The Assist debug view shows what Jev answered for each command - #21
Merged
Merged
Conversation
Each command adds one agent detail to the conversation trace: the decision, the latency and tokens, and every answer with its probabilities. The debug view then shows why a command picked a device or fell back, without a diagnostics download.
chat_log.async_trace() writes to the conversation trace, and nothing in Home Assistant 2026.9.3 reads that: pipeline_debug/get showed only run-start, intent-start, intent-end and run-end. The agent now sends the record to the chat log's delta listener as thinking_content. The pipeline stores it as an intent-progress event, and the Assist dialog appends thinking_content under the reply. On a development instance pipeline_debug/get held the event for an action and for a refusal, with the decision, the slots, the top three options of each answer, the model, the input tokens and the latency. The delta goes to the listener only and is not added to the chat log, so a fallback agent reading the same conversation does not see it.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Each voice command now adds one agent detail to the conversation trace with
chat_log.async_trace. The Assist debug view shows it next to the pipeline's own steps.The detail holds the record that diagnostics already keep (text, latency, input tokens, exposed entity count and the decision) and also the model and every answer with its probabilities. The entity question's distribution explains why a command picked a device, and the decision alone does not show it. Diagnostics keep the shorter record, because they hold the last commands in memory.
Test:
test_the_assist_debug_view_shows_what_jev_answered. It fails on voice-budget (0 agent details) and passes here.Local gate: ruff, ruff format, mypy --strict, pytest (410 passed, 12 skipped, coverage 96.86%), config_flow 100%, mkdocs --strict, hassfest (0 invalid). EXIT 0.
Part 2 of the 1.16 work. Stacked on #20: the base is
voice-budgetand it moves tofeature/1.16when #20 merges.