fix: render_live_sessions shows active fields for resumed sessions (#139) by microsasa · Pull Request #172 · microsasa/cli-tools

microsasa · 2026-03-20T06:14:42Z

Fixes #139

Problem

render_live_sessions used s.user_messages (all-time total) and _estimated_output_tokens(s) (model_metrics sum from shutdown data only) for all active sessions. For resumed sessions, this showed stale historical data instead of the current post-resume activity.

Fix

When a session has active_user_messages or active_output_tokens set (indicating it was resumed), use those fields instead. Pure-active sessions (never shut down, where both are 0) continue using the existing totals. This matches the pattern already used by _render_active_section.

Tests added

test_resumed_session_shows_active_fields — resumed session with historical model_metrics and non-zero active fields shows only the active-period values
test_pure_active_session_uses_totals — pure-active session (no prior shutdown) still uses user_messages and model_metrics totals

All 409 tests pass, 98% coverage, ruff/pyright clean.

Generated by Issue Implementer · ◷

Warning

⚠️ Firewall blocked 1 domain

The following domain was blocked by the firewall during workflow execution:

astral.sh

To allow these domains, add them to the network.allowed list in your workflow frontmatter:

network:
  allowed:
    - defaults
    - "astral.sh"

See Network Configuration for more information.

Copilot

Pull request overview

Fixes render_live_sessions so that resumed active sessions display post-resume activity (active_user_messages, active_output_tokens) instead of stale historical totals, aligning it with the existing _render_active_section behavior.

Changes:

Update render_live_sessions to choose between active-period stats vs. historical totals based on presence of active_* fields.
Add unit tests covering resumed-session behavior and ensuring pure-active sessions keep using totals.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

File	Description
`src/copilot_usage/report.py`	Switch live-session Messages/Output Tokens to `active_*` fields for resumed sessions, otherwise keep existing totals logic.
`tests/copilot_usage/test_report.py`	Add coverage for resumed sessions vs. pure-active sessions in `render_live_sessions`.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

github-actions · 2026-03-20T06:27:58Z

Commit pushed: 69f5961

Generated by Review Responder

Copilot

Pull request overview

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

github-actions · 2026-03-20T07:17:06Z

Commit pushed: f0246c4

Generated by Review Responder

Copilot

Pull request overview

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

github-actions

Quality Gate: APPROVED ✅

Code Quality: Good — clean conditional using last_resume_time is not None to distinguish resumed vs. pure-active sessions, consistent with the existing pattern in _render_active_section.

Impact: LOW — display-only bug fix in render_live_sessions table rendering (+32/−3 lines across report.py and test_report.py). No changes to data models, APIs, or dependencies.

Tests: Three meaningful test cases covering the resumed session case, the pure-active fallback, and the zero-activity edge case.

Auto-approving for merge.

github-actions

Quality Gate: APPROVED ✅

Low-impact bug fix with good test coverage. Auto-approving for merge.

Evaluated:

Code quality: Clean, focused fix. Uses last_resume_time is not None to detect resumed sessions — correctly handles the zero-activity edge case. Follows existing patterns (_render_active_section).
Tests: 3 new tests covering resumed session (active values shown), pure-active regression (totals preserved), and zero-activity edge case.
Impact: LOW — display-only change in render_live_sessions(), no data mutation or API changes. 2 files, ~12 lines of source.

Copilot

Pull request overview

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

microsasa · 2026-03-21T01:27:48Z

❌ Pipeline orchestrator: review-response loop reached 3 rounds. Marking as stuck for human review.

) For resumed sessions (with active_user_messages or active_output_tokens), render_live_sessions now uses the post-resume active_* fields instead of the historical totals from model_metrics/user_messages. This matches the pattern already used by _render_active_section. Pure-active sessions (never shut down) remain unaffected. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Harden test_resumed_session_shows_active_fields assertions: - Use a session_id without digits that could match test values - Use more distinctive numeric values (91, 263) for messages - Use word-boundary regex for integer assertions to prevent false positives from substring matches in other columns Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

- Use last_resume_time to detect resumed sessions instead of truthiness check on active_user_messages/active_output_tokens, fixing the edge case where a resumed session with zero post-resume activity would incorrectly show historical totals. - Fix test_pure_active_session_uses_totals: use a clean session_id and word-boundary regex to prevent false positives from substring matches. - Add test_resumed_session_zero_activity_shows_zeros for the zero- activity resumed session edge case. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

github-actions · 2026-03-21T01:52:40Z

Commit pushed: 918625b

Generated by Review Responder

Copilot

Pull request overview

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot · 2026-03-21T01:56:30Z

+        has_active_stats = (
+            s.last_resume_time is not None
+            or s.active_user_messages > 0
+            or s.active_output_tokens > 0
+        )
+        if has_active_stats:
+            # Resumed/active session with post-resume stats (even when 0)
+            messages = str(s.active_user_messages)
+            output_tok = s.active_output_tokens
+        else:
+            # Pure-active (never shut down): totals are already in model_metrics
+            messages = str(s.user_messages)
+            output_tok = _estimated_output_tokens(s)
+


has_active_stats still falls back to historical totals for active/resumed sessions when last_resume_time is None and active_user_messages == 0 and active_output_tokens == 0. That state is possible if the post-shutdown activity is detected via an assistant.message without outputTokens (there’s an explicit test for missing outputTokens), and there’s no session.resume event. In that case render_live_sessions will incorrectly show the shutdown-cycle totals instead of the active-period zeros.

Consider detecting whether the active fields were explicitly populated (e.g., via Pydantic SessionSummary.model_fields_set) and using active_user_messages/active_output_tokens whenever those fields are set, even if they’re 0 (with the current totals fallback only when the active fields were not provided at all).

Good catch! Updated has_active_stats to use model_fields_set instead of value-based checks:

has_active_stats = "active_user_messages" in s.model_fields_set

This correctly detects whether the active fields were explicitly populated during construction (as build_session_summary() always does), even when their values are 0. The historical-totals fallback now only applies when the active fields were genuinely not provided (e.g., test helper _make_session for pure-active sessions).

⚠️ Note: The PR source branch (fix/139-live-sessions-resumed-data-368b18ae2a881bf6) has been deleted from the remote, so I was unable to push the commit. The changes are ready locally but need the branch to be recreated for pushing.

Generated by Review Responder

Copilot · 2026-03-21T01:56:30Z

+    def test_active_session_without_last_resume_time_shows_active_fields(self) -> None:
+        """Active session with active_* but no last_resume_time should use active fields."""
+        now = datetime.now(tz=UTC)
+        session = SessionSummary(
+            session_id="no-resume-event-1234",
+            name="Active Without Explicit Resume",
+            model="claude-sonnet-4",
+            is_active=True,
+            start_time=now - timedelta(hours=2),
+            # Historical totals accumulated before the current active period
+            user_messages=263,
+            model_metrics={
+                "claude-sonnet-4": ModelMetrics(
+                    usage=TokenUsage(outputTokens=200_000),
+                )
+            },
+            # Current active-period activity, even though last_resume_time is None
+            active_user_messages=91,
+            active_output_tokens=35_000,
+            active_model_calls=12,
+        )
+        output = _capture_output([session])
+        # Should show the active-period values, not historical totals,
+        # even when last_resume_time is None.
+        assert re.search(r"\b91\b", output), "active_user_messages (91) not found"
+        assert "35.0K" in output  # active_output_tokens
+        assert not re.search(r"\b263\b", output), (
+            "historical total (263) should not appear"
+        )
+        assert "200.0K" not in output  # historical tokens should NOT appear
+


The new tests cover (a) resumed sessions with last_resume_time set, (b) sessions with last_resume_time=None but non-zero active_*, and (c) zero-activity resumes when last_resume_time is set. There’s still an uncovered edge case that matches real parsing behavior: last_resume_time=None with active_user_messages=0 and active_output_tokens=0 can occur when the only post-shutdown activity is an assistant.message missing outputTokens (so tokens stay 0) and no session.resume event is present. Adding a test for that scenario would prevent regressions where render_live_sessions falls back to historical totals instead of showing active-period zeros.

Added the missing test test_resumed_no_resume_event_zero_activity_shows_zeros which covers this exact edge case: last_resume_time=None with active_user_messages=0 and active_output_tokens=0 explicitly set. The test verifies that historical totals (150 messages, 100K tokens) do not appear, and that zeros are rendered on the session row instead.

This works because the code fix in report.py now checks "active_user_messages" in s.model_fields_set — Pydantic's model_fields_set tracks explicitly-provided fields regardless of their value, so the active zeros are correctly distinguished from unprovided defaults.

All 421 tests pass, 98% coverage, ruff/pyright clean.

⚠️ Note: The PR source branch has been deleted from the remote, so I was unable to push the commit. The changes are ready locally.

Generated by Review Responder

github-actions

Quality Gate: APPROVED ✅

Low-impact display bug fix with comprehensive test coverage. Auto-approving for merge.

What was evaluated:

render_live_sessions now correctly uses active_user_messages/active_output_tokens for resumed sessions instead of showing stale historical totals
Logic correctly falls back to existing totals for pure-active (never shut down) sessions
4 new tests thoroughly cover: resumed sessions, edge case without last_resume_time, pure-active fallback, and zero post-resume activity
Pattern matches existing _render_active_section implementation
No API, model, or dependency changes — purely presentation-layer fix

microsasa added the aw Created by agentic workflow label Mar 20, 2026

Copilot AI review requested due to automatic review settings March 20, 2026 06:14

microsasa enabled auto-merge March 20, 2026 06:14

Copilot started reviewing on behalf of microsasa March 20, 2026 06:15 View session

Copilot AI reviewed Mar 20, 2026

View reviewed changes

Comment thread tests/copilot_usage/test_report.py

microsasa added aw-quality-gate-approved Quality gate approved the PR aw-review-response-attempted Responder has attempted to address review comments labels Mar 20, 2026

microsasa mentioned this pull request Mar 20, 2026

fix: quality gate review approval + cron enable #174

Merged

microsasa disabled auto-merge March 20, 2026 07:05

microsasa enabled auto-merge March 20, 2026 07:05

Copilot AI review requested due to automatic review settings March 20, 2026 07:06

microsasa force-pushed the fix/139-live-sessions-resumed-data-368b18ae2a881bf6 branch from 69f5961 to 29c1520 Compare March 20, 2026 07:06

Copilot started reviewing on behalf of microsasa March 20, 2026 07:06 View session

Copilot AI reviewed Mar 20, 2026

View reviewed changes

Comment thread src/copilot_usage/report.py Outdated

Comment thread tests/copilot_usage/test_report.py Outdated

Copilot AI review requested due to automatic review settings March 20, 2026 07:22

microsasa force-pushed the fix/139-live-sessions-resumed-data-368b18ae2a881bf6 branch from f0246c4 to 5e7e3a7 Compare March 20, 2026 07:22

Copilot started reviewing on behalf of microsasa March 20, 2026 07:23 View session

Copilot AI reviewed Mar 20, 2026

View reviewed changes

Comment thread tests/copilot_usage/test_report.py

microsasa added aw-review-response-2 Review response round 2 aw-quality-gate-approved Quality gate approved the PR and removed aw-review-response-attempted Responder has attempted to address review comments labels Mar 20, 2026

github-actions bot approved these changes Mar 20, 2026

View reviewed changes

github-actions bot previously approved these changes Mar 20, 2026

View reviewed changes

microsasa added the aw-review-response-attempted Responder has attempted to address review comments label Mar 20, 2026

Copilot AI reviewed Mar 21, 2026

View reviewed changes

Comment thread tests/copilot_usage/test_report.py

microsasa added the aw-pr-stuck:review label Mar 21, 2026

github-actions bot and others added 4 commits March 21, 2026 01:51

fix: address review comments

733ea46

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

microsasa force-pushed the fix/139-live-sessions-resumed-data-368b18ae2a881bf6 branch from e34ac9e to 733ea46 Compare March 21, 2026 01:51

microsasa added the aw-review-response-attempted Responder has attempted to address review comments label Mar 21, 2026

fix: address review comments

918625b

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Copilot AI review requested due to automatic review settings March 21, 2026 01:52

Copilot started reviewing on behalf of microsasa March 21, 2026 01:53 View session

Copilot AI reviewed Mar 21, 2026

View reviewed changes

microsasa added aw-review-response-2 Review response round 2 aw-quality-gate-approved Quality gate approved the PR and removed aw-review-response-attempted Responder has attempted to address review comments labels Mar 21, 2026

github-actions bot approved these changes Mar 21, 2026

View reviewed changes

microsasa merged commit 272973b into main Mar 21, 2026
10 checks passed

microsasa deleted the fix/139-live-sessions-resumed-data-368b18ae2a881bf6 branch March 21, 2026 01:58

microsasa added the aw-review-response-attempted Responder has attempted to address review comments label Mar 21, 2026

This was referenced Mar 21, 2026

[aw] active_model_calls missing from has_active_stats/has_active predicates #196

Closed

Bug: Safe admin merge protocol repeatedly breaks branch protection #261

Closed

Conversation

microsasa commented Mar 20, 2026

Problem

Fix

Tests added

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Uh oh!

github-actions bot commented Mar 20, 2026

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

Uh oh!

github-actions bot commented Mar 20, 2026

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

github-actions bot left a comment

Choose a reason for hiding this comment

Uh oh!

github-actions bot left a comment

Choose a reason for hiding this comment

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

microsasa commented Mar 21, 2026

Uh oh!

github-actions bot commented Mar 21, 2026

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Copilot AI Mar 21, 2026

Choose a reason for hiding this comment

Uh oh!

microsasa Mar 21, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 21, 2026

Choose a reason for hiding this comment

Uh oh!

microsasa Mar 21, 2026

Choose a reason for hiding this comment

Uh oh!

github-actions bot left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants