S10.3: Time-locked sessions

Open
  • Is something wrong?
#154 0 comments 0 reactions 0 assignees View on GitHub

Maintainers usually reply within 1 day

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
55/100
Issue type
Feature
Clarity
Mostly clear
Activity status
Active
Tech stack
python
Domain
ai, backend

Research direction

Start by reading the parent epic #103, dependency #153, and the roadmap; then locate the session context and tool layer described by the tasks. Trace how sessions make tool calls and where those calls request market data. Add a maximum knowledge time, refuse later data requests with an explanation, log the lock, and verify the June 5, 2020 session cannot fetch June 6 prices.

Written by the indexing model from the issue text.

Description

area: ai priority: P1 story

Roadmap story S10.3 · Project · Roadmap

Parent epic: E10 #103

Dependencies: S10.2 #153

Priority: P1 · Size: M · Sprint: 8 · Milestone: M7 · Area: ai · Depends on: S10.2 · Reqs: FR-AI10 · Status: Backlog

Story: As a researcher, I want to lock a conversation to a moment in history, so that the assistant can't look past it, even by accident.

Acceptance criteria

  • A session can set a maximum knowledge time, and tool calls asking for later data are refused with an explanation.
  • The lock is logged.
  • Test: a session locked to June 5, 2020, can't fetch June 6 prices.

Tasks

  • Add the session context
  • Enforce the lock in the tool layer
  • Write the tests

Progress evidence (2026-11-08): No implementation or completion evidence for these acceptance criteria is present in the audited commit. This remains planned work.

Audited against committed main at 0c32c57. Local, staged, and untracked work is excluded.

Dominant language
Python
Stars
0
Forks
0
Avg merge
3h 33m
Merged PRs (30d)
50

Getting set up

  • No Dockerfile or Docker Compose file
  • Has a pull request template
  • No contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from nfiasco/Quant-Time-Machine

All issues in nfiasco/Quant-Time-Machine

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.