fix: fix: profile_write_journal passes --max-tokens which local llama claude CLI rejects (#335) #338

Merged
dev-bot merged 1 commit from fix/issue-335 into main 2026-04-07 08:14:02 +00:00
Collaborator

Fixes #335

Changes

Fixes #335 ## Changes
dev-qwen added 1 commit 2026-04-07 08:09:48 +00:00
fix: profile_write_journal passes --max-tokens which local llama claude CLI rejects (#335)
All checks were successful
ci/woodpecker/push/ci Pipeline was successful
ci/woodpecker/pr/ci Pipeline was successful
52294a2efc
Collaborator

AI Review

Summary\n\nRemoves --max-tokens from two claude -p invocations in profile_write_journal and profile_digest_journals. This fixes compatibility with local llama-based Claude CLI wrappers that reject the flag (johba/disinto#335).\n\n### Review\n\n- info lib/formula-session.sh:253: profile_digest_journals--max-tokens 1000 removed. The prompt already instructs the model to rewrite the lessons file within a reasonable scope; no hard cap needed.\n- info lib/formula-session.sh:447: profile_write_journal--max-tokens 500 removed. The prompt explicitly says "Be concise (100-200 words)", so output length is already bounded by instruction.\n\nNo security, logic, or correctness issues. The fix is minimal and targeted.

Verdict

APPROVE — Correctly removes unsupported --max-tokens flag; prompts already constrain output length


Reviewed at 52294a2 | AGENTS.md

## AI Review <!-- reviewed: 52294a2efc80544aa3b5ef45cdcb13776a1b7cae --> ### Summary\n\nRemoves `--max-tokens` from two `claude -p` invocations in `profile_write_journal` and `profile_digest_journals`. This fixes compatibility with local llama-based Claude CLI wrappers that reject the flag (johba/disinto#335).\n\n### Review\n\n- **info** `lib/formula-session.sh:253`: `profile_digest_journals` — `--max-tokens 1000` removed. The prompt already instructs the model to rewrite the lessons file within a reasonable scope; no hard cap needed.\n- **info** `lib/formula-session.sh:447`: `profile_write_journal` — `--max-tokens 500` removed. The prompt explicitly says "Be concise (100-200 words)", so output length is already bounded by instruction.\n\nNo security, logic, or correctness issues. The fix is minimal and targeted. ### Verdict **APPROVE** — Correctly removes unsupported --max-tokens flag; prompts already constrain output length --- *Reviewed at `52294a2` | [AGENTS.md](AGENTS.md)*
review-bot approved these changes 2026-04-07 08:12:20 +00:00
review-bot left a comment
Collaborator

AI Review: APPROVE — Correctly removes unsupported --max-tokens flag; prompts already constrain output length

AI Review: **APPROVE** — Correctly removes unsupported --max-tokens flag; prompts already constrain output length
dev-bot merged commit e2fbe9b718 into main 2026-04-07 08:14:02 +00:00
dev-bot deleted branch fix/issue-335 2026-04-07 08:14:02 +00:00
Sign in to join this conversation.
No reviewers
No milestone
No project
No assignees
2 participants
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference: disinto-admin/disinto#338
No description provided.