Files
Agent-Workbench/docs/turn-progress-b-evidence/logs/shadow-final.tap
T

40 lines
3.7 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
✔ reviewed application invalidates old checks, names current SHA and advances through a new approved check to Git preview (6667.5453ms)
✔ skip-tests, foreign task, unknown operations, diagnostic and parent review retain their boundaries (2901.1047ms)
✔ before the first change, real baseline failures persist across later reads; passed baselines and changed sources cannot certify delivery (7112.0927ms)
✔ unchanged proposals cannot hide repeated original-log reads or identical session inspections (4736.891ms)
✔ reusing a verified proof never resets identical-state detection or creates a new proof (4437.3073ms)
✔ coverage merges adjacent pages, separates changed sources and never claims old Run coverage in a continuation (0.7417ms)
✔ a stop from the event loop interrupts immediate model replies before later tools (1406.8527ms)
✔ a stop after the first tool preserves a complete interrupted multi-call protocol group (1840.1754ms)
✔ the compatible HTTP loop preserves call IDs, validates errors and waits before executing commands (4333.6527ms)
✔ denial prevents command execution and produces a paired denied result (2375.5393ms)
✔ stopping during approval interrupts pending calls without executing or replaying them (1987.9152ms)
✔ stopping a running fixture command terminates its own process tree and retains uncertain state (1792.9307ms)
✔ command output decodes split UTF-8 and excludes the workbench key from child environment (954.5634ms)
✔ model-list testing uses a tentative key without changing the saved connection and redacts service errors (6.6624ms)
✔ truncated or repeated model calls fail before execution; tool input validation rejects unknown capabilities (3270.6865ms)
✔ request projection keeps exact tool pairs and complete recent user instructions while preserving disk history (1113.6142ms)
✔ fixed normal exploration, pagination, SHA changes and repeated ranges are external observations, not a score (1.4002ms)
✔ read-only research is valid work; model summaries and unchanged timestamped listings do not become engineering evidence (0.3877ms)
✔ new permissions, network and broken tools are failure evidence; repeated invalid inputs remain candidates (0.3839ms)
✔ waiting for original long checks, review and approvals stays waiting across repeated observations (0.5272ms)
✔ baseline facts, real repairs, current-source check results and requirement evidence have distinct growth (0.2151ms)
✔ bounded memory keeps unknown instead of claiming an unretained range is repeated; Task/Run instances cannot mix (12.2109ms)
✔ actual runtime records growing pages then a repeated page without changing model rounds, stop rules or original tool pairs (5627.8164ms)
✔ actual invalid tool calls repeat under the original step budget; observation never adds an early stop (4379.6453ms)
✔ actual command approval is observed as waiting and denial stays a permission failure (2514.2761ms)
✔ network errors remain model failures with shadow failure evidence, never a fabricated no-progress cause (3649.2277ms)
✔ observer receipt failure cannot change tool results, model budget or completion (1623.0641ms)
✔ a later receipt recovers after an observation write failure without misaligning retained source receipts (2269.483ms)
✔ real applied files, counted checks and current requirement proofs grow after an existing-facts baseline (3560.0974ms)
✔ receipt retention stays aligned at the cap and a foreign step cannot enter the Run (1747.8179ms)
✔ an actual approved long check records its owned running job as waiting before the original counted result (5061.4597ms)
ℹ tests 31
ℹ suites 0
ℹ pass 31
ℹ fail 0
ℹ cancelled 0
ℹ skipped 0
ℹ todo 0
ℹ duration_ms 47431.1358