NousResearch/hermes-agent

Reasoning effort clamping fixes across vendors

Cluster 69855 · agent. Data as of

1 open item. Fix merged in #90350 on 20 Aug 2026. Check it covers your case.

The short answer

1open issue
0open PRs
4items grouped
Known?
Yes. 4 related items grouped here, 0 issues already closed.
Fix event
A fix was merged to main in PR #90350. 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
1 issue and 0 PRs.

These items address bugs and refactoring around reasoning effort values (e.g. 'ultra') causing errors or incorrect behavior on non-Anthropic and GLM model wires. A refactor consolidates vendor-specific effort clamping into a single canonical ladder to prevent future drift.

Open issues1

  • Issue#69855did a branch, failed

Open PRs0

No open pull requests.

Fixes on record

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

  • #90330 fix: reasoning effort 'ultra' no longer 400s on non-Anthropic wires (#89503 class, salvage #89509)

    merged to main

    files: agent/auxiliary_client.py, agent/transports/chat_completions.py, agent/transports/codex.py, plugins/model-providers/copilot/__init__.py, plugins/model-providers/custom/__init__.py, tests/agent/test_reasoning_effort_wire_translation.py, tests/agent/transports/test_reasoning_effort_sibling_sites.py

  • #90350 refactor: reasoning-effort clamps can no longer drift per vendor — one canonical ladder + declared wire vocabularies

    merged to main

    files: agent/auxiliary_client.py, agent/reasoning_effort.py, agent/transports/chat_completions.py, agent/transports/codex.py, hermes_cli/models.py, plugins/model-providers/custom/__init__.py, plugins/model-providers/deepseek/__init__.py, plugins/model-providers/kimi-coding/__init__.py, plugins/model-providers/meta-ai/__init__.py, plugins/model-providers/ollama-cloud/__init__.py, plugins/model-providers/opencode-zen/__init__.py, plugins/model-providers/upstage/__init__.py, plugins/model-providers/zai/__init__.py, tests/agent/test_reasoning_effort_module.py, tests/plugins/model_providers/test_ollama_cloud_profile.py, tests/plugins/model_providers/test_opencode_go_profile.py

1 PR closed without merging

From the close comments: done elsewhere 1

  • #69917 fix(agent): clamp GLM-5.2 ultra reasoning effort · done elsewhere → #90330, #90350
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
#90330, #90350
Closed issues
0
Attempts
1 PR closed without merging
Fix link checked
20 Aug 2026

For your agent

The same facts, typed.