feat: implement file upload handler and related functionality

- Added file upload handler to process both multipart and raw file uploads.
- Implemented parsing logic for upload requests, including handling file metadata.
- Introduced SaveFileDecodedInput structure for handling decoded file uploads.
- Created unit tests for file upload parsing and validation.

feat: add metadata retry configuration and functionality

- Introduced MetadataRetryConfig to the application configuration.
- Implemented MetadataRetryer to handle retrying metadata extraction for thoughts.
- Added new tool for retrying failed metadata extractions.
- Updated thought metadata structure to include status and timestamps for metadata processing.

fix: enhance metadata normalization and error handling

- Updated metadata normalization functions to track status and errors.
- Improved handling of metadata extraction failures during thought updates and captures.
- Ensured that metadata status is correctly set during various operations.

refactor: streamline file saving logic in FilesTool

- Refactored Save method in FilesTool to utilize new SaveDecoded method.
- Simplified project and thought ID resolution logic during file saving.

README.md

@@ -46,6 +46,7 @@ A Go MCP server for capturing and retrieving thoughts, memory, and project conte
 | `list_files` | Browse stored files by thought, project, or kind |
 | `backfill_embeddings` | Generate missing embeddings for stored thoughts |
 | `reparse_thought_metadata` | Re-extract and normalize metadata for stored thoughts |
+| `retry_failed_metadata` | Retry metadata extraction for thoughts still pending or failed |
 
 ## Configuration
 
@@ -115,6 +116,24 @@ Run `reparse_thought_metadata` to fix stale or inconsistent metadata by re-extra
 - If extraction fails for a thought, existing metadata is normalized and written only if it changes
 - Metadata reparse runs in parallel (4 workers); one failure does not abort the run
 
+## Failed Metadata Retry
+
+`capture_thought` now stores the thought even when metadata extraction times out or fails. Those thoughts are marked with `metadata_status: "pending"` and retried in the background. Use `retry_failed_metadata` to sweep any thoughts still marked `pending` or `failed`.
+
+```json
+{
+  "project": "optional-project-name",
+  "limit": 100,
+  "include_archived": false,
+  "older_than_days": 1,
+  "dry_run": false
+}
+```
+
+- `dry_run: true` scans only and does not call metadata extraction or write updates
+- successful retries mark the thought metadata as `complete` and clear the last error
+- failed retries update the retry markers so the daily sweep can pick them up again later
+
 ## File Storage
 
 Use `save_file` to persist binary files as base64. Files can optionally be linked to a memory by passing `thought_id`, which also adds an attachment reference to that thought's metadata.
@@ -148,6 +167,27 @@ List files for a thought or project with:
 }
 ```
 
+AMCS also supports direct authenticated HTTP uploads to `/files` for clients that want to stream file bodies instead of base64-encoding them into an MCP tool call.
+
+Multipart upload:
+
+```bash
+curl -X POST http://localhost:8080/files \
+  -H "x-brain-key: <key>" \
+  -F "file=@./diagram.png" \
+  -F "project=amcs" \
+  -F "kind=image"
+```
+
+Raw body upload:
+
+```bash
+curl -X POST "http://localhost:8080/files?project=amcs&name=meeting-notes.pdf" \
+  -H "x-brain-key: <key>" \
+  -H "Content-Type: application/pdf" \
+  --data-binary @./meeting-notes.pdf
+```
+
 **Automatic backfill** (optional, config-gated):
 
 ```yaml
@@ -160,6 +200,15 @@ backfill:
   include_archived: false
 ```
 
+```yaml
+metadata_retry:
+  enabled: true
+  run_on_startup: true   # retry failed metadata once on server start
+  interval: "24h"        # retry pending/failed metadata daily
+  max_per_run: 100
+  include_archived: false
+```
+
 **Search fallback**: when no embeddings exist for the active model in scope, `search_thoughts`, `recall_context`, `get_project_context`, `summarize_thoughts`, and `related_thoughts` automatically fall back to Postgres full-text search so results are never silently empty.
 
 ## Client Setup