Code Mode: model writes tool call markup as plain text — call is dropped and the step ends idle #57344

Summary

In Code Mode, the model intermittently writes its tool call as plain
assistant text (Anthropic-style <invoke> / <parameter name="…"> markup)
instead of emitting a structured tool call. OpenCode does not parse or execute
that text: no tool part is created, the step finishes with idle, and the
intended tool call is silently lost. The session then stalls and only proceeds
when another turn is issued.

Environment

• opencode version: 2.0.32 (latest release, Oct 16 2026)
• OS: Linux 6.18.54.1-microsoft-standard-WSL2 x86_64 GNU/Linux
• Agent: build, Code Mode
• Provider/model: opencode/big-pickle, variant default
• Plugins: none (no opencode.json / .opencode/opencode.json)

Reproduction

1. Run a long multi-step build task in Code Mode.
2. Observe the last assistant message of a step. Instead of a structured tool
   call it contains prose followed by raw call markup, and no tool part.

Concrete transcript from session ses_ea9cd281cffe9pJbrBsyPQSpup (read-only
query against ~/.local/share/opencode/opencode.db):

10:50:33  assistant  [text, TOOL:grep:completed, TOOL:shell:completed]   <- real calls, fine
10:50:36  assistant  [text*MK*]                                          <- only text, NO tool part
10:50:39  idle                                                           <- step ends
10:52:03  user                                                            <- new turn needed to continue

The text*MK* message body looks like:

Let me look at `get_deployed_stems` and `_refresh_deployed_flag` — this is the core of the bug.
<parameter name="path">/root/zorq-sigma-bridge/app/…

The read it asks for never runs in that step; the same read is repeated and
executed only in the following turn.

Expected Behavior

The intended tool call should not be dropped. Either:

• parse the text-form call and execute it (a text fallback parser), or
• immediately re-prompt the model to emit a real tool call instead of ending
  the step and leaving the session idle,

and in all cases surface why the step ended.

Actual Behavior

No tool part is created, the step ends with idle, the call is lost, and the
session needs an extra turn to move on — effectively stalling long agent runs.

Occurrences (text parts containing call markup, excluding transcripts where the
agent itself quotes the markup while discussing it):

9 other sessions on the same provider/model/version never produced it, so it
is intermittent and session-dependent.

Additional Context

• Prompt-level workarounds do not help. A repo AGENTS.md rule was added
  that forbids emitting this markup (initially listing the forbidden tokens as
  examples, then rewritten to avoid mentioning them at all). The rules were
  removed from the instructions before the last reproduction: session
  ses_ea9cd281… was created at 01:05 on 20 Oct, after the instruction files
  were already clean, and still reproduced at 10:40–10:54. Its recorded
  instruction blob contains no markup tokens.
• Not a skills/plugins issue. All installed skill files were scanned for
  <invoke / <parameter name= / antml: / function_calls — no matches;
  no plugins are configured.
• The markup always appears in the final assistant message of a step,
  immediately before the idle message, and is interleaved with normal
  structured tool calls earlier in the same step.
• A separate issue in the same environment is a recurring
  AI.Error: Rate limit exceeded (provider.quota, FreeUsageLimitError) on
  the free tier; it is independent of the markup problem and is not
  contributing to the reports above.

Related

• MiMo V2.5 outputs tml:function_calls as plain text instead of structured tool calls #43385 — model outputs function-call syntax as plain text (closed against 1.x, invitation to re-file for 2.0)
• Raw <tool_calls> markup in reasoning breaks tool calls on several models #25644 — raw <tool_calls> markup in reasoning breaks tool calls
• Empty bash tool arguments {} can still be submitted and interrupt the session #27871 — invalid tool arguments leave the session interrupted