Cairn
NousResearch/hermes-agent

Reasoning model token budget and output limit issues

Cluster 9571 · agent. Data as of

Nothing open on GitHub. Fix merged in #14273 on 23 Apr 2026. Check it covers your case.

The short answer

0open issues
0open PRs
4items grouped
Known?
Yes. 4 related items grouped here, 1 issue already closed.
Fix event
A fix was merged to main in PR #14273. Check it covers your case. No release data is tracked.
Tracker
The maintainers' tracker marks this resolved, deciding PR #14273. That is separate from the fix event.
Still open
Nothing open on GitHub.

These issues and PRs concern problems where reasoning/thinking models exhaust their output token budgets, producing empty or truncated responses, incomplete title generation, and related adjustments to max_tokens defaults and retry behavior.

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.

  • #14273 fix(title): bump title_generator max_tokens to 500 for reasoning-model headroom (salvage #9606)

    merged to main

    files: agent/title_generator.py, scripts/release.py

    Show the diff
    • agent/title_generator.py
      @@ -38,7 +38,7 @@ def generate_title(user_message: str, assistant_response: str, timeout: float =
         response = call_llm(
             task="title_generation",
             messages=messages,
-            max_tokens=30,
+            max_tokens=500,
             temperature=0.3,
             timeout=timeout,
         )
    • scripts/release.py
      @@ -371,6 +371,7 @@
     "[redacted:email]": "projectadmin-dev",
     "[redacted:email]": "Dev-Mriganka",
     "[email protected]": "shushuzn",
+    "[redacted:email]": "iborazzi",
 }

2 PRs closed without merging

From the close comments: done elsewhere 1 · superseded by another PR 1

  • #9583 fix(agent): #9571 increase max_tokens in title generation to support … · done elsewhere → f41031a, #14273, #9571
  • #9606 fix(agent): increase max_tokens for title generation to support reasoning models #9571 · superseded by another PR → #14273
Closed issues · 1
  • Closed#9571[Bug]: Fail to generate short descriptive title. Model: GLM 5.1.
How this cluster was grouped
  • Link evidence (structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.
  • Pairwise link density 0.50: 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
#14273
Closed issues
1
Attempts
2 PRs closed without merging
Fix link checked
23 Apr 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.

cluster/9571.json
cluster/9571.md