fix(telegram): always inject reply context; use partial quote text - #2694
Closed
aleph-tr wants to merge 1 commit into
Closed
fix(telegram): always inject reply context; use partial quote text#2694aleph-tr wants to merge 1 commit into
aleph-tr wants to merge 1 commit into
Conversation
When a user replies to a message in the current session, the agent had no way to know which specific message was being referenced from a flat conversation history. The found_in_history check was silently dropping the [Replying to: "..."] prefix in this exact case, making replies ambiguous. Now reply context is always injected. Also use message.quote.text when available so partial text selections are used instead of the full message.
2 tasks
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
When a user replies to a message in the current session, the agent had no way to know which specific message was being referenced from a flat conversation history. The
found_in_historycheck was silently dropping the[Replying to: "..."]prefix in this exact case, making replies ambiguous. Also ignoring Telegram's partial-quote feature (selected text), always using the full message instead.Changes
gateway/run.py — removed
found_in_historysuppression. Reply context is now always injected.gateway/platforms/telegram.py — use
message.quote.textwhen available instead of full message text.Testing
Verified on a live Telegram bot.