warm-resume: drop "read PLAN.md" from the resume nudge
Follow-up to bd517f28. When --resume succeeds, claude-code restores the
full prior conversation — the agent already has its file reads, tool
results, and reasoning in context. Telling it to "read PLAN.md" forces
a redundant tool call to re-read a doc it wrote itself. PLAN.md is the
cold-start orientation doc (driven by AGENT.md); the resume -p prompt
should just be a continuation nudge.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -267,11 +267,13 @@ pub(super) async fn run_agent_spawn(
|
|||||||
// resumed session has a deferred-tool marker. Watchdog-killed
|
// resumed session has a deferred-tool marker. Watchdog-killed
|
||||||
// sessions don't have one, so an empty -p aborts the CLI with
|
// sessions don't have one, so an empty -p aborts the CLI with
|
||||||
// "No deferred tool marker found... Provide a prompt to continue
|
// "No deferred tool marker found... Provide a prompt to continue
|
||||||
// the conversation." We default to a brief "continue from
|
// the conversation." When resume succeeds, the agent already has
|
||||||
// PLAN.md" message when no gate-failure context was provided.
|
// its full prior conversation restored (no need to point at
|
||||||
|
// PLAN.md — that's the cold-start orientation path). A brief
|
||||||
|
// "continue" nudge is all the CLI needs.
|
||||||
let resume_msg = resume_context_owned.filter(|s| !s.is_empty()).unwrap_or_else(
|
let resume_msg = resume_context_owned.filter(|s| !s.is_empty()).unwrap_or_else(
|
||||||
|| {
|
|| {
|
||||||
"Continue from your prior session. Read PLAN.md for your current state and pick up where you left off.".to_string()
|
"Continue your prior work.".to_string()
|
||||||
},
|
},
|
||||||
);
|
);
|
||||||
(resume_msg, Some(fallback))
|
(resume_msg, Some(fallback))
|
||||||
|
|||||||
Reference in New Issue
Block a user