Add hashtag support to Bluesky post facets

Added hashtag parsing to both reply_to_post() in bsky_utils.py and
create_new_bluesky_post() in tools/post.py. Hashtags are now properly
parsed and converted to app.bsky.richtext.facet#tag facets with correct
byte positions.

- Parse hashtags using regex pattern that matches #word patterns
- Create facets with proper byte slice positioning
- Include hashtag tracking in debug logging
- Tested regex with various hashtag patterns

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <[e-mail]>

bsky_utils.py

···
     
     # Parse URLs - fixed to handle URLs at start of text
     url_regex = rb"(?:^|[$|\W])(https?:\/\/(www\.)?[-a-zA-Z0-9@:%._\+~#=]{1,256}\.[a-zA-Z0-9()]{1,6}\b([-a-zA-Z0-9()@:%_\+.~#?&//=]*[-a-zA-Z0-9@%_\+~#//=])?)"
-    
+
     for m in re.finditer(url_regex, text_bytes):
         url = m.group(1).decode("UTF-8")
         urls_found.append(url)
···
             )
         )
         logger.debug(f"[{correlation_id}] Found URL: {url}")
+
+    # Parse hashtags
+    hashtag_regex = rb"(?:^|[$|\s])#([a-zA-Z0-9_]+)"
+    hashtags_found = []
+
+    for m in re.finditer(hashtag_regex, text_bytes):
+        tag = m.group(1).decode("UTF-8")  # Get tag without # prefix
+        hashtags_found.append(tag)
+        # Get byte positions for the entire hashtag including #
+        tag_start = m.start(0)
+        # Adjust start if there's a space/prefix
+        if text_bytes[tag_start:tag_start+1] in (b' ', b'$'):
+            tag_start += 1
+        tag_end = m.end(0)
+        facets.append(
+            models.AppBskyRichtextFacet.Main(
+                index=models.AppBskyRichtextFacet.ByteSlice(
+                    byteStart=tag_start,
+                    byteEnd=tag_end
+                ),
+                features=[models.AppBskyRichtextFacet.Tag(tag=tag)]
+            )
+        )
+        logger.debug(f"[{correlation_id}] Found hashtag: #{tag}")
     
     logger.debug(f"[{correlation_id}] Facet parsing complete", extra={
         'correlation_id': correlation_id,
···
         'mentions': mentions_found,
         'urls_count': len(urls_found),
         'urls': urls_found,
+        'hashtags_count': len(hashtags_found),
+        'hashtags': hashtags_found,
         'total_facets': len(facets)
     })
 

tools/post.py

···
             
             # Parse URLs - fixed to handle URLs at start of text
             url_regex = rb"(?:^|[$|\W])(https?:\/\/(www\.)?[-a-zA-Z0-9@:%._\+~#=]{1,256}\.[a-zA-Z0-9()]{1,6}\b([-a-zA-Z0-9()@:%_\+.~#?&//=]*[-a-zA-Z0-9@%_\+~#//=])?)"
-            
+
             for m in re.finditer(url_regex, text_bytes):
                 url = m.group(1).decode("UTF-8")
                 # Adjust byte positions to account for the optional prefix
···
                     },
                     "features": [{"$type": "app.bsky.richtext.facet#link", "uri": url}],
                 })
-            
+
+            # Parse hashtags
+            hashtag_regex = rb"(?:^|[$|\s])#([a-zA-Z0-9_]+)"
+
+            for m in re.finditer(hashtag_regex, text_bytes):
+                tag = m.group(1).decode("UTF-8")  # Get tag without # prefix
+                # Get byte positions for the entire hashtag including #
+                tag_start = m.start(0)
+                # Adjust start if there's a space/prefix
+                if text_bytes[tag_start:tag_start+1] in (b' ', b'$'):
+                    tag_start += 1
+                tag_end = m.end(0)
+                facets.append({
+                    "index": {
+                        "byteStart": tag_start,
+                        "byteEnd": tag_end,
+                    },
+                    "features": [{"$type": "app.bsky.richtext.facet#tag", "tag": tag}],
+                })
+
             if facets:
                 post_record["facets"] = facets