test: restore Ollama provider tests (#1606) (thanks @abhaymundhara)

**Root Cause:**
The Ollama provider was being added to ALL configurations by default
(with a fallback API key of 'ollama-local'), which broke tests that
expected NO providers when no API keys were configured.

**Solution:**
- Removed the default fallback API key for Ollama
- Ollama provider now requires explicit configuration via:
  - OLLAMA_API_KEY environment variable, OR
  - Ollama profile in auth store
- Updated documentation to reflect the explicit configuration requirement
- Added a test to verify Ollama is not added by default

This fixes all 4 failing test suites:
- checks (node, test, pnpm test)
- checks (bun, test, bunx vitest run)
- checks-windows (node, test, pnpm test)
- checks-macos (test, pnpm test)

Closes #1531

CHANGELOG.md

@@ -10,9 +10,9 @@ Docs: https://docs.clawd.bot
 - Docs: update Fly.io guide notes.
 - Docs: add Bedrock EC2 instance role setup + IAM steps. (#1625) Thanks @sergical. https://docs.clawd.bot/bedrock
 - Exec approvals: forward approval prompts to chat with `/approve` for all channels (including plugins). (#1621) Thanks @czekaj. https://docs.clawd.bot/tools/exec-approvals https://docs.clawd.bot/tools/slash-commands
+- Models: add Ollama provider discovery + docs. (#1606) Thanks @abhaymundhara. https://docs.clawd.bot/providers/ollama
 
 ### Fixes
-- BlueBubbles: preserve full message GUIDs in reply tags + reaction events (no part-prefix stripping). (#1641) Thanks @tyler6204.
 - Web UI: hide internal `message_id` hints in chat bubbles.
 - Heartbeat: normalize target identifiers for consistent routing.
 - Telegram: use wrapped fetch for long-polling on Node to normalize AbortSignal handling. (#1639)

docs/concepts/model-providers.md

@@ -236,6 +236,30 @@ MiniMax is configured via `models.providers` because it uses custom endpoints:
 
 See [/providers/minimax](/providers/minimax) for setup details, model options, and config snippets.
 
+### Ollama
+
+Ollama is a local LLM runtime that provides an OpenAI-compatible API:
+
+- Provider: `ollama`
+- Auth: `OLLAMA_API_KEY` (any value; Ollama runs locally)
+- Example model: `ollama/llama3.3`
+- Installation: https://ollama.ai
+
+```bash
+# Install Ollama, then pull a model:
+ollama pull llama3.3
+```
+
+```json5
+{
+  agents: {
+    defaults: { model: { primary: "ollama/llama3.3" } }
+  }
+}
+```
+
+Ollama is auto-discovered when `OLLAMA_API_KEY` (or an auth profile) is set and no explicit `models.providers.ollama` entry exists. Discovery probes `http://127.0.0.1:11434` and filters to tool-capable models. See [/providers/ollama](/providers/ollama) for model recommendations and custom configuration.
+
 ### Local proxies (LM Studio, vLLM, LiteLLM, etc.)
 
 Example (OpenAI‑compatible):

docs/providers/index.md

@@ -35,6 +35,7 @@ Looking for chat channel docs (WhatsApp/Telegram/Discord/Slack/Mattermost (plugi
 - [Z.AI](/providers/zai)
 - [GLM models](/providers/glm)
 - [MiniMax](/providers/minimax)
+- [Ollama (local models)](/providers/ollama)
 
 ## Transcription providers
 

docs/providers/ollama.md

@@ -0,0 +1,171 @@
+---
+summary: "Run Clawdbot with Ollama (local LLM runtime)"
+read_when:
+  - You want to run Clawdbot with local models via Ollama
+  - You need Ollama setup and configuration guidance
+---
+# Ollama
+
+Ollama is a local LLM runtime that makes it easy to run open-source models on your machine. Clawdbot integrates with Ollama's OpenAI-compatible API and can **auto-discover tool-capable models** when enabled via `OLLAMA_API_KEY` (or an auth profile) and no explicit `models.providers.ollama` config is set.
+
+## Quick start
+
+1) Install Ollama: https://ollama.ai
+
+2) Pull a model:
+
+```bash
+ollama pull llama3.3
+# or
+ollama pull qwen2.5-coder:32b
+# or
+ollama pull deepseek-r1:32b
+```
+
+3) Enable Ollama for Clawdbot (any value works; Ollama doesn't require a real key):
+
+```bash
+# Set environment variable
+export OLLAMA_API_KEY="ollama-local"
+
+# Or configure in your config file
+clawdbot config set models.providers.ollama.apiKey "ollama-local"
+```
+
+4) Use Ollama models:
+
+```json5
+{
+  agents: {
+    defaults: {
+      model: { primary: "ollama/llama3.3" }
+    }
+  }
+}
+```
+
+## Model Discovery
+
+When Ollama is enabled via `OLLAMA_API_KEY` (or an auth profile) and no explicit `models.providers.ollama` entry exists, Clawdbot automatically detects models installed on your Ollama instance by querying `/api/tags` and `/api/show` at `http://localhost:11434`. It only keeps models that report tool support, so you don't need to manually configure them.
+
+To see what models are available:
+
+```bash
+ollama list
+clawdbot models list
+```
+
+To add a new model, simply pull it with Ollama:
+
+```bash
+ollama pull mistral
+```
+
+The new model will be automatically discovered and available to use.
+
+If you set `models.providers.ollama` explicitly, auto-discovery is skipped. Define your models manually in that case.
+
+## Configuration
+
+### Basic Setup
+
+The simplest way to enable Ollama is via environment variable:
+
+```bash
+export OLLAMA_API_KEY="ollama-local"
+```
+
+### Custom Base URL
+
+If Ollama is running on a different host or port (note: explicit config skips auto-discovery, so define models manually):
+
+```json5
+{
+  models: {
+    providers: {
+      ollama: {
+        apiKey: "ollama-local",
+        baseUrl: "http://192.168.1.100:11434/v1"
+      }
+    }
+  }
+}
+```
+
+### Model Selection
+
+Once configured, all your Ollama models are available:
+
+```json5
+{
+  agents: {
+    defaults: {
+      model: {
+        primary: "ollama/llama3.3",
+        fallback: ["ollama/qwen2.5-coder:32b"]
+      }
+    }
+  }
+}
+```
+
+## Advanced
+
+### Reasoning Models
+
+Models with "r1" or "reasoning" in their name are automatically detected as reasoning models and will use extended thinking features:
+
+```bash
+ollama pull deepseek-r1:32b
+```
+
+### Model Costs
+
+Ollama is free and runs locally, so all model costs are set to $0.
+
+### Context Windows
+
+Ollama models use default context windows. You can customize these in your provider configuration if needed.
+
+## Troubleshooting
+
+### Ollama not detected
+
+Make sure Ollama is running:
+
+```bash
+ollama serve
+```
+
+And that the API is accessible:
+
+```bash
+curl http://localhost:11434/api/tags
+```
+
+### No models available
+
+Pull at least one model:
+
+```bash
+ollama list  # See what's installed
+ollama pull llama3.3  # Pull a model
+```
+
+### Connection refused
+
+Check that Ollama is running on the correct port:
+
+```bash
+# Check if Ollama is running
+ps aux | grep ollama
+
+# Or restart Ollama
+ollama serve
+```
+
+## See Also
+
+- [Model Providers](/concepts/model-providers) - Overview of all providers
+- [Model Selection](/agents/model-selection) - How to choose models
+- [Configuration](/configuration) - Full config reference

extensions/bluebubbles/src/monitor.test.ts

@@ -1189,8 +1189,9 @@ describe("BlueBubbles webhook monitor", () => {
       expect(callArgs.ctx.ReplyToId).toBe("msg-0");
       expect(callArgs.ctx.ReplyToBody).toBe("original message");
       expect(callArgs.ctx.ReplyToSender).toBe("+15550000000");
-      // Body uses inline [[reply_to:N]] tag format
-      expect(callArgs.ctx.Body).toContain("[[reply_to:msg-0]]");
+      // Body uses just the ID (no sender) for token savings
+      expect(callArgs.ctx.Body).toContain("[Replying to id:msg-0]");
+      expect(callArgs.ctx.Body).toContain("original message");
     });
 
     it("hydrates missing reply sender/body from the recent-message cache", async () => {
@@ -1259,8 +1260,9 @@ describe("BlueBubbles webhook monitor", () => {
       expect(callArgs.ctx.ReplyToIdFull).toBe("cache-msg-0");
       expect(callArgs.ctx.ReplyToBody).toBe("original message (cached)");
       expect(callArgs.ctx.ReplyToSender).toBe("+15550000000");
-      // Body uses inline [[reply_to:N]] tag format with short ID
-      expect(callArgs.ctx.Body).toContain("[[reply_to:1]]");
+      // Body uses just the short ID (no sender) for token savings
+      expect(callArgs.ctx.Body).toContain("[Replying to id:1]");
+      expect(callArgs.ctx.Body).toContain("original message (cached)");
     });
 
     it("falls back to threadOriginatorGuid when reply metadata is absent", async () => {
@@ -1303,88 +1305,6 @@ describe("BlueBubbles webhook monitor", () => {
     });
   });
 
-  describe("tapback text parsing", () => {
-    it("does not rewrite tapback-like text without metadata", async () => {
-      const account = createMockAccount({ dmPolicy: "open" });
-      const config: ClawdbotConfig = {};
-      const core = createMockRuntime();
-      setBlueBubblesRuntime(core);
-
-      unregister = registerBlueBubblesWebhookTarget({
-        account,
-        config,
-        runtime: { log: vi.fn(), error: vi.fn() },
-        core,
-        path: "/bluebubbles-webhook",
-      });
-
-      const payload = {
-        type: "new-message",
-        data: {
-          text: "Loved this idea",
-          handle: { address: "+15551234567" },
-          isGroup: false,
-          isFromMe: false,
-          guid: "msg-1",
-          chatGuid: "iMessage;-;+15551234567",
-          date: Date.now(),
-        },
-      };
-
-      const req = createMockRequest("POST", "/bluebubbles-webhook", payload);
-      const res = createMockResponse();
-
-      await handleBlueBubblesWebhookRequest(req, res);
-      await flushAsync();
-
-      expect(mockDispatchReplyWithBufferedBlockDispatcher).toHaveBeenCalled();
-      const callArgs = mockDispatchReplyWithBufferedBlockDispatcher.mock.calls[0][0];
-      expect(callArgs.ctx.RawBody).toBe("Loved this idea");
-      expect(callArgs.ctx.Body).toContain("Loved this idea");
-      expect(callArgs.ctx.Body).not.toContain("reacted with");
-    });
-
-    it("parses tapback text with custom emoji when metadata is present", async () => {
-      const account = createMockAccount({ dmPolicy: "open" });
-      const config: ClawdbotConfig = {};
-      const core = createMockRuntime();
-      setBlueBubblesRuntime(core);
-
-      unregister = registerBlueBubblesWebhookTarget({
-        account,
-        config,
-        runtime: { log: vi.fn(), error: vi.fn() },
-        core,
-        path: "/bluebubbles-webhook",
-      });
-
-      const payload = {
-        type: "new-message",
-        data: {
-          text: 'Reacted 😅 to "nice one"',
-          handle: { address: "+15551234567" },
-          isGroup: false,
-          isFromMe: false,
-          guid: "msg-2",
-          chatGuid: "iMessage;-;+15551234567",
-          date: Date.now(),
-        },
-      };
-
-      const req = createMockRequest("POST", "/bluebubbles-webhook", payload);
-      const res = createMockResponse();
-
-      await handleBlueBubblesWebhookRequest(req, res);
-      await flushAsync();
-
-      expect(mockDispatchReplyWithBufferedBlockDispatcher).toHaveBeenCalled();
-      const callArgs = mockDispatchReplyWithBufferedBlockDispatcher.mock.calls[0][0];
-      expect(callArgs.ctx.RawBody).toBe("reacted with 😅");
-      expect(callArgs.ctx.Body).toContain("reacted with 😅");
-      expect(callArgs.ctx.Body).not.toContain("[[reply_to:");
-    });
-  });
-
   describe("ack reactions", () => {
     it("sends ack reaction when configured", async () => {
       const { sendBlueBubblesReaction } = await import("./reactions.js");
@@ -1839,7 +1759,7 @@ describe("BlueBubbles webhook monitor", () => {
       await flushAsync();
 
       expect(mockEnqueueSystemEvent).toHaveBeenCalledWith(
-        expect.stringContaining("reacted with ❤️ [[reply_to:"),
+        expect.stringContaining("reaction added"),
         expect.any(Object),
       );
     });
@@ -1879,7 +1799,7 @@ describe("BlueBubbles webhook monitor", () => {
       await flushAsync();
 
       expect(mockEnqueueSystemEvent).toHaveBeenCalledWith(
-        expect.stringContaining("removed ❤️ reaction [[reply_to:"),
+        expect.stringContaining("reaction removed"),
         expect.any(Object),
       );
     });
@@ -1985,7 +1905,7 @@ describe("BlueBubbles webhook monitor", () => {
           handle: { address: "+15551234567" },
           isGroup: false,
           isFromMe: false,
-          guid: "p:1/msg-uuid-12345",
+          guid: "msg-uuid-12345",
           chatGuid: "iMessage;-;+15551234567",
           date: Date.now(),
         },
@@ -2001,7 +1921,7 @@ describe("BlueBubbles webhook monitor", () => {
       const callArgs = mockDispatchReplyWithBufferedBlockDispatcher.mock.calls[0][0];
       // MessageSid should be short ID "1" instead of full UUID
       expect(callArgs.ctx.MessageSid).toBe("1");
-      expect(callArgs.ctx.MessageSidFull).toBe("p:1/msg-uuid-12345");
+      expect(callArgs.ctx.MessageSidFull).toBe("msg-uuid-12345");
     });
 
     it("resolves short ID back to UUID", async () => {
@@ -2025,7 +1945,7 @@ describe("BlueBubbles webhook monitor", () => {
           handle: { address: "+15551234567" },
           isGroup: false,
           isFromMe: false,
-          guid: "p:1/msg-uuid-12345",
+          guid: "msg-uuid-12345",
           chatGuid: "iMessage;-;+15551234567",
           date: Date.now(),
         },
@@ -2038,7 +1958,7 @@ describe("BlueBubbles webhook monitor", () => {
       await flushAsync();
 
       // The short ID "1" should resolve back to the full UUID
-      expect(resolveBlueBubblesMessageId("1")).toBe("p:1/msg-uuid-12345");
+      expect(resolveBlueBubblesMessageId("1")).toBe("msg-uuid-12345");
     });
 
     it("returns UUID unchanged when not in cache", () => {

extensions/bluebubbles/src/monitor.ts

@@ -55,7 +55,7 @@ type BlueBubblesReplyCacheEntry = {
 // Best-effort cache for resolving reply context when BlueBubbles webhooks omit sender/body.
 const blueBubblesReplyCacheByMessageId = new Map<string, BlueBubblesReplyCacheEntry>();
 
-// Bidirectional maps for short ID ↔ message GUID resolution (token savings optimization)
+// Bidirectional maps for short ID ↔ UUID resolution (token savings optimization)
 const blueBubblesShortIdToUuid = new Map<string, string>();
 const blueBubblesUuidToShortId = new Map<string, string>();
 let blueBubblesShortIdCounter = 0;
@@ -78,7 +78,7 @@ function rememberBlueBubblesReplyCache(
     return { ...entry, shortId: "" };
   }
 
-  // Check if we already have a short ID for this GUID
+  // Check if we already have a short ID for this UUID
   let shortId = blueBubblesUuidToShortId.get(messageId);
   if (!shortId) {
     shortId = generateShortId();
@@ -86,7 +86,7 @@ function rememberBlueBubblesReplyCache(
     blueBubblesUuidToShortId.set(messageId, shortId);
   }
 
-  const fullEntry: BlueBubblesReplyCacheEntry = { ...entry, messageId, shortId };
+  const fullEntry: BlueBubblesReplyCacheEntry = { ...entry, shortId };
 
   // Refresh insertion order.
   blueBubblesReplyCacheByMessageId.delete(messageId);
@@ -122,8 +122,8 @@ function rememberBlueBubblesReplyCache(
 }
 
 /**
- * Resolves a short message ID (e.g., "1", "2") to a full BlueBubbles GUID.
- * Returns the input unchanged if it's already a GUID or not found in the mapping.
+ * Resolves a short message ID (e.g., "1", "2") to a full BlueBubbles UUID.
+ * Returns the input unchanged if it's already a UUID or not found in the mapping.
  */
 export function resolveBlueBubblesMessageId(
   shortOrUuid: string,
@@ -159,7 +159,7 @@ export function _resetBlueBubblesShortIdState(): void {
 }
 
 /**
- * Gets the short ID for a message GUID, if one exists.
+ * Gets the short ID for a UUID, if one exists.
  */
 function getShortIdForUuid(uuid: string): string | undefined {
   return blueBubblesUuidToShortId.get(uuid.trim());
@@ -390,15 +390,29 @@ function buildMessagePlaceholder(message: NormalizedWebhookMessage): string {
   return "";
 }
 
-// Returns inline reply tag like "[[reply_to:4]]" for prepending to message body
-function formatReplyTag(message: {
+const REPLY_BODY_TRUNCATE_LENGTH = 60;
+
+function formatReplyContext(message: {
   replyToId?: string;
   replyToShortId?: string;
+  replyToBody?: string;
+  replyToSender?: string;
 }): string | null {
-  // Prefer short ID
-  const rawId = message.replyToShortId || message.replyToId;
-  if (!rawId) return null;
-  return `[[reply_to:${rawId}]]`;
+  if (!message.replyToId && !message.replyToBody && !message.replyToSender) return null;
+  // Prefer short ID for token savings
+  const displayId = message.replyToShortId || message.replyToId;
+  // Only include sender if we don't have an ID (fallback)
+  const label = displayId ? `id:${displayId}` : (message.replyToSender?.trim() || "unknown");
+  const rawBody = message.replyToBody?.trim();
+  if (!rawBody) {
+    return `[Replying to ${label}]\n[/Replying]`;
+  }
+  // Truncate long reply bodies for token savings
+  const body =
+    rawBody.length > REPLY_BODY_TRUNCATE_LENGTH
+      ? `${rawBody.slice(0, REPLY_BODY_TRUNCATE_LENGTH)}…`
+      : rawBody;
+  return `[Replying to ${label}]\n${body}\n[/Replying]`;
 }
 
 function readNumberLike(record: Record<string, unknown> | null, key: string): number | undefined {
@@ -615,10 +629,6 @@ type NormalizedWebhookMessage = {
   fromMe?: boolean;
   attachments?: BlueBubblesAttachment[];
   balloonBundleId?: string;
-  associatedMessageGuid?: string;
-  associatedMessageType?: number;
-  associatedMessageEmoji?: string;
-  isTapback?: boolean;
   participants?: BlueBubblesParticipant[];
   replyToId?: string;
   replyToBody?: string;
@@ -655,113 +665,6 @@ const REACTION_TYPE_MAP = new Map<number, { emoji: string; action: "added" | "re
   [3005, { emoji: "❓", action: "removed" }],
 ]);
 
-// Maps tapback text patterns (e.g., "Loved", "Liked") to emoji + action
-const TAPBACK_TEXT_MAP = new Map<string, { emoji: string; action: "added" | "removed" }>([
-  ["loved", { emoji: "❤️", action: "added" }],
-  ["liked", { emoji: "👍", action: "added" }],
-  ["disliked", { emoji: "👎", action: "added" }],
-  ["laughed at", { emoji: "😂", action: "added" }],
-  ["emphasized", { emoji: "‼️", action: "added" }],
-  ["questioned", { emoji: "❓", action: "added" }],
-  // Removal patterns (e.g., "Removed a heart from")
-  ["removed a heart from", { emoji: "❤️", action: "removed" }],
-  ["removed a like from", { emoji: "👍", action: "removed" }],
-  ["removed a dislike from", { emoji: "👎", action: "removed" }],
-  ["removed a laugh from", { emoji: "😂", action: "removed" }],
-  ["removed an emphasis from", { emoji: "‼️", action: "removed" }],
-  ["removed a question from", { emoji: "❓", action: "removed" }],
-]);
-
-const TAPBACK_EMOJI_REGEX =
-  /(?:\p{Regional_Indicator}{2})|(?:[0-9#*]\uFE0F?\u20E3)|(?:\p{Extended_Pictographic}(?:\uFE0F|\uFE0E)?(?:\p{Emoji_Modifier})?(?:\u200D\p{Extended_Pictographic}(?:\uFE0F|\uFE0E)?(?:\p{Emoji_Modifier})?)*)/u;
-
-function extractFirstEmoji(text: string): string | null {
-  const match = text.match(TAPBACK_EMOJI_REGEX);
-  return match ? match[0] : null;
-}
-
-function extractQuotedTapbackText(text: string): string | null {
-  const match = text.match(/[“"]([^”"]+)[”"]/s);
-  return match ? match[1] : null;
-}
-
-function isTapbackAssociatedType(type: number | undefined): boolean {
-  return typeof type === "number" && Number.isFinite(type) && type >= 2000 && type < 4000;
-}
-
-function resolveTapbackActionHint(type: number | undefined): "added" | "removed" | undefined {
-  if (typeof type !== "number" || !Number.isFinite(type)) return undefined;
-  if (type >= 3000 && type < 4000) return "removed";
-  if (type >= 2000 && type < 3000) return "added";
-  return undefined;
-}
-
-function resolveTapbackContext(message: NormalizedWebhookMessage): {
-  emojiHint?: string;
-  actionHint?: "added" | "removed";
-  replyToId?: string;
-} | null {
-  const associatedType = message.associatedMessageType;
-  const hasTapbackType = isTapbackAssociatedType(associatedType);
-  const hasTapbackMarker = Boolean(message.associatedMessageEmoji) || Boolean(message.isTapback);
-  if (!hasTapbackType && !hasTapbackMarker) return null;
-  const replyToId = message.associatedMessageGuid?.trim() || message.replyToId?.trim() || undefined;
-  const actionHint = resolveTapbackActionHint(associatedType);
-  const emojiHint =
-    message.associatedMessageEmoji?.trim() || REACTION_TYPE_MAP.get(associatedType ?? -1)?.emoji;
-  return { emojiHint, actionHint, replyToId };
-}
-
-// Detects tapback text patterns like 'Loved "message"' and converts to structured format
-function parseTapbackText(params: {
-  text: string;
-  emojiHint?: string;
-  actionHint?: "added" | "removed";
-  requireQuoted?: boolean;
-}): {
-  emoji: string;
-  action: "added" | "removed";
-  quotedText: string;
-} | null {
-  const trimmed = params.text.trim();
-  const lower = trimmed.toLowerCase();
-  if (!trimmed) return null;
-
-  for (const [pattern, { emoji, action }] of TAPBACK_TEXT_MAP) {
-    if (lower.startsWith(pattern)) {
-      // Extract quoted text if present (e.g., 'Loved "hello"' -> "hello")
-      const afterPattern = trimmed.slice(pattern.length).trim();
-      if (params.requireQuoted) {
-        const strictMatch = afterPattern.match(/^[“"](.+)[”"]$/s);
-        if (!strictMatch) return null;
-        return { emoji, action, quotedText: strictMatch[1] };
-      }
-      const quotedText =
-        extractQuotedTapbackText(afterPattern) ?? extractQuotedTapbackText(trimmed) ?? afterPattern;
-      return { emoji, action, quotedText };
-    }
-  }
-
-  if (lower.startsWith("reacted")) {
-    const emoji = extractFirstEmoji(trimmed) ?? params.emojiHint;
-    if (!emoji) return null;
-    const quotedText = extractQuotedTapbackText(trimmed);
-    if (params.requireQuoted && !quotedText) return null;
-    const fallback = trimmed.slice("reacted".length).trim();
-    return { emoji, action: params.actionHint ?? "added", quotedText: quotedText ?? fallback };
-  }
-
-  if (lower.startsWith("removed")) {
-    const emoji = extractFirstEmoji(trimmed) ?? params.emojiHint;
-    if (!emoji) return null;
-    const quotedText = extractQuotedTapbackText(trimmed);
-    if (params.requireQuoted && !quotedText) return null;
-    const fallback = trimmed.slice("removed".length).trim();
-    return { emoji, action: params.actionHint ?? "removed", quotedText: quotedText ?? fallback };
-  }
-  return null;
-}
-
 function maskSecret(value: string): string {
   if (value.length <= 6) return "***";
   return `${value.slice(0, 2)}***${value.slice(-2)}`;
@@ -902,25 +805,6 @@ function normalizeWebhookMessage(payload: Record<string, unknown>): NormalizedWe
     readString(message, "messageId") ??
     undefined;
   const balloonBundleId = readString(message, "balloonBundleId");
-  const associatedMessageGuid =
-    readString(message, "associatedMessageGuid") ??
-    readString(message, "associated_message_guid") ??
-    readString(message, "associatedMessageId") ??
-    undefined;
-  const associatedMessageType =
-    readNumberLike(message, "associatedMessageType") ??
-    readNumberLike(message, "associated_message_type");
-  const associatedMessageEmoji =
-    readString(message, "associatedMessageEmoji") ??
-    readString(message, "associated_message_emoji") ??
-    readString(message, "reactionEmoji") ??
-    readString(message, "reaction_emoji") ??
-    undefined;
-  const isTapback =
-    readBoolean(message, "isTapback") ??
-    readBoolean(message, "is_tapback") ??
-    readBoolean(message, "tapback") ??
-    undefined;
 
   const timestampRaw =
     readNumber(message, "date") ??
@@ -951,10 +835,6 @@ function normalizeWebhookMessage(payload: Record<string, unknown>): NormalizedWe
     fromMe,
     attachments: extractAttachments(message),
     balloonBundleId,
-    associatedMessageGuid,
-    associatedMessageType,
-    associatedMessageEmoji,
-    isTapback,
     participants: normalizedParticipants,
     replyToId: replyMetadata.replyToId,
     replyToBody: replyMetadata.replyToBody,
@@ -976,13 +856,8 @@ function normalizeWebhookReaction(payload: Record<string, unknown>): NormalizedW
   if (!associatedGuid || associatedType === undefined) return null;
 
   const mapping = REACTION_TYPE_MAP.get(associatedType);
-  const associatedEmoji =
-    readString(message, "associatedMessageEmoji") ??
-    readString(message, "associated_message_emoji") ??
-    readString(message, "reactionEmoji") ??
-    readString(message, "reaction_emoji");
-  const emoji = (associatedEmoji?.trim() || mapping?.emoji) ?? `reaction:${associatedType}`;
-  const action = mapping?.action ?? resolveTapbackActionHint(associatedType) ?? "added";
+  const emoji = mapping?.emoji ?? `reaction:${associatedType}`;
+  const action = mapping?.action ?? "added";
 
   const handleValue = message.handle ?? message.sender;
   const handle =
@@ -1247,21 +1122,7 @@ async function processMessage(
   const text = message.text.trim();
   const attachments = message.attachments ?? [];
   const placeholder = buildMessagePlaceholder(message);
-  // Check if text is a tapback pattern (e.g., 'Loved "hello"') and transform to emoji format
-  // For tapbacks, we'll append [[reply_to:N]] at the end; for regular messages, prepend it
-  const tapbackContext = resolveTapbackContext(message);
-  const tapbackParsed = parseTapbackText({
-    text,
-    emojiHint: tapbackContext?.emojiHint,
-    actionHint: tapbackContext?.actionHint,
-    requireQuoted: !tapbackContext,
-  });
-  const isTapbackMessage = Boolean(tapbackParsed);
-  const rawBody = tapbackParsed
-    ? tapbackParsed.action === "removed"
-      ? `removed ${tapbackParsed.emoji} reaction`
-      : `reacted with ${tapbackParsed.emoji}`
-    : text || placeholder;
+  const rawBody = text || placeholder;
 
   const cacheMessageId = message.messageId?.trim();
   let messageShortId: string | undefined;
@@ -1588,11 +1449,7 @@ async function processMessage(
   let replyToSender = message.replyToSender;
   let replyToShortId: string | undefined;
 
-  if (isTapbackMessage && tapbackContext?.replyToId) {
-    replyToId = tapbackContext.replyToId;
-  }
-
-  if (replyToId) {
+  if (replyToId && (!replyToBody || !replyToSender)) {
     const cached = resolveReplyContextFromCache({
       accountId: account.accountId,
       replyToId,
@@ -1620,15 +1477,8 @@ async function processMessage(
     replyToShortId = getShortIdForUuid(replyToId);
   }
 
-  // Use inline [[reply_to:N]] tag format
-  // For tapbacks/reactions: append at end (e.g., "reacted with ❤️ [[reply_to:4]]")
-  // For regular replies: prepend at start (e.g., "[[reply_to:4]] Awesome")
-  const replyTag = formatReplyTag({ replyToId, replyToShortId });
-  const baseBody = replyTag
-    ? isTapbackMessage
-      ? `${rawBody} ${replyTag}`
-      : `${replyTag} ${rawBody}`
-    : rawBody;
+  const replyContext = formatReplyContext({ replyToId, replyToShortId, replyToBody, replyToSender });
+  const baseBody = replyContext ? `${rawBody}\n\n${replyContext}` : rawBody;
   const fromLabel = isGroup ? undefined : message.senderName || `user:${message.senderId}`;
   const groupSubject = isGroup ? message.chatName?.trim() || undefined : undefined;
   const groupMembers = isGroup
@@ -2021,11 +1871,7 @@ async function processReaction(
   const chatLabel = reaction.isGroup ? ` in group:${peerId}` : "";
   // Use short ID for token savings
   const messageDisplayId = getShortIdForUuid(reaction.messageId) || reaction.messageId;
-  // Format: "Tyler reacted with ❤️ [[reply_to:5]]" or "Tyler removed ❤️ reaction [[reply_to:5]]"
-  const text =
-    reaction.action === "removed"
-      ? `${senderLabel} removed ${reaction.emoji} reaction [[reply_to:${messageDisplayId}]]${chatLabel}`
-      : `${senderLabel} reacted with ${reaction.emoji} [[reply_to:${messageDisplayId}]]${chatLabel}`;
+  const text = `BlueBubbles reaction ${reaction.action}: ${reaction.emoji} by ${senderLabel}${chatLabel} on msg ${messageDisplayId}`;
   core.system.enqueueSystemEvent(text, {
     sessionKey: route.sessionKey,
     contextKey: `bluebubbles:reaction:${reaction.action}:${peerId}:${reaction.messageId}:${reaction.senderId}:${reaction.emoji}`,

src/agents/model-auth.ts

@@ -284,6 +284,7 @@ export function resolveEnvApiKey(provider: string): EnvApiKeyResult | null {
     synthetic: "SYNTHETIC_API_KEY",
     mistral: "MISTRAL_API_KEY",
     opencode: "OPENCODE_API_KEY",
+    ollama: "OLLAMA_API_KEY",
   };
   const envVar = envMap[normalized];
   if (!envVar) return null;

src/agents/models-config.providers.ollama.test.ts

@@ -0,0 +1,106 @@
+import { afterEach, describe, expect, it, vi } from "vitest";
+import { resolveImplicitProviders } from "./models-config.providers.js";
+import { mkdtempSync } from "node:fs";
+import { join } from "node:path";
+import { tmpdir } from "node:os";
+
+describe("Ollama provider", () => {
+  const previousEnv = { ...process.env };
+
+  afterEach(() => {
+    for (const key of Object.keys(process.env)) {
+      if (!(key in previousEnv)) delete process.env[key];
+    }
+    for (const [key, value] of Object.entries(previousEnv)) {
+      process.env[key] = value;
+    }
+    vi.restoreAllMocks();
+    vi.unstubAllGlobals();
+  });
+
+  it("should not include ollama when no API key is configured", async () => {
+    const agentDir = mkdtempSync(join(tmpdir(), "clawd-test-"));
+    const providers = await resolveImplicitProviders({ agentDir });
+
+    // Ollama requires explicit configuration via OLLAMA_API_KEY env var or profile
+    expect(providers?.ollama).toBeUndefined();
+  });
+
+  it("discovers tool-capable models when OLLAMA_API_KEY is set", async () => {
+    process.env.OLLAMA_API_KEY = "ollama-local";
+    delete process.env.VITEST;
+    process.env.NODE_ENV = "development";
+
+    const fetchMock = vi
+      .fn()
+      .mockResolvedValueOnce({
+        ok: true,
+        status: 200,
+        json: async () => ({
+          models: [{ name: "llama3.3" }, { name: "no-tools-model" }],
+        }),
+      })
+      .mockResolvedValueOnce({
+        ok: true,
+        status: 200,
+        json: async () => ({
+          capabilities: ["tools", "thinking"],
+          model_info: {
+            "general.architecture": "llama",
+            "llama.context_length": "4096",
+          },
+        }),
+      })
+      .mockResolvedValueOnce({
+        ok: true,
+        status: 200,
+        json: async () => ({
+          capabilities: ["thinking"],
+          model_info: {
+            "general.architecture": "llama",
+            "llama.context_length": "2048",
+          },
+        }),
+      });
+    vi.stubGlobal("fetch", fetchMock as unknown as typeof fetch);
+
+    const agentDir = mkdtempSync(join(tmpdir(), "clawd-test-"));
+    const providers = await resolveImplicitProviders({ agentDir });
+
+    expect(fetchMock).toHaveBeenCalledTimes(3);
+    expect(fetchMock.mock.calls[0]?.[0]).toBe("http://127.0.0.1:11434/api/tags");
+    expect(fetchMock.mock.calls[1]?.[0]).toBe("http://127.0.0.1:11434/api/show");
+
+    const provider = providers?.ollama;
+    expect(provider?.baseUrl).toBe("http://127.0.0.1:11434/v1");
+    expect(provider?.models).toHaveLength(1);
+    expect(provider?.models?.[0]?.id).toBe("llama3.3");
+    expect(provider?.models?.[0]?.reasoning).toBe(true);
+    expect(provider?.models?.[0]?.contextWindow).toBe(4096);
+    expect(provider?.models?.[0]?.maxTokens).toBe(4096 * 10);
+  });
+
+  it("skips discovery when ollama is explicitly configured", async () => {
+    process.env.OLLAMA_API_KEY = "ollama-local";
+    delete process.env.VITEST;
+    process.env.NODE_ENV = "development";
+
+    const fetchMock = vi.fn();
+    vi.stubGlobal("fetch", fetchMock as unknown as typeof fetch);
+
+    const agentDir = mkdtempSync(join(tmpdir(), "clawd-test-"));
+    const providers = await resolveImplicitProviders({
+      agentDir,
+      explicitProviders: {
+        ollama: {
+          baseUrl: "http://example.com/v1",
+          api: "openai-completions",
+          models: [],
+        },
+      },
+    });
+
+    expect(fetchMock).not.toHaveBeenCalled();
+    expect(providers?.ollama).toBeUndefined();
+  });
+});

src/agents/models-config.providers.ts

@@ -1,9 +1,11 @@
 import type { ClawdbotConfig } from "../config/config.js";
+import type { ModelDefinitionConfig } from "../config/types.models.js";
 import {
   DEFAULT_COPILOT_API_BASE_URL,
   resolveCopilotApiToken,
 } from "../providers/github-copilot-token.js";
 import { ensureAuthProfileStore, listProfilesForProvider } from "./auth-profiles.js";
+import { normalizeProviderId } from "./model-selection.js";
 import { resolveAwsSdkEnvVarName, resolveEnvApiKey } from "./model-auth.js";
 import { discoverBedrockModels } from "./bedrock-discovery.js";
 import {
@@ -62,6 +64,127 @@ const QWEN_PORTAL_DEFAULT_COST = {
   cacheWrite: 0,
 };
 
+const OLLAMA_HOST_BASE_URL = "http://127.0.0.1:11434";
+const OLLAMA_DEFAULT_CONTEXT_WINDOW = 8192;
+const OLLAMA_MAX_TOKENS_MULTIPLIER = 10;
+const OLLAMA_DISCOVERY_TIMEOUT_MS = 5000;
+const OLLAMA_DEFAULT_COST = {
+  input: 0,
+  output: 0,
+  cacheRead: 0,
+  cacheWrite: 0,
+};
+
+interface OllamaModel {
+  name: string;
+  modified_at: string;
+  size: number;
+  digest: string;
+  details?: {
+    family?: string;
+    parameter_size?: string;
+  };
+}
+
+interface OllamaTagsResponse {
+  models: OllamaModel[];
+}
+
+interface OllamaShowResponse {
+  capabilities?: string[];
+  model_info?: Record<string, string | number>;
+}
+
+function parseOllamaNumber(value: unknown): number | undefined {
+  if (typeof value === "number" && Number.isFinite(value)) return value;
+  if (typeof value === "string" && value.trim()) {
+    const parsed = Number(value);
+    if (Number.isFinite(parsed)) return parsed;
+  }
+  return undefined;
+}
+
+function resolveOllamaContextWindow(
+  modelInfo: Record<string, string | number> | undefined,
+): number {
+  if (!modelInfo) return OLLAMA_DEFAULT_CONTEXT_WINDOW;
+  const architecture = String(modelInfo["general.architecture"] ?? "").trim();
+  const contextKey = architecture ? `${architecture}.context_length` : "";
+  const contextWindow =
+    (contextKey ? parseOllamaNumber(modelInfo[contextKey]) : undefined) ??
+    parseOllamaNumber(modelInfo["context_length"]);
+  return contextWindow ?? OLLAMA_DEFAULT_CONTEXT_WINDOW;
+}
+
+function normalizeOllamaHostBaseUrl(baseUrl: string): string {
+  const trimmed = baseUrl.trim().replace(/\/+$/, "");
+  return trimmed.endsWith("/v1") ? trimmed.slice(0, -3) : trimmed;
+}
+
+async function discoverOllamaModels(baseUrl: string): Promise<ModelDefinitionConfig[]> {
+  // Skip Ollama discovery in test environments
+  if (process.env.VITEST || process.env.NODE_ENV === "test") {
+    return [];
+  }
+  try {
+    const response = await fetch(`${baseUrl}/api/tags`, {
+      signal: AbortSignal.timeout(OLLAMA_DISCOVERY_TIMEOUT_MS),
+    });
+    if (!response.ok) {
+      console.warn(`Failed to discover Ollama models: ${response.status}`);
+      return [];
+    }
+    const data = (await response.json()) as OllamaTagsResponse;
+    if (!data.models || data.models.length === 0) {
+      console.warn("No Ollama models found on local instance");
+      return [];
+    }
+    const models = await Promise.all(
+      data.models.map(async (model) => {
+        try {
+          const detailsResponse = await fetch(`${baseUrl}/api/show`, {
+            method: "POST",
+            headers: {
+              "Content-Type": "application/json",
+            },
+            body: JSON.stringify({ name: model.name }),
+            signal: AbortSignal.timeout(OLLAMA_DISCOVERY_TIMEOUT_MS),
+          });
+          if (!detailsResponse.ok) {
+            console.warn(
+              `Failed to fetch Ollama model details for ${model.name}: ${detailsResponse.status}`,
+            );
+            return null;
+          }
+          const details = (await detailsResponse.json()) as OllamaShowResponse;
+          const capabilities = Array.isArray(details.capabilities) ? details.capabilities : [];
+          if (!capabilities.includes("tools")) {
+            console.debug(`Skipping Ollama model ${model.name}: does not support tools`);
+            return null;
+          }
+          const contextWindow = resolveOllamaContextWindow(details.model_info);
+          return {
+            id: model.name,
+            name: model.name,
+            reasoning: capabilities.includes("thinking"),
+            input: ["text"],
+            cost: OLLAMA_DEFAULT_COST,
+            contextWindow,
+            maxTokens: contextWindow * OLLAMA_MAX_TOKENS_MULTIPLIER,
+          };
+        } catch (error) {
+          console.warn(`Failed to fetch Ollama model details for ${model.name}: ${String(error)}`);
+          return null;
+        }
+      }),
+    );
+    return models.filter((model): model is ModelDefinitionConfig => Boolean(model));
+  } catch (error) {
+    console.warn(`Failed to discover Ollama models: ${String(error)}`);
+    return [];
+  }
+}
+
 function normalizeApiKeyConfig(value: string): string {
   const trimmed = value.trim();
   const match = /^\$\{([A-Z0-9_]+)\}$/.exec(trimmed);
@@ -275,11 +398,28 @@ function buildSyntheticProvider(): ProviderConfig {
   };
 }
 
-export function resolveImplicitProviders(params: { agentDir: string }): ModelsConfig["providers"] {
+async function buildOllamaProvider(baseUrl: string): Promise<ProviderConfig> {
+  const hostBaseUrl = normalizeOllamaHostBaseUrl(baseUrl);
+  const models = await discoverOllamaModels(hostBaseUrl);
+  return {
+    baseUrl: `${hostBaseUrl}/v1`,
+    api: "openai-completions",
+    models,
+  };
+}
+
+export async function resolveImplicitProviders(params: {
+  agentDir: string;
+  explicitProviders?: ModelsConfig["providers"];
+}): Promise<ModelsConfig["providers"]> {
   const providers: Record<string, ProviderConfig> = {};
   const authStore = ensureAuthProfileStore(params.agentDir, {
     allowKeychainPrompt: false,
   });
+  const explicitProviders = params.explicitProviders ?? {};
+  const hasExplicitOllama = Object.keys(explicitProviders).some(
+    (key) => normalizeProviderId(key) === "ollama",
+  );
 
   const minimaxKey =
     resolveEnvApiKeyVarName("minimax") ??
@@ -317,6 +457,14 @@ export function resolveImplicitProviders(params: { agentDir: string }): ModelsCo
     };
   }
 
+  // Ollama provider - only add if explicitly configured
+  const ollamaKey =
+    resolveEnvApiKeyVarName("ollama") ??
+    resolveApiKeyFromProfiles({ provider: "ollama", store: authStore });
+  if (ollamaKey && !hasExplicitOllama) {
+    providers.ollama = { ...(await buildOllamaProvider(OLLAMA_HOST_BASE_URL)), apiKey: ollamaKey };
+  }
+
   return providers;
 }
 

src/agents/models-config.ts

@@ -80,7 +80,7 @@ export async function ensureClawdbotModelsJson(
   const agentDir = agentDirOverride?.trim() ? agentDirOverride.trim() : resolveClawdbotAgentDir();
 
   const explicitProviders = (cfg.models?.providers ?? {}) as Record<string, ProviderConfig>;
-  const implicitProviders = resolveImplicitProviders({ agentDir });
+  const implicitProviders = await resolveImplicitProviders({ agentDir, explicitProviders });
   const providers: Record<string, ProviderConfig> = mergeProviders({
     implicit: implicitProviders,
     explicit: explicitProviders,

src/agents/pi-embedded-runner.applygoogleturnorderingfix.test.ts

@@ -72,7 +72,7 @@ const _makeOpenAiConfig = (modelIds: string[]) =>
   }) satisfies ClawdbotConfig;
 
 const _ensureModels = (cfg: ClawdbotConfig, agentDir: string) =>
-  ensureClawdbotModelsJson(cfg, agentDir);
+  ensureClawdbotModelsJson(cfg, agentDir) as unknown;
 
 const _textFromContent = (content: unknown) => {
   if (typeof content === "string") return content;

src/agents/pi-embedded-runner.buildembeddedsandboxinfo.test.ts

@@ -71,7 +71,7 @@ const _makeOpenAiConfig = (modelIds: string[]) =>
   }) satisfies ClawdbotConfig;
 
 const _ensureModels = (cfg: ClawdbotConfig, agentDir: string) =>
-  ensureClawdbotModelsJson(cfg, agentDir);
+  ensureClawdbotModelsJson(cfg, agentDir) as unknown;
 
 const _textFromContent = (content: unknown) => {
   if (typeof content === "string") return content;

src/agents/pi-embedded-runner.createsystempromptoverride.test.ts

@@ -70,7 +70,7 @@ const _makeOpenAiConfig = (modelIds: string[]) =>
   }) satisfies ClawdbotConfig;
 
 const _ensureModels = (cfg: ClawdbotConfig, agentDir: string) =>
-  ensureClawdbotModelsJson(cfg, agentDir);
+  ensureClawdbotModelsJson(cfg, agentDir) as unknown;
 
 const _textFromContent = (content: unknown) => {
   if (typeof content === "string") return content;

src/agents/pi-embedded-runner.get-dm-history-limit-from-session-key.returns-undefined-sessionkey-is-undefined.test.ts

@@ -70,7 +70,7 @@ const _makeOpenAiConfig = (modelIds: string[]) =>
   }) satisfies ClawdbotConfig;
 
 const _ensureModels = (cfg: ClawdbotConfig, agentDir: string) =>
-  ensureClawdbotModelsJson(cfg, agentDir);
+  ensureClawdbotModelsJson(cfg, agentDir) as unknown;
 
 const _textFromContent = (content: unknown) => {
   if (typeof content === "string") return content;

src/agents/pi-embedded-runner.limithistoryturns.test.ts

@@ -71,7 +71,7 @@ const _makeOpenAiConfig = (modelIds: string[]) =>
   }) satisfies ClawdbotConfig;
 
 const _ensureModels = (cfg: ClawdbotConfig, agentDir: string) =>
-  ensureClawdbotModelsJson(cfg, agentDir);
+  ensureClawdbotModelsJson(cfg, agentDir) as unknown;
 
 const _textFromContent = (content: unknown) => {
   if (typeof content === "string") return content;

src/agents/pi-embedded-runner.resolvesessionagentids.test.ts

@@ -70,7 +70,7 @@ const _makeOpenAiConfig = (modelIds: string[]) =>
   }) satisfies ClawdbotConfig;
 
 const _ensureModels = (cfg: ClawdbotConfig, agentDir: string) =>
-  ensureClawdbotModelsJson(cfg, agentDir);
+  ensureClawdbotModelsJson(cfg, agentDir) as unknown;
 
 const _textFromContent = (content: unknown) => {
   if (typeof content === "string") return content;

src/agents/pi-embedded-runner.splitsdktools.test.ts

@@ -71,7 +71,7 @@ const _makeOpenAiConfig = (modelIds: string[]) =>
   }) satisfies ClawdbotConfig;
 
 const _ensureModels = (cfg: ClawdbotConfig, agentDir: string) =>
-  ensureClawdbotModelsJson(cfg, agentDir);
+  ensureClawdbotModelsJson(cfg, agentDir) as unknown;
 
 const _textFromContent = (content: unknown) => {
   if (typeof content === "string") return content;

src/agents/pi-embedded-runner.test.ts

@@ -130,7 +130,7 @@ const makeOpenAiConfig = (modelIds: string[]) =>
     },
   }) satisfies ClawdbotConfig;
 
-const ensureModels = (cfg: ClawdbotConfig) => ensureClawdbotModelsJson(cfg, agentDir);
+const ensureModels = (cfg: ClawdbotConfig) => ensureClawdbotModelsJson(cfg, agentDir) as unknown;
 
 const nextSessionFile = () => {
   sessionCounter += 1;

test/setup.ts

@@ -1,5 +1,8 @@
 import { afterAll, afterEach, beforeEach, vi } from "vitest";
 
+// Ensure Vitest environment is properly set
+process.env.VITEST = "true";
+
 import type {
   ChannelId,
   ChannelOutboundAdapter,