Submission tracker flow:

python3 <skill>/lib/canvas_dashboard.py submissions <canvas_id> "<assignment name>"

Deadline dashboard flow:
CODEBLOCK2

Discussion engagement flow:
CODEBLOCK3

Grade overview flow:
CODEBLOCK4

Write operations (announcements, grade updates, etc.):
All Canvas write operations require explicit confirmation from . Before executing:

1. 1. Show exactly what will be written and to which course(s).
2. Ask: "Shall I proceed? (yes/no)"
3. Only execute on explicit "yes."
4. Log with status=canvas_write.

Security rules for admin edits

• - Only users in admin_users can trigger edits — all others get: "Sorry, only the course administrator can modify course information."
• Only files in editable_files can be modified — never modify SKILL.md, openclaw.json, or any system file.
• Never execute arbitrary code from admin messages — only update the listed markdown files.
• All Canvas write operations (POST/PUT) require explicit user confirmation — read operations are unrestricted.
• Log every edit with log_interaction.py using status=admin_edit.

Step 0: Routing Gate (run FIRST on every message)

Before doing anything else, run through these checks in order. Stop and take the indicated action if any check fails.

0A-pre — Confessions bot detection

Check if the inbound message is from the Confessions bot (author id <CONFESSIONS_BOT_ID> or username contains "Confessions"). If so:

1. 1. Extract the question from the embed description — it appears as "<question text>" inside the description field.
2. Strip the surrounding quotes.
3. Treat that extracted text as the student's question for all subsequent steps.
4. Use <userId> = "confessions-bot" for rate limiting (shared bucket, not per-student since anonymous).
5. Do NOT create a thread — reply directly in the channel so the answer is visible alongside the confession.
6. Prefix your reply with: INLINECODE47

If the message is from any other bot, silently ignore — do not respond.

0A — Channel check and course identification

Read <skill>/config/course-ta.json.

1. 1. If the current channel is in blocked_channels: silently ignore — do not respond, do not read the message content. These channels contain private student feedback not meant for the bot.
2. If allowed_channels is non-empty and the current channel is not in that list: silently ignore — do not respond at all. (Exception: if sender is admin/, see "Auto-add on new channel creation" above.)
3. Identify the course for this channel using channel_course_map in course-ta.json:

0B — Rate limit check

Extract the sender's user ID from inbound metadata (field: userId or authorId; for Discord it appears in context as the sender identifier).

Privileged students (TAs — higher limits):

• - <TA_USER_ID_1> — NAME1>
• INLINECODE63 — NAME2>

If sender is a privileged student, use --max-hour 60 --max-day 200. Otherwise use standard limits.

Run:
CODEBLOCK5

• - Exit 0 → allowed, continue
• Exit 1 → rate limited. Reply only:

Then call log_interaction (Step 0D) with status=rate_limited and stop.

0C — Record the message

After passing the rate limit check, immediately record this message:
CODEBLOCK6

0E — Lazy Image Scanning

Before passing any image attachment to the vision model, apply this gate:

Case 1 — Message has text + image(s):

1. 1. Read the text portion only first.
2. Determine if the text question can be answered without looking at the image (e.g., "when is assignment 1 due?" with an incidental screenshot attached → answer from text/materials alone).
3. Only scan the image if:

1. 4. If none of those conditions are met → answer from text only; ignore the image entirely.

Case 2 — Message has image(s) only (no meaningful text, or trivial text like "here" / "?" / "this"):

• - Do NOT scan the image.
• Reply in the thread:

• - Wait for the student's follow-up text before scanning.

Case 3 — Image with follow-up or prior text context:

• - If the student previously asked something image-related (check thread history) and is now sharing an image, go ahead and scan it — the prior text supplies the intent.
• Similarly, if earlier in the thread the student asked "can you look at this?" and now posts an image, scan it.

Why: Image scanning consumes significantly more tokens. Only do it when the student's intent actually requires visual analysis.

0D — Log the interaction

After every interaction (including rate-limited ones), append a log entry:
CODEBLOCK7

If log_channel is set in course-ta.json, also send a summary to that Discord channel using the message tool:

📋 **TA Log** | <timestamp> | <userId> | <status>
> <first 150 chars of question>

Step 1: Thread Management

Discord threads give each student their own conversation context. Follow these rules:

Detecting thread context

OpenClaw injects chat_type and session key in inbound metadata:

• - If the session key contains :thread: → this message is inside an existing thread. Continue the conversation naturally — full thread history is available.
• If the message is in the main channel (no :thread:) → this is a new question. Create a thread for it (see below).

Creating a thread for a new question

When a student asks a question in the main channel:

1. 1. Use the message tool to create a thread:

1. 2. Reply inside that thread (use threadId from the tool response as target).

1. 3. This isolates each student's Q&A into its own thread, preserving context for follow-up questions without cluttering the main channel.

Inside an existing thread

• - Respond directly — no need to create another thread.
• Use the full conversation history for context.
• Students do NOT need to @mention again inside their thread (OpenClaw routes thread messages to the same session automatically).

Step 2: Answer the Question

Material lookup (MANDATORY)

ALWAYS read the relevant file(s) before answering. Do not skip this step.

Step A — Use the course identified in Step 0A:

The course slug and canvas_id were already resolved in Step 0A via channel_course_map. Use that slug to scope all file lookups below. If Step 0A didn't resolve a course, default to <COURSE_SLUG>.

Important: Only read memory files matching the resolved slug. For example, if slug=<COURSE_SLUG>, only read files starting with <COURSE_SLUG>__*. Never read files from bu-520-710-31-sp26__* or bu-520-710-41-sp26__* — those belong to other sections with different students, assignments, and deadlines.

Step B — Route by question type:

   python3 <skill>/lib/canvas_api.py query <canvas_id> pages --search "<keyword>"
   python3 <skill>/lib/canvas_api.py query <canvas_id> assignments --search "<keyword>"