Lazy version detection and startup overhead reduction

NousResearch/hermes-agent · cluster 3338 · agent

Data as of

Nothing open on GitHub. Fix merged in #3395. Check it covers your case.

The short answer

0open issues
0open PRs
5items grouped
Known?
Yes. 5 related items grouped here, 2 issues already closed.
Fix event
A fix was merged to main in PR #3395. Check it covers your case. No release data is tracked.
Tracker
The maintainers' tracker marks this unresolved. That is separate from the fix event.
Still open
Nothing open on GitHub.

A set of related efforts to improve time-to-first-token (TTFT) by deferring Claude Code version detection and reducing pre-request startup costs. Includes superseded and successor iterations of the same optimization approach.

Open issues0

No open issues.

Open PRs0

No open pull requests.

Fixes on record

Merged to main. A stamp counts the issues a fix is linked to.

  • #3395 perf(ttft): salvage easy-win startup optimizations from #3346

    merged to main

    files: agent/anthropic_adapter.py, agent/auxiliary_client.py, run_agent.py, tests/agent/test_auxiliary_client.py, tests/test_run_agent.py, tests/tools/test_registry.py, tools/registry.py

2 PRs closed without merging

From the close comments: merged via another change 1 · superseded by another PR 1

  • #3345 perf(ttft): reduce pre-request startup overhead · superseded by another PR → #3361, #3348, #3362, #3349, #3363, #3350, #3364, #3351, #3365, #3353, #3366, #3352, #3354, #3367, #3355
  • #3363 perf(ttft): make Claude Code version detection lazy · merged via another change → #3395
Closed issues · 2
  • Closed#3338[superseded] perf(ttft): make Anthropic Claude Code version detection lazy
  • Closed#3350perf(ttft): make Anthropic Claude Code version detection lazy
How this cluster was grouped
  • Link evidence (partly structural links): some members are connected by structural evidence (shared changed files, or a closing/superseded reference); the rest are joined by an automated relevance judgement over their text.
  • Members outside that structural core may belong to a different underlying problem.
  • Pairwise link density 0.34: the share of item pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36. 1.00 means every pair is linked.

Pick up a Lab task

Check whether a fix covers the open issues here, with your own agent. Bring back evidence for maintainers.

Open the Lab

At a glance

Subsystem
agent
Merged PRs
#3395
Closed issues
2
Attempts
2 PRs closed without merging
Fix link checked
27 Mar 2026. This confirmation is old and may be out of date (a revert or reopen would not have invalidated it here); re-verify.

For your agent

The same facts, typed.