Document session-continuity rules in AGENTS.md

opencode ends the turn when an assistant message contains no tool call,
including analysis-only messages. Document the working fix (end bursts
with a tool call or a final report, land work incrementally, resume
without re-deriving) so every session inherits it.

AGENTS.md

@@ -5,6 +5,29 @@ auto-loads this file as instructions, overriding the built-in defaults for
 this project. Custom agents in `.opencode/agents/` inherit these rules
 unless their own prompts say otherwise.
 
+## Session Continuity (keep the agent loop alive)
+
+opencode ends the turn whenever an assistant message contains no tool
+call — including messages that are pure analysis. Long reasoning bursts
+are welcome in this repo (they pre-catch errors and self-correct), but a
+burst that ends as analysis-only text silently stops the session
+mid-task. Past sessions documented this repeatedly ("the session
+stalled"; the working fix discovered there: "call tools frequently, keep
+thinking bursts short"). Keep the depth; change where the burst ends:
+
+1. **Never end a turn with analysis-only text.** Every visible message
+   must either issue a tool call or be a final report for a genuinely
+   completed phase/task. When a thinking burst converges on a decision,
+   act on it (read, edit, bash) in the same turn.
+2. **Land work incrementally.** Once a design decision is settled, write
+   the code before analyzing the next one. Do not emit full-design
+   essays in a single chat message; reasoning belongs in thinking tokens
+   or committed docs, not in the transcript.
+3. **On a silent turn end, resume without re-deriving.** If the turn
+   ended after an analysis-only message and the task is incomplete,
+   pick up from the last settled decision — do not redo the analysis
+   and do not ask the user whether to continue.
+
 ## Git Workflow
 
 **Commit and push when reasonable.** When a change is complete and