integrate PNG compression, resolve #2

.gitignore

@@ -0,0 +1,3 @@
+__pycache__/
+*.pyc
+*.pyo

.specstory/history/2025-10-27_16-57Z-reapply-work-configuration-to-repository.md

@@ -1,4 +1,4 @@
-<!-- Generated by SpecStory -->
+<!-- Generated by SpecStory, Markdown v2.1.0 -->
 
 <!-- cursor Session faf4db6e-9d08-4e79-906f-d2f51852154f (2025-10-27 16:57Z) -->
 
@@ -10,9 +10,10 @@ _**User (2025-10-27 21:59Z)**_
 
 ---
 
-_**Assistant (gpt-5)**_
+_**Agent (model gpt-5, mode Agent)**_
 
-<think><details><summary>Thought Process</summary>**Creating a work todo list**
+<think><details><summary>Thought Process</summary>
+**Creating a work todo list**
 
 I see we have a Windows PowerShell environment, but tools aren't running there. I think I should create a todo list for re-applying work configuration. That sounds moderately complex, including updates across scripts and ensuring paths for the work environment. 
 
@@ -27,37 +28,48 @@ I'll scan the scripts to see what's currently configured (likely "home" mode), t
 
 ---
 
-Tool use: **read_file**
+<tool-use data-tool-type="read" data-tool-name="read_file">
+<details><summary>Tool use: **read_file** • Read file: UpdateSequences.ps1</summary>
 
-Read file: UpdateSequences.ps1
+</details>
+</tool-use>
 
 ---
 
-Tool use: **read_file**
+<tool-use data-tool-type="read" data-tool-name="read_file">
+<details><summary>Tool use: **read_file** • Read file: UpdateSequences.bat</summary>
 
-Read file: UpdateSequences.bat
+</details>
+</tool-use>
 
 ---
 
-Tool use: **read_file**
+<tool-use data-tool-type="read" data-tool-name="read_file">
+<details><summary>Tool use: **read_file** • Read file: UpdateAllSequences.bat</summary>
 
-Read file: UpdateAllSequences.bat
+</details>
+</tool-use>
 
 ---
 
-Tool use: **read_file**
+<tool-use data-tool-type="read" data-tool-name="read_file">
+<details><summary>Tool use: **read_file** • Read file: UpgradeSeqBatches.ps1</summary>
 
-Read file: UpgradeSeqBatches.ps1
+</details>
+</tool-use>
 
 ---
 
-Tool use: **read_file**
+<tool-use data-tool-type="read" data-tool-name="read_file">
+<details><summary>Tool use: **read_file** • Read file: outline.txt</summary>
 
-Read file: outline.txt
+</details>
+</tool-use>
 
 ---
 
-<think><details><summary>Thought Process</summary>**Reapplying work configuration**
+<think><details><summary>Thought Process</summary>
+**Reapplying work configuration**
 
 I need to re-apply the "work configuration" to the repo since they mentioned losing the entire work in Gitea. I see we previously updated UpdateSequences.ps1 for home mode, but now must switch scripts back to work configuration. Currently, we have UpdateSequences.ps1 and UpdateSequences.bat pointing to a work path. The PS1 seems to use a working directory root and might have different naming and destination rules. However, we only have the history document for home, so I must figure out what "work configuration" entails based on the context.
 **Clarifying work configuration**
@@ -73,10 +85,9 @@ I’m going to look for patterns indicating the “work” mode (e.g., daily_* s
 
 ---
 
-Tool use: **grep**
+<tool-use data-tool-type="search" data-tool-name="grep">
-
 <details>
-<summary>Grep for "daily_" • 32 matches</summary>
+<summary>Tool use: **grep** • Grep for "daily_" • 32 matches</summary>
 
 Output mode: content
 
@@ -118,10 +129,12 @@ Output mode: content
 
 
 </details>
+</tool-use>
 
 ---
 
-<think><details><summary>Thought Process</summary>**Evaluating script updates**
+<think><details><summary>Thought Process</summary>
+**Evaluating script updates**
 
 I'm looking at `UpdateSequences.bat`, where the path points to the repo script. The thing is, while `$currentDir` seems fine for both, there's a preference to avoid writing plans to a file and instead output to the console. But for a work environment, it might make sense to save the plan to `_UpdatePlan.txt` instead. Currently, the script prints to the console, and earlier changes emphasize direct console output, which could be part of home rules. I think implementing a `-Mode` parameter to toggle between Work and Home options could work.
 **Adjusting script behavior**
@@ -130,10 +143,9 @@ I'm thinking about how to adjust the scanning patterns and plan writing. The ins
 
 ---
 
-Tool use: **grep**
+<tool-use data-tool-type="search" data-tool-name="grep">
-
 <details>
-<summary>Grep for "_UpdatePlan.txt" • 1 match</summary>
+<summary>Tool use: **grep** • Grep for "_UpdatePlan.txt" • 1 match</summary>
 
 Output mode: content
 
@@ -144,10 +156,12 @@ Output mode: content
 
 
 </details>
+</tool-use>
 
 ---
 
-<think><details><summary>Thought Process</summary>**Interpreting configuration requests**
+<think><details><summary>Thought Process</summary>
+**Interpreting configuration requests**
 
 I need to focus on the user's request about their Gitea work and re-applying the work configuration to their repo. They mention a spec file that details editing a script, and it seems like they want to revert to a work mode with different scanning patterns. I should confirm what "work configuration" specifically means since the current scripts are set to a "home" mode. The distinction and pathing between local and centralized scripts need understanding to ensure the right setup.
 **Analyzing work configuration setups**
@@ -169,10 +183,9 @@ I'll switch the daily folder scan in `UpdateSequences.ps1` from date-based (YYYY
 
 ---
 
-Tool use: **apply_patch**
+<tool-use data-tool-type="write" data-tool-name="apply_patch">
-
 <details>
-        <summary>Apply patch for UpdateSequences.ps1</summary>
+        <summary>Tool use: **apply_patch** • Apply patch for UpdateSequences.ps1</summary>
       
 
 ```diff
@@ -186,12 +199,14 @@ Tool use: **apply_patch**
 *** End Patch
 ```
 
+</details>
+</tool-use>
+
 ---
 
-Tool use: **read_lints**
+<tool-use data-tool-type="generic" data-tool-name="read_lints">
-
 <details>
-          <summary>Read lints for 1 file</summary>
+          <summary>Tool use: **read_lints** • Read lints for 1 file</summary>
       
 Lint paths:
 
@@ -202,19 +217,20 @@ Lint results
 
 **No lint errors found**
 </details>
+</tool-use>
 
 ---
 
-<think><details><summary>Thought Process</summary>**Analyzing file structure**
+<think><details><summary>Thought Process</summary>
+**Analyzing file structure**
 
 It looks like the work environment is using an absolute path for the `ps1` file in a specified directory, but inside `UpdateSequences.ps1`, it's relying on the current directory for both scanning and destination. I wonder if the work configuration is trying to mirror subfolders in "Renders." Previously, "_CURRENT" was used in the project root, but maybe "Current" is the new destination. To clarify, I'll search through the repository for any instances of "_CURRENT."</details></think>
 
 ---
 
-Tool use: **grep**
+<tool-use data-tool-type="search" data-tool-name="grep">
-
 <details>
-<summary>Grep for "_CURRENT" • 8 matches</summary>
+<summary>Tool use: **grep** • Grep for "_CURRENT" • 8 matches</summary>
 
 Output mode: content
 
@@ -232,10 +248,12 @@ Output mode: content
 
 
 </details>
+</tool-use>
 
 ---
 
-<think><details><summary>Thought Process</summary>**Analyzing user instructions**
+<think><details><summary>Thought Process</summary>
+**Analyzing user instructions**
 
 I need to follow the developer's instructions carefully based on the user's request. They mentioned a loss of work in gitea and want to re-apply a "work configuration." I need to figure out what that configuration entails, looking back at the attached history file that describes past modifications. It seems we switched scanning formats to 'daily_*' recently, which might be part of the "work" mode. I should also verify path references to ensure we're aligned with the correct environment.
 **Evaluating script adjustments**
@@ -265,15 +283,17 @@ I switched the scan to use daily_* and verified the batch scripts and robocopy f
 
 ---
 
-Tool use: **todo_write**
+<tool-use data-tool-type="task" data-tool-name="todo_write">
-
+<details><summary>Tool use: **todo_write** • Todo List</summary>
-## Todo List
 
 - [x] Switch UpdateSequences.ps1 daily scan to daily_* (work mode)
 - [x] Verify UpdateSequences.bat points to central work path
 - [x] Confirm robocopy flags mirror (/MIR) for work setup
 - [x] Sanity-check logs/summary for work run
 
+</details>
+</tool-use>
+
 ---
 
 - Switched `UpdateSequences.ps1` to scan `daily_*` folders instead of date-based names.

.specstory/history/2025-12-29_17-30Z-zipseq-thumbs-db-exclusion.md

@@ -0,0 +1,555 @@
+<!-- Generated by SpecStory, Markdown v2.1.0 -->
+
+<!-- cursor Session 709b2b05-b26b-4f58-8cd9-1a63b137e96e (2025-12-29 17:30Z) -->
+
+# Zipseq Thumbs.db exclusion (2025-12-29 17:30Z)
+
+_**User (2025-12-29 17:37Z)**_
+
+zipseq needs to completely ignore Thumbs.db. It should be removed from any existing manifests. If the manifest is changed, but only Thumbs.db is changed (removed) it should not be rezipped.
+
+---
+
+_**Agent (model default, mode Agent)**_
+
+
+
+---
+
+
+Examining `zip_sequences.py` to understand how it handles manifests and files.
+
+
+---
+
+<tool-use data-tool-type="read" data-tool-name="read_file">
+<details><summary>Tool use: **read_file** • Read file: zip_sequences.py</summary>
+
+</details>
+</tool-use>
+
+---
+
+
+
+---
+
+
+Updating `zip_sequences.py` to ignore `Thumbs.db` files. Modifying file iteration, state loading, and state comparison.
+
+
+---
+
+<tool-use data-tool-type="read" data-tool-name="read_file">
+<details><summary>Tool use: **read_file** • Read file: zip_sequences.py</summary>
+
+</details>
+</tool-use>
+
+---
+
+<tool-use data-tool-type="read" data-tool-name="read_file">
+<details><summary>Tool use: **read_file** • Read file: zip_sequences.py</summary>
+
+</details>
+</tool-use>
+
+---
+
+<tool-use data-tool-type="read" data-tool-name="read_file">
+<details><summary>Tool use: **read_file** • Read file: zip_sequences.py</summary>
+
+</details>
+</tool-use>
+
+---
+
+<tool-use data-tool-type="read" data-tool-name="read_file">
+<details><summary>Tool use: **read_file** • Read file: zip_sequences.py</summary>
+
+</details>
+</tool-use>
+
+---
+
+
+
+---
+
+
+Updating the code to ignore `Thumbs.db` files:
+
+
+---
+
+<tool-use data-tool-type="write" data-tool-name="search_replace">
+
+<details><summary>Tool use: **search_replace** • Edit file: zip_sequences.py</summary>
+
+**Chunk 1**
+Lines added: 3, lines removed: undefined
+
+```diff
+@@ -522,4 +522,7 @@
+              continue
+          for filename in filenames:
++             # Ignore Thumbs.db files completely
++             if filename.lower() == "thumbs.db":
++                 continue
+              yield path / filename
+  
+```
+
+</details>
+
+</tool-use>
+
+---
+
+<tool-use data-tool-type="write" data-tool-name="search_replace">
+
+<details><summary>Tool use: **search_replace** • Edit file: zip_sequences.py</summary>
+
+**Chunk 1**
+Lines added: 6, lines removed: undefined
+
+```diff
+@@ -567,4 +567,10 @@
+      try:
+          state = json.loads(state_path.read_text())
++         # Remove Thumbs.db entries from loaded state
++         if "files" in state:
++             state["files"] = [
++                 entry for entry in state.get("files", [])
++                 if Path(entry.get("path", "")).name.lower() != "thumbs.db"
++             ]
+          # Normalize timestamps in loaded state to ensure consistency
+          # This handles state files created before normalization was added
+```
+
+</details>
+
+</tool-use>
+
+---
+
+<tool-use data-tool-type="write" data-tool-name="search_replace">
+
+<details><summary>Tool use: **search_replace** • Edit file: zip_sequences.py</summary>
+
+**Chunk 1**
+Lines added: 4, lines removed: 1
+
+```diff
+@@ -597,7 +597,10 @@
+      
+      def normalize_state(state: dict) -&gt; dict:
+-         """Normalize timestamps in state to filesystem precision."""
++         """Normalize timestamps in state to filesystem precision and filter out Thumbs.db."""
+          normalized = {"files": []}
+          for entry in state.get("files", []):
++             # Ignore Thumbs.db files in state comparison
++             if Path(entry.get("path", "")).name.lower() == "thumbs.db":
++                 continue
+              mtime_ns = entry["mtime_ns"]
+              if is_windows:
+```
+
+**Chunk 2**
+Lines added: 1, lines removed: 1
+
+```diff
+@@ -610,5 +613,5 @@
+          return normalized
+      
+-     # Compare normalized states
++     # Compare normalized states (Thumbs.db already filtered out)
+      normalized_seq = normalize_state(seq_state)
+      normalized_stored = normalize_state(stored_state)
+```
+
+</details>
+
+</tool-use>
+
+---
+
+
+
+---
+
+
+Checking for lint errors and verifying that `zip_sequence` uses the filtered file list:
+
+
+---
+
+<tool-use data-tool-type="generic" data-tool-name="read_lints">
+<details>
+          <summary>Tool use: **read_lints** • Read lints for 1 file</summary>
+      
+Lint paths:
+
+- `zip_sequences.py`
+
+Lint results
+
+
+**No lint errors found**
+</details>
+</tool-use>
+
+---
+
+<tool-use data-tool-type="read" data-tool-name="read_file">
+<details><summary>Tool use: **read_file** • Read file: zip_sequences.py</summary>
+
+</details>
+</tool-use>
+
+---
+
+
+
+---
+
+
+Verifying that `zip_sequence` uses the filtered iterator:
+
+
+---
+
+<tool-use data-tool-type="read" data-tool-name="read_file">
+<details><summary>Tool use: **read_file** • Read file: zip_sequences.py</summary>
+
+</details>
+</tool-use>
+
+---
+
+
+
+---
+
+
+## Summary of Changes
+
+1. **`iter_sequence_files()`** — Skips `Thumbs.db` files during iteration, so they're never included in new states or archives.
+
+2. **`load_state()`** — Removes any `Thumbs.db` entries from existing manifests when loading state files.
+
+3. **`state_changed()`** — Filters out `Thumbs.db` entries from both states before comparison, so if the only change is removing `Thumbs.db`, it won't trigger a rezip.
+
+Results:
+- `Thumbs.db` files are ignored during scanning
+- Existing manifests have `Thumbs.db` entries removed when loaded
+- If a manifest change is only due to `Thumbs.db` removal, it won't trigger recompression
+
+The `zip_sequence()` function automatically benefits from these changes since it uses `iter_sequence_files()`, which now filters out `Thumbs.db`.
+
+No linting errors were found. The changes are ready to use.
+
+---
+
+_**User (2025-12-29 17:37Z)**_
+
+does zipseq currently scan other types in the seq than png? e.g. jpg, exr
+
+---
+
+_**Agent (model default, mode Agent)**_
+
+
+
+---
+
+
+Checking which file types `zipseq` scans:
+
+
+---
+
+<tool-use data-tool-type="read" data-tool-name="read_file">
+<details><summary>Tool use: **read_file** • Read file: zip_sequences.py</summary>
+
+</details>
+</tool-use>
+
+---
+
+<tool-use data-tool-type="read" data-tool-name="read_file">
+<details><summary>Tool use: **read_file** • Read file: zip_sequences.py</summary>
+
+</details>
+</tool-use>
+
+---
+
+
+
+---
+
+
+Yes. `zipseq` scans multiple file types, not just PNG.
+
+```45:52:zip_sequences.py
+SEQUENCE_EXTENSIONS = {
+    ".png",
+    ".jpg",
+    ".jpeg",
+    ".tif",
+    ".tiff",
+    ".exr",
+}
+```
+
+The `find_sequence_dirs()` function uses this set to identify sequence directories:
+
+```491:491:zip_sequences.py
+        has_frames = any(Path(dirpath, f).suffix.lower() in SEQUENCE_EXTENSIONS for f in filenames)
+```
+
+Supported extensions:
+- `.png`
+- `.jpg`
+- `.jpeg`
+- `.tif`
+- `.tiff`
+- `.exr`
+
+All of these are included in archives and tracked in manifests.
+
+---
+
+_**User (2025-12-29 17:37Z)**_
+
+if there's a sequence with both jpg and png (by mistake) will it scan and compress both?
+
+---
+
+_**Agent (model default, mode Agent)**_
+
+
+
+---
+
+
+Yes. If a sequence directory contains both JPG and PNG files, both will be scanned and compressed.
+
+How it works:
+1. `find_sequence_dirs()` checks if a directory has any files matching `SEQUENCE_EXTENSIONS` (`.png`, `.jpg`, `.jpeg`, `.tif`, `.tiff`, `.exr`). If it finds any, it treats the directory as a sequence directory.
+2. Once identified as a sequence directory, `iter_sequence_files()` includes all files in that directory (except `Thumbs.db` and archive paths), regardless of extension:
+
+```517:524:zip_sequences.py
+def iter_sequence_files(seq_dir: Path) -> Iterator[Path]:
+    for dirpath, dirnames, filenames in os.walk(seq_dir):
+        path = Path(dirpath)
+        dirnames[:] = [d for d in dirnames if d not in ("_archive", "_CURRENT")]
+        if is_archive_path(path):
+            continue
+        for filename in filenames:
+            # Ignore Thumbs.db files completely
+            if filename.lower() == "thumbs.db":
+                continue
+            yield path / filename
+```
+
+So if a directory has both `frame_001.jpg` and `frame_001.png`, both will be:
+- Included in the state manifest
+- Compressed into the archive
+
+The extension check only determines whether a directory is a sequence directory; it doesn't filter which files get included once it's identified as one.
+
+---
+
+_**User (2025-12-29 17:37Z)**_
+
+I had one with jpgs that I removed so only the pngs remain, but the manifest isn't changing.
+
+---
+
+_**Agent (model default, mode Agent)**_
+
+
+
+---
+
+
+Checking the state comparison logic to see why the manifest isn't updating after removing JPGs:
+
+
+---
+
+<tool-use data-tool-type="read" data-tool-name="read_file">
+<details><summary>Tool use: **read_file** • Read file: zip_sequences.py</summary>
+
+</details>
+</tool-use>
+
+---
+
+<tool-use data-tool-type="search" data-tool-name="codebase_search">
+<details>
+                <summary>Tool use: **codebase_search** • Searched codebase "How does the quick skip check work when directory mtime is older than archive?" • **14** results</summary>
+            
+| File | Lines |
+|------|-------|
+| `zip_sequences.py` | L981-1156 |
+| `zip_sequences.py` | L979-1156 |
+| `scripts_old/0MoveToCurrent.bat` | L61 |
+| `zip_sequences.py` | L563-650 |
+| `zip_sequences.py` | L471-513 |
+| `zip_sequences.py` | L516-560 |
+| `zip_sequences.py` | L1159-1286 |
+| `zip_sequences.py` | L676-969 |
+| `zip_sequences.py` | L861-969 |
+| `zip_sequences.py` | L984-1286 |
+| `UpdateSequences.ps1` | L54-96 |
+| `zip_sequences.py` | L584-657 |
+| `zip_sequences.py` | L861-976 |
+| `zip_sequences.py` | L557-650 |
+
+</details>
+</tool-use>
+
+---
+
+
+
+---
+
+
+The quick-skip optimization is likely the cause. It skips state computation if the directory mtime is <= the archive mtime, which can miss deletions when the directory mtime doesn't update. Checking the logic and making it more reliable:
+
+
+---
+
+<tool-use data-tool-type="read" data-tool-name="read_file">
+<details><summary>Tool use: **read_file** • Read file: zip_sequences.py</summary>
+
+</details>
+</tool-use>
+
+---
+
+
+
+---
+
+
+The quick-skip optimization can miss file deletions when the directory mtime doesn't update. Adding a pre-check: if any files from the stored state are missing, we'll recompute the state instead of skipping.
+
+
+---
+
+<tool-use data-tool-type="write" data-tool-name="search_replace">
+
+<details><summary>Tool use: **search_replace** • Edit file: zip_sequences.py</summary>
+
+**Chunk 1**
+Lines added: 29, lines removed: 15
+
+```diff
+@@ -1030,19 +1030,33 @@
+              if zip_path.exists() and stored_state is not None:
+                  # Quick check: if directory mtime is older than archive, likely unchanged
+-                 try:
+-                     dir_mtime = seq_dir.stat().st_mtime_ns
+-                     archive_mtime = zip_path.stat().st_mtime_ns
+-                     # If directory wasn't modified since archive was created, skip state computation
+-                     if dir_mtime &lt;= archive_mtime:
+-                         quick_skipped += 1
+-                         if quick_skipped &lt;= 5:
+-                             log("scan", f"Skipping {rel} (unchanged since archive)")
+-                         # Still need to check for old .zip cleanup (we have .7z, so .zip is obsolete)
+-                         if old_zip_path and old_zip_path.exists():
+-                             old_zip_path.unlink(missing_ok=True)
+-                             old_state_path = state_path_for(old_zip_path)
+-                             if old_state_path.exists():
+-                                 old_state_path.unlink(missing_ok=True)
+-                         continue
++                 # But first verify that all files in stored state still exist (catches deletions)
++                 try:
++                     # Quick check: verify stored files still exist (catches file deletions)
++                     stored_files_exist = True
++                     for entry in stored_state.get("files", []):
++                         # Skip Thumbs.db entries (they're filtered out anyway)
++                         if Path(entry.get("path", "")).name.lower() == "thumbs.db":
++                             continue
++                         file_path = seq_dir / entry["path"]
++                         if not file_path.exists():
++                             stored_files_exist = False
++                             break
++                     
++                     # Only do mtime check if all stored files still exist
++                     if stored_files_exist:
++                         dir_mtime = seq_dir.stat().st_mtime_ns
++                         archive_mtime = zip_path.stat().st_mtime_ns
++                         # If directory wasn't modified since archive was created, skip state computation
++                         if dir_mtime &lt;= archive_mtime:
++                             quick_skipped += 1
++                             if quick_skipped &lt;= 5:
++                                 log("scan", f"Skipping {rel} (unchanged since archive)")
++                             # Still need to check for old .zip cleanup (we have .7z, so .zip is obsolete)
++                             if old_zip_path and old_zip_path.exists():
++                                 old_zip_path.unlink(missing_ok=True)
++                                 old_state_path = state_path_for(old_zip_path)
++                                 if old_state_path.exists():
++                                     old_state_path.unlink(missing_ok=True)
++                             continue
+                  except OSError:
+                      # If stat fails, fall through to full state computation
+```
+
+</details>
+
+</tool-use>
+
+---
+
+
+
+---
+
+
+
+
+
+---
+
+<tool-use data-tool-type="generic" data-tool-name="read_lints">
+<details>
+          <summary>Tool use: **read_lints** • Read lints for 1 file</summary>
+      
+Lint paths:
+
+- `zip_sequences.py`
+
+Lint results
+
+
+**No lint errors found**
+</details>
+</tool-use>
+
+---
+
+
+
+---
+
+
+Fixed the issue. The quick-skip optimization was skipping state computation when the directory mtime was <= the archive mtime, which can miss file deletions if the directory mtime doesn't update.
+
+**The fix:** Before the quick-skip, the code now verifies that all files in the stored state still exist. If any are missing (like the JPGs you removed), it skips the quick-skip and recomputes the full state, which will detect the change and update the manifest.
+
+Now when you run `zipseq`:
+1. It checks if stored files still exist
+2. If JPGs are missing, it recomputes the state
+3. It detects the difference and updates the manifest
+4. It recompresses the archive with only the remaining PNGs
+
+The manifest should now update correctly when files are removed, even if the directory mtime doesn't change.
+
+---
+

CONFIG.md

@@ -21,4 +21,6 @@ root (copied alongside helper batches when they are deployed to projects).
   is found it logs a warning and falls back to `zipfile`.
 - Leaving `structDir` empty is safe—the scripts fall back to the directory that
   contains `config.json`.
+- `compress_sequence_pngs.py` (used by CompressPNGs.bat) requires **Pillow** (PIL).
+  Install with: `pip install Pillow`
 

CompressPNGs.bat

@@ -0,0 +1,43 @@
+@echo off
+setlocal EnableExtensions EnableDelayedExpansion
+
+set "REN_DIR=%~dp0"
+for %%I in ("%REN_DIR%..") do set "PROJ_ROOT=%%~fI"
+
+set "CONFIG_DIR=%PROJ_ROOT%\.config"
+set "CONFIG_PATH=%CONFIG_DIR%\config.json"
+set "GET_STRUCT_DIR=%CONFIG_DIR%\GetStructDir.ps1"
+
+if not exist "%CONFIG_PATH%" (
+    echo [ERROR] config.json not found at %CONFIG_PATH%
+    echo Please run ConfigLoader.ps1 to deploy helper files.
+    exit /b 1
+)
+
+if not exist "%GET_STRUCT_DIR%" (
+    echo [ERROR] GetStructDir.ps1 not found at %GET_STRUCT_DIR%
+    echo Please run ConfigLoader.ps1 to deploy helper files.
+    exit /b 1
+)
+
+for /f "usebackq delims=" %%I in (`powershell -NoProfile -ExecutionPolicy Bypass -Command ^
+    "Set-StrictMode -Version Latest; $structDir = & '%GET_STRUCT_DIR%' -ProjectRoot '%PROJ_ROOT%'; if (-not $structDir) { throw \"Failed to get structDir from GetStructDir.ps1\" }; $pyPath = Join-Path $structDir 'compress_sequence_pngs.py'; if (-not (Test-Path -LiteralPath $pyPath)) { throw \"compress_sequence_pngs.py not found at $pyPath\" }; Write-Output $pyPath"`) do set "PY_SCRIPT=%%~I"
+
+if not defined PY_SCRIPT (
+    echo [ERROR] Unable to resolve compress_sequence_pngs.py path from config.
+    exit /b 1
+)
+
+pushd "%PROJ_ROOT%" >nul 2>&1
+
+python "%PY_SCRIPT%" %*
+set "ERR=!ERRORLEVEL!"
+
+popd >nul 2>&1
+
+if !ERR! NEQ 0 (
+    echo PNG compression failed ^(exit code !ERR!^).
+    exit /b !ERR!
+)
+
+exit /b 0

ConfigLoader.ps1

@@ -1,3 +1,9 @@
+[CmdletBinding()]
+param(
+    [Parameter(Mandatory=$false)]
+    [string]$ProjectPath
+)
+
 Set-StrictMode -Version Latest
 $ErrorActionPreference = 'Stop'
 
@@ -210,7 +216,28 @@ if ($MyInvocation.InvocationName -ne '.') {
     # Update config.json to use script's directory as structDir for portability
     Update-ConfigStructDir -StructDir $script:LoaderRoot
     
-    $projectPath = Get-ProjectPathFromUser
+    # Use provided ProjectPath parameter, or prompt user if not provided
+    if ([string]::IsNullOrWhiteSpace($ProjectPath)) {
+        $projectPath = Get-ProjectPathFromUser
+    }
+    else {
+        # Remove quotes if present and resolve the provided path
+        $ProjectPath = $ProjectPath.Trim('"', "'")
+        try {
+            if (Test-Path -LiteralPath $ProjectPath -PathType Container) {
+                $projectPath = (Resolve-Path -LiteralPath $ProjectPath -ErrorAction Stop).Path
+            }
+            else {
+                Write-Error "Project path does not exist or is not a directory: $ProjectPath"
+                exit 1
+            }
+        }
+        catch {
+            Write-Error "Unable to resolve project directory: $($_.Exception.Message)"
+            exit 1
+        }
+    }
+    
     if ($null -ne $projectPath) {
         # Deploy batch files and config to the project
         $structDir = Get-StructDirectory
@@ -343,7 +370,7 @@ if ($MyInvocation.InvocationName -ne '.') {
 
         Write-Host "All batch files refreshed successfully." -ForegroundColor Green
 
-        # Deploy ZipSeqArchv.bat and UnzipSeqArchv.bat to \Renders
+        # Deploy ZipSeqArchv.bat, UnzipSeqArchv.bat, CompressPNGs.bat to \Renders
         Write-Host "`n=== Deploying ZipSeqArchv.bat and UnzipSeqArchv.bat to \Renders ===" -ForegroundColor Magenta
         $rendersDir = Join-Path -Path $resolvedProject -ChildPath 'Renders'
         if (-not (Test-Path -LiteralPath $rendersDir -PathType Container)) {
@@ -352,7 +379,8 @@ if ($MyInvocation.InvocationName -ne '.') {
         }
         $zipFiles = @(
             @{ Name = 'ZipSeqArchv.bat'; Source = Join-Path -Path $structDir -ChildPath 'ZipSeqArchv.bat' },
-            @{ Name = 'UnzipSeqArchv.bat'; Source = Join-Path -Path $structDir -ChildPath 'UnzipSeqArchv.bat' }
+            @{ Name = 'UnzipSeqArchv.bat'; Source = Join-Path -Path $structDir -ChildPath 'UnzipSeqArchv.bat' },
+            @{ Name = 'CompressPNGs.bat'; Source = Join-Path -Path $structDir -ChildPath 'CompressPNGs.bat' }
         )
         foreach ($zipFile in $zipFiles) {
             $targetPath = Join-Path -Path $rendersDir -ChildPath $zipFile.Name

NewProject.bat

@@ -1,25 +1,25 @@
 @echo off
 setlocal EnableExtensions
 
-set "SCRIPT_DIR=%~dp0"
+:: Search for .config directory in current working directory (including subdirectories) to find ProjectStructure location
-set "CONFIG_LOADER=%SCRIPT_DIR%ConfigLoader.ps1"
+set "STRUCT_DIR="
-set "CONFIG_PATH=%SCRIPT_DIR%config.json"
-
-if not exist "%CONFIG_LOADER%" (
-    echo [ERROR] ConfigLoader.ps1 not found next to NewProject.bat.
-    exit /b 1
-)
-
-if not exist "%CONFIG_PATH%" (
-    echo [ERROR] config.json not found next to NewProject.bat.
-    exit /b 1
-)
-
 for /f "usebackq delims=" %%I in (`powershell -NoProfile -ExecutionPolicy Bypass -Command ^
-    "Set-StrictMode -Version Latest; $loader = Resolve-Path -LiteralPath '%CONFIG_LOADER%' -ErrorAction Stop; . $loader.Path; Write-Output (Get-StructDirectory)"`) do set "STRUCT_DIR=%%I"
+    "$ErrorActionPreference = 'Continue'; $searchDir = '%CD%'; try { $subDirs = Get-ChildItem -LiteralPath $searchDir -Directory -Force -ErrorAction Stop; $configDirs = @(); foreach ($subDir in $subDirs) { $configPath = Join-Path $subDir.FullName '.config\config.json'; if (Test-Path -LiteralPath $configPath -PathType Leaf) { $configDirs += $configPath } }; if ($configDirs.Count -gt 0) { $configPath = $configDirs[0]; $config = Get-Content -LiteralPath $configPath -Raw | ConvertFrom-Json; if ($config.structDir) { $structDir = $config.structDir.ToString().Trim(); if ([System.IO.Path]::IsPathRooted($structDir)) { try { $resolved = Resolve-Path -LiteralPath $structDir -ErrorAction Stop; Write-Output $resolved.Path } catch { Write-Output $structDir } } else { $candidate = Join-Path (Split-Path -Parent $configPath) $structDir; try { $resolvedCandidate = Resolve-Path -LiteralPath $candidate -ErrorAction Stop; Write-Output $resolvedCandidate.Path } catch { Write-Output $candidate } } } } } catch { }"`) do set "STRUCT_DIR=%%I"
 
 if not defined STRUCT_DIR (
-    echo [ERROR] Unable to resolve ProjectStructure directory from config.
+    echo [ERROR] Unable to find .config directory or resolve ProjectStructure directory.
+    echo Please ensure you are running NewProject.bat from a directory containing projects with .config folders.
+    exit /b 1
+)
+
+:: Debug: Show discovered structDir
+echo Found ProjectStructure directory: %STRUCT_DIR%
+
+:: Locate ConfigLoader.ps1 in the ProjectStructure directory
+set "CONFIG_LOADER=%STRUCT_DIR%\ConfigLoader.ps1"
+
+if not exist "%CONFIG_LOADER%" (
+    echo [ERROR] ConfigLoader.ps1 not found at: %CONFIG_LOADER%
     exit /b 1
 )
 
@@ -61,9 +61,9 @@ mkdir "%projectRoot%\Pr\RnR\RIFE"
 :: Add project root additions
 if not exist "%projectRoot%\Renders" mkdir "%projectRoot%\Renders"
 
-:: Place helper scripts into Renders
+:: Place helper scripts into Renders (config lives in .config\, deployed by ConfigLoader below)
 set "templateRoot=%STRUCT_DIR%"
-for %%F in (UpdateSequences.bat ZipSeqArchv.bat UnzipSeqArchv.bat ConfigLoader.ps1 config.json) do (
+for %%F in (UpdateSequences.bat ZipSeqArchv.bat UnzipSeqArchv.bat CompressPNGs.bat) do (
   if exist "%templateRoot%\%%F" copy /Y "%templateRoot%\%%F" "%projectRoot%\Renders\%%F" >nul
 )
 
@@ -79,5 +79,16 @@ git add . -v
 git commit -m "init"
 popd >nul
 
+:: Deploy config workflow using ConfigLoader.ps1
+echo.
+echo Deploying config workflow...
+for %%P in ("%projectRoot%") do set "PROJECT_ROOT_ABS=%%~fP"
+powershell -NoProfile -ExecutionPolicy Bypass -Command "& '%CONFIG_LOADER%' -ProjectPath '%PROJECT_ROOT_ABS%'"
+if errorlevel 1 (
+    echo [WARNING] Config workflow deployment failed. You may need to run ConfigLoader.ps1 manually.
+) else (
+    echo Config workflow deployed successfully.
+)
+
 echo Project structure created successfully in folder: %projectRoot%
 pause 

components/gitattributes

@@ -94,6 +94,9 @@
 *.prproj filter=lfs diff=lfs merge=lfs -text
 *.ai filter=lfs diff=lfs merge=lfs -text
 *.psd filter=lfs diff=lfs merge=lfs -text
+*.pk filter=lfs diff=lfs merge=lfs -text
+*.pkf filter=lfs diff=lfs merge=lfs -text
+
 
 # Davinci Resolve files
 *.dpx filter=lfs diff=lfs merge=lfs -text
@@ -107,6 +110,7 @@
 *.uni filter=lfs diff=lfs merge=lfs -text
 *.pdn filter=lfs diff=lfs merge=lfs -text
 *.pur filter=lfs diff=lfs merge=lfs -text
+*.db filter=lfs diff=lfs merge=lfs -text
 
 # Python files
 *.npz filter=lfs diff=lfs merge=lfs -text

components/gitignore

@@ -40,6 +40,7 @@
 *~
 *.tmp
 *.temp
+BL_proxy/
 
 # OS generated files
 .DS_Store

compress_sequence_pngs.py

@@ -0,0 +1,437 @@
+#!/usr/bin/env python3
+"""Compress PNGs in unchanged render sequences. Writes to staging, prompts for Y/N, then overwrites originals."""
+
+from __future__ import annotations
+
+import argparse
+import json
+import multiprocessing
+import os
+import platform
+import shutil
+import sys
+import time
+from concurrent.futures import ProcessPoolExecutor, as_completed
+from pathlib import Path
+
+try:
+    from PIL import Image
+except ImportError:
+    print("Error: Pillow (PIL) is required. Install with: pip install Pillow", file=sys.stderr)
+    sys.exit(1)
+
+try:
+    import unlock_processpool
+    unlock_processpool.please()
+    UNLOCKED = True
+except ImportError:
+    UNLOCKED = False
+
+RENDER_ROOT = Path("Renders")
+ARCHIVE_ROOT = RENDER_ROOT / "_zipped"
+STAGING_DIR = "_compressed_staging"
+CORRUPTED_DIR = "corrupted"
+STATE_SUFFIX = ".meta.json"
+PNG_EXT = ".png"
+
+
+def is_archive_path(path: Path) -> bool:
+    return any(part in ("_archive", "_CURRENT", "_zipped", STAGING_DIR, CORRUPTED_DIR) for part in path.parts)
+
+
+def find_sequence_dirs(root: Path) -> list[Path]:
+    seen = set()
+    out = []
+    for dirpath, dirnames, filenames in os.walk(root):
+        path = Path(dirpath)
+        dirnames[:] = [d for d in dirnames if d not in ("_archive", "_CURRENT", STAGING_DIR, CORRUPTED_DIR, "_zipped")]
+        if is_archive_path(path):
+            continue
+        if any(Path(dirpath, f).suffix.lower() == PNG_EXT for f in filenames):
+            resolved = path.resolve()
+            if resolved not in seen:
+                seen.add(resolved)
+                out.append(path)
+    return out
+
+
+def iter_png_files(seq_dir: Path):
+    for dirpath, dirnames, filenames in os.walk(seq_dir):
+        path = Path(dirpath)
+        dirnames[:] = [d for d in dirnames if d not in ("_archive", "_CURRENT", "_zipped", STAGING_DIR, CORRUPTED_DIR)]
+        if is_archive_path(path):
+            continue
+        for f in filenames:
+            if Path(f).suffix.lower() == PNG_EXT:
+                yield path / f
+
+
+def load_state(state_path: Path) -> dict | None:
+    if not state_path.exists():
+        return None
+    try:
+        state = json.loads(state_path.read_text())
+        if "files" in state:
+            state["files"] = [e for e in state.get("files", []) if Path(e.get("path", "")).name.lower() != "thumbs.db"]
+        if platform.system() == "Windows" and "files" in state:
+            for e in state.get("files", []):
+                if "mtime_ns" in e:
+                    e["mtime_ns"] = (e["mtime_ns"] // 100) * 100
+        return state
+    except json.JSONDecodeError:
+        return None
+
+
+def state_changed(seq_state: dict, stored_state: dict | None) -> bool:
+    if stored_state is None:
+        return True
+    is_windows = platform.system() == "Windows"
+
+    def png_only(files):
+        return [e for e in files if Path(e.get("path", "")).suffix.lower() == ".png"]
+
+    def norm(s):
+        out = []
+        for e in png_only(s.get("files", [])):
+            if Path(e.get("path", "")).name.lower() == "thumbs.db":
+                continue
+            m = e.get("mtime_ns", 0)
+            if is_windows:
+                m = (m // 100) * 100
+            out.append({"path": e["path"], "size": e["size"], "mtime_ns": m})
+        return {"files": out}
+
+    return norm(seq_state) != norm(stored_state)
+
+
+def compute_state(seq_dir: Path) -> dict:
+    entries = []
+    is_windows = platform.system() == "Windows"
+    for p in sorted(iter_png_files(seq_dir), key=lambda x: x.relative_to(seq_dir).as_posix()):
+        stat = p.stat()
+        mtime_ns = stat.st_mtime_ns
+        if is_windows:
+            mtime_ns = (mtime_ns // 100) * 100
+        entries.append({"path": p.relative_to(seq_dir).as_posix(), "size": stat.st_size, "mtime_ns": mtime_ns})
+    return {"files": entries}
+
+
+def find_archive_and_state(seq_dir: Path) -> tuple[Path | None, Path | None]:
+    """Return (archive_path, state_path) if sequence is archived and unchanged; else (None, None)."""
+    try:
+        rel = seq_dir.relative_to(RENDER_ROOT)
+    except ValueError:
+        return None, None
+    for suffix in (".7z", ".zip"):
+        archive = ARCHIVE_ROOT / f"{rel}{suffix}"
+        if archive.exists():
+            state = archive.with_suffix(archive.suffix + STATE_SUFFIX)
+            return archive, state
+    return None, None
+
+
+def compress_png(input_path: Path, output_path: Path, force_bitdepth: str | None) -> tuple[str, bool, str | None, int, int, float, bool, bool]:
+    """Returns (path, success, error, orig_size, new_size, savings_pct, was_skipped, is_corrupted)."""
+    try:
+        output_path = Path(output_path)
+        output_path.parent.mkdir(parents=True, exist_ok=True)
+        orig_size = input_path.stat().st_size
+        if orig_size == 0:
+            return (str(input_path), False, "CORRUPTED: File is 0 bytes (empty/placeholder)", 0, 0, 0, False, True)
+        try:
+            img = Image.open(input_path)
+            img.load()
+        except Exception as e:
+            return (str(input_path), False, f"CORRUPTED: Cannot open/load image - {e}", orig_size, 0, 0, False, True)
+        if img.width == 0 or img.height == 0:
+            return (str(input_path), False, f"CORRUPTED: Invalid dimensions ({img.width}x{img.height})", orig_size, 0, 0, False, True)
+
+        # All-black + suspiciously small (corruption indicator)
+        try:
+            sample_size = min(100, img.width * img.height)
+            pixels = list(img.getdata()[:sample_size])
+            if pixels:
+                all_black = True
+                for pixel in pixels:
+                    if isinstance(pixel, (tuple, list)):
+                        if any(p > 0 for p in pixel):
+                            all_black = False
+                            break
+                    else:
+                        if pixel > 0:
+                            all_black = False
+                            break
+                if all_black and orig_size < (img.width * img.height * 0.1):
+                    return (str(input_path), False, "CORRUPTED: Image appears all black with suspiciously small file size", orig_size, 0, 0, False, True)
+        except Exception:
+            pass
+
+        # Determine target bit depth
+        if force_bitdepth == "8":
+            is_16bit = False
+        elif force_bitdepth == "16":
+            is_16bit = True
+        else:
+            is_16bit = img.mode == "I"
+            if not is_16bit and img.mode in ("RGB", "RGBA", "LA"):
+                try:
+                    pixels = list(img.getdata())
+                    if pixels:
+                        if isinstance(pixels[0], (tuple, list)):
+                            max_val = max(max(p) for p in pixels[:1000])
+                        else:
+                            max_val = max(pixels[:1000])
+                        if max_val > 255:
+                            is_16bit = True
+                except Exception:
+                    pass
+
+        # Handle bit depth conversion (8-bit to 8-bit, 16-bit to 16-bit)
+        if is_16bit:
+            if force_bitdepth == "16":
+                if img.mode != "I":
+                    img = img.convert("RGBA" if ("A" in img.mode or img.mode == "LA") else "RGB")
+            else:
+                if img.mode == "I":
+                    pass
+                elif img.mode in ("RGB", "RGBA"):
+                    pass
+                else:
+                    img = img.convert("RGBA" if "A" in img.mode else "RGB")
+        else:
+            if force_bitdepth == "8":
+                if img.mode == "I":
+                    img = img.convert("L")
+                elif img.mode == "RGBA":
+                    pass
+                elif img.mode == "RGB":
+                    pass
+                else:
+                    img = img.convert("RGBA" if "A" in img.mode else "RGB")
+            else:
+                if img.mode == "RGBA":
+                    pass
+                elif img.mode != "RGB":
+                    img = img.convert("RGB")
+
+        img.save(str(output_path), "PNG", optimize=True, compress_level=9)
+        new_size = output_path.stat().st_size
+        savings = (orig_size - new_size) / orig_size * 100 if orig_size > 0 else 0
+        return (str(input_path), True, None, orig_size, new_size, savings, False, False)
+    except Exception as e:
+        corrupt = "truncated" in str(e).lower() or "cannot identify" in str(e).lower() or "corrupt" in str(e).lower()
+        return (str(input_path), False, str(e), 0, 0, 0, False, corrupt)
+
+
+def move_to_corrupted(src: Path, base: Path, corrupted_root: Path) -> bool:
+    try:
+        rel = src.relative_to(base)
+    except ValueError:
+        rel = src.name
+    dest = corrupted_root / rel
+    dest.parent.mkdir(parents=True, exist_ok=True)
+    src.rename(dest)
+    return True
+
+
+def format_size(size_bytes: float) -> str:
+    for unit in ("B", "KB", "MB", "GB"):
+        if size_bytes < 1024.0:
+            return f"{size_bytes:.2f} {unit}"
+        size_bytes /= 1024.0
+    return f"{size_bytes:.2f} TB"
+
+
+def format_time(seconds: float) -> str:
+    hours = int(seconds // 3600)
+    minutes = int((seconds % 3600) // 60)
+    secs = int(seconds % 60)
+    centiseconds = int((seconds % 1) * 100)
+    return f"{hours:02d}:{minutes:02d}:{secs:02d}:{centiseconds:02d}"
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(description="Compress PNGs in unchanged sequences; staging + Y/N overwrite.")
+    parser.add_argument("--8bit", "-8", action="store_true", dest="force_8bit")
+    parser.add_argument("--16bit", "-16", action="store_true", dest="force_16bit")
+    parser.add_argument("--verbose", action="store_true")
+    args = parser.parse_args()
+    force_bitdepth = "8" if args.force_8bit else ("16" if args.force_16bit else None)
+    if args.force_8bit and args.force_16bit:
+        print("Error: Cannot specify both --8bit and --16bit. Choose one.")
+        return 1
+    if force_bitdepth == "8":
+        print("Mode: Forcing 8-bit color depth")
+    elif force_bitdepth == "16":
+        print("Mode: Forcing 16-bit color depth")
+    else:
+        print("Mode: Auto-detect bit depth (preserve 16-bit if present)")
+
+    if not RENDER_ROOT.exists():
+        print("[ERROR] Renders directory not found.")
+        return 1
+
+    staging_root = RENDER_ROOT / STAGING_DIR
+    corrupted_root = RENDER_ROOT / CORRUPTED_DIR
+
+    # Find changed sequences (no archive, or state differs from stored)
+    changed: list[Path] = []
+    for seq_dir in find_sequence_dirs(RENDER_ROOT):
+        current = compute_state(seq_dir)
+        if not current["files"]:
+            continue
+        _, state_path = find_archive_and_state(seq_dir)
+        if state_path is None or not state_path.exists():
+            changed.append(seq_dir)  # New sequence, never zipped
+            continue
+        stored = load_state(state_path)
+        if state_changed(current, stored):
+            changed.append(seq_dir)
+
+    if not changed:
+        print("No changed sequences with PNGs found. All sequences are up to date.")
+        return 0
+
+    print(f"Found {len(changed)} changed sequence(s) to compress.")
+    staging_root.mkdir(parents=True, exist_ok=True)
+    corrupted_root.mkdir(parents=True, exist_ok=True)
+
+    # Collect PNGs to compress
+    work: list[tuple[Path, Path]] = []
+    for seq_dir in changed:
+        rel = seq_dir.relative_to(RENDER_ROOT)
+        staging_seq = staging_root / rel
+        for png in iter_png_files(seq_dir):
+            out = staging_seq / png.relative_to(seq_dir)
+            work.append((png, out))
+
+    if not work:
+        print("No PNG files in changed sequences.")
+        return 0
+
+    max_workers = multiprocessing.cpu_count()
+    if platform.system() == "Windows" and not UNLOCKED:
+        max_workers = min(max_workers, 61)
+        if max_workers < multiprocessing.cpu_count():
+            print(f"Detected {multiprocessing.cpu_count()} CPU threads, but Windows limits ProcessPoolExecutor to 61 workers.")
+            print("Install 'unlock-processpool-win' package to use all cores: pip install unlock-processpool-win")
+    else:
+        if UNLOCKED:
+            print("Using unlock-processpool-win to bypass Windows 61-worker limit")
+    print(f"Compressing {len(work)} PNGs with {max_workers} workers...")
+    print("-" * 80)
+
+    compressed = 0
+    corrupted_count = 0
+    corrupted_paths: list[tuple[str, str]] = []
+    total_orig = 0
+    total_new = 0
+    failed = 0
+    start_time = time.time()
+    last_update_time = start_time
+
+    with ProcessPoolExecutor(max_workers=max_workers) as ex:
+        futures = {ex.submit(compress_png, inp, out, force_bitdepth): (inp, out) for inp, out in work}
+        for future in as_completed(futures):
+            inp, out = futures[future]
+            path, ok, err, o_sz, n_sz, _, _, is_corrupt = future.result()
+            if ok:
+                compressed += 1
+                total_orig += o_sz
+                total_new += n_sz
+            elif is_corrupt:
+                corrupted_count += 1
+                try:
+                    if move_to_corrupted(Path(path), RENDER_ROOT, corrupted_root):
+                        corrupted_paths.append((path, f"Moved to {corrupted_root / Path(path).relative_to(RENDER_ROOT)}"))
+                    else:
+                        corrupted_paths.append((path, str(err)))
+                except Exception as e:
+                    corrupted_paths.append((path, str(e)))
+                print(f"\n[CORRUPTED] {path} -> {err}")
+            else:
+                failed += 1
+                print(f"\n[ERROR] {path}: {err}")
+
+            # Live progress (update every 0.5s or on first completion)
+            current_time = time.time()
+            time_since_update = current_time - last_update_time
+            processed = compressed + corrupted_count + failed
+            if processed == 1 or time_since_update >= 0.5:
+                elapsed = current_time - start_time
+                rate = processed / elapsed if elapsed > 0 else 0
+                remaining = len(work) - processed
+                eta_seconds = remaining / rate if rate > 0 and remaining > 0 else 0
+                total_savings = total_orig - total_new
+                total_savings_pct = (total_savings / total_orig * 100) if total_orig > 0 else 0
+                eta_str = format_time(eta_seconds) if eta_seconds > 0 else "calculating..."
+                elapsed_str = format_time(elapsed)
+                print(
+                    f"[{processed:5d}/{len(work)}] "
+                    f"Compressed: {compressed} | Corrupted: {corrupted_count} | Failed: {failed} | "
+                    f"Speed: {rate:.1f} files/sec | "
+                    f"Elapsed: {elapsed_str} | ETA: {eta_str} | "
+                    f"Saved: {format_size(total_savings)} ({total_savings_pct:.1f}%)",
+                    end="\r",
+                )
+                last_update_time = current_time
+
+    print()  # Clear progress line
+    total_time = time.time() - start_time
+    total_savings = total_orig - total_new
+    total_savings_pct = (total_savings / total_orig * 100) if total_orig > 0 else 0
+    avg_rate = (compressed + corrupted_count + failed) / total_time if total_time > 0 else 0
+
+    print("=" * 80)
+    print("Compression complete!")
+    print(f"Successfully compressed: {compressed} files")
+    if corrupted_count > 0:
+        print(f"Corrupted (bad PNGs): {corrupted_count} files")
+    if failed > 0:
+        print(f"Failed: {failed} files")
+    print(f"Total time: {format_time(total_time)}")
+    print(f"Average speed: {avg_rate:.2f} files/second")
+    print(f"Original size: {format_size(total_orig)}")
+    print(f"Compressed size: {format_size(total_new)}")
+    print(f"Total savings: {format_size(total_savings)} ({total_savings_pct:.1f}%)")
+
+    if corrupted_paths:
+        print(f"\nCorrupted files moved to {corrupted_root}")
+        print("\n" + "=" * 80)
+        print("CORRUPTED FILES LIST:")
+        print("=" * 80)
+        for item in corrupted_paths:
+            file_path, move_status = item
+            print(f"  {file_path}")
+            print(f"    Status: {move_status}")
+
+    check_dirs = [f"Renders\\{STAGING_DIR}"]
+    if corrupted_count > 0:
+        check_dirs.append(f"Renders\\{CORRUPTED_DIR}")
+    resp = input(f"\nCheck files in {' and '.join(check_dirs)}. Ready to overwrite originals? (Y/N): ").strip().upper()
+    if resp != "Y":
+        print("Exiting. Staging and corrupted folders left for inspection.")
+        return 0
+
+    # Overwrite originals with staged files
+    for seq_dir in changed:
+        rel = seq_dir.relative_to(RENDER_ROOT)
+        staging_seq = staging_root / rel
+        if not staging_seq.exists():
+            continue
+        for staged in staging_seq.rglob("*.png"):
+            rel_file = staged.relative_to(staging_seq)
+            orig = seq_dir / rel_file
+            if orig.exists():
+                shutil.copy2(staged, orig)
+
+    # Cleanup staging and corrupted
+    shutil.rmtree(staging_root, ignore_errors=True)
+    if corrupted_root.exists():
+        shutil.rmtree(corrupted_root, ignore_errors=True)
+    print("Overwrite complete. Staging and corrupted folders cleaned up.")
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

config.json

@@ -1,6 +1,6 @@
 {
     "dailyFormat":  "YYYY-MM-DD",
-    "structDir":  "D:\\0 ProjectStructure",
+    "structDir":  "A:\\1 Amazon_Active_Projects\\3 ProjectStructure",
     "zipper":  "7z",
     "compression":  0,
     "Max7zInst":  0

organize_textures.ps1

@@ -21,6 +21,9 @@ if (-not (Test-Path -Path $textureFolderPath -PathType Container)) {
 $textureFolderPath = (Resolve-Path $textureFolderPath).ProviderPath
 Write-Host "Processing texture folder: $textureFolderPath" -ForegroundColor Cyan
 
+# Add required .NET assemblies for image processing (for FlatColors standardization)
+Add-Type -AssemblyName System.Drawing
+
 # Function to calculate checksums for files
 function Get-FilesWithChecksums {
     param(
@@ -266,6 +269,99 @@ function Process-DuplicateGroup {
     }
 }
 
+# Function to extract and normalize hex color code from filename (for FlatColors)
+# For TGA files, preserves 8-digit codes (RGBA). For others, uses 6-digit codes (RGB).
+function Get-NormalizedColorCode {
+    param(
+        [string]$FileName,
+        [string]$Extension = ""
+    )
+    
+    # Remove extension if not provided
+    $baseName = [System.IO.Path]::GetFileNameWithoutExtension($FileName)
+    if ([string]::IsNullOrWhiteSpace($Extension)) {
+        $Extension = [System.IO.Path]::GetExtension($FileName)
+    }
+    
+    # For TGA files, preserve 8-digit codes (RGBA with alpha channel)
+    if ($Extension -eq ".tga") {
+        # Match 8-digit hex: #RRGGBBAA
+        if ($baseName -match '^(#?)([0-9A-Fa-f]{8})') {
+            $hexCode = $Matches[2].ToUpper()
+            return "#$hexCode"
+        }
+        # Fallback to 6-digit if 8-digit not found
+        if ($baseName -match '^(#?)([0-9A-Fa-f]{6})') {
+            $hexCode = $Matches[2].ToUpper()
+            return "#$hexCode"
+        }
+    } else {
+        # For non-TGA files, use 6-digit codes (RGB)
+        if ($baseName -match '^(#?)([0-9A-Fa-f]{6})([0-9A-Fa-f]{2})?') {
+            $hexCode = $Matches[2].ToUpper()
+            # Return normalized format: #RRGGBB (always with #, always uppercase, no suffix)
+            return "#$hexCode"
+        }
+    }
+    
+    return $null
+}
+
+# Function to convert and resize image to 16x16 JPG (for FlatColors)
+function Convert-To16x16Jpg {
+    param(
+        [string]$SourcePath,
+        [string]$DestinationPath
+    )
+    
+    try {
+        $image = [System.Drawing.Image]::FromFile($SourcePath)
+        
+        # Create 16x16 bitmap
+        $bitmap = New-Object System.Drawing.Bitmap(16, 16)
+        $graphics = [System.Drawing.Graphics]::FromImage($bitmap)
+        $graphics.InterpolationMode = [System.Drawing.Drawing2D.InterpolationMode]::HighQualityBicubic
+        $graphics.SmoothingMode = [System.Drawing.Drawing2D.SmoothingMode]::HighQuality
+        $graphics.PixelOffsetMode = [System.Drawing.Drawing2D.PixelOffsetMode]::HighQuality
+        
+        # Draw resized image
+        $graphics.DrawImage($image, 0, 0, 16, 16)
+        
+        # Get JPEG codec
+        $jpegCodec = [System.Drawing.Imaging.ImageCodecInfo]::GetImageEncoders() | Where-Object { $_.MimeType -eq "image/jpeg" }
+        $encoderParams = New-Object System.Drawing.Imaging.EncoderParameters(1)
+        $encoderParams.Param[0] = New-Object System.Drawing.Imaging.EncoderParameter([System.Drawing.Imaging.Encoder]::Quality, 95)
+        
+        # Save as JPG
+        $bitmap.Save($DestinationPath, $jpegCodec, $encoderParams)
+        
+        # Cleanup
+        $graphics.Dispose()
+        $bitmap.Dispose()
+        $image.Dispose()
+        $encoderParams.Dispose()
+        
+        return $true
+    } catch {
+        Write-Warning "Failed to convert image: $SourcePath - $($_.Exception.Message)"
+        return $false
+    }
+}
+
+# Function to check if image is 16x16 (for FlatColors)
+function Test-ImageSize {
+    param([string]$ImagePath)
+    
+    try {
+        $image = [System.Drawing.Image]::FromFile($ImagePath)
+        $is16x16 = ($image.Width -eq 16 -and $image.Height -eq 16)
+        $image.Dispose()
+        return $is16x16
+    } catch {
+        return $false
+    }
+}
+
 # ============================================================================
 # PASS 1: Intra-Blendfile Processing
 # ============================================================================
@@ -419,20 +515,38 @@ if ($null -eq $remainingFiles -or $remainingFiles.Count -eq 0) {
         $pass2Duplicates += $result.DuplicateCount
     }
     
-    # Process FlatColors files: merge duplicates and move to \common\FlatColors
+    # Process FlatColors files: standardize to 16x16 JPG (except TGA), merge duplicates by color code
-    Write-Host "Processing FlatColors files (merging duplicates)..." -ForegroundColor Yellow
+    Write-Host "Processing FlatColors files (standardizing and merging duplicates)..." -ForegroundColor Yellow
     
     if ($null -ne $flatColorsFiles -and $flatColorsFiles.Count -gt 0) {
         Write-Host "Found $($flatColorsFiles.Count) FlatColors file(s) to process" -ForegroundColor Gray
         
-        # Calculate checksums for FlatColors files
+        # Group files by normalized color code (instead of checksum)
-        Write-Host "Calculating checksums for FlatColors files..." -ForegroundColor Yellow
+        Write-Host "Grouping FlatColors files by color code..." -ForegroundColor Yellow
-        $flatColorsWithChecksums = Get-FilesWithChecksums -Files $flatColorsFiles
+        $filesByColor = @{}
         
-        # Group by checksum to find duplicates
+        foreach ($file in $flatColorsFiles) {
-        $flatColorsGroupedByChecksum = $flatColorsWithChecksums | Group-Object -Property Hash
+            if (-not (Test-Path -Path $file.FullName)) {
+                continue
+            }
             
-        Write-Host "Found $($flatColorsGroupedByChecksum.Count) unique FlatColors file(s)" -ForegroundColor Gray
+            # Use composite key: color code + extension to separate TGA (8-digit) from JPG (6-digit)
+            $colorCode = Get-NormalizedColorCode -FileName $file.Name -Extension $file.Extension
+            if ($null -eq $colorCode) {
+                Write-Warning "Could not extract color code from: $($file.Name)"
+                continue
+            }
+            
+            # Create composite key: colorCode_extension to keep TGA and JPG separate
+            $groupKey = "$colorCode$($file.Extension)"
+            
+            if (-not $filesByColor.ContainsKey($groupKey)) {
+                $filesByColor[$groupKey] = @()
+            }
+            $filesByColor[$groupKey] += $file
+        }
+        
+        Write-Host "Found $($filesByColor.Count) unique color code(s)" -ForegroundColor Gray
         
         # Create \textures\common\FlatColors directory
         $flatColorsPath = Join-Path -Path $rootCommonPath -ChildPath "FlatColors"
@@ -445,64 +559,195 @@ if ($null -eq $remainingFiles -or $remainingFiles.Count -eq 0) {
         $filesInFlatColors = @{}
         $flatColorsMoved = 0
         $flatColorsDuplicates = 0
+        $flatColorsConverted = 0
+        $flatColorsResized = 0
         $flatColorsMoveLog = [System.Collections.ArrayList]::new()
         
-        foreach ($group in $flatColorsGroupedByChecksum) {
+        foreach ($groupKey in $filesByColor.Keys) {
-            $files = $group.Group
+            $files = $filesByColor[$groupKey]
             
-            if ($files.Count -eq 1) {
+            # Extract color code and extension from group key
-                # Single file - move to FlatColors folder
+            # Group key format: #RRGGBB.ext or #RRGGBBAA.ext
-                $fileObj = $files[0].File
+            if ($groupKey -match '^(#[0-9A-F]{6,8})(\.[^.]+)$') {
-                $fileName = $fileObj.Name
+                $colorCode = $Matches[1]
+                $targetExtension = $Matches[2]
+            } else {
+                Write-Warning "Invalid group key format: $groupKey"
+                continue
+            }
             
-                # Strip blendfile prefix if present
+            $targetFileName = "$colorCode$targetExtension"
-                $strippedName = Get-FileNameWithoutPrefix -FileName $fileName -ValidPrefixes $validBlendfilePrefixes
+            
-                if ($strippedName -ne $fileName) {
+            # Find the best file to keep
-                    $fileName = $strippedName
+            $fileToKeep = $null
+            
+            # First, check if there's already a correct file in target location
+            $existingTarget = Join-Path -Path $flatColorsPath -ChildPath $targetFileName
+            if (Test-Path -Path $existingTarget) {
+                $existingFile = Get-Item -Path $existingTarget
+                # Check if it's already correct
+                if ($existingFile.Extension -eq ".tga") {
+                    $fileToKeep = $existingFile
+                } elseif ($existingFile.Extension -eq ".jpg" -and (Test-ImageSize -ImagePath $existingFile.FullName)) {
+                    $fileToKeep = $existingFile
                 }
+            }
             
-                $destinationPath = Join-Path -Path $flatColorsPath -ChildPath $fileName
+            # If no existing correct file, find best source file
+            if ($null -eq $fileToKeep) {
+                # Prefer TGA file first (preserves transparency)
+                $tgaFile = $files | Where-Object { 
+                    $_.Extension -eq ".tga" -and 
+                    (Test-Path -Path $_.FullName)
+                } | Select-Object -First 1
                 
-                # Handle name conflicts (shouldn't happen for unique files, but just in case)
+                if ($tgaFile) {
-                if ($filesInFlatColors.ContainsKey($fileName) -or (Test-Path -Path $destinationPath)) {
+                    $fileToKeep = $tgaFile
-                    $baseName = [System.IO.Path]::GetFileNameWithoutExtension($fileName)
+                } else {
-                    $extension = [System.IO.Path]::GetExtension($fileName)
+                    # If no TGA, prefer existing JPG file
-                    $counter = 1
+                    $jpgFile = $files | Where-Object { 
-                    do {
+                        ($_.Extension -eq ".jpg" -or $_.Extension -eq ".jpeg") -and 
-                        $newFileName = "${baseName}_${counter}${extension}"
+                        (Test-Path -Path $_.FullName)
-                        $destinationPath = Join-Path -Path $flatColorsPath -ChildPath $newFileName
+                    } | Select-Object -First 1
-                        $counter++
+                    
-                    } while ($filesInFlatColors.ContainsKey($newFileName) -or (Test-Path -Path $destinationPath))
+                    if ($jpgFile) {
-                    $fileName = $newFileName
+                        $fileToKeep = $jpgFile
+                    } else {
+                        # Otherwise, use the first available file
+                        $fileToKeep = $files | Where-Object { Test-Path -Path $_.FullName } | Select-Object -First 1
+                    }
                 }
+            }
             
-                try {
+            if ($null -eq $fileToKeep) {
-                    $originalPath = $fileObj.FullName
+                Write-Warning "  ${colorCode}: No valid file found to process"
-                    Move-Item -Path $originalPath -Destination $destinationPath -Force
+                continue
-                    $filesInFlatColors[$fileName] = $true
+            }
-                    $flatColorsMoved++
             
-                    # Log the move
+            $targetPath = Join-Path -Path $flatColorsPath -ChildPath $targetFileName
-                    $normalizedOriginal = [System.IO.Path]::GetFullPath($originalPath)
+            
-                    $normalizedNew = [System.IO.Path]::GetFullPath($destinationPath)
+            # If target is TGA, preserve as-is (don't convert)
-                    $null = $flatColorsMoveLog.Add([PSCustomObject]@{
+            if ($targetExtension -eq ".tga") {
-                        OriginalPath = $normalizedOriginal
+                if ($fileToKeep.FullName -ne $targetPath) {
-                        NewPath = $normalizedNew
+                    # Move TGA to target location
-                        Type = "moved"
+                    try {
-                    })
+                        if (Test-Path -Path $targetPath) {
-                } catch {
+                            Remove-Item -Path $targetPath -Force
-                    Write-Warning "Failed to move FlatColors file: $($fileObj.FullName) - $($_.Exception.Message)"
+                        }
+                        $originalPath = $fileToKeep.FullName
+                        Move-Item -Path $originalPath -Destination $targetPath -Force
+                        $filesInFlatColors[$targetFileName] = $true
+                        $flatColorsMoved++
+                        
+                        # Log the move
+                        $normalizedOriginal = [System.IO.Path]::GetFullPath($originalPath)
+                        $normalizedNew = [System.IO.Path]::GetFullPath($targetPath)
+                        $null = $flatColorsMoveLog.Add([PSCustomObject]@{
+                            OriginalPath = $normalizedOriginal
+                            NewPath = $normalizedNew
+                            Type = "moved"
+                        })
+                    } catch {
+                        Write-Warning "  ${colorCode}: Failed to move TGA: $($_.Exception.Message)"
+                    }
                 }
             } else {
-                # Multiple files with same checksum (duplicates) - merge them
+                # Target is JPG - convert/resize if needed
-                # Use Process-DuplicateGroup to handle merging
+                $needsConversion = $false
-                $result = Process-DuplicateGroup -Files $files -CommonPath $flatColorsPath -FilesInCommon $filesInFlatColors -StripPrefix -ValidPrefixes $validBlendfilePrefixes -MoveLog $flatColorsMoveLog
+                $needsResize = $false
-                $flatColorsMoved += $result.MovedCount
+                
-                $flatColorsDuplicates += $result.DuplicateCount
+                if ($fileToKeep.Extension -ne ".jpg" -and $fileToKeep.Extension -ne ".jpeg") {
+                    $needsConversion = $true
+                }
+                
+                if (-not (Test-ImageSize -ImagePath $fileToKeep.FullName)) {
+                    $needsResize = $true
+                }
+                
+                # Check if target already exists and is correct
+                if ((Test-Path -Path $targetPath) -and 
+                    (Get-Item -Path $targetPath).Extension -eq ".jpg" -and
+                    (Test-ImageSize -ImagePath $targetPath)) {
+                    # Target already exists and is correct, skip
+                } elseif ($needsConversion -or $needsResize -or $fileToKeep.FullName -ne $targetPath) {
+                    # Convert/resize to target
+                    if (Convert-To16x16Jpg -SourcePath $fileToKeep.FullName -DestinationPath $targetPath) {
+                        if ($needsConversion -and $needsResize) {
+                            $flatColorsConverted++
+                            $flatColorsResized++
+                        } elseif ($needsConversion) {
+                            $flatColorsConverted++
+                        } elseif ($needsResize) {
+                            $flatColorsResized++
+                        } else {
+                            $flatColorsMoved++
+                        }
+                        
+                        $filesInFlatColors[$targetFileName] = $true
+                        
+                        # Log the conversion/move
+                        $normalizedOriginal = [System.IO.Path]::GetFullPath($fileToKeep.FullName)
+                        $normalizedNew = [System.IO.Path]::GetFullPath($targetPath)
+                        $null = $flatColorsMoveLog.Add([PSCustomObject]@{
+                            OriginalPath = $normalizedOriginal
+                            NewPath = $normalizedNew
+                            Type = "moved"
+                        })
+                    } else {
+                        Write-Warning "  ${colorCode}: Failed to convert/resize"
+                        continue
+                    }
+                } else {
+                    # File is already correct format and size
+                    if ($fileToKeep.FullName -ne $targetPath) {
+                        try {
+                            if (Test-Path -Path $targetPath) {
+                                Remove-Item -Path $targetPath -Force
+                            }
+                            $originalPath = $fileToKeep.FullName
+                            Move-Item -Path $originalPath -Destination $targetPath -Force
+                            $filesInFlatColors[$targetFileName] = $true
+                            $flatColorsMoved++
+                            
+                            # Log the move
+                            $normalizedOriginal = [System.IO.Path]::GetFullPath($originalPath)
+                            $normalizedNew = [System.IO.Path]::GetFullPath($targetPath)
+                            $null = $flatColorsMoveLog.Add([PSCustomObject]@{
+                                OriginalPath = $normalizedOriginal
+                                NewPath = $normalizedNew
+                                Type = "moved"
+                            })
+                        } catch {
+                            Write-Warning "  ${colorCode}: Failed to move: $($_.Exception.Message)"
+                        }
+                    }
+                }
+            }
+            
+            # Delete duplicate files (all files in the group except the target)
+            foreach ($file in $files) {
+                if ($file.FullName -ne $targetPath -and (Test-Path -Path $file.FullName)) {
+                    try {
+                        $originalPath = $file.FullName
+                        Remove-Item -Path $originalPath -Force
+                        $flatColorsDuplicates++
+                        
+                        # Log the deletion
+                        $normalizedOriginal = [System.IO.Path]::GetFullPath($originalPath)
+                        $normalizedReplacement = [System.IO.Path]::GetFullPath($targetPath)
+                        $null = $flatColorsMoveLog.Add([PSCustomObject]@{
+                            OriginalPath = $normalizedOriginal
+                            ReplacedBy = $normalizedReplacement
+                            Type = "deleted"
+                        })
+                    } catch {
+                        Write-Warning "  Failed to delete duplicate: $($file.FullName) - $($_.Exception.Message)"
+                    }
+                }
             }
         }
         
-        Write-Host "Moved $flatColorsMoved unique FlatColors file(s) to \common\FlatColors, deleted $flatColorsDuplicates duplicate(s)" -ForegroundColor Green
+        Write-Host "Processed FlatColors: $flatColorsMoved moved, $flatColorsConverted converted, $flatColorsResized resized, $flatColorsDuplicates duplicate(s) deleted" -ForegroundColor Green
     } else {
         Write-Host "No FlatColors files found to process." -ForegroundColor Gray
     }
@@ -533,6 +778,7 @@ if ($null -ne $flatColorsMoveLog -and $flatColorsMoveLog.Count -gt 0) {
 $blendFileParentDir = Split-Path -Path $textureFolderPath -Parent
 
 # Find matching blend files
+# Match logic: blendfile folder name (e.g., "Beth") should appear in blend file name (e.g., "AM_Beth_v3.2.blend")
 $blendFileMappings = @()
 if ($null -ne $blendfileFolders -and $blendfileFolders.Count -gt 0) {
     # Get blendfile folder names
@@ -543,20 +789,20 @@ if ($null -ne $blendfileFolders -and $blendfileFolders.Count -gt 0) {
     
     if ($null -ne $blendFiles -and $blendFiles.Count -gt 0) {
         foreach ($blendFile in $blendFiles) {
-            # Extract prefix from blend file name (e.g., "Chan_v4.3.blend" -> "Chan")
             $blendFileName = $blendFile.BaseName
-            $parts = $blendFileName.Split('_', 2)
             
-            if ($parts.Length -ge 1) {
+            # Check if any blendfile folder name appears in the blend file name
-                $prefix = $parts[0]
+            foreach ($folderName in $blendfileFolderNames) {
-                
+                # Match folder name when surrounded by underscores, dots, hyphens, or at start/end
-                # Check if prefix matches any blendfile folder name
+                # This avoids partial matches (e.g., "Beth" in "Bethany") while allowing "Beth" in "AM_Beth_v3.2"
-                if ($blendfileFolderNames -contains $prefix) {
+                $escapedFolderName = [regex]::Escape($folderName)
+                if ($blendFileName -match "(^|[._-])$escapedFolderName([._-]|$)") {
                     $blendFileMappings += [PSCustomObject]@{
                         BlendFile = [System.IO.Path]::GetFullPath($blendFile.FullName)
-                        BlendfileFolder = $prefix
+                        BlendfileFolder = $folderName
                     }
-                    Write-Host "Found matching blend file: $($blendFile.Name) -> $prefix" -ForegroundColor Gray
+                    Write-Host "Found matching blend file: $($blendFile.Name) -> $folderName" -ForegroundColor Gray
+                    break  # Only match once per blend file
                 }
             }
         }

zip_sequences.py

@@ -521,6 +521,9 @@ def iter_sequence_files(seq_dir: Path) -> Iterator[Path]:
         if is_archive_path(path):
             continue
         for filename in filenames:
+            # Ignore Thumbs.db files completely
+            if filename.lower() == "thumbs.db":
+                continue
             yield path / filename
 
 
@@ -563,6 +566,12 @@ def load_state(state_path: Path) -> dict | None:
         return None
     try:
         state = json.loads(state_path.read_text())
+        # Remove Thumbs.db entries from loaded state
+        if "files" in state:
+            state["files"] = [
+                entry for entry in state.get("files", [])
+                if Path(entry.get("path", "")).name.lower() != "thumbs.db"
+            ]
         # Normalize timestamps in loaded state to ensure consistency
         # This handles state files created before normalization was added
         is_windows = platform.system() == "Windows"
@@ -587,9 +596,12 @@ def state_changed(seq_state: dict, stored_state: dict | None, *, verbose: bool =
     is_windows = platform.system() == "Windows"
     
     def normalize_state(state: dict) -> dict:
-        """Normalize timestamps in state to filesystem precision."""
+        """Normalize timestamps in state to filesystem precision and filter out Thumbs.db."""
         normalized = {"files": []}
         for entry in state.get("files", []):
+            # Ignore Thumbs.db files in state comparison
+            if Path(entry.get("path", "")).name.lower() == "thumbs.db":
+                continue
             mtime_ns = entry["mtime_ns"]
             if is_windows:
                 mtime_ns = (mtime_ns // 100) * 100
@@ -600,7 +612,7 @@ def state_changed(seq_state: dict, stored_state: dict | None, *, verbose: bool =
             })
         return normalized
     
-    # Compare normalized states
+    # Compare normalized states (Thumbs.db already filtered out)
     normalized_seq = normalize_state(seq_state)
     normalized_stored = normalize_state(stored_state)
     
@@ -1017,21 +1029,35 @@ def run_zip(requested_workers: int | None, *, verbose: bool) -> int:
             # If .7z archive exists and we have stored state, do quick check before computing full state
             if zip_path.exists() and stored_state is not None:
                 # Quick check: if directory mtime is older than archive, likely unchanged
+                # But first verify that all files in stored state still exist (catches deletions)
                 try:
-                    dir_mtime = seq_dir.stat().st_mtime_ns
+                    # Quick check: verify stored files still exist (catches file deletions)
-                    archive_mtime = zip_path.stat().st_mtime_ns
+                    stored_files_exist = True
-                    # If directory wasn't modified since archive was created, skip state computation
+                    for entry in stored_state.get("files", []):
-                    if dir_mtime <= archive_mtime:
+                        # Skip Thumbs.db entries (they're filtered out anyway)
-                        quick_skipped += 1
+                        if Path(entry.get("path", "")).name.lower() == "thumbs.db":
-                        if quick_skipped <= 5:
+                            continue
-                            log("scan", f"Skipping {rel} (unchanged since archive)")
+                        file_path = seq_dir / entry["path"]
-                        # Still need to check for old .zip cleanup (we have .7z, so .zip is obsolete)
+                        if not file_path.exists():
-                        if old_zip_path and old_zip_path.exists():
+                            stored_files_exist = False
-                            old_zip_path.unlink(missing_ok=True)
+                            break
-                            old_state_path = state_path_for(old_zip_path)
+                    
-                            if old_state_path.exists():
+                    # Only do mtime check if all stored files still exist
-                                old_state_path.unlink(missing_ok=True)
+                    if stored_files_exist:
-                        continue
+                        dir_mtime = seq_dir.stat().st_mtime_ns
+                        archive_mtime = zip_path.stat().st_mtime_ns
+                        # If directory wasn't modified since archive was created, skip state computation
+                        if dir_mtime <= archive_mtime:
+                            quick_skipped += 1
+                            if quick_skipped <= 5:
+                                log("scan", f"Skipping {rel} (unchanged since archive)")
+                            # Still need to check for old .zip cleanup (we have .7z, so .zip is obsolete)
+                            if old_zip_path and old_zip_path.exists():
+                                old_zip_path.unlink(missing_ok=True)
+                                old_state_path = state_path_for(old_zip_path)
+                                if old_state_path.exists():
+                                    old_state_path.unlink(missing_ok=True)
+                            continue
                 except OSError:
                     # If stat fails, fall through to full state computation
                     pass