Files
Lumotia/docs/issues/llm-prompt-preflight.md
Jake 9b0067b4c0
Some checks failed
check / cargo check (macos-latest) (push) Has been cancelled
check / cargo check (ubuntu-22.04) (push) Has been cancelled
check / cargo check (windows-latest) (push) Has been cancelled
check / svelte build + lint (push) Has been cancelled
Land release blocker fixes and workspace cleanup
2026-04-23 00:16:09 +01:00

44 lines
2.0 KiB
Markdown
Raw Permalink 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.
# RB-10 MAJOR: LLM prompts not preflighted against context window
**Severity:** MAJOR
**Path:** `crates/llm/src/lib.rs:143-166`, `:317-321`
**Source:** [2026-04-22 code review](../code-review-2026-04-22.md)
**Labels:** release-blocker, major, llm
**Status:** RESOLVED (2026-04-22)
## Resolution
`LlmEngine::generate` still tokenises the whole prompt up front, but it
now runs a dedicated prompt-budget preflight before creating the llama
context. The chosen behaviour is an early typed failure rather than
silent truncation:
- If `prompt_tokens + max_tokens + 64 reserve tokens` exceeds the
8192-token cap, generation returns
`EngineError::PromptTooLong { prompt_tokens, max_tokens, available_prompt_tokens, context_window }`.
- Prompts that fit exactly within the available budget still proceed and
allocate an 8192-token context as before.
Regression tests:
- `prompt_preflight_rejects_oversized_prompt_tokens`
- `prompt_preflight_keeps_prompts_within_budget`
## Problem
`generate` tokenises and batches the full prompt at runtime. `context_window_size` hard-caps context at 8192 tokens. Long transcripts (a 30-minute dictation session is easily 40006000 tokens after segment joining) reach inference with prompts already bigger than the available context — causing late runtime failure instead of a controlled early-exit path.
## Acceptance
- Before inference begins, the prompt token count is compared against the available context window (minus the expected response budget).
- Oversized prompts either (a) surface a typed error the caller can handle gracefully, or (b) are truncated with a logged warning — decide during the fix.
- Regression test: synthesise a transcript whose tokenised form exceeds 8192 tokens, assert the chosen behaviour (early error or truncated input).
## Fix scope
Medium. Tokeniser access is already on the LLM path; the check is cheap. Decision work is in what to do when a prompt is too long (fail hard vs truncate).
## Dependencies
- None — standalone fix.