Add llm-perplexity-agent to the plugin directory - #1570
Open
zalez wants to merge 1 commit into
Open
Conversation
Provides the perplexity-agent model, wrapping Perplexity's Agent API. Placed next to llm-perplexity since the two cover different Perplexity endpoints and the adjacency makes the distinction visible.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds one line to
docs/plugins/directory.mdfor llm-perplexity-agent, which provides aperplexity-agentmodel.llm install llm-perplexity-agent llm -m perplexity-agent 'What changed in MCP 2026-07-28?'Why a second Perplexity plugin
It is complementary to
llm-perplexity, not a replacement, and I placed it directly after that entry so the distinction is visible from adjacency.llm-perplexitywraps Perplexity's Sonar chat models —sonar,sonar-pro,sonar-deep-research,sonar-reasoning-pro. This wraps their Agent API (POST /v1/agent), a different endpoint: a multi-step agent that runs its own searches, fetches pages and synthesises one cited answer.There is no model-name overlap, and both use the same
perplexitykey alias, so having both installed works with no extra configuration — which is how I run them.Options
presetselects research depth and is passed through unvalidated, since Perplexity's schema declares no enum for it. Poll progress goes to stderr so the answer still pipes cleanly.Published on PyPI as
llm-perplexity-agent. BSD-3-Clause. Tested against Python 3.10–3.14.