Commit 5dcee2e
committed
Keep embedded delivery mirrors out of provider replay
Embedded assistant gap-fill transcript rows are display-only delivery state. Store them as OpenClaw delivery mirrors so provider replay filters do not mistake child provider text for provider conversation state.
Constraint: Embedded gap-fill transcript rows are display-only state and must match existing transcript-only replay filters.
Rejected: Preserve child runtime provider/model metadata for gap-fill rows | that makes display mirrors look like provider conversation state.
Confidence: high
Scope-risk: narrow
Directive: Do not tag embedded assistant gap-fill mirrors with child provider/model metadata unless replay filters are updated with an equivalent transcript-only contract.
Tested: git diff --check origin/main...HEAD; oxlint changed files; targeted Vitest attempt-execution/replay-history suites (3 files, 95 passed); tsgo core-test project; codex review --base origin/main.
Not-tested: No live provider-managed thinking/signature conversation was replayed end to end; external raw transcript consumers may observe the intentional gap-fill metadata change.1 parent f789081 commit 5dcee2e
2 files changed
Lines changed: 23 additions & 7 deletions
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
93 | 93 | | |
94 | 94 | | |
95 | 95 | | |
96 | | - | |
| 96 | + | |
| 97 | + | |
| 98 | + | |
| 99 | + | |
| 100 | + | |
| 101 | + | |
| 102 | + | |
97 | 103 | | |
98 | 104 | | |
99 | 105 | | |
| |||
770 | 776 | | |
771 | 777 | | |
772 | 778 | | |
| 779 | + | |
| 780 | + | |
| 781 | + | |
773 | 782 | | |
774 | 783 | | |
775 | 784 | | |
| |||
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
365 | 365 | | |
366 | 366 | | |
367 | 367 | | |
| 368 | + | |
| 369 | + | |
| 370 | + | |
| 371 | + | |
| 372 | + | |
| 373 | + | |
| 374 | + | |
| 375 | + | |
| 376 | + | |
| 377 | + | |
| 378 | + | |
| 379 | + | |
368 | 380 | | |
369 | 381 | | |
370 | 382 | | |
| |||
381 | 393 | | |
382 | 394 | | |
383 | 395 | | |
384 | | - | |
385 | | - | |
386 | | - | |
387 | | - | |
388 | | - | |
389 | | - | |
| 396 | + | |
390 | 397 | | |
391 | 398 | | |
392 | 399 | | |
| |||
0 commit comments