canary: detect provider API schema drift; release v0.7.0
The export reads ChatGPT's and Claude's undocumented internal web APIs, which can change shape without notice; the worst failure for a backup tool is a silent one (skipped/mis-parsed content with no error). Add a `canary` command + BaseProvider.check_drift() (overridden by ChatGPT/Claude) that fetches one listing page + one conversation per provider and asserts only the normalizer's load-bearing fields — not the full response shape, which churns harmlessly. The top silent risk it guards is a renamed retrieval-tool author bypassing the hidden-content collapse. ERROR findings exit non-zero; WARN findings are surfaced but non-fatal so a backup run is never blocked. Also retires the in-app watch mode and headless StartOS direction from the roadmap (tool stays a local, manually-run CLI) and updates docs. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Opus 4.8
parent
ef603cf659
commit
1e016ea652
+72
-1
@@ -16,7 +16,14 @@ from src.blocks import (
|
||||
make_unknown_block,
|
||||
)
|
||||
from src.loss_report import LossReport
|
||||
from src.providers.base import BaseProvider, ProviderError
|
||||
from src.providers.base import (
|
||||
BaseProvider,
|
||||
DRIFT_ERROR,
|
||||
DRIFT_OK,
|
||||
DRIFT_WARN,
|
||||
ProviderError,
|
||||
drift_finding,
|
||||
)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@@ -232,6 +239,70 @@ class ClaudeProvider(BaseProvider):
|
||||
"messages": messages,
|
||||
}
|
||||
|
||||
def check_drift(self) -> list[dict]:
|
||||
"""Probe one listing page + one conversation; assert load-bearing fields.
|
||||
|
||||
See FUTURE.md §10. Real Claude messages are flat ``text``/``sender``;
|
||||
the rich ``content`` block path is dormant, so its activation (content
|
||||
becoming a list) is itself a drift event worth flagging. ``attachments``
|
||||
/ ``files`` are ignored by the normalizer — non-empty values are a
|
||||
silent-loss risk.
|
||||
"""
|
||||
findings: list[dict] = []
|
||||
page = self.list_conversations(offset=0, limit=5)
|
||||
if not page:
|
||||
return [drift_finding(DRIFT_WARN, "listing",
|
||||
"empty listing — cannot verify shape")]
|
||||
|
||||
item = page[0]
|
||||
if not (item.get("uuid") or item.get("id")):
|
||||
findings.append(drift_finding(DRIFT_ERROR, "listing", "summary missing uuid/id"))
|
||||
if not (item.get("name") or item.get("title")):
|
||||
findings.append(drift_finding(DRIFT_WARN, "listing", "no name/title on summary"))
|
||||
if not (item.get("updated_at") or item.get("update_time")):
|
||||
findings.append(drift_finding(DRIFT_WARN, "listing", "no updated_at on summary"))
|
||||
|
||||
conv_id = item.get("uuid") or item.get("id")
|
||||
if not conv_id:
|
||||
return findings or [drift_finding(DRIFT_ERROR, "listing", "no id to fetch")]
|
||||
raw = self.get_conversation(conv_id)
|
||||
if not (raw.get("uuid") or raw.get("id")):
|
||||
findings.append(drift_finding(DRIFT_ERROR, "detail", "no uuid/id on detail"))
|
||||
msgs = raw.get("chat_messages") or raw.get("messages")
|
||||
if not isinstance(msgs, list) or not msgs:
|
||||
findings.append(drift_finding(
|
||||
DRIFT_ERROR, "detail", "chat_messages missing/empty — 0 messages"))
|
||||
return findings
|
||||
|
||||
saw_sender = saw_text = False
|
||||
flagged_list = flagged_attach = False
|
||||
for m in msgs:
|
||||
if m.get("sender") or m.get("role"):
|
||||
saw_sender = True
|
||||
content = m.get("content")
|
||||
if isinstance(content, list) and not flagged_list:
|
||||
findings.append(drift_finding(
|
||||
DRIFT_WARN, "content",
|
||||
"message.content is now a LIST — Claude switched to typed blocks; "
|
||||
"the dormant _dispatch_claude_block path is now live, verify rendering"))
|
||||
flagged_list = True
|
||||
if m.get("text") or content:
|
||||
saw_text = True
|
||||
if (m.get("attachments") or m.get("files")) and not flagged_attach:
|
||||
findings.append(drift_finding(
|
||||
DRIFT_WARN, "attachments",
|
||||
"message has non-empty attachments/files — the normalizer ignores "
|
||||
"these (silent loss); add handling"))
|
||||
flagged_attach = True
|
||||
|
||||
if not saw_sender:
|
||||
findings.append(drift_finding(DRIFT_ERROR, "messages", "no sender/role on any message"))
|
||||
if not saw_text:
|
||||
findings.append(drift_finding(DRIFT_WARN, "messages", "no text/content found"))
|
||||
if not findings:
|
||||
findings.append(drift_finding(DRIFT_OK, "schema", "all load-bearing fields present"))
|
||||
return findings
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Internal helpers
|
||||
|
||||
Reference in New Issue
Block a user