feat(code): show conversation turns alongside message counts - #5571
Merged
Conversation
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
github-actions
Bot
added
dcode
![open-swe[bot]](https://avatars.githubusercontent.com/in/1395372?s=60&v=4){kind=small}
The re-offload assertion stopped before the turn parenthetical, so `turns_offloaded` never exercised a non-zero `prior_cutoff`: slicing `before_messages[:new_cutoff]` instead of `[prior_cutoff:new_cutoff]` passed the whole suite while re-reporting turns that a previous `/offload` had already archived. Anchor that assertion on the parenthetical and add the kept-slice counterpart. Also cover the branches no test rendered: a singular kept message, a zero-turn offloaded slice, a zero-turn kept slice, singular and mixed-plurality Debug Console labels, and `turn_count` parametrized over every `MessageType` so a new enum member fails loudly. The Debug Console liveness test recomputed the production ternaries, so it agreed with itself; it now asserts a literal string. Drop the duplicated cutoff comment (the surviving copy said "Message counts" where both message and turn counts are derived) and the dead `total == 0` branch, which returned a string byte-identical to the fall-through. Correct the `turn_count` docstring: it spans the store rather than the rendered window, `APP` is app-authored rather than agent-authored, and the cross-module pointer to a private constant in `app.py` invited the opposite conclusion about `SKILL`.
Conflict in `test_build_snapshot_message_count_reports_rendered_window`: main's #5479 replaced the mounted-window expectation with `min(INITIAL_WINDOW_SIZE, WINDOW_SIZE)` while this branch changed the same assertion's string to carry turn counts. Both sides were needed, so the resolution keeps main's `rendered` computation inside this branch's `"N messages (M rendered), K turns"` format. Main also added `MessageType.TOOL_GROUP`, which the new parametrized `turn_count` test flagged on contact -- the enum-drift guard behaving as intended. `TOOL_GROUP` is agent-authored, so it stays outside the counted set; the case only needed `tool_group_messages` to construct. `test_footers_render_for_hydrated_messages_above` fails on this merge, but it fails identically on clean origin/main (verified by swapping in main's copies of both source files), so it is pre-existing and unrelated to these counts.
Mason Daugherty (mdrxy)
pushed a commit
that referenced
this pull request
Aug 18, 2026
> [!CAUTION] > Merging this PR will automatically publish to **PyPI** and create a **GitHub release**. For the full release process, see [`.github/RELEASING.md`](https://github.com/langchain-ai/deepagents/blob/main/.github/RELEASING.md). --- _Release notes preview: keep this section in sync with the package `CHANGELOG.md`. Publish reads the merged CHANGELOG via `release.yml`, not this PR description — keep them aligned anyway so the PR stays an accurate historical record for reviewers and anyone returning later._ --- ## [0.1.57](deepagents-code==0.1.56...deepagents-code==0.1.57) (2026-08-18) ### Features - Added warnings before expensive cold-cache turns and trust user-declared endpoints for cold-cache policies ([#5439](#5439), [#5462](#5462)). - Made the chat input resizable by dragging its top border ([#5524](#5524)). - Added a `multi_select` question type to `ask_user` ([#5097](#5097)). - Added support for ACP approval modes ([#5394](#5394)). - Added `DeepSeek-V4-Pro-0813` to the model picker ([#5512](#5512)). - Show conversation turns alongside message counts ([#5571](#5571)). - Include `TERM_PROGRAM` in the resume hint ([#5548](#5548)). ### Bug Fixes - Report total context after `/offload` ([#5488](#5488)). - Fixed transcript and thread restoration issues, including hydration lag, scrolling resumed threads to the bottom, and hiding empty previous-thread hints ([#5479](#5479), [#5543](#5543), [#5552](#5552)). - Fixed Auto-mode approval handling by binding “yes” to the paired `ask_user` question and avoiding duplicate Auto denial notices ([#5038](#5038), [#5501](#5501)). - Improved reload behavior by keeping the chat input responsive during `/reload`, reporting MCP server changes, and avoiding plugin reload prompt flashes or startup hints ([#5529](#5529), [#5504](#5504), [#5500](#5500), [#5502](#5502)). - Improved dependency update UI by preserving editable fields and hiding dependency details after updates ([#5521](#5521), [#5519](#5519)). - Fixed chat UI polish issues, including detached spacer mount anchors, the unfocused input cursor, and relative timestamp toggle display ([#5516](#5516), [#5258](#5258), [#5503](#5503)). - Refresh the splash version after updates ([#5520](#5520)). _End release notes preview._ --- > [!NOTE] > A **community contributors** list and a **Special thanks** section (crediting the users who filed the issues this release's PRs closed) are appended to the GitHub release notes automatically at publish time (see [Release Pipeline](https://github.com/langchain-ai/deepagents/blob/main/.github/RELEASING.md#release-pipeline), step 3). --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: langchain-oss-automated-triage[bot] <248757908+langchain-oss-automated-triage[bot]@users.noreply.github.com>
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.
/offloadfeedback and the Debug Console now show conversation turns together with raw message counts.Message counts are hard to interpret. One user prompt can become several provider messages (a tool call, a tool result, and a follow-up model turn), and the count changes from provider to provider. Conversation turns — the user prompts the model actually saw — do not change between providers. This makes them a better unit for comparing offloads.
Changes:
Offloaded 4 older messages (2 conversation turns)and6 messages (3 conversation turns) kept. The turn count excludes internal human messages (goal-state notices and[SYSTEM]interruptions) that collect below the cutoff.Messagesfield showsN messages (M rendered), K turns, with correct singular and plural labels.MessageStore.turn_countproperty countsUSERandSKILLrows. A/skillinvocation creates oneSKILLrow instead of aUSERrow, so each skill use counts as one turn. It counts all rendered rows, including local-only flows such as!shelland most slash commands. That is a broader set than the offload report's turn count, which comes from graph state; the property's docstring describes the difference.