fix(#3189): prevent write_file streaming timeout on long reports (#3195)

* fix(#3189): prevent write_file streaming timeout on long reports

Adds a layered defense against StreamChunkTimeoutError caused by oversized
single-shot write_file tool calls:

- factory: default stream_chunk_timeout to 240s for OpenAI-compatible
  clients (overridable via ModelConfig.stream_chunk_timeout in config.yaml)
- sandbox/tools: server-side 80 KB length guard on non-append write_file
  calls (configurable via DEERFLOW_WRITE_FILE_MAX_BYTES env var, 0 disables);
  rejects oversized payloads with a structured error pointing the model at
  str_replace or append=True
- middleware: classify StreamChunkTimeoutError as transient but cap retries
  at 1 via per-exception _RETRY_BUDGET_OVERRIDES (same-payload retry on a
  chunk-gap timeout buffers the same way upstream; full 3-attempt loop
  would stack 6-12 min of dead air)
- middleware: surface an actionable user-facing message for stream-drop
  exceptions instead of leaking the raw langchain stack
- prompts: add a routing-style File Editing Workflow hint to both lead_agent
  and general_purpose subagent prompts, pointing the model at str_replace
  for incremental edits (mirrors Claude Code's Edit / Codex's apply_patch)
- tests: behavioural coverage for size guard, retry budget override,
  stream-drop user message, factory default injection

Refs #3189

* fix(#3189): drop stream_chunk_timeout for non-OpenAI providers

Address CR feedback on PR #3195:

- factory: pop `stream_chunk_timeout` from kwargs for any model_use_path other than `langchain_openai:ChatOpenAI` instead of returning early. `ModelConfig.stream_chunk_timeout` is part of the shared schema, so a user-supplied value on a non-OpenAI provider would otherwise be forwarded to its constructor and raise `TypeError: unexpected keyword argument`.

- factory: rewrite docstring to describe the actual `exclude_none=True` behaviour (explicit null is excluded and falls back to the default) instead of the misleading "None falling out via exclude_none=True keeps its value".

- tests: add regression coverage asserting the kwarg is stripped before reaching a non-OpenAI provider's constructor.

Refs: bytedance#3189

* fix(#3189): restrict stream-drop user copy to StreamChunkTimeoutError only

Per CR on #3195: narrow _STREAM_DROP_EXCEPTIONS to StreamChunkTimeoutError. Generic httpx RemoteProtocolError / ReadError fall back to the standard 'temporarily unavailable' copy, since they routinely fire on transient network blips where the 'split the output' guidance is misleading. Retry/backoff classification is unchanged — both remain transient/retriable. Tests updated to reflect new copy, plus a symmetric regression test for ReadError.

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>

backend/tests/test_lead_agent_prompt.py

@@ -373,3 +373,44 @@ def test_warm_enabled_skills_cache_logs_on_timeout(monkeypatch, caplog):
 
     assert warmed is False
     assert "Timed out waiting" in caplog.text
+
+
+def test_system_prompt_template_contains_file_editing_workflow_rule():
+    """The File Editing Workflow rule must remain in the system prompt
+    template so the planner picks the right tool (str_replace for edits,
+    write_file + append=True for long new content) and avoids mid-stream
+    chunk-gap timeouts on oversized single-shot writes. See issue #3189
+    / PR #3195.
+
+    We deliberately do NOT assert on any specific byte / word threshold
+    here — that would re-introduce the docstring-lock-in pattern the
+    reviewers flagged. The numeric cap lives in the server-side guard
+    (see test_write_file_tool_size_guard.py), which is where it belongs.
+    """
+    template = prompt_module.SYSTEM_PROMPT_TEMPLATE
+    # Section anchor — keeps the rule discoverable in the assembled prompt.
+    assert "File Editing Workflow" in template
+    # Behavioural anchors — if either of these disappears, the model will
+    # silently regress to single-shot write_file calls for long content.
+    assert "str_replace" in template
+    assert "append=True" in template
+
+
+def test_system_prompt_template_preserves_placeholders():
+    """Ensure the chunking-rule edit didn't drop any f-string placeholder
+    consumed by apply_prompt_template(). A missing placeholder would
+    crash prompt rendering at runtime.
+    """
+    template = prompt_module.SYSTEM_PROMPT_TEMPLATE
+    for ph in (
+        "{agent_name}",
+        "{soul}",
+        "{self_update_section}",
+        "{subagent_thinking}",
+        "{skills_section}",
+        "{deferred_tools_section}",
+        "{subagent_section}",
+        "{acp_section}",
+        "{subagent_reminder}",
+    ):
+        assert ph in template, f"placeholder {ph} accidentally removed"