ed/manual_slop
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

wip better file support and word wrap

Browse Source
This commit is contained in:
Edward R. Gonzalez
2026-02-21 21:16:50 -05:00
parent d9a51332ef
commit 0a591d58eb
4 changed files with 105 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
manual_slop.toml
View File

@@ -26,7 +26,9 @@ paths = [
[screenshots]
base_dir = "C:/Users/Ed/scoop/apps/sharex/current/ShareX/Screenshots/2026-02"
paths = []
paths = [
"C:/Users/Ed/scoop/apps/sharex/current/ShareX/Screenshots/2026-02/Fork_2026-02-21_21-10-30.png",
]
[discussion]
roles = [
@@ -39,7 +41,7 @@ active = "Support files or mcp, or proper dynamic context uptake."
[discussion.discussions.main]
git_commit = "3b2da7873f839bf062c06c7539fadd9df7a3e2b9"
last_updated = "2026-02-21T20:59:25"
last_updated = "2026-02-21T21:15:21"
history = [
"User:\nLets add multiple project support. currently this project would be the \"manual_slop\" project. \nI need to make a separate \"manual_slop.toml\" for this and offload things that would be within a per project to it.\nI also want to have several discussion histories that I can label. \nThis would allow me to stash and continue separate effort's histories..\nIt would be important if these discussions saved the last git commit they were on. (I'll need a buton to manually update it).\nAnd timestamps on each discussion entry to give an idea of the duration involved and \nhow the project has evolved since the discussion stream's effort was last done.\nBasically preserve context so ai can use that as valuable information in its working memory.\n\nTo load a project I'll need to hoist it into the config by providing the path.\nMaybe allow multiple project tomls to be specified path wise in the array.",
"User:\nOk your started to work on multiple-project support, you added project_manager.py and manaual_slop.toml, its not being used yet. the rest of the codebase hasn't intergrated with the changes.\nThere might be something wrong with powershell tool use. If you suspect so try to fix that but otherwise lets finish the support for multiple projects.",
@@ -59,6 +61,23 @@ history = [
]
[discussion.discussions."Support files or mcp, or proper dynamic context uptake."]
git_commit = "d9a51332efb3354c81876f9a230bcedd632e7fd2"
last_updated = "2026-02-21T21:16:37"
history = [
"@2026-02-21T21:04:10\nUser:\nLets add support for mcp, files, or proper dynamic context update. \n\nRight now I'm feeding you files in a giant md text message but you seem to still have the habit of just grabbing the file's latest \ncontents again with powershell... Problably because we are not actually using proper file upload or gathering that \nyour used to with anthropic api or an mcp server.",
"@2026-02-21T21:04:48\nAI:\n(Annotation from user, no reponse from ai.)",
"@2026-02-21T21:06:15\nUser:\nSo you were doing script calls and didn't compelete what you were doing, continue.",
"@2026-02-21T21:07:15\nAI:\nThe system prompt didn't get updated — the old and new strings didn't match exactly (likely a quoting issue in the Python script). Let me check and fix that, and also verify the anthropic tool result injection:",
"@2026-02-21T21:09:49\nUser:\nThis time it seems to have actually patched stuff, let me know if your done and I should restart the gui, otherwise keep going its fine.",
"@2026-02-21T21:09:55\nAI:\n(Annotation from user, no reponse from ai. Seems like it did some work I'll take a screencap of latest and send over)",
"@2026-02-21T21:11:31\nAI:\nEverything is done. You can restart the GUI now. Here's a summary of all changes:\n\n**What changed:**\n\n1. **`ai_client.py`** — 3 new functions + modifications to 4 existing functions:\n - `_reread_file_items(file_items)` — re-reads every file from disk, returns fresh list\n - `_build_file_context_text(file_items)` — formats files as markdown code blocks for injection\n - `_ANTHROPIC_SYSTEM` — added instruction telling the AI not to re-read files already in context\n - `send()` — new `file_items` parameter, passed through to provider functions\n - `_send_anthropic()` — after each tool call round, re-reads files and appends a `[FILES UPDATED]` text block to the tool results message\n - `_send_gemini()` — after each tool call round, re-reads files (updates list, though can't inject into Gemini's structured responses)\n - `tool_result_send` comms logging — filters with `r.get(\"type\") == \"tool_result\"` so the injected text block doesn't crash the list comprehension\n\n2. **`gui.py`** — one-line change:\n - `ai_client.send(self.last_md, user_msg, base_dir, self.last_file_items)` — passes file items through\n\n3. **`MainContext.md`** — new \"Dynamic file context refresh\" documentation section",
]
[discussion.discussions."Word Wrap"]
git_commit = ""
last_updated = "2026-02-21T21:02:07"
history = []
last_updated = "2026-02-21T21:15:22"
history = [
"@2026-02-21T21:13:42\nUser:\nLets add support for all heavy text panels.",
"@2026-02-21T21:13:46\nAI:\nThe file is fixed and reading cleanly now. The `gui.py` file has the UTF-8 BOM restored, the em-dash is proper UTF-8 again, and `wrap=0` is in place.\n\n**Summary of what changed:**\n\n- `gui.py` line 80: `wrap=460` → `wrap=0` in `_add_text_field()` — this is the only `dpg.add_text()` call that had a hardcoded pixel wrap width. With `wrap=0`, DearPyGUI wraps the text to the available parent container width dynamically, so it adapts when panels are resized/docked differently.\n\nAll the other text panels (`ai_input`, `ai_response`, `disc_content_*`, tool log results, confirm dialog script) use `dpg.add_input_text(multiline=True, width=-1)` which already wraps to available width automatically.",
"@2026-02-21T21:15:14\nUser:\nI don't see discussion entries wrapping, nor the message box...",
]