Commit Graph
3 Commits
Author SHA1 Message Date
steveandClaude Fable 5 127966bb3a fix(agent): recover the front-loaded answer over a summary closer
CI / Build & Test (pull_request) Successful in 9m49s
CI / Tidy (pull_request) Successful in 10m28s
Gadfly review (reusable) / review (pull_request) Successful in 11m49s
Adversarial Review (Gadfly) / review (pull_request) Successful in 11m49s
A third degenerate terminal shape from the glm-5.2 cite pattern: the model
front-loads its full answer into the cite-call turn, then closes with a
bookkeeping ack plus a one-line compression ("Citations are logged. Short
version: ..."). mort run b3cb9ee9 delivered 151 chars of a 2,089-char
answer this way — the closer was neither a back-reference (over the 120
cap, no back-ref phrase) nor a citations addendum (no label-colon, no
links), so finalOutput let it stand.

isSummaryCloser keys on the ack sentence alone (the verb must end the
sentence, so prose about citations never matches; a compression marker
without the ack is deliberately out of scope), and the new modeSummary
recovery bar makes the 3x dwarf ratio mandatory at every length: unlike a
back-reference this closer carries real answer content, so it is only
displaced by the clearly-fuller original it compressed.

The citations/back-ref bool becomes a three-way recoveryMode; existing
behavior for both old modes is unchanged.

Co-Authored-By: Claude Fable 5 <[email protected]>
2026-08-05 08:47:40 -04:00
steveandClaude Opus 4.8 6abb399f5b fix(agent): recover front-loaded answer past a citations-only terminal turn (#11)
CI / Tidy (push) Successful in 9m35s
CI / Build & Test (push) Successful in 10m31s
finalOutput now recovers the front-loaded answer when the terminal turn is a
sources/citations-only addendum ("Sources: [x](url), ..."), not just when it is
empty or a back-reference. It recovers the prior substantive answer and appends
the (real) citations below it. Guards: citation-DOMINANCE (a prose answer that
merely opens with "Source: ... http://..." is left as the answer), ^-anchored
heading, citations recovery decoupled from the terminal-length ratio (concise
answers recover too), preamble filter applied only in the borderline band
(long answers opening with "Sure,"/"Let me" are not vetoed), and a dedup that
ignores <url> angle-bracket wrappers. Healthy terminal answers unchanged; zero
extra model calls.

Fixes mort #1418. Gadfly-reviewed (6 reviewers) + adversarially pre-verified;
all findings graded, real ones addressed.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
2026-07-10 16:47:32 +00:00
steveandClaude Opus 4.8 1fd7109a42 fix(agent): recover front-loaded answer when terminal turn is degenerate
CI / Tidy (pull_request) Successful in 9m31s
CI / Build & Test (pull_request) Successful in 10m14s
CI / Tidy (push) Successful in 9m26s
CI / Build & Test (push) Successful in 10m19s
The agent loop took the final answer only from the terminal (no-tool-call)
turn. Models that "front-load" their answer into an earlier turn that also
calls a tool — then close with a trivial pointer like "(Already answered
above.)" — had their real answer discarded and the pointer delivered. This
recurs across several open-weight models (glm-5.2, etc.); well-behaved models
(Claude/GPT) defer their answer to the terminal turn and are unaffected.

finalOutput() now falls back to the last substantive assistant content in the
transcript when the terminal text is weak (empty, or a short back-reference).
The predicate is narrow and back-reference-gated so short-but-correct answers
("42", "It's down, restarting now.") are never overridden; recovery only picks
a prior turn that reads like a real answer, not a preamble. Zero extra model
calls. Terminal-answer behavior for normal runs is unchanged.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
2026-06-26 18:37:38 -04:00