telegram bot: refactor + multimedia + reply support

Refactor Telegram.hs into submodules to reduce file size:
- Types.hs: data types, JSON parsing
- Media.hs: file downloads, image/voice analysis
- Reminders.hs: reminder loop, user chat persistence

Multimedia improvements:
- Vision uses third-person to avoid LLM confusion
- Better message framing for embedded descriptions
- Size validation (10MB images, 20MB voice)
- MIME type validation for voice messages

New features:
- Reply support: bot sees context when users reply
- Web search: default 5->10, max 10->20 results
- Guardrails: duplicate tool limit 3->10 for research
- Timezone: todos parse/display in Eastern time (ET)

1 files changed, 3 insertions, 3 deletions

diff --git a/Omni/Agent/Tools/WebSearch.hs b/Omni/Agent/Tools/WebSearch.hs
index f7250b8..58c945c 100644
--- a/Omni/Agent/Tools/WebSearch.hs
+++ b/Omni/Agent/Tools/WebSearch.hs
@@ -172,7 +172,7 @@ webSearchTool apiKey =
                   "limit"
                     .= Aeson.object
                       [ "type" .= ("integer" :: Text),
-                        "description" .= ("Max results to return (default: 5, max: 10)" :: Text)
+                        "description" .= ("Max results to return (default: 10, max: 20)" :: Text)
                       ]
                 ],
             "required" .= (["query"] :: [Text])
@@ -185,7 +185,7 @@ executeWebSearch apiKey v =
   case Aeson.fromJSON v of
     Aeson.Error e -> pure (Aeson.object ["error" .= Text.pack e])
     Aeson.Success (args :: WebSearchArgs) -> do
-      let lim = min 10 (max 1 (wsLimit args))
+      let lim = min 20 (max 1 (wsLimit args))
       result <- kagiSearch apiKey (wsQuery args) lim
       case result of
         Left err ->
@@ -209,4 +209,4 @@ instance Aeson.FromJSON WebSearchArgs where
   parseJSON =
     Aeson.withObject "WebSearchArgs" <| \v ->
       (WebSearchArgs </ (v Aeson..: "query"))
-        <*> (v Aeson..:? "limit" Aeson..!= 5)
+        <*> (v Aeson..:? "limit" Aeson..!= 10)