Repository navigation
docs(threat-model): a question's tool picks and limit, version ids, and the export's PDF - #554
Merged
Merged
Conversation
…nd the export's PDF The chat row names a conversation's or question's picks (tools, max_tool_calls, scope) and the message ids a version names, with what keeps them in bounds. P-RETRIEVAL says a question's tool-call limit can take the loop past ai.max_steps, up to ai.max_tool_calls. The export row says its PDF prints HTML cleaned of anything that could fetch or run. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Requested by Adeel · project thread
Description
Before: the threat model's chat input row named only prompt text and the model's tool calls, P-RETRIEVAL said the tool loop always stops at
ai.max_steps, and the export row didn't say how its PDF is printed.After:
tools,max_tool_calls,scope) and the message ids a version names (regenerate,edit,parent,PUT /chats/{cid}/head). Picks only narrow: a tool not offered isn't run, admin switches win, a scope naming a namespace the person can't read is a 404, and a limit is a whole number up toai.max_tool_calls. A message id outside the conversation is a 404.ai.max_steps, up toai.max_tool_calls(chat.tool_answer).convert.clean_html), by the converters documents use.The YAML and JSON companions match;
ci/validate_threat_model.pypasses.Motivation and Context
Chat-app gaps, C9: a threat model consistency pass over the chat features (C1 versions, C2 export, C3 tool choice). README and
docs/requirements.mdlabels are left to #536, which covers them.Types of changes
!in the title)Docs only.
Checklist:
make hookschecks it on commit).docs/accordingly: the threat model and its companions.Done questions (AGENTS.md)
routes/chats.py,domain/chat.py,domain/chat_export.py).ci/validate_threat_model.pypasses.Generated by Claude Code