fix: bound workflow keyword matching - #79
Merged
Merged
Conversation
SSS135
changed the title
SSS135
force-pushed
the
split/pr74-keyword-trigger
branch
from
July 16, 2026 11:59
9c8171a to
b3d280c
Compare
SSS135
marked this pull request as ready for review
July 16, 2026 15:42
Owner
|
Thanks @SSS135 — clean first split, and I appreciate you rebasing onto 2.14.0 already. Reviewed closely: the Unicode identifier-boundary regex is correct and ReDoS-safe (fixed-length lookarounds + a literal match, no nested quantifiers), default-on keyword triggering is genuinely preserved (only a new test locks it in — the Merging. Looking forward to the rest as you mark them ready — |
QuintinShaw
added a commit
that referenced
this pull request
Jul 18, 2026
…, #89) (#93) * feat(workflow): authorize keyword triggering instead of forcing it Reframes keyword/effort triggering from 'force a workflow' to 'arm the tool and let the model decide', addressing #88 (over-triggering), #89 (triggered runs going idle instead of staying interactive), and cutting the always-on prompt (part of #65). - buildForcedWorkflowPrompt -> buildArmedWorkflowPrompt: the trigger now injects an authorize directive ('typing the word is explicit opt-in; if it's a request call workflow, if it's a question just answer -- the opt-in does not force a workflow') instead of 'You MUST / the ONLY acceptable action / Do NOT answer'. A lexical false-positive is no longer amplified into a forced wrong action. - #89 falls out of de-forcing: the idle was a downstream effect of the model being told to emit nothing but one bare background workflow call (which ends the turn). Handled in a normal turn, Pi stays interactive and the model can fold results inline. No change to the tool's background machinery. - Always-on prompt shrunk ~91% (6500 -> ~600 bytes): the ~20 'For workflow,' how-to lines moved off the always-on promptGuidelines into workflowHowToGuidelines(), injected into the message only on an armed turn; the always-on guideline is now a single gate line. Cuts self-priming and the always-on token cost, and stops churning the prompt-prefix cache. - byEffort path de-forced too, with an explicit conversational-turn escape. - Kept: keywordTriggerEnabled default ON (under authorize semantics the worst case is just an armed-turn directive), the #79 boundary regex, rainbow highlight, Backspace-to-disarm. README updated (force -> arm). 914 tests; always-on prompt budget ratcheted 6500 -> 650. * refactor(workflow): root-and-branch authorize fix (P1-P5) - Move the how-to mechanics from the per-armed-turn message into the workflow tool's static description, so the model has the manual on every arming path AND on off-keyword natural-language opt-ins, cacheably, not as per-turn priming (P2). Always-on promptGuidelines stays the single gate line. - buildArmedWorkflowPrompt now leads with the decision boundary, states the truthful opt-in reason per path (keyword vs standing-effort), and carries the #89 background/deliver-back reassurance so an ending turn reads as expected, not a stall (P1, P3). - /workflows run uses a distinct forcing directive (no question-escape) while avoiding the old MUST/ONLY language (P5). - Gate line gains task-shape positives, balancing the strong negative (P4). - Tests: trigger regression corpus (negatives/positives), gate-line R3, how-to now in tool description, armed-directive content, /workflows run forcing; honest prompt-budget ratchets (always-on ~766B, tool def grows to ~8.8KB as a MOVE, armed message drops ~6.8KB -> ~0.9KB; how-to trimming is #65, separate). * docs: note the off-keyword natural-language path needs the workflow tool default-active The how-to now lives in the tool description, so a bare natural-language opt-in ('fan this out') sees the mechanics only if the host keeps the workflow tool in its default active set. The arming paths add it on arm; document the dependency.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds Unicode-aware identifier boundaries for workflow keyword matching while preserving the existing default-on auto-trigger behavior.
Windows test portability
Full Windows validation identified three test-harness portability issues on current
main: home-directory isolation acrossHOMEandUSERPROFILE, platform-aware expected paths withnode:path.join, and file-URL conversion for absolute dynamic-import paths. The corrections are confined to test setup and path handling and preserve the existing assertions.Validation
npm test: 899/899 passedgit diff --check: passedSplit from and supersedes the keyword-matching portion of #74.