Skip to content

docs(threat-model): a question's tool picks and limit, version ids, and the export's PDF - #554

Merged
adeelahmad merged 1 commit into
mainfrom
claude/project-thread-r960xc-c9-labels
Oct 18, 2026
Merged

adeelahmad merged 1 commit into
mainfrom
claude/project-thread-r960xc-c9-labels

Conversation

@adeelahmad

Copy link
Copy Markdown
Owner

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:

  • The chat row names a conversation's or question's picks (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 to ai.max_tool_calls. A message id outside the conversation is a 404.
  • P-RETRIEVAL says a question's tool-call limit can take the loop past ai.max_steps, up to ai.max_tool_calls (chat.tool_answer).
  • The export row says the PDF prints its Markdown as HTML cleaned of anything that could fetch or run (convert.clean_html), by the converters documents use.

The YAML and JSON companions match; ci/validate_threat_model.py passes.

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.md labels are left to #536, which covers them.

Types of changes

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to change; ! in the title)

Docs only.

Checklist:

  • The title is a Conventional Commit.
  • My code follows the code style of this project (make hooks checks it on commit).
  • I added or updated tests: n/a, docs only.
  • My change requires documentation updates, and I have updated docs/ accordingly: the threat model and its companions.
  • Users need more than the title to understand it: n/a.

Done questions (AGENTS.md)

  • Goal: delivers what the user wanted, merged on green CI. Not merged yet.
  • Agents: n/a, docs only.
  • Zero setup: n/a.
  • Fewest clicks and keystrokes: n/a.
  • Configurable: n/a.
  • Light: n/a.
  • Private and secure: the threat model now covers these inputs and the export's printing.
  • Cost: n/a.
  • User decides: n/a.
  • Upgrades: n/a, no stored data.
  • Honest: each line was checked against the code (routes/chats.py, domain/chat.py, domain/chat_export.py).
  • Tests, docs and generated files updated: ci/validate_threat_model.py passes.
  • Open standards; dependencies keep Lens MIT: n/a.
  • Result reported with evidence; "refine later" items written down: n/a.
  • Reuse: n/a.

Generated by Claude Code

…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
@adeelahmad
adeelahmad merged commit da7f6a4 into main Oct 18, 2026
10 checks passed
@adeelahmad
adeelahmad deleted the claude/project-thread-r960xc-c9-labels branch October 18, 2026 06:19
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants