight maxsumrall + xadenryan rodrigouroz juanpablodlc hsrvc magimetal zerone0x tyler6204 meaningfool patelhiren NicholasSpisak + jonisjongithub abhisekbasu1 jamesgroat claude JustYannicc Mariano Belinky Hyaxia dantelex SocialNerd42069 daveonkels + google-labs-jules[bot] lc0rp mousberg adam91holt hougangdev shakkernerd gumadeiras mteam88 hirefrank joeynyc + orlyjamie dbhurley Eng. Juan Combetto TSavo julianengel bradleypriest benithors rohannagpal timolins f-trycua + benostein elliotsecops nachx639 pvoo sreekaransrinath gupsammy cristip73 stefangalescu nachoiacovino Vasanth Rao Naik Sabavat + petter-b thewilloftheshadow cpojer scald andranik-sahakyan davidguttman sleontenko denysvitali sircrumpet peschee + nonggialiang rafaelreis-r dominicnunez lploc94 ratulsarna lutr0 danielz1z AdeboyeDN Alg0rix papago2355 + emanuelst KristijanJovanovski rdev rhuanssauro joshrad-dev kiranjd osolmaz adityashaw2 CashWilliams sheeek + ryancontent artuskg Takhoffman onutc pauloportella neooriginal manuelhettich minghinmatthewlam myfunc travisirby + obviyus buddyh connorshea kyleok mcinteerj dependabot[bot] John-Rood timkrase uos-status gerardward2007 + roshanasingh4 tosh-hamburg azade-c dlauer JonUleis shivamraut101 bjesuiter cheeeee robbyczgw-cla Josh Phillips + YuriNachos pookNast Whoaa512 chriseidhof ngutman ysqander aj47 kennyklee superman32432432 Yurii Chukhlib + grp06 antons austinm911 blacksmith-sh[bot] damoahdominic dan-dr HeimdallStrategy imfing jalehman jarvis-medmatic + kkarimi mahmoudashraf93 pkrmf RandyVentures Ryan Lisse dougvk erikpr1994 fal3 Ghost jonasjancarik + Keith the Silly Goose L36 Server Marc mitschabaude-bot mkbehr neist sibbl chrisrodz Friederike Seiler gabriel-trigo + iamadig Jonathan D. Rhyne (DJ-D) Joshua Mitchell Kit koala73 manmal ogulcancelik pasogott petradonka rubyrunsstuff + siddhantjain suminhthanh svkozak VACInc wes-davis zats 24601 ameno- Chris Taylor dguido + Django Navarro evalexpr henrino3 humanwritten larlyssa Lukavyi odysseus0 oswalpalash pcty-nextgen-service-account pi0 + rmorse Roopak Nijhara Syhids Aaron Konyer aaronveklabs andreabadesso Andrii cash-echo-bot Clawd ClawdFx + EnzeD erik-agens Evizero fcatuhe itsjaydesu ivancasco ivanrvpereira Jarvis jayhickey jeffersonwarrior + jeffersonwarrior jverdi longmaba MarvinCui mickahouan mjrussell odnxe p6l-richard philipp-spiess Pocket Clawd + robaxelsen Sash Catanzarite Suksham-sharma T5-AndyML tewatia travisp VAC william arzt zknicker 0oAstro + abhaymundhara aduk059 alejandro maza Alex-Alaniz alexstyl andrewting19 anpoirier araa47 arthyn Asleep123 + bguidolim bolismauro chenyuan99 Clawdbot Maintainers conhecendoia dasilva333 David-Marsh-Photo Developer Dimitrios Ploutarchos Drake Thomsen + dylanneve1 Felix Krause foeken frankekn ganghyun kim grrowl gtsifrikas HazAT hrdwdmrbl hugobarauna + Jamie Openshaw Jane Jarvis Deploy Jefferson Nunn jogi47 kentaro Kevin Lin kira-ariaki kitze Kiwitwitter + levifig Lloyd longjos loukotal louzhixian martinpucik Matt mini mertcicekci0 Miles mrdbstn + MSch Mustafa Tag Eldeen ndraiman nexty5870 Noctivoro ppamment prathamdby ptn1411 reeltimeapps RLTCmpe + Rolf Fredheim Rony Kelner Samrat Jha senoldogann sergical shiv19 shiyuanhai siraht snopoke techboss + testingabc321 The Admiral thesash Ubuntu voidserf Vultr-Clawd Admin Wimmie wolfred wstock YangHuang2280 + yazinsai YiWang24 ymat19 Zach Knickerbocker zackerthescar 0xJonHoldsCrypto aaronn Alphonse-arianee atalovesyou Azade + carlulsoe ddyo Erik latitudeki5223 Manuel Maly Mourad Boustani odrobnik pcty-nextgen-ios-builder Quentin Randy Torres + rhjoh ronak-guliani William Stock

diff --git a/docs/channels/whatsapp.md b/docs/channels/whatsapp.md index 6fd30c751..b6ae260ce 100644 --- a/docs/channels/whatsapp.md +++ b/docs/channels/whatsapp.md @@ -125,7 +125,7 @@ the prefix (use `""` to remove it). - **DM policy**: `channels.whatsapp.dmPolicy` controls direct chat access (default: `pairing`). - Pairing: unknown senders get a pairing code (approve via `moltbot pairing approve whatsapp `; codes expire after 1 hour). - Open: requires `channels.whatsapp.allowFrom` to include `"*"`. - - Self messages are always allowed; “self-chat mode” still requires `channels.whatsapp.allowFrom` to include your own number. + - Your linked WhatsApp number is implicitly trusted, so self messages skip ⁠`channels.whatsapp.dmPolicy` and `channels.whatsapp.allowFrom` checks. ### Personal-number mode (fallback) If you run Moltbot on your **personal WhatsApp number**, enable `channels.whatsapp.selfChatMode` (see sample above). diff --git a/docs/cli/memory.md b/docs/cli/memory.md index 3dc79932f..513b7ef07 100644 --- a/docs/cli/memory.md +++ b/docs/cli/memory.md @@ -39,3 +39,4 @@ Notes: - `memory status --deep` probes vector + embedding availability. - `memory status --deep --index` runs a reindex if the store is dirty. - `memory index --verbose` prints per-phase details (provider, model, sources, batch activity). +- `memory status` includes any extra paths configured via `memorySearch.extraPaths`. diff --git a/docs/concepts/memory.md b/docs/concepts/memory.md index 8a386aba9..f2bca461a 100644 --- a/docs/concepts/memory.md +++ b/docs/concepts/memory.md @@ -75,8 +75,9 @@ For the full compaction lifecycle, see ## Vector memory search -Moltbot can build a small vector index over `MEMORY.md` and `memory/*.md` so -semantic queries can find related notes even when wording differs. +Moltbot can build a small vector index over `MEMORY.md` and `memory/*.md` (plus +any extra directories or files you opt in) so semantic queries can find related +notes even when wording differs. Defaults: - Enabled by default. @@ -96,6 +97,27 @@ embeddings for memory search. For Gemini, use `GEMINI_API_KEY` or `models.providers.google.apiKey`. When using a custom OpenAI-compatible endpoint, set `memorySearch.remote.apiKey` (and optional `memorySearch.remote.headers`). +### Additional memory paths + +If you want to index Markdown files outside the default workspace layout, add +explicit paths: + +```json5 +agents: { + defaults: { + memorySearch: { + extraPaths: ["../team-docs", "/srv/shared-notes/overview.md"] + } + } +} +``` + +Notes: +- Paths can be absolute or workspace-relative. +- Directories are scanned recursively for `.md` files. +- Only Markdown files are indexed. +- Symlinks are ignored (files or directories). + ### Gemini embeddings (native) Set the provider to `gemini` to use the Gemini embeddings API directly: @@ -189,14 +211,14 @@ Local mode: ### How the memory tools work - `memory_search` semantically searches Markdown chunks (~400 token target, 80-token overlap) from `MEMORY.md` + `memory/**/*.md`. It returns snippet text (capped ~700 chars), file path, line range, score, provider/model, and whether we fell back from local → remote embeddings. No full file payload is returned. -- `memory_get` reads a specific memory Markdown file (workspace-relative), optionally from a starting line and for N lines. Paths outside `MEMORY.md` / `memory/` are rejected. +- `memory_get` reads a specific memory Markdown file (workspace-relative), optionally from a starting line and for N lines. Paths outside `MEMORY.md` / `memory/` are allowed only when explicitly listed in `memorySearch.extraPaths`. - Both tools are enabled only when `memorySearch.enabled` resolves true for the agent. ### What gets indexed (and when) -- File type: Markdown only (`MEMORY.md`, `memory/**/*.md`). +- File type: Markdown only (`MEMORY.md`, `memory/**/*.md`, plus any `.md` files under `memorySearch.extraPaths`). - Index storage: per-agent SQLite at `~/.clawdbot/memory/.sqlite` (configurable via `agents.defaults.memorySearch.store.path`, supports `{agentId}` token). -- Freshness: watcher on `MEMORY.md` + `memory/` marks the index dirty (debounce 1.5s). Sync is scheduled on session start, on search, or on an interval and runs asynchronously. Session transcripts use delta thresholds to trigger background sync. +- Freshness: watcher on `MEMORY.md`, `memory/`, and `memorySearch.extraPaths` marks the index dirty (debounce 1.5s). Sync is scheduled on session start, on search, or on an interval and runs asynchronously. Session transcripts use delta thresholds to trigger background sync. - Reindex triggers: the index stores the embedding **provider/model + endpoint fingerprint + chunking params**. If any of those change, Moltbot automatically resets and reindexes the entire store. ### Hybrid search (BM25 + vector) diff --git a/docs/gateway/configuration-examples.md b/docs/gateway/configuration-examples.md index 11ac14337..470689673 100644 --- a/docs/gateway/configuration-examples.md +++ b/docs/gateway/configuration-examples.md @@ -267,7 +267,8 @@ Save to `~/.clawdbot/moltbot.json` and you can DM the bot from that number. model: "gemini-embedding-001", remote: { apiKey: "${GEMINI_API_KEY}" - } + }, + extraPaths: ["../team-docs", "/srv/shared-notes"] }, sandbox: { mode: "non-main", diff --git a/docs/providers/venice.md b/docs/providers/venice.md index f6b535a68..140aa9ae0 100644 --- a/docs/providers/venice.md +++ b/docs/providers/venice.md @@ -4,9 +4,9 @@ read_when: - You want privacy-focused inference in Moltbot - You want Venice AI setup guidance --- -# Venice AI (Venius highlight) +# Venice AI (Venice highlight) -**Venius** is our highlight Venice setup for privacy-first inference with optional anonymized access to proprietary models. +**Venice** is our highlight Venice setup for privacy-first inference with optional anonymized access to proprietary models. Venice AI provides privacy-focused AI inference with support for uncensored models and access to major proprietary models through their anonymized proxy. All inference is private by default—no training on your data, no logging. diff --git a/src/agents/memory-search.test.ts b/src/agents/memory-search.test.ts index e6b86ea3d..c3165815f 100644 --- a/src/agents/memory-search.test.ts +++ b/src/agents/memory-search.test.ts @@ -82,6 +82,29 @@ describe("memory search config", () => { expect(resolved?.store.vector.extensionPath).toBe("/opt/sqlite-vec.dylib"); }); + it("merges extra memory paths from defaults and overrides", () => { + const cfg = { + agents: { + defaults: { + memorySearch: { + extraPaths: ["/shared/notes", " docs "], + }, + }, + list: [ + { + id: "main", + default: true, + memorySearch: { + extraPaths: ["/shared/notes", "../team-notes"], + }, + }, + ], + }, + }; + const resolved = resolveMemorySearchConfig(cfg, "main"); + expect(resolved?.extraPaths).toEqual(["/shared/notes", "docs", "../team-notes"]); + }); + it("includes batch defaults for openai without remote overrides", () => { const cfg = { agents: { diff --git a/src/agents/memory-search.ts b/src/agents/memory-search.ts index c08161d4f..25aeb7cac 100644 --- a/src/agents/memory-search.ts +++ b/src/agents/memory-search.ts @@ -9,6 +9,7 @@ import { resolveAgentConfig } from "./agent-scope.js"; export type ResolvedMemorySearchConfig = { enabled: boolean; sources: Array<"memory" | "sessions">; + extraPaths: string[]; provider: "openai" | "local" | "gemini" | "auto"; remote?: { baseUrl?: string; @@ -162,6 +163,10 @@ function mergeConfig( modelCacheDir: overrides?.local?.modelCacheDir ?? defaults?.local?.modelCacheDir, }; const sources = normalizeSources(overrides?.sources ?? defaults?.sources, sessionMemory); + const rawPaths = [...(defaults?.extraPaths ?? []), ...(overrides?.extraPaths ?? [])] + .map((value) => value.trim()) + .filter(Boolean); + const extraPaths = Array.from(new Set(rawPaths)); const vector = { enabled: overrides?.store?.vector?.enabled ?? defaults?.store?.vector?.enabled ?? true, extensionPath: @@ -236,6 +241,7 @@ function mergeConfig( return { enabled, sources, + extraPaths, provider, remote, experimental: { diff --git a/src/agents/tools/memory-tool.ts b/src/agents/tools/memory-tool.ts index b7b619af3..274af4c02 100644 --- a/src/agents/tools/memory-tool.ts +++ b/src/agents/tools/memory-tool.ts @@ -83,7 +83,7 @@ export function createMemoryGetTool(options: { label: "Memory Get", name: "memory_get", description: - "Safe snippet read from MEMORY.md or memory/*.md with optional from/lines; use after memory_search to pull only the needed lines and keep context small.", + "Safe snippet read from MEMORY.md, memory/*.md, or configured memorySearch.extraPaths with optional from/lines; use after memory_search to pull only the needed lines and keep context small.", parameters: MemoryGetSchema, execute: async (_toolCallId, params) => { const relPath = readStringParam(params, "path", { required: true }); diff --git a/src/auto-reply/reply/dispatch-from-config.test.ts b/src/auto-reply/reply/dispatch-from-config.test.ts index c080ef55f..2604038ec 100644 --- a/src/auto-reply/reply/dispatch-from-config.test.ts +++ b/src/auto-reply/reply/dispatch-from-config.test.ts @@ -138,7 +138,7 @@ describe("dispatchReplyFromConfig", () => { ); }); - it("does not provide onToolResult when routing cross-provider", async () => { + it("provides onToolResult in DM sessions", async () => { mocks.tryFastAbortFromMessage.mockResolvedValue({ handled: false, aborted: false, @@ -147,9 +147,34 @@ describe("dispatchReplyFromConfig", () => { const cfg = {} as MoltbotConfig; const dispatcher = createDispatcher(); const ctx = buildTestCtx({ - Provider: "slack", - OriginatingChannel: "telegram", - OriginatingTo: "telegram:999", + Provider: "telegram", + ChatType: "direct", + }); + + const replyResolver = async ( + _ctx: MsgContext, + opts: GetReplyOptions | undefined, + _cfg: ClawdbotConfig, + ) => { + expect(opts?.onToolResult).toBeDefined(); + expect(typeof opts?.onToolResult).toBe("function"); + return { text: "hi" } satisfies ReplyPayload; + }; + + await dispatchReplyFromConfig({ ctx, cfg, dispatcher, replyResolver }); + expect(dispatcher.sendFinalReply).toHaveBeenCalledTimes(1); + }); + + it("does not provide onToolResult in group sessions", async () => { + mocks.tryFastAbortFromMessage.mockResolvedValue({ + handled: false, + aborted: false, + }); + const cfg = {} as ClawdbotConfig; + const dispatcher = createDispatcher(); + const ctx = buildTestCtx({ + Provider: "telegram", + ChatType: "group", }); const replyResolver = async ( @@ -162,12 +187,62 @@ describe("dispatchReplyFromConfig", () => { }; await dispatchReplyFromConfig({ ctx, cfg, dispatcher, replyResolver }); + expect(dispatcher.sendFinalReply).toHaveBeenCalledTimes(1); + }); - expect(mocks.routeReply).toHaveBeenCalledWith( - expect.objectContaining({ - payload: expect.objectContaining({ text: "hi" }), - }), + it("sends tool results via dispatcher in DM sessions", async () => { + mocks.tryFastAbortFromMessage.mockResolvedValue({ + handled: false, + aborted: false, + }); + const cfg = {} as ClawdbotConfig; + const dispatcher = createDispatcher(); + const ctx = buildTestCtx({ + Provider: "telegram", + ChatType: "direct", + }); + + const replyResolver = async ( + _ctx: MsgContext, + opts: GetReplyOptions | undefined, + _cfg: ClawdbotConfig, + ) => { + // Simulate tool result emission + await opts?.onToolResult?.({ text: "🔧 exec: ls" }); + return { text: "done" } satisfies ReplyPayload; + }; + + await dispatchReplyFromConfig({ ctx, cfg, dispatcher, replyResolver }); + expect(dispatcher.sendToolResult).toHaveBeenCalledWith( + expect.objectContaining({ text: "🔧 exec: ls" }), ); + expect(dispatcher.sendFinalReply).toHaveBeenCalledTimes(1); + }); + + it("does not provide onToolResult for native slash commands", async () => { + mocks.tryFastAbortFromMessage.mockResolvedValue({ + handled: false, + aborted: false, + }); + const cfg = {} as ClawdbotConfig; + const dispatcher = createDispatcher(); + const ctx = buildTestCtx({ + Provider: "telegram", + ChatType: "direct", + CommandSource: "native", + }); + + const replyResolver = async ( + _ctx: MsgContext, + opts: GetReplyOptions | undefined, + _cfg: ClawdbotConfig, + ) => { + expect(opts?.onToolResult).toBeUndefined(); + return { text: "hi" } satisfies ReplyPayload; + }; + + await dispatchReplyFromConfig({ ctx, cfg, dispatcher, replyResolver }); + expect(dispatcher.sendFinalReply).toHaveBeenCalledTimes(1); }); it("fast-aborts without calling the reply resolver", async () => { diff --git a/src/auto-reply/reply/dispatch-from-config.ts b/src/auto-reply/reply/dispatch-from-config.ts index 58d5d71b5..c85e654de 100644 --- a/src/auto-reply/reply/dispatch-from-config.ts +++ b/src/auto-reply/reply/dispatch-from-config.ts @@ -276,6 +276,27 @@ export async function dispatchReplyFromConfig(params: { ctx, { ...params.replyOptions, + onToolResult: + ctx.ChatType !== "group" && ctx.CommandSource !== "native" + ? (payload: ReplyPayload) => { + const run = async () => { + const ttsPayload = await maybeApplyTtsToPayload({ + payload, + cfg, + channel: ttsChannel, + kind: "tool", + inboundAudio, + ttsAuto: sessionTtsAuto, + }); + if (shouldRouteToOriginating) { + await sendPayloadAsync(ttsPayload, undefined, false); + } else { + dispatcher.sendToolResult(ttsPayload); + } + }; + return run(); + } + : undefined, onBlockReply: (payload: ReplyPayload, context) => { const run = async () => { // Accumulate block text for TTS generation after streaming diff --git a/src/auto-reply/reply/mentions.test.ts b/src/auto-reply/reply/mentions.test.ts index 7742b4f30..07cff23a9 100644 --- a/src/auto-reply/reply/mentions.test.ts +++ b/src/auto-reply/reply/mentions.test.ts @@ -4,7 +4,7 @@ import { matchesMentionWithExplicit } from "./mentions.js"; describe("matchesMentionWithExplicit", () => { const mentionRegexes = [/\bclawd\b/i]; - it("prefers explicit mentions when other mentions are present", () => { + it("checks mentionPatterns even when explicit mention is available", () => { const result = matchesMentionWithExplicit({ text: "@clawd hello", mentionRegexes, @@ -14,6 +14,19 @@ describe("matchesMentionWithExplicit", () => { canResolveExplicit: true, }, }); + expect(result).toBe(true); + }); + + it("returns false when explicit is false and no regex match", () => { + const result = matchesMentionWithExplicit({ + text: "<@999999> hello", + mentionRegexes, + explicit: { + hasAnyMention: true, + isExplicitlyMentioned: false, + canResolveExplicit: true, + }, + }); expect(result).toBe(false); }); diff --git a/src/auto-reply/reply/mentions.ts b/src/auto-reply/reply/mentions.ts index 71964ac5f..9554a3c7b 100644 --- a/src/auto-reply/reply/mentions.ts +++ b/src/auto-reply/reply/mentions.ts @@ -90,7 +90,9 @@ export function matchesMentionWithExplicit(params: { const explicit = params.explicit?.isExplicitlyMentioned === true; const explicitAvailable = params.explicit?.canResolveExplicit === true; const hasAnyMention = params.explicit?.hasAnyMention === true; - if (hasAnyMention && explicitAvailable) return explicit; + if (hasAnyMention && explicitAvailable) { + return explicit || params.mentionRegexes.some((re) => re.test(cleaned)); + } if (!cleaned) return explicit; return explicit || params.mentionRegexes.some((re) => re.test(cleaned)); } diff --git a/src/cli/memory-cli.ts b/src/cli/memory-cli.ts index 68894adf5..b72267a2a 100644 --- a/src/cli/memory-cli.ts +++ b/src/cli/memory-cli.ts @@ -12,7 +12,7 @@ import { setVerbose } from "../globals.js"; import { withProgress, withProgressTotals } from "./progress.js"; import { formatErrorMessage, withManager } from "./cli-utils.js"; import { getMemorySearchManager, type MemorySearchManagerResult } from "../memory/index.js"; -import { listMemoryFiles } from "../memory/internal.js"; +import { listMemoryFiles, normalizeExtraMemoryPaths } from "../memory/internal.js"; import { defaultRuntime } from "../runtime.js"; import { formatDocsLink } from "../terminal/links.js"; import { colorize, isRich, theme } from "../terminal/theme.js"; @@ -74,6 +74,10 @@ function resolveAgentIds(cfg: ReturnType, agent?: string): st return [resolveDefaultAgentId(cfg)]; } +function formatExtraPaths(workspaceDir: string, extraPaths: string[]): string[] { + return normalizeExtraMemoryPaths(workspaceDir, extraPaths).map((entry) => shortenHomePath(entry)); +} + async function checkReadableFile(pathname: string): Promise<{ exists: boolean; issue?: string }> { try { await fs.access(pathname, fsSync.constants.R_OK); @@ -110,7 +114,10 @@ async function scanSessionFiles(agentId: string): Promise { } } -async function scanMemoryFiles(workspaceDir: string): Promise { +async function scanMemoryFiles( + workspaceDir: string, + extraPaths: string[] = [], +): Promise { const issues: string[] = []; const memoryFile = path.join(workspaceDir, "MEMORY.md"); const altMemoryFile = path.join(workspaceDir, "memory.md"); @@ -121,6 +128,25 @@ async function scanMemoryFiles(workspaceDir: string): Promise { if (primary.issue) issues.push(primary.issue); if (alt.issue) issues.push(alt.issue); + const resolvedExtraPaths = normalizeExtraMemoryPaths(workspaceDir, extraPaths); + for (const extraPath of resolvedExtraPaths) { + try { + const stat = await fs.lstat(extraPath); + if (stat.isSymbolicLink()) continue; + const extraCheck = await checkReadableFile(extraPath); + if (extraCheck.issue) issues.push(extraCheck.issue); + } catch (err) { + const code = (err as NodeJS.ErrnoException).code; + if (code === "ENOENT") { + issues.push(`additional memory path missing (${shortenHomePath(extraPath)})`); + } else { + issues.push( + `additional memory path not accessible (${shortenHomePath(extraPath)}): ${code ?? "error"}`, + ); + } + } + } + let dirReadable: boolean | null = null; try { await fs.access(memoryDir, fsSync.constants.R_OK); @@ -141,7 +167,7 @@ async function scanMemoryFiles(workspaceDir: string): Promise { let listed: string[] = []; let listedOk = false; try { - listed = await listMemoryFiles(workspaceDir); + listed = await listMemoryFiles(workspaceDir, resolvedExtraPaths); listedOk = true; } catch (err) { const code = (err as NodeJS.ErrnoException).code; @@ -176,11 +202,13 @@ async function scanMemorySources(params: { workspaceDir: string; agentId: string; sources: MemorySourceName[]; + extraPaths?: string[]; }): Promise { const scans: SourceScan[] = []; + const extraPaths = params.extraPaths ?? []; for (const source of params.sources) { if (source === "memory") { - scans.push(await scanMemoryFiles(params.workspaceDir)); + scans.push(await scanMemoryFiles(params.workspaceDir, extraPaths)); } if (source === "sessions") { scans.push(await scanSessionFiles(params.agentId)); @@ -268,6 +296,7 @@ export async function runMemoryStatus(opts: MemoryCommandOptions) { workspaceDir: status.workspaceDir, agentId, sources, + extraPaths: status.extraPaths, }); allResults.push({ agentId, status, embeddingProbe, indexError, scan }); }, @@ -299,6 +328,7 @@ export async function runMemoryStatus(opts: MemoryCommandOptions) { const line = indexError ? `Memory index failed: ${indexError}` : "Memory index complete."; defaultRuntime.log(line); } + const extraPaths = formatExtraPaths(status.workspaceDir, status.extraPaths ?? []); const lines = [ `${heading("Memory Search")} ${muted(`(${agentId})`)}`, `${label("Provider")} ${info(status.provider)} ${muted( @@ -306,6 +336,7 @@ export async function runMemoryStatus(opts: MemoryCommandOptions) { )}`, `${label("Model")} ${info(status.model)}`, status.sources?.length ? `${label("Sources")} ${info(status.sources.join(", "))}` : null, + extraPaths.length ? `${label("Extra paths")} ${info(extraPaths.join(", "))}` : null, `${label("Indexed")} ${success(indexedLabel)}`, `${label("Dirty")} ${status.dirty ? warn("yes") : muted("no")}`, `${label("Store")} ${info(shortenHomePath(status.dbPath))}`, @@ -469,6 +500,7 @@ export function registerMemoryCli(program: Command) { const sourceLabels = status.sources.map((source) => formatSourceLabel(source, status.workspaceDir, agentId), ); + const extraPaths = formatExtraPaths(status.workspaceDir, status.extraPaths ?? []); const lines = [ `${heading("Memory Index")} ${muted(`(${agentId})`)}`, `${label("Provider")} ${info(status.provider)} ${muted( @@ -478,6 +510,9 @@ export function registerMemoryCli(program: Command) { sourceLabels.length ? `${label("Sources")} ${info(sourceLabels.join(", "))}` : null, + extraPaths.length + ? `${label("Extra paths")} ${info(extraPaths.join(", "))}` + : null, ].filter(Boolean) as string[]; if (status.fallback) { lines.push(`${label("Fallback")} ${warn(status.fallback.from)}`); diff --git a/src/config/schema.ts b/src/config/schema.ts index b4ec8723b..28c994f3d 100644 --- a/src/config/schema.ts +++ b/src/config/schema.ts @@ -222,6 +222,7 @@ const FIELD_LABELS: Record = { "agents.defaults.memorySearch": "Memory Search", "agents.defaults.memorySearch.enabled": "Enable Memory Search", "agents.defaults.memorySearch.sources": "Memory Search Sources", + "agents.defaults.memorySearch.extraPaths": "Extra Memory Paths", "agents.defaults.memorySearch.experimental.sessionMemory": "Memory Search Session Index (Experimental)", "agents.defaults.memorySearch.provider": "Memory Search Provider", @@ -499,6 +500,8 @@ const FIELD_HELP: Record = { "Vector search over MEMORY.md and memory/*.md (per-agent overrides supported).", "agents.defaults.memorySearch.sources": 'Sources to index for memory search (default: ["memory"]; add "sessions" to include session transcripts).', + "agents.defaults.memorySearch.extraPaths": + "Extra paths to include in memory search (directories or .md files; relative paths resolved from workspace).", "agents.defaults.memorySearch.experimental.sessionMemory": "Enable experimental session transcript indexing for memory search (default: false).", "agents.defaults.memorySearch.provider": 'Embedding provider ("openai", "gemini", or "local").', diff --git a/src/config/types.tools.ts b/src/config/types.tools.ts index bb1d45bf0..db32cb59d 100644 --- a/src/config/types.tools.ts +++ b/src/config/types.tools.ts @@ -226,6 +226,8 @@ export type MemorySearchConfig = { enabled?: boolean; /** Sources to index and search (default: ["memory"]). */ sources?: Array<"memory" | "sessions">; + /** Extra paths to include in memory search (directories or .md files). */ + extraPaths?: string[]; /** Experimental memory search settings. */ experimental?: { /** Enable session transcript indexing (experimental, default: false). */ diff --git a/src/config/zod-schema.agent-runtime.ts b/src/config/zod-schema.agent-runtime.ts index 7a63e307d..7e95c3538 100644 --- a/src/config/zod-schema.agent-runtime.ts +++ b/src/config/zod-schema.agent-runtime.ts @@ -304,6 +304,7 @@ export const MemorySearchSchema = z .object({ enabled: z.boolean().optional(), sources: z.array(z.union([z.literal("memory"), z.literal("sessions")])).optional(), + extraPaths: z.array(z.string()).optional(), experimental: z .object({ sessionMemory: z.boolean().optional(), diff --git a/src/discord/monitor.tool-result.accepts-guild-messages-mentionpatterns-match.test.ts b/src/discord/monitor.tool-result.accepts-guild-messages-mentionpatterns-match.test.ts index 80bb5ff8f..bd4ec38ca 100644 --- a/src/discord/monitor.tool-result.accepts-guild-messages-mentionpatterns-match.test.ts +++ b/src/discord/monitor.tool-result.accepts-guild-messages-mentionpatterns-match.test.ts @@ -135,7 +135,7 @@ describe("discord tool result dispatch", () => { expect(sendMock).toHaveBeenCalledTimes(1); }, 20_000); - it("skips guild messages when another user is explicitly mentioned", async () => { + it("accepts guild messages when mentionPatterns match even if another user is mentioned", async () => { const { createDiscordMessageHandler } = await import("./monitor.js"); const cfg = { agents: { @@ -211,8 +211,8 @@ describe("discord tool result dispatch", () => { client, ); - expect(dispatchMock).not.toHaveBeenCalled(); - expect(sendMock).not.toHaveBeenCalled(); + expect(dispatchMock).toHaveBeenCalledTimes(1); + expect(sendMock).toHaveBeenCalledTimes(1); }, 20_000); it("accepts guild reply-to-bot messages as implicit mentions", async () => { diff --git a/src/media-understanding/apply.test.ts b/src/media-understanding/apply.test.ts index 8bebb8e20..e06adbc24 100644 --- a/src/media-understanding/apply.test.ts +++ b/src/media-understanding/apply.test.ts @@ -41,7 +41,7 @@ describe("applyMediaUnderstanding", () => { mockedResolveApiKey.mockClear(); mockedFetchRemoteMedia.mockReset(); mockedFetchRemoteMedia.mockResolvedValue({ - buffer: Buffer.from("audio-bytes"), + buffer: Buffer.from([0, 255, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]), contentType: "audio/ogg", fileName: "note.ogg", }); @@ -51,7 +51,7 @@ describe("applyMediaUnderstanding", () => { const { applyMediaUnderstanding } = await loadApply(); const dir = await fs.mkdtemp(path.join(os.tmpdir(), "moltbot-media-")); const audioPath = path.join(dir, "note.ogg"); - await fs.writeFile(audioPath, "hello"); + await fs.writeFile(audioPath, Buffer.from([0, 255, 0, 1, 2, 3, 4, 5, 6, 7, 8])); const ctx: MsgContext = { Body: "", @@ -94,7 +94,7 @@ describe("applyMediaUnderstanding", () => { const { applyMediaUnderstanding } = await loadApply(); const dir = await fs.mkdtemp(path.join(os.tmpdir(), "moltbot-media-")); const audioPath = path.join(dir, "note.ogg"); - await fs.writeFile(audioPath, "hello"); + await fs.writeFile(audioPath, Buffer.from([0, 255, 0, 1, 2, 3, 4, 5, 6, 7, 8])); const ctx: MsgContext = { Body: " /capture status", @@ -176,7 +176,7 @@ describe("applyMediaUnderstanding", () => { const { applyMediaUnderstanding } = await loadApply(); const dir = await fs.mkdtemp(path.join(os.tmpdir(), "moltbot-media-")); const audioPath = path.join(dir, "large.wav"); - await fs.writeFile(audioPath, "0123456789"); + await fs.writeFile(audioPath, Buffer.from([0, 255, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10])); const ctx: MsgContext = { Body: "", @@ -211,7 +211,7 @@ describe("applyMediaUnderstanding", () => { const { applyMediaUnderstanding } = await loadApply(); const dir = await fs.mkdtemp(path.join(os.tmpdir(), "moltbot-media-")); const audioPath = path.join(dir, "note.ogg"); - await fs.writeFile(audioPath, "hello"); + await fs.writeFile(audioPath, Buffer.from([0, 255, 0, 1, 2, 3, 4, 5, 6, 7, 8])); const ctx: MsgContext = { Body: "", @@ -352,7 +352,7 @@ describe("applyMediaUnderstanding", () => { const { applyMediaUnderstanding } = await loadApply(); const dir = await fs.mkdtemp(path.join(os.tmpdir(), "moltbot-media-")); const audioPath = path.join(dir, "fallback.ogg"); - await fs.writeFile(audioPath, "hello"); + await fs.writeFile(audioPath, Buffer.from([0, 255, 0, 1, 2, 3, 4, 5, 6])); const ctx: MsgContext = { Body: "", @@ -390,8 +390,8 @@ describe("applyMediaUnderstanding", () => { const dir = await fs.mkdtemp(path.join(os.tmpdir(), "moltbot-media-")); const audioPathA = path.join(dir, "note-a.ogg"); const audioPathB = path.join(dir, "note-b.ogg"); - await fs.writeFile(audioPathA, "hello"); - await fs.writeFile(audioPathB, "world"); + await fs.writeFile(audioPathA, Buffer.from([200, 201, 202, 203, 204, 205, 206, 207, 208])); + await fs.writeFile(audioPathB, Buffer.from([200, 201, 202, 203, 204, 205, 206, 207, 208])); const ctx: MsgContext = { Body: "", @@ -435,7 +435,7 @@ describe("applyMediaUnderstanding", () => { const audioPath = path.join(dir, "note.ogg"); const videoPath = path.join(dir, "clip.mp4"); await fs.writeFile(imagePath, "image-bytes"); - await fs.writeFile(audioPath, "audio-bytes"); + await fs.writeFile(audioPath, Buffer.from([200, 201, 202, 203, 204, 205, 206, 207, 208])); await fs.writeFile(videoPath, "video-bytes"); const ctx: MsgContext = { @@ -487,4 +487,187 @@ describe("applyMediaUnderstanding", () => { expect(ctx.CommandBody).toBe("audio ok"); expect(ctx.BodyForCommands).toBe("audio ok"); }); + + it("treats text-like audio attachments as CSV (comma wins over tabs)", async () => { + const { applyMediaUnderstanding } = await loadApply(); + const dir = await fs.mkdtemp(path.join(os.tmpdir(), "moltbot-media-")); + const csvPath = path.join(dir, "data.mp3"); + const csvText = '"a","b"\t"c"\n"1","2"\t"3"'; + const csvBuffer = Buffer.concat([Buffer.from([0xff, 0xfe]), Buffer.from(csvText, "utf16le")]); + await fs.writeFile(csvPath, csvBuffer); + + const ctx: MsgContext = { + Body: "", + MediaPath: csvPath, + MediaType: "audio/mpeg", + }; + const cfg: MoltbotConfig = { + tools: { + media: { + audio: { enabled: false }, + image: { enabled: false }, + video: { enabled: false }, + }, + }, + }; + + const result = await applyMediaUnderstanding({ ctx, cfg }); + + expect(result.appliedFile).toBe(true); + expect(ctx.Body).toContain(''); + expect(ctx.Body).toContain('"a","b"\t"c"'); + }); + + it("infers TSV when tabs are present without commas", async () => { + const { applyMediaUnderstanding } = await loadApply(); + const dir = await fs.mkdtemp(path.join(os.tmpdir(), "moltbot-media-")); + const tsvPath = path.join(dir, "report.mp3"); + const tsvText = "a\tb\tc\n1\t2\t3"; + await fs.writeFile(tsvPath, tsvText); + + const ctx: MsgContext = { + Body: "", + MediaPath: tsvPath, + MediaType: "audio/mpeg", + }; + const cfg: MoltbotConfig = { + tools: { + media: { + audio: { enabled: false }, + image: { enabled: false }, + video: { enabled: false }, + }, + }, + }; + + const result = await applyMediaUnderstanding({ ctx, cfg }); + + expect(result.appliedFile).toBe(true); + expect(ctx.Body).toContain(''); + expect(ctx.Body).toContain("a\tb\tc"); + }); + + it("escapes XML special characters in filenames to prevent injection", async () => { + const { applyMediaUnderstanding } = await loadApply(); + const dir = await fs.mkdtemp(path.join(os.tmpdir(), "moltbot-media-")); + // Create file with XML special characters in the name (what filesystem allows) + // Note: The sanitizeFilename in store.ts would strip most dangerous chars, + // but we test that even if some slip through, they get escaped in output + const filePath = path.join(dir, "file.txt"); + await fs.writeFile(filePath, "safe content"); + + const ctx: MsgContext = { + Body: "", + MediaPath: filePath, + MediaType: "text/plain", + }; + const cfg: MoltbotConfig = { + tools: { + media: { + audio: { enabled: false }, + image: { enabled: false }, + video: { enabled: false }, + }, + }, + }; + + const result = await applyMediaUnderstanding({ ctx, cfg }); + + expect(result.appliedFile).toBe(true); + // Verify XML special chars are escaped in the output + expect(ctx.Body).toContain("<"); + expect(ctx.Body).toContain(">"); + // The raw < and > should not appear unescaped in the name attribute + expect(ctx.Body).not.toMatch(/name="[^"]*<[^"]*"/); + }); + + it("normalizes MIME types to prevent attribute injection", async () => { + const { applyMediaUnderstanding } = await loadApply(); + const dir = await fs.mkdtemp(path.join(os.tmpdir(), "moltbot-media-")); + const filePath = path.join(dir, "data.txt"); + await fs.writeFile(filePath, "test content"); + + const ctx: MsgContext = { + Body: "", + MediaPath: filePath, + // Attempt to inject via MIME type with quotes - normalization should strip this + MediaType: 'text/plain" onclick="alert(1)', + }; + const cfg: MoltbotConfig = { + tools: { + media: { + audio: { enabled: false }, + image: { enabled: false }, + video: { enabled: false }, + }, + }, + }; + + const result = await applyMediaUnderstanding({ ctx, cfg }); + + expect(result.appliedFile).toBe(true); + // MIME normalization strips everything after first ; or " - verify injection is blocked + expect(ctx.Body).not.toContain("onclick="); + expect(ctx.Body).not.toContain("alert(1)"); + // Verify the MIME type is normalized to just "text/plain" + expect(ctx.Body).toContain('mime="text/plain"'); + }); + + it("handles path traversal attempts in filenames safely", async () => { + const { applyMediaUnderstanding } = await loadApply(); + const dir = await fs.mkdtemp(path.join(os.tmpdir(), "moltbot-media-")); + // Even if a file somehow got a path-like name, it should be handled safely + const filePath = path.join(dir, "normal.txt"); + await fs.writeFile(filePath, "legitimate content"); + + const ctx: MsgContext = { + Body: "", + MediaPath: filePath, + MediaType: "text/plain", + }; + const cfg: MoltbotConfig = { + tools: { + media: { + audio: { enabled: false }, + image: { enabled: false }, + video: { enabled: false }, + }, + }, + }; + + const result = await applyMediaUnderstanding({ ctx, cfg }); + + expect(result.appliedFile).toBe(true); + // Verify the file was processed and output contains expected structure + expect(ctx.Body).toContain(' { + const { applyMediaUnderstanding } = await loadApply(); + const dir = await fs.mkdtemp(path.join(os.tmpdir(), "moltbot-media-")); + const filePath = path.join(dir, "文档.txt"); + await fs.writeFile(filePath, "中文内容"); + + const ctx: MsgContext = { + Body: "", + MediaPath: filePath, + MediaType: "text/plain", + }; + const cfg: MoltbotConfig = { + tools: { + media: { + audio: { enabled: false }, + image: { enabled: false }, + video: { enabled: false }, + }, + }, + }; + + const result = await applyMediaUnderstanding({ ctx, cfg }); + + expect(result.appliedFile).toBe(true); + expect(ctx.Body).toContain("中文内容"); + }); }); diff --git a/src/media-understanding/apply.ts b/src/media-understanding/apply.ts index dab640789..7c2a18006 100644 --- a/src/media-understanding/apply.ts +++ b/src/media-understanding/apply.ts @@ -1,6 +1,22 @@ +import path from "node:path"; + import type { MoltbotConfig } from "../config/config.js"; import type { MsgContext } from "../auto-reply/templating.js"; import { finalizeInboundContext } from "../auto-reply/reply/inbound-context.js"; +import { logVerbose, shouldLogVerbose } from "../globals.js"; +import { + DEFAULT_INPUT_FILE_MAX_BYTES, + DEFAULT_INPUT_FILE_MAX_CHARS, + DEFAULT_INPUT_FILE_MIMES, + DEFAULT_INPUT_MAX_REDIRECTS, + DEFAULT_INPUT_PDF_MAX_PAGES, + DEFAULT_INPUT_PDF_MAX_PIXELS, + DEFAULT_INPUT_PDF_MIN_TEXT_CHARS, + DEFAULT_INPUT_TIMEOUT_MS, + extractFileContentFromSource, + normalizeMimeList, + normalizeMimeType, +} from "../media/input-files.js"; import { extractMediaUserText, formatAudioTranscripts, @@ -14,6 +30,7 @@ import type { } from "./types.js"; import { runWithConcurrency } from "./concurrency.js"; import { resolveConcurrency } from "./resolve.js"; +import { resolveAttachmentKind } from "./attachments.js"; import { type ActiveMediaModel, buildProviderRegistry, @@ -28,9 +45,279 @@ export type ApplyMediaUnderstandingResult = { appliedImage: boolean; appliedAudio: boolean; appliedVideo: boolean; + appliedFile: boolean; }; const CAPABILITY_ORDER: MediaUnderstandingCapability[] = ["image", "audio", "video"]; +const EXTRA_TEXT_MIMES = [ + "application/xml", + "text/xml", + "application/x-yaml", + "text/yaml", + "application/yaml", + "application/javascript", + "text/javascript", + "text/tab-separated-values", +]; +const TEXT_EXT_MIME = new Map([ + [".csv", "text/csv"], + [".tsv", "text/tab-separated-values"], + [".txt", "text/plain"], + [".md", "text/markdown"], + [".log", "text/plain"], + [".ini", "text/plain"], + [".cfg", "text/plain"], + [".conf", "text/plain"], + [".env", "text/plain"], + [".json", "application/json"], + [".yaml", "text/yaml"], + [".yml", "text/yaml"], + [".xml", "application/xml"], +]); + +const XML_ESCAPE_MAP: Record = { + "<": "<", + ">": ">", + "&": "&", + '"': """, + "'": "'", +}; + +/** + * Escapes special XML characters in attribute values to prevent injection. + */ +function xmlEscapeAttr(value: string): string { + return value.replace(/[<>&"']/g, (char) => XML_ESCAPE_MAP[char] ?? char); +} + +function resolveFileLimits(cfg: MoltbotConfig) { + const files = cfg.gateway?.http?.endpoints?.responses?.files; + return { + allowUrl: files?.allowUrl ?? true, + allowedMimes: normalizeMimeList(files?.allowedMimes, DEFAULT_INPUT_FILE_MIMES), + maxBytes: files?.maxBytes ?? DEFAULT_INPUT_FILE_MAX_BYTES, + maxChars: files?.maxChars ?? DEFAULT_INPUT_FILE_MAX_CHARS, + maxRedirects: files?.maxRedirects ?? DEFAULT_INPUT_MAX_REDIRECTS, + timeoutMs: files?.timeoutMs ?? DEFAULT_INPUT_TIMEOUT_MS, + pdf: { + maxPages: files?.pdf?.maxPages ?? DEFAULT_INPUT_PDF_MAX_PAGES, + maxPixels: files?.pdf?.maxPixels ?? DEFAULT_INPUT_PDF_MAX_PIXELS, + minTextChars: files?.pdf?.minTextChars ?? DEFAULT_INPUT_PDF_MIN_TEXT_CHARS, + }, + }; +} + +function appendFileBlocks(body: string | undefined, blocks: string[]): string { + if (!blocks || blocks.length === 0) { + return body ?? ""; + } + const base = typeof body === "string" ? body.trim() : ""; + const suffix = blocks.join("\n\n").trim(); + if (!base) { + return suffix; + } + return `${base}\n\n${suffix}`.trim(); +} + +function resolveUtf16Charset(buffer?: Buffer): "utf-16le" | "utf-16be" | undefined { + if (!buffer || buffer.length < 2) return undefined; + const b0 = buffer[0]; + const b1 = buffer[1]; + if (b0 === 0xff && b1 === 0xfe) { + return "utf-16le"; + } + if (b0 === 0xfe && b1 === 0xff) { + return "utf-16be"; + } + const sampleLen = Math.min(buffer.length, 2048); + let zeroCount = 0; + for (let i = 0; i < sampleLen; i += 1) { + if (buffer[i] === 0) zeroCount += 1; + } + if (zeroCount / sampleLen > 0.2) { + return "utf-16le"; + } + return undefined; +} + +function looksLikeUtf8Text(buffer?: Buffer): boolean { + if (!buffer || buffer.length === 0) return false; + const sampleLen = Math.min(buffer.length, 4096); + let printable = 0; + let other = 0; + for (let i = 0; i < sampleLen; i += 1) { + const byte = buffer[i]; + if (byte === 0) { + other += 1; + continue; + } + if (byte === 9 || byte === 10 || byte === 13 || (byte >= 32 && byte <= 126)) { + printable += 1; + } else { + other += 1; + } + } + const total = printable + other; + if (total === 0) return false; + return printable / total > 0.85; +} + +function decodeTextSample(buffer?: Buffer): string { + if (!buffer || buffer.length === 0) return ""; + const sample = buffer.subarray(0, Math.min(buffer.length, 8192)); + const utf16Charset = resolveUtf16Charset(sample); + if (utf16Charset === "utf-16be") { + const swapped = Buffer.alloc(sample.length); + for (let i = 0; i + 1 < sample.length; i += 2) { + swapped[i] = sample[i + 1]; + swapped[i + 1] = sample[i]; + } + return new TextDecoder("utf-16le").decode(swapped); + } + if (utf16Charset === "utf-16le") { + return new TextDecoder("utf-16le").decode(sample); + } + return new TextDecoder("utf-8").decode(sample); +} + +function guessDelimitedMime(text: string): string | undefined { + if (!text) return undefined; + const line = text.split(/\r?\n/)[0] ?? ""; + const tabs = (line.match(/\t/g) ?? []).length; + const commas = (line.match(/,/g) ?? []).length; + if (commas > 0) { + return "text/csv"; + } + if (tabs > 0) { + return "text/tab-separated-values"; + } + return undefined; +} + +function resolveTextMimeFromName(name?: string): string | undefined { + if (!name) return undefined; + const ext = path.extname(name).toLowerCase(); + return TEXT_EXT_MIME.get(ext); +} + +async function extractFileBlocks(params: { + attachments: ReturnType; + cache: ReturnType; + limits: ReturnType; +}): Promise { + const { attachments, cache, limits } = params; + if (!attachments || attachments.length === 0) { + return []; + } + const blocks: string[] = []; + for (const attachment of attachments) { + if (!attachment) { + continue; + } + const forcedTextMime = resolveTextMimeFromName(attachment.path ?? attachment.url ?? ""); + const kind = forcedTextMime ? "document" : resolveAttachmentKind(attachment); + if (!forcedTextMime && (kind === "image" || kind === "video")) { + continue; + } + if (!limits.allowUrl && attachment.url && !attachment.path) { + if (shouldLogVerbose()) { + logVerbose(`media: file attachment skipped (url disabled) index=${attachment.index}`); + } + continue; + } + let bufferResult: Awaited>; + try { + bufferResult = await cache.getBuffer({ + attachmentIndex: attachment.index, + maxBytes: limits.maxBytes, + timeoutMs: limits.timeoutMs, + }); + } catch (err) { + if (shouldLogVerbose()) { + logVerbose(`media: file attachment skipped (buffer): ${String(err)}`); + } + continue; + } + const nameHint = bufferResult?.fileName ?? attachment.path ?? attachment.url; + const forcedTextMimeResolved = forcedTextMime ?? resolveTextMimeFromName(nameHint ?? ""); + const utf16Charset = resolveUtf16Charset(bufferResult?.buffer); + const textSample = decodeTextSample(bufferResult?.buffer); + const textLike = Boolean(utf16Charset) || looksLikeUtf8Text(bufferResult?.buffer); + if (!forcedTextMimeResolved && kind === "audio" && !textLike) { + continue; + } + const guessedDelimited = textLike ? guessDelimitedMime(textSample) : undefined; + const textHint = + forcedTextMimeResolved ?? guessedDelimited ?? (textLike ? "text/plain" : undefined); + const rawMime = bufferResult?.mime ?? attachment.mime; + const mimeType = textHint ?? normalizeMimeType(rawMime); + // Log when MIME type is overridden from non-text to text for auditability + if (textHint && rawMime && !rawMime.startsWith("text/")) { + logVerbose( + `media: MIME override from "${rawMime}" to "${textHint}" for index=${attachment.index}`, + ); + } + if (!mimeType) { + if (shouldLogVerbose()) { + logVerbose(`media: file attachment skipped (unknown mime) index=${attachment.index}`); + } + continue; + } + const allowedMimes = new Set(limits.allowedMimes); + for (const extra of EXTRA_TEXT_MIMES) { + allowedMimes.add(extra); + } + if (mimeType.startsWith("text/")) { + allowedMimes.add(mimeType); + } + if (!allowedMimes.has(mimeType)) { + if (shouldLogVerbose()) { + logVerbose( + `media: file attachment skipped (unsupported mime ${mimeType}) index=${attachment.index}`, + ); + } + continue; + } + let extracted: Awaited>; + try { + const mediaType = utf16Charset ? `${mimeType}; charset=${utf16Charset}` : mimeType; + extracted = await extractFileContentFromSource({ + source: { + type: "base64", + data: bufferResult.buffer.toString("base64"), + mediaType, + filename: bufferResult.fileName, + }, + limits: { + ...limits, + allowedMimes, + }, + }); + } catch (err) { + if (shouldLogVerbose()) { + logVerbose(`media: file attachment skipped (extract): ${String(err)}`); + } + continue; + } + const text = extracted?.text?.trim() ?? ""; + let blockText = text; + if (!blockText) { + if (extracted?.images && extracted.images.length > 0) { + blockText = "[PDF content rendered to images; images not forwarded to model]"; + } else { + blockText = "[No extractable text]"; + } + } + const safeName = (bufferResult.fileName ?? `file-${attachment.index + 1}`) + .replace(/[\r\n\t]+/g, " ") + .trim(); + // Escape XML special characters in attributes to prevent injection + blocks.push( + `\n${blockText}\n`, + ); + } + return blocks; +} export async function applyMediaUnderstanding(params: { ctx: MsgContext; @@ -51,6 +338,12 @@ export async function applyMediaUnderstanding(params: { const cache = createMediaAttachmentCache(attachments); try { + const fileBlocks = await extractFileBlocks({ + attachments, + cache, + limits: resolveFileLimits(cfg), + }); + const tasks = CAPABILITY_ORDER.map((capability) => async () => { const config = cfg.tools?.media?.[capability]; return await runCapability({ @@ -99,7 +392,15 @@ export async function applyMediaUnderstanding(params: { ctx.RawBody = originalUserText; } ctx.MediaUnderstanding = [...(ctx.MediaUnderstanding ?? []), ...outputs]; - finalizeInboundContext(ctx, { forceBodyForAgent: true, forceBodyForCommands: true }); + } + if (fileBlocks.length > 0) { + ctx.Body = appendFileBlocks(ctx.Body, fileBlocks); + } + if (outputs.length > 0 || fileBlocks.length > 0) { + finalizeInboundContext(ctx, { + forceBodyForAgent: true, + forceBodyForCommands: outputs.length > 0, + }); } return { @@ -108,6 +409,7 @@ export async function applyMediaUnderstanding(params: { appliedImage: outputs.some((output) => output.kind === "image.description"), appliedAudio: outputs.some((output) => output.kind === "audio.transcription"), appliedVideo: outputs.some((output) => output.kind === "video.description"), + appliedFile: fileBlocks.length > 0, }; } finally { await cache.cleanup(); diff --git a/src/memory/index.test.ts b/src/memory/index.test.ts index 58a98e580..cccd1fa49 100644 --- a/src/memory/index.test.ts +++ b/src/memory/index.test.ts @@ -412,4 +412,52 @@ describe("memory index", () => { manager = result.manager; await expect(result.manager.readFile({ relPath: "NOTES.md" })).rejects.toThrow("path required"); }); + + it("allows reading from additional memory paths and blocks symlinks", async () => { + const extraDir = path.join(workspaceDir, "extra"); + await fs.mkdir(extraDir, { recursive: true }); + await fs.writeFile(path.join(extraDir, "extra.md"), "Extra content."); + + const cfg = { + agents: { + defaults: { + workspace: workspaceDir, + memorySearch: { + provider: "openai", + model: "mock-embed", + store: { path: indexPath }, + sync: { watch: false, onSessionStart: false, onSearch: true }, + extraPaths: [extraDir], + }, + }, + list: [{ id: "main", default: true }], + }, + }; + const result = await getMemorySearchManager({ cfg, agentId: "main" }); + expect(result.manager).not.toBeNull(); + if (!result.manager) throw new Error("manager missing"); + manager = result.manager; + await expect(result.manager.readFile({ relPath: "extra/extra.md" })).resolves.toEqual({ + path: "extra/extra.md", + text: "Extra content.", + }); + + const linkPath = path.join(extraDir, "linked.md"); + let symlinkOk = true; + try { + await fs.symlink(path.join(extraDir, "extra.md"), linkPath, "file"); + } catch (err) { + const code = (err as NodeJS.ErrnoException).code; + if (code === "EPERM" || code === "EACCES") { + symlinkOk = false; + } else { + throw err; + } + } + if (symlinkOk) { + await expect(result.manager.readFile({ relPath: "extra/linked.md" })).rejects.toThrow( + "path required", + ); + } + }); }); diff --git a/src/memory/internal.test.ts b/src/memory/internal.test.ts index 29c698779..7530d8e44 100644 --- a/src/memory/internal.test.ts +++ b/src/memory/internal.test.ts @@ -1,6 +1,117 @@ -import { describe, expect, it } from "vitest"; +import fs from "node:fs/promises"; +import os from "node:os"; +import path from "node:path"; -import { chunkMarkdown } from "./internal.js"; +import { afterEach, beforeEach, describe, expect, it } from "vitest"; + +import { chunkMarkdown, listMemoryFiles, normalizeExtraMemoryPaths } from "./internal.js"; + +describe("normalizeExtraMemoryPaths", () => { + it("trims, resolves, and dedupes paths", () => { + const workspaceDir = path.join(os.tmpdir(), "memory-test-workspace"); + const absPath = path.resolve(path.sep, "shared-notes"); + const result = normalizeExtraMemoryPaths(workspaceDir, [ + " notes ", + "./notes", + absPath, + absPath, + "", + ]); + expect(result).toEqual([path.resolve(workspaceDir, "notes"), absPath]); + }); +}); + +describe("listMemoryFiles", () => { + let tmpDir: string; + + beforeEach(async () => { + tmpDir = await fs.mkdtemp(path.join(os.tmpdir(), "memory-test-")); + }); + + afterEach(async () => { + await fs.rm(tmpDir, { recursive: true, force: true }); + }); + + it("includes files from additional paths (directory)", async () => { + await fs.writeFile(path.join(tmpDir, "MEMORY.md"), "# Default memory"); + const extraDir = path.join(tmpDir, "extra-notes"); + await fs.mkdir(extraDir, { recursive: true }); + await fs.writeFile(path.join(extraDir, "note1.md"), "# Note 1"); + await fs.writeFile(path.join(extraDir, "note2.md"), "# Note 2"); + await fs.writeFile(path.join(extraDir, "ignore.txt"), "Not a markdown file"); + + const files = await listMemoryFiles(tmpDir, [extraDir]); + expect(files).toHaveLength(3); + expect(files.some((file) => file.endsWith("MEMORY.md"))).toBe(true); + expect(files.some((file) => file.endsWith("note1.md"))).toBe(true); + expect(files.some((file) => file.endsWith("note2.md"))).toBe(true); + expect(files.some((file) => file.endsWith("ignore.txt"))).toBe(false); + }); + + it("includes files from additional paths (single file)", async () => { + await fs.writeFile(path.join(tmpDir, "MEMORY.md"), "# Default memory"); + const singleFile = path.join(tmpDir, "standalone.md"); + await fs.writeFile(singleFile, "# Standalone"); + + const files = await listMemoryFiles(tmpDir, [singleFile]); + expect(files).toHaveLength(2); + expect(files.some((file) => file.endsWith("standalone.md"))).toBe(true); + }); + + it("handles relative paths in additional paths", async () => { + await fs.writeFile(path.join(tmpDir, "MEMORY.md"), "# Default memory"); + const extraDir = path.join(tmpDir, "subdir"); + await fs.mkdir(extraDir, { recursive: true }); + await fs.writeFile(path.join(extraDir, "nested.md"), "# Nested"); + + const files = await listMemoryFiles(tmpDir, ["subdir"]); + expect(files).toHaveLength(2); + expect(files.some((file) => file.endsWith("nested.md"))).toBe(true); + }); + + it("ignores non-existent additional paths", async () => { + await fs.writeFile(path.join(tmpDir, "MEMORY.md"), "# Default memory"); + + const files = await listMemoryFiles(tmpDir, ["/does/not/exist"]); + expect(files).toHaveLength(1); + }); + + it("ignores symlinked files and directories", async () => { + await fs.writeFile(path.join(tmpDir, "MEMORY.md"), "# Default memory"); + const extraDir = path.join(tmpDir, "extra"); + await fs.mkdir(extraDir, { recursive: true }); + await fs.writeFile(path.join(extraDir, "note.md"), "# Note"); + + const targetFile = path.join(tmpDir, "target.md"); + await fs.writeFile(targetFile, "# Target"); + const linkFile = path.join(extraDir, "linked.md"); + + const targetDir = path.join(tmpDir, "target-dir"); + await fs.mkdir(targetDir, { recursive: true }); + await fs.writeFile(path.join(targetDir, "nested.md"), "# Nested"); + const linkDir = path.join(tmpDir, "linked-dir"); + + let symlinksOk = true; + try { + await fs.symlink(targetFile, linkFile, "file"); + await fs.symlink(targetDir, linkDir, "dir"); + } catch (err) { + const code = (err as NodeJS.ErrnoException).code; + if (code === "EPERM" || code === "EACCES") { + symlinksOk = false; + } else { + throw err; + } + } + + const files = await listMemoryFiles(tmpDir, [extraDir, linkDir]); + expect(files.some((file) => file.endsWith("note.md"))).toBe(true); + if (symlinksOk) { + expect(files.some((file) => file.endsWith("linked.md"))).toBe(false); + expect(files.some((file) => file.endsWith("nested.md"))).toBe(false); + } + }); +}); describe("chunkMarkdown", () => { it("splits overly long lines into max-sized chunks", () => { diff --git a/src/memory/internal.ts b/src/memory/internal.ts index b68570c35..b2ab8c0a4 100644 --- a/src/memory/internal.ts +++ b/src/memory/internal.ts @@ -30,6 +30,17 @@ export function normalizeRelPath(value: string): string { return trimmed.replace(/\\/g, "/"); } +export function normalizeExtraMemoryPaths(workspaceDir: string, extraPaths?: string[]): string[] { + if (!extraPaths?.length) return []; + const resolved = extraPaths + .map((value) => value.trim()) + .filter(Boolean) + .map((value) => + path.isAbsolute(value) ? path.resolve(value) : path.resolve(workspaceDir, value), + ); + return Array.from(new Set(resolved)); +} + export function isMemoryPath(relPath: string): boolean { const normalized = normalizeRelPath(relPath); if (!normalized) return false; @@ -37,19 +48,11 @@ export function isMemoryPath(relPath: string): boolean { return normalized.startsWith("memory/"); } -async function exists(filePath: string): Promise { - try { - await fs.access(filePath); - return true; - } catch { - return false; - } -} - async function walkDir(dir: string, files: string[]) { const entries = await fs.readdir(dir, { withFileTypes: true }); for (const entry of entries) { const full = path.join(dir, entry.name); + if (entry.isSymbolicLink()) continue; if (entry.isDirectory()) { await walkDir(full, files); continue; @@ -60,15 +63,48 @@ async function walkDir(dir: string, files: string[]) { } } -export async function listMemoryFiles(workspaceDir: string): Promise { +export async function listMemoryFiles( + workspaceDir: string, + extraPaths?: string[], +): Promise { const result: string[] = []; const memoryFile = path.join(workspaceDir, "MEMORY.md"); const altMemoryFile = path.join(workspaceDir, "memory.md"); - if (await exists(memoryFile)) result.push(memoryFile); - if (await exists(altMemoryFile)) result.push(altMemoryFile); const memoryDir = path.join(workspaceDir, "memory"); - if (await exists(memoryDir)) { - await walkDir(memoryDir, result); + + const addMarkdownFile = async (absPath: string) => { + try { + const stat = await fs.lstat(absPath); + if (stat.isSymbolicLink() || !stat.isFile()) return; + if (!absPath.endsWith(".md")) return; + result.push(absPath); + } catch {} + }; + + await addMarkdownFile(memoryFile); + await addMarkdownFile(altMemoryFile); + try { + const dirStat = await fs.lstat(memoryDir); + if (!dirStat.isSymbolicLink() && dirStat.isDirectory()) { + await walkDir(memoryDir, result); + } + } catch {} + + const normalizedExtraPaths = normalizeExtraMemoryPaths(workspaceDir, extraPaths); + if (normalizedExtraPaths.length > 0) { + for (const inputPath of normalizedExtraPaths) { + try { + const stat = await fs.lstat(inputPath); + if (stat.isSymbolicLink()) continue; + if (stat.isDirectory()) { + await walkDir(inputPath, result); + continue; + } + if (stat.isFile() && inputPath.endsWith(".md")) { + result.push(inputPath); + } + } catch {} + } } if (result.length <= 1) return result; const seen = new Set(); diff --git a/src/memory/manager-cache-key.ts b/src/memory/manager-cache-key.ts index 9fbe3e436..d143a9057 100644 --- a/src/memory/manager-cache-key.ts +++ b/src/memory/manager-cache-key.ts @@ -13,6 +13,7 @@ export function computeMemoryManagerCacheKey(params: { JSON.stringify({ enabled: settings.enabled, sources: [...settings.sources].sort((a, b) => a.localeCompare(b)), + extraPaths: [...settings.extraPaths].sort((a, b) => a.localeCompare(b)), provider: settings.provider, model: settings.model, fallback: settings.fallback, diff --git a/src/memory/manager.ts b/src/memory/manager.ts index 9a9991d10..a799a5e0f 100644 --- a/src/memory/manager.ts +++ b/src/memory/manager.ts @@ -1,4 +1,5 @@ import { randomUUID } from "node:crypto"; +import fsSync from "node:fs"; import fs from "node:fs/promises"; import path from "node:path"; @@ -35,9 +36,9 @@ import { hashText, isMemoryPath, listMemoryFiles, + normalizeExtraMemoryPaths, type MemoryChunk, type MemoryFileEntry, - normalizeRelPath, parseEmbedding, } from "./internal.js"; import { bm25RankToScore, buildFtsQuery, mergeHybridResults } from "./hybrid.js"; @@ -396,13 +397,52 @@ export class MemoryIndexManager { from?: number; lines?: number; }): Promise<{ text: string; path: string }> { - const relPath = normalizeRelPath(params.relPath); - if (!relPath || !isMemoryPath(relPath)) { + const rawPath = params.relPath.trim(); + if (!rawPath) { throw new Error("path required"); } - const absPath = path.resolve(this.workspaceDir, relPath); - if (!absPath.startsWith(this.workspaceDir)) { - throw new Error("path escapes workspace"); + const absPath = path.isAbsolute(rawPath) + ? path.resolve(rawPath) + : path.resolve(this.workspaceDir, rawPath); + const relPath = path.relative(this.workspaceDir, absPath).replace(/\\/g, "/"); + const inWorkspace = + relPath.length > 0 && !relPath.startsWith("..") && !path.isAbsolute(relPath); + const allowedWorkspace = inWorkspace && isMemoryPath(relPath); + let allowedAdditional = false; + if (!allowedWorkspace && this.settings.extraPaths.length > 0) { + const additionalPaths = normalizeExtraMemoryPaths( + this.workspaceDir, + this.settings.extraPaths, + ); + for (const additionalPath of additionalPaths) { + try { + const stat = await fs.lstat(additionalPath); + if (stat.isSymbolicLink()) continue; + if (stat.isDirectory()) { + if (absPath === additionalPath || absPath.startsWith(`${additionalPath}${path.sep}`)) { + allowedAdditional = true; + break; + } + continue; + } + if (stat.isFile()) { + if (absPath === additionalPath && absPath.endsWith(".md")) { + allowedAdditional = true; + break; + } + } + } catch {} + } + } + if (!allowedWorkspace && !allowedAdditional) { + throw new Error("path required"); + } + if (!absPath.endsWith(".md")) { + throw new Error("path required"); + } + const stat = await fs.lstat(absPath); + if (stat.isSymbolicLink() || !stat.isFile()) { + throw new Error("path required"); } const content = await fs.readFile(absPath, "utf-8"); if (!params.from && !params.lines) { @@ -425,6 +465,7 @@ export class MemoryIndexManager { model: string; requestedProvider: string; sources: MemorySource[]; + extraPaths: string[]; sourceCounts: Array<{ source: MemorySource; files: number; chunks: number }>; cache?: { enabled: boolean; entries?: number; maxEntries?: number }; fts?: { enabled: boolean; available: boolean; error?: string }; @@ -498,6 +539,7 @@ export class MemoryIndexManager { model: this.provider.model, requestedProvider: this.requestedProvider, sources: Array.from(this.sources), + extraPaths: this.settings.extraPaths, sourceCounts, cache: this.cache.enabled ? { @@ -769,11 +811,23 @@ export class MemoryIndexManager { private ensureWatcher() { if (!this.sources.has("memory") || !this.settings.sync.watch || this.watcher) return; - const watchPaths = [ + const additionalPaths = normalizeExtraMemoryPaths(this.workspaceDir, this.settings.extraPaths) + .map((entry) => { + try { + const stat = fsSync.lstatSync(entry); + return stat.isSymbolicLink() ? null : entry; + } catch { + return null; + } + }) + .filter((entry): entry is string => Boolean(entry)); + const watchPaths = new Set([ path.join(this.workspaceDir, "MEMORY.md"), + path.join(this.workspaceDir, "memory.md"), path.join(this.workspaceDir, "memory"), - ]; - this.watcher = chokidar.watch(watchPaths, { + ...additionalPaths, + ]); + this.watcher = chokidar.watch(Array.from(watchPaths), { ignoreInitial: true, awaitWriteFinish: { stabilityThreshold: this.settings.sync.watchDebounceMs, @@ -975,7 +1029,7 @@ export class MemoryIndexManager { needsFullReindex: boolean; progress?: MemorySyncProgressState; }) { - const files = await listMemoryFiles(this.workspaceDir); + const files = await listMemoryFiles(this.workspaceDir, this.settings.extraPaths); const fileEntries = await Promise.all( files.map(async (file) => buildFileEntry(file, this.workspaceDir)), ); diff --git a/src/memory/sync-memory-files.ts b/src/memory/sync-memory-files.ts index 53fed7ebe..c5073dc50 100644 --- a/src/memory/sync-memory-files.ts +++ b/src/memory/sync-memory-files.ts @@ -14,6 +14,7 @@ type ProgressState = { export async function syncMemoryFiles(params: { workspaceDir: string; + extraPaths?: string[]; db: DatabaseSync; needsFullReindex: boolean; progress?: ProgressState; @@ -27,7 +28,7 @@ export async function syncMemoryFiles(params: { ftsAvailable: boolean; model: string; }) { - const files = await listMemoryFiles(params.workspaceDir); + const files = await listMemoryFiles(params.workspaceDir, params.extraPaths); const fileEntries = await Promise.all( files.map(async (file) => buildFileEntry(file, params.workspaceDir)), ); diff --git a/src/slack/monitor.tool-result.sends-tool-summaries-responseprefix.test.ts b/src/slack/monitor.tool-result.sends-tool-summaries-responseprefix.test.ts index ce7015399..4481d7589 100644 --- a/src/slack/monitor.tool-result.sends-tool-summaries-responseprefix.test.ts +++ b/src/slack/monitor.tool-result.sends-tool-summaries-responseprefix.test.ts @@ -392,7 +392,7 @@ describe("monitorSlackProvider tool results", () => { expect(replyMock.mock.calls[0][0].WasMentioned).toBe(true); }); - it("skips channel messages when another user is explicitly mentioned", async () => { + it("accepts channel messages when mentionPatterns match even if another user is mentioned", async () => { slackTestState.config = { messages: { responsePrefix: "PFX", @@ -433,8 +433,8 @@ describe("monitorSlackProvider tool results", () => { controller.abort(); await run; - expect(replyMock).not.toHaveBeenCalled(); - expect(sendMock).not.toHaveBeenCalled(); + expect(replyMock).toHaveBeenCalledTimes(1); + expect(replyMock.mock.calls[0][0].WasMentioned).toBe(true); }); it("treats replies to bot threads as implicit mentions", async () => { diff --git a/src/telegram/bot-message-context.ts b/src/telegram/bot-message-context.ts index 832a4413d..abd06cdef 100644 --- a/src/telegram/bot-message-context.ts +++ b/src/telegram/bot-message-context.ts @@ -335,6 +335,7 @@ export const buildTelegramMessageContext = async ({ let placeholder = ""; if (msg.photo) placeholder = ""; else if (msg.video) placeholder = ""; + else if (msg.video_note) placeholder = ""; else if (msg.audio || msg.voice) placeholder = ""; else if (msg.document) placeholder = ""; else if (msg.sticker) placeholder = ""; diff --git a/src/telegram/bot-native-commands.ts b/src/telegram/bot-native-commands.ts index 3415ea927..73a5a148a 100644 --- a/src/telegram/bot-native-commands.ts +++ b/src/telegram/bot-native-commands.ts @@ -468,6 +468,7 @@ export const registerTelegramNativeCommands = ({ CommandAuthorized: commandAuthorized, CommandSource: "native" as const, SessionKey: `telegram:slash:${senderId || chatId}`, + AccountId: route.accountId, CommandTargetSessionKey: sessionKey, MessageThreadId: threadIdForSend, IsForum: isForum, diff --git a/src/telegram/bot.create-telegram-bot.accepts-group-messages-mentionpatterns-match-without-botusername.test.ts b/src/telegram/bot.create-telegram-bot.accepts-group-messages-mentionpatterns-match-without-botusername.test.ts index 8bfe1fdd3..03aaeebd7 100644 --- a/src/telegram/bot.create-telegram-bot.accepts-group-messages-mentionpatterns-match-without-botusername.test.ts +++ b/src/telegram/bot.create-telegram-bot.accepts-group-messages-mentionpatterns-match-without-botusername.test.ts @@ -212,7 +212,7 @@ describe("createTelegramBot", () => { ); }); - it("skips group messages when another user is explicitly mentioned", async () => { + it("accepts group messages when mentionPatterns match even if another user is mentioned", async () => { onSpy.mockReset(); const replySpy = replyModule.__replySpy as unknown as ReturnType; replySpy.mockReset(); @@ -249,7 +249,8 @@ describe("createTelegramBot", () => { getFile: async () => ({ download: async () => new Uint8Array() }), }); - expect(replySpy).not.toHaveBeenCalled(); + expect(replySpy).toHaveBeenCalledTimes(1); + expect(replySpy.mock.calls[0][0].WasMentioned).toBe(true); }); it("keeps group envelope headers stable (sender identity is separate)", async () => { diff --git a/src/telegram/bot/delivery.ts b/src/telegram/bot/delivery.ts index 4f45f9997..8c1e74b73 100644 --- a/src/telegram/bot/delivery.ts +++ b/src/telegram/bot/delivery.ts @@ -310,7 +310,14 @@ export async function resolveMedia( fetchImpl, filePathHint: file.file_path, }); - const saved = await saveMediaBuffer(fetched.buffer, fetched.contentType, "inbound", maxBytes); + const originalName = fetched.fileName ?? file.file_path; + const saved = await saveMediaBuffer( + fetched.buffer, + fetched.contentType, + "inbound", + maxBytes, + originalName, + ); // Check sticker cache for existing description const cached = sticker.file_unique_id ? getCachedSticker(sticker.file_unique_id) : null; @@ -361,7 +368,12 @@ export async function resolveMedia( } const m = - msg.photo?.[msg.photo.length - 1] ?? msg.video ?? msg.document ?? msg.audio ?? msg.voice; + msg.photo?.[msg.photo.length - 1] ?? + msg.video ?? + msg.video_note ?? + msg.document ?? + msg.audio ?? + msg.voice; if (!m?.file_id) return null; const file = await ctx.getFile(); if (!file.file_path) { @@ -377,10 +389,18 @@ export async function resolveMedia( fetchImpl, filePathHint: file.file_path, }); - const saved = await saveMediaBuffer(fetched.buffer, fetched.contentType, "inbound", maxBytes); + const originalName = fetched.fileName ?? file.file_path; + const saved = await saveMediaBuffer( + fetched.buffer, + fetched.contentType, + "inbound", + maxBytes, + originalName, + ); let placeholder = ""; if (msg.photo) placeholder = ""; else if (msg.video) placeholder = ""; + else if (msg.video_note) placeholder = ""; else if (msg.audio || msg.voice) placeholder = ""; return { path: saved.path, contentType: saved.contentType, placeholder }; } diff --git a/src/telegram/download.ts b/src/telegram/download.ts index 1b3c61e22..31f431db0 100644 --- a/src/telegram/download.ts +++ b/src/telegram/download.ts @@ -40,7 +40,7 @@ export async function downloadTelegramFile( filePath: info.file_path, }); // save with inbound subdir - const saved = await saveMediaBuffer(array, mime, "inbound", maxBytes); + const saved = await saveMediaBuffer(array, mime, "inbound", maxBytes, info.file_path); // Ensure extension matches mime if possible if (!saved.contentType && mime) saved.contentType = mime; return saved; diff --git a/src/tts/tts.ts b/src/tts/tts.ts index af3d7fda5..faa83d3a6 100644 --- a/src/tts/tts.ts +++ b/src/tts/tts.ts @@ -757,11 +757,19 @@ export const OPENAI_TTS_MODELS = ["gpt-4o-mini-tts", "tts-1", "tts-1-hd"] as con * Custom OpenAI-compatible TTS endpoint. * When set, model/voice validation is relaxed to allow non-OpenAI models. * Example: OPENAI_TTS_BASE_URL=http://localhost:8880/v1 + * + * Note: Read at runtime (not module load) to support config.env loading. */ -const OPENAI_TTS_BASE_URL = ( - process.env.OPENAI_TTS_BASE_URL?.trim() || "https://api.openai.com/v1" -).replace(/\/+$/, ""); -const isCustomOpenAIEndpoint = OPENAI_TTS_BASE_URL !== "https://api.openai.com/v1"; +function getOpenAITtsBaseUrl(): string { + return (process.env.OPENAI_TTS_BASE_URL?.trim() || "https://api.openai.com/v1").replace( + /\/+$/, + "", + ); +} + +function isCustomOpenAIEndpoint(): boolean { + return getOpenAITtsBaseUrl() !== "https://api.openai.com/v1"; +} export const OPENAI_TTS_VOICES = [ "alloy", "ash", @@ -778,13 +786,13 @@ type OpenAiTtsVoice = (typeof OPENAI_TTS_VOICES)[number]; function isValidOpenAIModel(model: string): boolean { // Allow any model when using custom endpoint (e.g., Kokoro, LocalAI) - if (isCustomOpenAIEndpoint) return true; + if (isCustomOpenAIEndpoint()) return true; return OPENAI_TTS_MODELS.includes(model as (typeof OPENAI_TTS_MODELS)[number]); } function isValidOpenAIVoice(voice: string): voice is OpenAiTtsVoice { // Allow any voice when using custom endpoint (e.g., Kokoro Chinese voices) - if (isCustomOpenAIEndpoint) return true; + if (isCustomOpenAIEndpoint()) return true; return OPENAI_TTS_VOICES.includes(voice as OpenAiTtsVoice); } @@ -1011,7 +1019,7 @@ async function openaiTTS(params: { const timeout = setTimeout(() => controller.abort(), timeoutMs); try { - const response = await fetch(`${OPENAI_TTS_BASE_URL}/audio/speech`, { + const response = await fetch(`${getOpenAITtsBaseUrl()}/audio/speech`, { method: "POST", headers: { Authorization: `Bearer ${apiKey}`, diff --git a/ui/src/ui/app-render.ts b/ui/src/ui/app-render.ts index a088c33ff..422af6863 100644 --- a/ui/src/ui/app-render.ts +++ b/ui/src/ui/app-render.ts @@ -42,6 +42,7 @@ import { renderNodes } from "./views/nodes"; import { renderOverview } from "./views/overview"; import { renderSessions } from "./views/sessions"; import { renderExecApprovalPrompt } from "./views/exec-approval"; +import { renderGatewayUrlConfirmation } from "./views/gateway-url-confirmation"; import { approveDevicePairing, loadDevices, @@ -578,6 +579,7 @@ export function renderApp(state: AppViewState) { : nothing} ${renderExecApprovalPrompt(state)} + ${renderGatewayUrlConfirmation(state)} `; } diff --git a/ui/src/ui/app-settings.ts b/ui/src/ui/app-settings.ts index e269742b2..7e3ab29cf 100644 --- a/ui/src/ui/app-settings.ts +++ b/ui/src/ui/app-settings.ts @@ -33,6 +33,7 @@ type SettingsHost = { basePath: string; themeMedia: MediaQueryList | null; themeMediaHandler: ((event: MediaQueryListEvent) => void) | null; + pendingGatewayUrl?: string | null; }; export function applySettings(host: SettingsHost, next: UiSettings) { @@ -98,7 +99,7 @@ export function applySettingsFromUrl(host: SettingsHost) { if (gatewayUrlRaw != null) { const gatewayUrl = gatewayUrlRaw.trim(); if (gatewayUrl && gatewayUrl !== host.settings.gatewayUrl) { - applySettings(host, { ...host.settings, gatewayUrl }); + host.pendingGatewayUrl = gatewayUrl; } params.delete("gatewayUrl"); shouldCleanUrl = true; diff --git a/ui/src/ui/app-view-state.ts b/ui/src/ui/app-view-state.ts index 069465e32..f58656bfb 100644 --- a/ui/src/ui/app-view-state.ts +++ b/ui/src/ui/app-view-state.ts @@ -73,6 +73,7 @@ export type AppViewState = { execApprovalQueue: ExecApprovalRequest[]; execApprovalBusy: boolean; execApprovalError: string | null; + pendingGatewayUrl: string | null; configLoading: boolean; configRaw: string; configRawOriginal: string; @@ -165,6 +166,8 @@ export type AppViewState = { handleNostrProfileImport: () => Promise; handleNostrProfileToggleAdvanced: () => void; handleExecApprovalDecision: (decision: "allow-once" | "allow-always" | "deny") => Promise; + handleGatewayUrlConfirm: () => void; + handleGatewayUrlCancel: () => void; handleConfigLoad: () => Promise; handleConfigSave: () => Promise; handleConfigApply: () => Promise; diff --git a/ui/src/ui/app.ts b/ui/src/ui/app.ts index d23e543cd..26f4a5836 100644 --- a/ui/src/ui/app.ts +++ b/ui/src/ui/app.ts @@ -152,6 +152,7 @@ export class MoltbotApp extends LitElement { @state() execApprovalQueue: ExecApprovalRequest[] = []; @state() execApprovalBusy = false; @state() execApprovalError: string | null = null; + @state() pendingGatewayUrl: string | null = null; @state() configLoading = false; @state() configRaw = "{\n}\n"; @@ -448,6 +449,21 @@ export class MoltbotApp extends LitElement { } } + handleGatewayUrlConfirm() { + const nextGatewayUrl = this.pendingGatewayUrl; + if (!nextGatewayUrl) return; + this.pendingGatewayUrl = null; + applySettingsInternal( + this as unknown as Parameters[0], + { ...this.settings, gatewayUrl: nextGatewayUrl }, + ); + this.connect(); + } + + handleGatewayUrlCancel() { + this.pendingGatewayUrl = null; + } + // Sidebar handlers for tool output viewing handleOpenSidebar(content: string) { if (this.sidebarCloseTimer != null) { diff --git a/ui/src/ui/views/config-form.node.ts b/ui/src/ui/views/config-form.node.ts index 9d121d7f1..17a182281 100644 --- a/ui/src/ui/views/config-form.node.ts +++ b/ui/src/ui/views/config-form.node.ts @@ -260,6 +260,11 @@ function renderTextInput(params: { } onPatch(path, raw); }} + @change=${(e: Event) => { + if (inputType === "number") return; + const raw = (e.target as HTMLInputElement).value; + onPatch(path, raw.trim()); + }} /> ${schema.default !== undefined ? html` + + + + + `; +}