Skip to content

fix: allow ollama input limit override#7281

Merged
jh-block merged 2 commits intoblock:mainfrom
fresh3nough:fix/7264-input-prompt-limit
Feb 18, 2026
Merged

fix: allow ollama input limit override#7281
jh-block merged 2 commits intoblock:mainfrom
fresh3nough:fix/7264-input-prompt-limit

Conversation

@fresh3nough
Copy link
Contributor

@fresh3nough fresh3nough commented Feb 17, 2026

Summary

  • Add GOOSE_INPUT_LIMIT support for ollama requests (maps to options.num_ctx) with fallback to model context limit.
  • Add tests for input limit resolution and document the new env var.
  • Repro:
    1. Start ollama with a model that supports larger contexts (for example, qwen3-coder).
    2. Set GOOSE_INPUT_LIMIT=32000 and start goose with ollama.
    3. Send a prompt longer than 4096 tokens/characters and confirm ollama no longer logs input prompt truncation.

Type of Change

  • Feature
  • Bug fix
  • Refactor / Code quality
  • Performance improvement
  • Documentation
  • Tests
  • Security fix
  • Build / Release
  • Other (specify below)

AI Assistance

  • This PR was created or reviewed with AI assistance

Testing

Related Issues

Relates to #7264
Discussion: N/A

Screenshots/Demos (for UX changes)

Before:

After:

@fresh3nough fresh3nough requested a review from a team as a code owner February 17, 2026 22:18
@DOsinga
Copy link
Collaborator

DOsinga commented Feb 18, 2026

we should split the documentation off since we don't want to push that until it is actually there

fresh3nough and others added 2 commits February 18, 2026 11:52
Co-Authored-By: Warp <agent@warp.dev>
Signed-off-by: anonwurcod <anonwurcod@proton.me>
@jh-block jh-block force-pushed the fix/7264-input-prompt-limit branch from e2bf493 to c15f92d Compare February 18, 2026 10:52
@jh-block
Copy link
Collaborator

Split documentation changes out to #7299. This PR now contains only the code changes (ollama.rs).

Copy link
Collaborator

@jh-block jh-block left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Nice improvement to ollama usability! Docs split out to #7299

@jh-block jh-block enabled auto-merge February 18, 2026 10:55
@jh-block jh-block added this pull request to the merge queue Feb 18, 2026
Merged via the queue into block:main with commit 9d3792f Feb 18, 2026
20 checks passed
jh-block added a commit that referenced this pull request Feb 18, 2026
* origin/main:
  fix: allow ollama input limit override (#7281)
@fresh3nough
Copy link
Contributor Author

ty

aharvard added a commit that referenced this pull request Feb 18, 2026
* origin/main:
  feat: add GOOSE_SUBAGENT_MODEL and GOOSE_SUBAGENT_PROVIDER config options (#7277)
  fix(openai): support "reasoning" field alias in streaming deltas (#7294)
  fix(ui): revert app-driven iframe width and send containerDimensions per ext-apps spec (#7300)
  New OpenAI event (#7301)
  ci: add fork guards to scheduled workflows (#7292)
  fix: allow ollama input limit override (#7281)
  chore: show important keys for provider configuration (#7265)
  fix: subrecipe relative path with summon (#7295)
  fix extension selector not displaying the correct enabled extensions (#7290)
  Use the working dir from the session (#7285)
  Fix: Minor logging uplift for debugging of prompt injection mitigation (#7195)
  feat(otel): make otel logging level configurable (#7271)
  docs: add documentation for Top Of Mind extension (#7283)
  Document gemini 3 thinking levels (#7282)
  docs: stream subagent tool calls (#7280)
  Docs: delete custom provider in desktop (#7279)

# Conflicts:
#	ui/desktop/src/components/McpApps/McpAppRenderer.tsx
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants

Comments