feat: activate plugin lifecycle hooks (pre/post_llm_call, session start/end)#2823
Closed
nicoloboschi wants to merge 2 commits into
Closed
feat: activate plugin lifecycle hooks (pre/post_llm_call, session start/end)#2823nicoloboschi wants to merge 2 commits into
nicoloboschi wants to merge 2 commits into
Conversation
…rt/end)
The plugin system defined six lifecycle hooks but only pre_tool_call and
post_tool_call were invoked. This activates the remaining four so that
external plugins (e.g. memory systems) can hook into the conversation
loop without touching core code.
Hook semantics:
- on_session_start: fires once when a new session is created
- pre_llm_call: fires once per turn before the tool-calling loop;
plugins can return {"context": "..."} to inject into the ephemeral
system prompt (not cached, not persisted)
- post_llm_call: fires once per turn after the loop completes, with
user_message and assistant_response for sync/storage
- on_session_end: fires at the end of every run_conversation call
invoke_hook() now returns a list of non-None callback return values,
enabling pre_llm_call context injection while remaining backward
compatible (existing hooks that return None are unaffected).
Pass platform to pre_llm_call and post_llm_call so plugins can tailor behavior per platform (cli, telegram, discord, etc.). Pass conversation_history to post_llm_call so plugins can see tool calls and intermediate messages from the turn, not just the final response text.
teknium1
pushed a commit
that referenced
this pull request
Mar 28, 2026
…rt/end)
The plugin system defined six lifecycle hooks but only pre_tool_call and
post_tool_call were invoked. This activates the remaining four so that
external plugins (e.g. memory systems) can hook into the conversation
loop without touching core code.
Hook semantics:
- on_session_start: fires once when a new session is created
- pre_llm_call: fires once per turn before the tool-calling loop;
plugins can return {"context": "..."} to inject into the ephemeral
system prompt (not cached, not persisted)
- post_llm_call: fires once per turn after the loop completes, with
user_message and assistant_response for sync/storage
- on_session_end: fires at the end of every run_conversation call
invoke_hook() now returns a list of non-None callback return values,
enabling pre_llm_call context injection while remaining backward
compatible (existing hooks that return None are unaffected).
Salvaged from PR #2823.
5 tasks
teknium1
added a commit
that referenced
this pull request
Mar 28, 2026
…rt/end) (#3542) The plugin system defined six lifecycle hooks but only pre_tool_call and post_tool_call were invoked. This activates the remaining four so that external plugins (e.g. memory systems) can hook into the conversation loop without touching core code. Hook semantics: - on_session_start: fires once when a new session is created - pre_llm_call: fires once per turn before the tool-calling loop; plugins can return {"context": "..."} to inject into the ephemeral system prompt (not cached, not persisted) - post_llm_call: fires once per turn after the loop completes, with user_message and assistant_response for sync/storage - on_session_end: fires at the end of every run_conversation call invoke_hook() now returns a list of non-None callback return values, enabling pre_llm_call context injection while remaining backward compatible (existing hooks that return None are unaffected). Salvaged from PR #2823. Co-authored-by: Nicolò Boschi <boschi1997@gmail.com>
Contributor
|
Merged via PR #3542. Your commits were cherry-picked onto current main with authorship preserved. Follow-up additions: conversation_history passed as a shallow copy to prevent plugin mutation, added model/platform to on_session_end for consistency, updated docs to remove (planned) markers. Thanks for the contribution! |
7 tasks
angelburgosrosado
pushed a commit
to angelburgosrosado/hermes-agent
that referenced
this pull request
Apr 27, 2026
…rt/end) (NousResearch#3542) The plugin system defined six lifecycle hooks but only pre_tool_call and post_tool_call were invoked. This activates the remaining four so that external plugins (e.g. memory systems) can hook into the conversation loop without touching core code. Hook semantics: - on_session_start: fires once when a new session is created - pre_llm_call: fires once per turn before the tool-calling loop; plugins can return {"context": "..."} to inject into the ephemeral system prompt (not cached, not persisted) - post_llm_call: fires once per turn after the loop completes, with user_message and assistant_response for sync/storage - on_session_end: fires at the end of every run_conversation call invoke_hook() now returns a list of non-None callback return values, enabling pre_llm_call context injection while remaining backward compatible (existing hooks that return None are unaffected). Salvaged from PR NousResearch#2823. Co-authored-by: Nicolò Boschi <boschi1997@gmail.com>
02356abc
pushed a commit
to 02356abc/hermes-agent
that referenced
this pull request
May 14, 2026
…rt/end) (NousResearch#3542) The plugin system defined six lifecycle hooks but only pre_tool_call and post_tool_call were invoked. This activates the remaining four so that external plugins (e.g. memory systems) can hook into the conversation loop without touching core code. Hook semantics: - on_session_start: fires once when a new session is created - pre_llm_call: fires once per turn before the tool-calling loop; plugins can return {"context": "..."} to inject into the ephemeral system prompt (not cached, not persisted) - post_llm_call: fires once per turn after the loop completes, with user_message and assistant_response for sync/storage - on_session_end: fires at the end of every run_conversation call invoke_hook() now returns a list of non-None callback return values, enabling pre_llm_call context injection while remaining backward compatible (existing hooks that return None are unaffected). Salvaged from PR NousResearch#2823. Co-authored-by: Nicolò Boschi <boschi1997@gmail.com>
olympus-terminal
pushed a commit
to olympus-terminal/hermes-agent
that referenced
this pull request
May 16, 2026
…rt/end) (NousResearch#3542) The plugin system defined six lifecycle hooks but only pre_tool_call and post_tool_call were invoked. This activates the remaining four so that external plugins (e.g. memory systems) can hook into the conversation loop without touching core code. Hook semantics: - on_session_start: fires once when a new session is created - pre_llm_call: fires once per turn before the tool-calling loop; plugins can return {"context": "..."} to inject into the ephemeral system prompt (not cached, not persisted) - post_llm_call: fires once per turn after the loop completes, with user_message and assistant_response for sync/storage - on_session_end: fires at the end of every run_conversation call invoke_hook() now returns a list of non-None callback return values, enabling pre_llm_call context injection while remaining backward compatible (existing hooks that return None are unaffected). Salvaged from PR NousResearch#2823. Co-authored-by: Nicolò Boschi <boschi1997@gmail.com>
gweeteve
pushed a commit
to gweeteve/hermes-agent
that referenced
this pull request
Jun 2, 2026
…rt/end) (NousResearch#3542) The plugin system defined six lifecycle hooks but only pre_tool_call and post_tool_call were invoked. This activates the remaining four so that external plugins (e.g. memory systems) can hook into the conversation loop without touching core code. Hook semantics: - on_session_start: fires once when a new session is created - pre_llm_call: fires once per turn before the tool-calling loop; plugins can return {"context": "..."} to inject into the ephemeral system prompt (not cached, not persisted) - post_llm_call: fires once per turn after the loop completes, with user_message and assistant_response for sync/storage - on_session_end: fires at the end of every run_conversation call invoke_hook() now returns a list of non-None callback return values, enabling pre_llm_call context injection while remaining backward compatible (existing hooks that return None are unaffected). Salvaged from PR NousResearch#2823. Co-authored-by: Nicolò Boschi <boschi1997@gmail.com>
Egavasyug
pushed a commit
to Egavasyug/hermes-agent
that referenced
this pull request
Jun 10, 2026
…rt/end) (NousResearch#3542) The plugin system defined six lifecycle hooks but only pre_tool_call and post_tool_call were invoked. This activates the remaining four so that external plugins (e.g. memory systems) can hook into the conversation loop without touching core code. Hook semantics: - on_session_start: fires once when a new session is created - pre_llm_call: fires once per turn before the tool-calling loop; plugins can return {"context": "..."} to inject into the ephemeral system prompt (not cached, not persisted) - post_llm_call: fires once per turn after the loop completes, with user_message and assistant_response for sync/storage - on_session_end: fires at the end of every run_conversation call invoke_hook() now returns a list of non-None callback return values, enabling pre_llm_call context injection while remaining backward compatible (existing hooks that return None are unaffected). Salvaged from PR NousResearch#2823. Co-authored-by: Nicolò Boschi <boschi1997@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
on_session_start,pre_llm_call,post_llm_call,on_session_endpre_llm_callcan return{"context": "..."}to inject context into the ephemeral system prompt — enabling memory plugins to provide recalled context without core changesinvoke_hook()now returns collected non-None callback results (backward compatible — existing hooks returning None are unaffected)Motivation
This enables external memory systems (e.g. Hindsight) to integrate as pip-installable plugins that hook every conversation turn, rather than requiring core integrations that add bloat. See discussion on #1811.
Hook semantics
on_session_startpre_llm_call{"context": "..."}post_llm_callon_session_endrun_conversation()Changes
hermes_cli/plugins.py—invoke_hook()returnsList[Any]of non-None resultsrun_agent.py— invoke all four hooks at the appropriate lifecycle pointswebsite/docs/guides/build-a-hermes-plugin.md— updated hook reference tabletests/test_plugins.py— added tests for return value collectionTest plan
pre_llm_call, verify context appears in system prompt