fix: SSE filter no longer drops content events for a different session
Bug: after switching to a new session via the SessionSelector, the
next /edit would not get a reply. Root cause: applyEvent dropped
ANY event whose sessionID didn't match the prompt's _sessionId,
including text deltas / reasoning / tool / idle. OpenCode's sessionID
extraction from event payloads is not perfectly consistent across
event types, so the prompt could end up with a stale _sessionId
that doesn't match the events coming in, and EVERY event got
filtered out -> no reply.
Fix: the cross-session filter is now strict ONLY for
permission.asked / question.asked (so the user can't accidentally
reply to another session's prompt). Content events always pass
through. The server's /events handler is the single source of
truth for session filtering (it has the URL ?session= param); the
client's filter would only ever mask the user's interaction with
their own active session.
Also: drop the cell-context auto-injection. The OpenCodeRequest
now carries only {notebookPath}. The user explicitly attaches
whatever they want via the new '📋 插入单元格内容' button
(inserts the cell source as a markdown code block into the input).
This makes the LLM context match user intent and stops the
OpenCode prompt from being polluted with stale previousCode /
traceback snapshots.
Backend
-------
- _build_request_body: now takes only the prompt, returns
parts=[{text: prompt}]. No more <previous_cell>/<traceback>/<cell>
tag wrapping.
Frontend
-------
- types.ts: CellContext collapsed to {notebookPath}. ErrorOutput /
cellId / source / previousCode / error / cellIndex / totalCells
/ language all removed.
- opencode_cell_actions.ts: extractCellContextFromCell() replaced
with extractNotebookPathFromCell(). _context field renamed to
_notebookPath. NotebookPanel / extractCellContext / context/
cell_context imports all removed.
- src/context/cell_context.ts + src/__tests__/cell_context.spec.ts:
deleted.
New feature: '📋 插入单元格内容' button
----------------------------------------
The button sits at the start of the actions row (visually
left-aligned via margin-right:auto) and appends the current cell's
source as a markdown code fence to the textarea. Caret is moved
to the end so the user can keep typing. The fence info string is
the cell's model type (falls back to a plain fence if the type
isn't a clean language identifier). No-op for empty cells.
Tests
-----
- 72 jest (was 78: -8 cell-context tests + 1 SSE filter test +
3 insert-cell tests + rewrites). 73 pytest (unchanged). Build
green.
This commit is contained in:
+12
-37
@@ -48,44 +48,19 @@ def get_session_manager(handler: APIHandler) -> SessionManager:
|
||||
return sm
|
||||
|
||||
|
||||
def _build_request_body(prompt: str, context: dict) -> dict:
|
||||
"""Build full request body for OpenCode POST /session/:id/prompt_async.
|
||||
def _build_request_body(prompt: str) -> dict:
|
||||
"""Build request body for OpenCode POST /session/:id/prompt_async.
|
||||
|
||||
Returns dict with 'parts' (list) and 'system' (str) keys. No mode concept:
|
||||
the LLM interprets the user's natural-language instruction, with the code
|
||||
context and the optional traceback in front of it.
|
||||
v0.2.x: only the user's prompt is sent to the LLM. We no longer
|
||||
auto-wrap the cell source / previous-cell / traceback in tags —
|
||||
the user inserts whatever they want via the "📋 插入单元格内容"
|
||||
button (or pastes manually), so the LLM context exactly matches
|
||||
user intent. Returns dict with 'parts' and 'system' keys.
|
||||
"""
|
||||
parts: list[dict] = []
|
||||
|
||||
if context.get("previousCode"):
|
||||
parts.append({
|
||||
"type": "text",
|
||||
"text": "<previous_cell>\n%s\n</previous_cell>\n" % context["previousCode"],
|
||||
})
|
||||
|
||||
error = context.get("error")
|
||||
if error:
|
||||
parts.append({
|
||||
"type": "text",
|
||||
"text": (
|
||||
"<traceback>\n%s: %s\n" % (error["ename"], error["evalue"])
|
||||
+ "\n".join(error.get("traceback", []))
|
||||
+ "\n</traceback>\n"
|
||||
),
|
||||
})
|
||||
|
||||
parts.append({
|
||||
"type": "text",
|
||||
"text": "<cell language='%s'>\n%s\n</cell>\n" % (
|
||||
context.get("language", "python"),
|
||||
context["source"],
|
||||
),
|
||||
})
|
||||
|
||||
if prompt:
|
||||
parts.append({"type": "text", "text": "<instruction>\n%s\n</instruction>" % prompt})
|
||||
|
||||
return {"parts": parts, "system": UNIFIED_SYSTEM_PROMPT}
|
||||
return {
|
||||
"parts": [{"type": "text", "text": prompt}],
|
||||
"system": UNIFIED_SYSTEM_PROMPT,
|
||||
}
|
||||
|
||||
|
||||
def _strip_code_fence(s: str) -> str:
|
||||
@@ -204,7 +179,7 @@ class EditHandler(APIHandler):
|
||||
sm = get_session_manager(self)
|
||||
try:
|
||||
sid = await sm.get_or_create(notebook_path)
|
||||
request_body = _build_request_body(prompt, context)
|
||||
request_body = _build_request_body(prompt)
|
||||
await client.send_message_async(
|
||||
sid,
|
||||
request_body["parts"],
|
||||
|
||||
Reference in New Issue
Block a user