Agent: a turn that changed nothing cannot say it did

Conversation 3 Commits 2 Files Changed 4

+243 -19

2 Commits

Author	SHA1	Message	Date
steveandClaude Fable 5	d4eb62a2ba	Address #132 review: one verb list, self-reporting tools, rune-safe log Build image / build-and-push (push) Successful in 8s Details - changeClaim is built from one changeVerbs list; the opener is just done/fixed/undone so an informational "Updated totals:" can't trip it. - public_link (get reads) and undo_change (nothing left to revert) are self-reporting: their success no longer counts as a change by name; the adapter says whether they changed something (noteChange / didChange). - whenMissing covers the object and plant tools too (move/update/delete object, clear/remove plantings by object, update/delete plant). - The step summary cuts on a rune boundary. Co-Authored-By: Claude Fable 5 <[email protected]>	2026-08-23 02:49:55 -04:00
steveandClaude Fable 5	d0ca56b79b	Agent: a turn that changed nothing cannot say it did Build image / build-and-push (push) Successful in 23s Details Gadfly review (reusable) / review (pull_request) Successful in 7m19s Details Adversarial Review (Gadfly) / review (pull_request) Successful in 7m20s Details Live, asked to delete a journal entry and later a seed lot, the model answered "Done — I've deleted it" both times having deleted nothing; each was still there a turn later. The prompt already forbade that. Now the run catches it: honestReply appends a correction when the reply claims a change ("Done", "I've deleted…") and no non-read-only tool call succeeded, and logs the steps so the mechanism can be read off the log next time. Alongside: the id-taking tools turn a bare "not found" into a message that names what was missing and which tool lists the ids ("nothing was changed"), the two delete descriptions say to look the id up in THIS turn, and the prompt says an error result means the thing did not happen. Co-Authored-By: Claude Fable 5 <[email protected]>	2026-08-23 02:37:06 -04:00

Author

SHA1

Message

Date

steveandClaude Fable 5

d4eb62a2ba

Address #132 review: one verb list, self-reporting tools, rune-safe log

Build image / build-and-push (push) Successful in 8s

Details

- changeClaim is built from one changeVerbs list; the opener is just
  done/fixed/undone so an informational "Updated totals:" can't trip it.
- public_link (get reads) and undo_change (nothing left to revert) are
  self-reporting: their success no longer counts as a change by name; the
  adapter says whether they changed something (noteChange / didChange).
- whenMissing covers the object and plant tools too (move/update/delete
  object, clear/remove plantings by object, update/delete plant).
- The step summary cuts on a rune boundary.

Co-Authored-By: Claude Fable 5 <[email protected]>

2026-08-23 02:49:55 -04:00

steveandClaude Fable 5

d0ca56b79b

Agent: a turn that changed nothing cannot say it did

Build image / build-and-push (push) Successful in 23s

Details

Gadfly review (reusable) / review (pull_request) Successful in 7m19s

Details

Adversarial Review (Gadfly) / review (pull_request) Successful in 7m20s

Details

Live, asked to delete a journal entry and later a seed lot, the model
answered "Done — I've deleted it" both times having deleted nothing; each
was still there a turn later. The prompt already forbade that. Now the run
catches it: honestReply appends a correction when the reply claims a change
("Done", "I've deleted…") and no non-read-only tool call succeeded, and logs
the steps so the mechanism can be read off the log next time.

Alongside: the id-taking tools turn a bare "not found" into a message that
names what was missing and which tool lists the ids ("nothing was changed"),
the two delete descriptions say to look the id up in THIS turn, and the
prompt says an error result means the thing did not happen.

Co-Authored-By: Claude Fable 5 <[email protected]>

2026-08-23 02:37:06 -04:00

Agent: a turn that changed nothing cannot say it did #132