fix(hermes): honor Ollama context floor#6767
Open
HwangJohn wants to merge 2 commits into
Open
Conversation
Contributor
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Enterprise Run ID: 📒 Files selected for processing (10)
🚧 Files skipped from review as they are similar to previous changes (10)
📝 WalkthroughWalkthroughHermes now requires a minimum 64,000-token context window. Local Ollama detection, onboarding state, daemon startup, systemd overrides, model selection, configuration generation, tests, and documentation enforce and propagate this floor. ChangesHermes validation and documentation
Ollama onboarding propagation
Estimated code review effort: 3 (Moderate) | ~25 minutes Sequence Diagram(s)sequenceDiagram
participant SetupNim
participant OllamaSelection
participant OllamaSystemd
participant OllamaRuntime
SetupNim->>OllamaSelection: provide agent context floor
OllamaSelection->>OllamaSystemd: configure contextWindowFloor
OllamaSelection->>OllamaRuntime: apply runtime context floor
OllamaSystemd->>OllamaRuntime: resolve and write Ollama context length
Possibly related PRs
Suggested labels: Suggested reviewers: 🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
Contributor
E2E Advisor RecommendationRequired E2E: Dispatch hint: Full advisor summaryE2E Recommendation AdvisorBase: Required E2E
Optional E2E
New E2E recommendations
Dispatch hint
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@docs/reference/troubleshooting.mdx`:
- Line 2419: Update the adjacent shared troubleshooting commands by splitting
them into agent-specific <AgentOnly> blocks: retain OLLAMA_CONTEXT_LENGTH=16384
for OpenClaw and use OLLAMA_CONTEXT_LENGTH=64000 for Hermes. Keep each command’s
existing behavior and agent-specific context unchanged.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Enterprise
Run ID: efa5bc21-d1b6-4a63-b484-1fcf11b88629
📒 Files selected for processing (20)
agents/hermes/config/build-env.tsdocs/inference/configure-model-limits.mdxdocs/inference/set-up-ollama.mdxdocs/reference/troubleshooting.mdxsrc/lib/inference/local.tssrc/lib/inference/ollama-runtime-context.test.tssrc/lib/inference/ollama-runtime-context.tssrc/lib/onboard.tssrc/lib/onboard/install-ollama-linux.test.tssrc/lib/onboard/install-ollama-linux.tssrc/lib/onboard/install-ollama-macos.test.tssrc/lib/onboard/install-ollama-macos.tssrc/lib/onboard/ollama-systemd.test.tssrc/lib/onboard/ollama-systemd.tssrc/lib/onboard/setup-nim-flow.test.tssrc/lib/onboard/setup-nim-flow.tssrc/lib/onboard/setup-nim-ollama.test.tssrc/lib/onboard/setup-nim-ollama.tssrc/lib/onboard/setup-nim-selection.tstest/generate-hermes-config.test.ts
HwangJohn
force-pushed
the
codex/6760-hermes-ollama-context
branch
from
9d2dca1 to
9c7952b
Compare
Signed-off-by: HwangJohn <angelic805@gmail.com>
HwangJohn
force-pushed
the
codex/6760-hermes-ollama-context
branch
from
9c7952b to
24a97b8
Compare
Contributor
|
Caution Failed to replace (edit) comment. This is likely due to insufficient permissions or the comment being deleted. Error details |
wscurran
added
area: local-models
Contributor
|
✨ Thanks for the fix, @HwangJohn. Honoring the Hermes Ollama context floor should prevent the silent inference failure after onboarding reports Ready. Ready for maintainer review. Related open issues: Related open issues: |
Signed-off-by: HwangJohn <angelic805@gmail.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
NemoHermes Local Ollama onboarding now carries Hermes Agent's 64000-token context floor through daemon setup, model validation, and generated Hermes config. OpenClaw keeps the existing 16384-token Ollama floor, while explicit Hermes
NEMOCLAW_CONTEXT_WINDOWvalues below 64000 fail config generation instead of producing a sandbox that fails on first inference.Related Issue
Fixes #6760
Changes
NEMOCLAW_CONTEXT_WINDOWvalues below 64000 in config generation.Type of Change
Quality Gates
Verification
Verifiedin GitHubpre-commit,commit-msg, andpre-pushhooks passed, ornpm run check:diffpassed when hooks were skipped or unavailable — local Windows note:npm run check:diffreaches repository checks but the existing runner hits Windows-onlyspawnSync("tsx.cmd")and executable-bit limitations; manual equivalent repository checks,npx commitlint --from origin/main --to HEAD, andnpx prek run --from-ref origin/main --to-ref HEAD --stage pre-pushpassed.src/lib/inference/ollama-runtime-context.test.ts,src/lib/onboard/ollama-systemd.test.ts,src/lib/onboard/setup-nim-flow.test.ts,src/lib/onboard/setup-nim-ollama.test.ts,src/lib/onboard/install-ollama-macos.test.ts,src/lib/onboard/install-ollama-linux.test.ts, andtest/generate-hermes-config.test.tswith the new [All Platforms][Onboard] NemoHermes Ollama onboard reports Ready but hermes inference fails: Ollama context 16384 below Hermes 64K minimum #6760 cases selected.npm testfor broad runtime/test-harness changes;npm run checkfor repo-wide validation/coverage changes — command/result:npm run docsbuilds without warnings (doc changes only) — local Windows note:npm run docs:check-agent-variants,npm run docs:check-routes, and PowerShell-equivalent Fern check passed with 0 errors; fullnpm run docsdoes not complete under Windows PowerShell because the existing script uses POSIXFERN_VERSION=$(...)syntax.Signed-off-by: HwangJohn angelic805@gmail.com
Summary by CodeRabbit