cli: add --agent mode for machine-friendly local review output - #591
Merged
Merged
Conversation
Sashiko review✓ No issues found across 1 commit. |
When AI coding agents invoke local Sashiko reviews in an automated development loop, the human-formatted inline review report is redundant with the structured verification findings, and the full --format json output includes raw LLM conversation histories, prompt contexts, and dismissed concerns that consume large amounts of context window tokens. Add --agent to both sashiko review and sashiko-cli local: - Skip the plain-text report and summary LLM stages during workflow execution when agent mode is enabled, saving an extra LLM round-trip and output tokens when findings are present. - Bypass the interactive dirty-worktree confirmation prompt and server queue submission so agent invocations always execute deterministically and non-interactively. - Emit a concise JSON object on stdout containing status, baseline, patches, findings, concerns, token usage counters, and any error or partial-completion metadata. - Update GEMINI.md to instruct agents to pass --agent when running sashiko review --project sashiko in the local agentic loop. Signed-off-by: Roman Gushchin <roman.gushchin@linux.dev>
rgushchin
force-pushed
the
feat/local-agent-mode
branch
from
September 29, 2026 12:23
6dd76d0 to
96e2480
Compare
Sashiko review — v2✓ No issues found across 1 commit. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
--agentflag tosashiko reviewandsashiko-cli localfor machine-friendly local review output in automated AI agent workflows.reportandsummaryLLM stages when--agentis enabled, saving an extra LLM round-trip and output tokens when findings are present.--agentis set so agent runs are deterministic and non-interactive.status,baseline,patches,findings,concerns, token usage counters (tokens_in,tokens_out,tokens_cached), and any error or partial-completion metadata.GEMINI.mdto instruct agents to pass--agentwhen runningsashiko review --project sashikoin the local agentic loop.Verification
make check-pr./target/debug/sashiko review --project sashiko --agent HEAD(status: clean, 0 findings)