codex-usage-tracking 0.10.0__tar.gz → 0.10.1__tar.gz

{codex_usage_tracking-0.10.0 → codex_usage_tracking-0.10.1}/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "codex-usage-tracker",
-  "version": "0.10.0",
+  "version": "0.10.1",
   "description": "Unofficial local tracker for aggregate Codex token usage from local session logs.",
   "author": {
     "name": "Douglas Monsky"

{codex_usage_tracking-0.10.0 → codex_usage_tracking-0.10.1}/CHANGELOG.md

@@ -2,6 +2,11 @@
 
 ## Unreleased
 
+## 0.10.1 - 2026-06-21
+
+- Add lightweight action timing metadata to context evidence so call investigations can show elapsed time for parsed tool and command actions without persisting raw command text or outputs.
+- Add synthetic README diagnostics coverage for the Git Interactions panel and package the screenshot with installed plugin docs.
+
 ## 0.10.0 - 2026-06-21
 
 - Add Git/GitHub CLI diagnostic snapshots with safe operation labels, coarse categories, mutability buckets, and terminal token-count coverage.

{codex_usage_tracking-0.10.0 → codex_usage_tracking-0.10.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: codex-usage-tracking
-Version: 0.10.0
+Version: 0.10.1
 Summary: Unofficial local Codex plugin and dashboard for investigating aggregate token usage, costs, caching, and thread patterns.
 Author: Douglas Monsky
 License-Expression: MIT
@@ -107,6 +107,10 @@ Diagnostics surfaces on-demand snapshot reports for tool output, commands, Git i
 
 ![Diagnostics view showing stored snapshot panels for tool output, commands, Git interactions, file modifications, and concentration.](docs/assets/dashboard-diagnostics.png?v=readme-drilldown)
 
+The Git Interactions panel expands the safe Git and GitHub CLI operation families without storing command text, branch names, release notes, or patch content.
+
+![Diagnostics Git Interactions panel showing aggregate Git and GitHub CLI operation counts.](docs/assets/dashboard-diagnostics-git-expanded.png?v=readme-diagnostics-git)
+
 Insights still gives a fast triage layer for costly threads, low cache reuse, context bloat, and pricing gaps.
 
 ![Insights view with ranked Needs Attention cards, investigation presets, and top threads by attention score.](docs/assets/dashboard-insights.png?v=readme-drilldown)

{codex_usage_tracking-0.10.0 → codex_usage_tracking-0.10.1}/README.md

@@ -69,6 +69,10 @@ Diagnostics surfaces on-demand snapshot reports for tool output, commands, Git i
 
 ![Diagnostics view showing stored snapshot panels for tool output, commands, Git interactions, file modifications, and concentration.](docs/assets/dashboard-diagnostics.png?v=readme-drilldown)
 
+The Git Interactions panel expands the safe Git and GitHub CLI operation families without storing command text, branch names, release notes, or patch content.
+
+![Diagnostics Git Interactions panel showing aggregate Git and GitHub CLI operation counts.](docs/assets/dashboard-diagnostics-git-expanded.png?v=readme-diagnostics-git)
+
 Insights still gives a fast triage layer for costly threads, low cache reuse, context bloat, and pricing gaps.
 
 ![Insights view with ranked Needs Attention cards, investigation presets, and top threads by attention score.](docs/assets/dashboard-insights.png?v=readme-drilldown)

{codex_usage_tracking-0.10.0 → codex_usage_tracking-0.10.1}/docs/cli-json-schemas.md

@@ -689,4 +689,4 @@ Most setup and file-writing commands accept `--json` and return a schema-specifi
 - `init-thresholds --json`, `init-projects --json`
 - `support-bundle --json`
 
-`context` already returns JSON because it is an explicit on-demand context request. Treat `codex-usage-tracker-context-v1` output as sensitive local context even though it is redacted and size-limited by default. `max_entries=0` requests all matching entries and `max_chars=0` removes the character cap for that explicit request. Tool output and compacted replacement history are omitted unless explicitly requested. Compaction entries may include metadata such as `replacement_history_available`, `replacement_entry_count`, and `replacement_history_included`; replacement text appears only when `include_compaction_history` is true for that local request. MCP returns `codex-usage-tracker-context-disabled-v1` when raw context loading has not been explicitly enabled with `CODEX_USAGE_TRACKER_ALLOW_RAW_CONTEXT=1`.
+`context` already returns JSON because it is an explicit on-demand context request. Treat `codex-usage-tracker-context-v1` output as sensitive local context even though it is redacted and size-limited by default. `max_entries=0` requests all matching entries and `max_chars=0` removes the character cap for that explicit request. Tool output and compacted replacement history are omitted unless explicitly requested. Compaction entries may include metadata such as `replacement_history_available`, `replacement_entry_count`, and `replacement_history_included`; replacement text appears only when `include_compaction_history` is true for that local request. Evidence responses include `action_timing`, derived from timestamps in the same selected-turn source scan, plus per-entry `action_timing` fields such as `since_turn_start_ms`, `since_previous_entry_ms`, and `reported_duration_ms` when available. MCP returns `codex-usage-tracker-context-disabled-v1` when raw context loading has not been explicitly enabled with `CODEX_USAGE_TRACKER_ALLOW_RAW_CONTEXT=1`.

{codex_usage_tracking-0.10.0 → codex_usage_tracking-0.10.1}/docs/dashboard-guide.md

@@ -171,7 +171,7 @@ Previous and next buttons move chronologically within the same resolved thread a
 
 The details rail is collapsed by default to preserve table space. Open `Call Details` when you want a compact aggregate preview without leaving the table. When expanded on desktop, it sticks inside the viewport and scrolls internally when the selected call has more fields or loaded context than can fit on screen.
 
-The call investigator loads a redacted turn-log evidence window by default when served from localhost with the context API enabled. The default request uses `mode=quick`: redacted tool output is included, no character cap is applied, and serialized local JSONL is reported as a fast character-based upper bound without bucket analysis. The default entry window is still bounded so very long sessions remain responsive. Older surrounding evidence is collapsed by default and can be expanded or loaded explicitly. Visible evidence token estimates are calculated from the full selected-turn evidence set before display limiting, using `tiktoken` when available and a conservative character fallback only when the tokenizer is unavailable.
+The call investigator loads a redacted turn-log evidence window by default when served from localhost with the context API enabled. The default request uses `mode=quick`: redacted tool output is included, no character cap is applied, and serialized local JSONL is reported as a fast character-based upper bound without bucket analysis. The default entry window is still bounded so very long sessions remain responsive. Older surrounding evidence is collapsed by default and can be expanded or loaded explicitly. Evidence entries include lightweight action timing derived from the timestamps already read during that same source-log scan, shown as elapsed time from the selected turn start, gap since the previous evidence entry, and reported event duration when the log provides one. Visible evidence token estimates are calculated from the full selected-turn evidence set before display limiting, using `tiktoken` when available and a conservative character fallback only when the tokenizer is unavailable.
 
 Use `Run full serialized analysis` when you specifically want tokenizer-counted serialized JSONL groups such as encrypted reasoning/state, local goal metadata, token callback metadata, and rate-limit metadata. This full mode can explain why visible text is much smaller than exact uncached input, but it can overcount because local JSONL includes client metadata that may not be prompt text. Raw grouped text is not returned. `encrypted_content` is an opaque encrypted field found on some reasoning response items. The tracker cannot decrypt it and treats it as serialized state, not readable prompt, assistant, or tool text. Token-count context entries are labeled as the selected call, previous token count in the same turn, or earlier token count in the same turn when possible, and show call/session cumulative totals for input, cached input, uncached input, output, reasoning output, and total tokens.
 

{codex_usage_tracking-0.10.0 → codex_usage_tracking-0.10.1}/docs/development.md

@@ -38,7 +38,7 @@ fix/<issue-number>-short-description
 docs/<issue-number>-short-description
 chore/<issue-number>-short-description
 test/<issue-number>-short-description
-release/0.10.0
+release/0.10.1
 hotfix/0.3.3
 ```
 
@@ -91,7 +91,7 @@ blocked
 Recommended milestones:
 
 ```text
-0.10.0
+0.10.1
 1.0-readiness
 1.0.0
 ```
@@ -146,8 +146,8 @@ python scripts/smoke_installed_package.py --docker
 To verify the public PyPI package instead of the local checkout:
 
 ```bash
-python scripts/smoke_installed_package.py --from-pypi --version 0.10.0
-python scripts/smoke_installed_package.py --docker --from-pypi --version 0.10.0
+python scripts/smoke_installed_package.py --from-pypi --version 0.10.1
+python scripts/smoke_installed_package.py --docker --from-pypi --version 0.10.1
 ```
 
 `scripts/check_release.py` treats these public-package smoke commands as release-state claims. Keep their `--version` and `codex-usage-tracking==...` values aligned with `pyproject.toml`; the release gate fails when the docs claim a different public version. It also checks that install docs point at the real PyPI distribution, `codex-usage-tracking`, and keep the warning that `codex-usage-tracker` is a different PyPI package.
@@ -294,8 +294,8 @@ After the release branch merges, tag from updated `main`, not from an unreviewed
 ```bash
 git switch main
 git pull --ff-only
-git tag -a v0.10.0 -m "codex-usage-tracker 0.10.0"
-git push origin v0.10.0
+git tag -a v0.10.1 -m "codex-usage-tracker 0.10.1"
+git push origin v0.10.1
 ```
 
 Do not create or push release tags without maintainer approval.
@@ -304,7 +304,7 @@ Do not create or push release tags without maintainer approval.
 
 Publishing uses GitHub Actions Trusted Publishing through `.github/workflows/publish.yml`; do not upload from a local machine and do not add PyPI or TestPyPI API tokens.
 
-The first public package release, `0.3.0`, was published on June 8, 2026. Patch release `0.3.1` followed the same day to ship the live-dashboard skill launch fix. Patch release `0.3.2` made dashboard launch refresh the default and added runtime enablement for context loading. Minor release `0.4.0` added Python 3.14 support, release recovery docs, stricter privacy/support-bundle regression coverage, and large-history benchmark thresholds. Patch release `0.4.1` was published by workflow dispatch from `main`; it hardened the PyPI publish workflow and checked off completed 1.0 readiness gates. Minor release `0.5.0` added dashboard localization support and initial language catalogs. Minor release `0.6.0` is the performance and call-drilldown release with SQL-backed live API slices, materialized thread summaries, faster evidence loading, and dashboard runtime module refactors. Patch release `0.6.1` aligns the final README/package screenshots and companion plugin assets. Minor release `0.7.0` adds observed usage snapshots and the latest-observed dashboard card while keeping raw evidence on demand only. Minor release `0.8.0` adds aggregate diagnostics, source-offset context seeking, and live dashboard loading hardening. Patch release `0.8.1` improves Diagnostics fact table readability with pinned fact names and sortable fact columns. Minor release `0.9.0` adds persisted diagnostic snapshots, on-demand diagnostic refresh, tool/command/file-read/concentration reports, and Diagnostics dashboard panels. Minor release `0.10.0` adds Git/GitHub CLI diagnostics, file-modification diagnostics, and derived call timing fields across the dashboard and API.
+The first public package release, `0.3.0`, was published on June 8, 2026. Patch release `0.3.1` followed the same day to ship the live-dashboard skill launch fix. Patch release `0.3.2` made dashboard launch refresh the default and added runtime enablement for context loading. Minor release `0.4.0` added Python 3.14 support, release recovery docs, stricter privacy/support-bundle regression coverage, and large-history benchmark thresholds. Patch release `0.4.1` was published by workflow dispatch from `main`; it hardened the PyPI publish workflow and checked off completed 1.0 readiness gates. Minor release `0.5.0` added dashboard localization support and initial language catalogs. Minor release `0.6.0` is the performance and call-drilldown release with SQL-backed live API slices, materialized thread summaries, faster evidence loading, and dashboard runtime module refactors. Patch release `0.6.1` aligns the final README/package screenshots and companion plugin assets. Minor release `0.7.0` adds observed usage snapshots and the latest-observed dashboard card while keeping raw evidence on demand only. Minor release `0.8.0` adds aggregate diagnostics, source-offset context seeking, and live dashboard loading hardening. Patch release `0.8.1` improves Diagnostics fact table readability with pinned fact names and sortable fact columns. Minor release `0.9.0` adds persisted diagnostic snapshots, on-demand diagnostic refresh, tool/command/file-read/concentration reports, and Diagnostics dashboard panels. Minor release `0.10.0` adds Git/GitHub CLI diagnostics, file-modification diagnostics, and derived call timing fields across the dashboard and API. Patch release `0.10.1` adds lightweight action timing to context evidence and ships the synthetic Git Interactions README screenshot.
 
 - GitHub Release: `https://github.com/douglasmonsky/codex-usage-tracker/releases/tag/v0.3.0`
 - GitHub Release: `https://github.com/douglasmonsky/codex-usage-tracker/releases/tag/v0.3.1`

{codex_usage_tracking-0.10.0 → codex_usage_tracking-0.10.1}/docs/one-dot-oh-readiness.md

@@ -24,12 +24,12 @@ Not guaranteed:
 
 ## 1. Public Install And Package Metadata
 
-- [x] Verify the current public PyPI version is visible as `0.10.0`: `python -c "import json, urllib.request; print(json.load(urllib.request.urlopen('https://pypi.org/pypi/codex-usage-tracking/json'))['info']['version'])"`.
-- [x] Verify public venv install for `0.10.0`: `python -m venv /tmp/codex-usage-pypi-smoke && . /tmp/codex-usage-pypi-smoke/bin/activate && python -m pip install codex-usage-tracking==0.10.0 && codex-usage-tracker --version`.
-- [x] Verify public pipx install path for `0.10.0`: `PIPX_HOME=/tmp/codex-usage-pipx-home PIPX_BIN_DIR=/tmp/codex-usage-pipx-bin pipx install codex-usage-tracking==0.10.0 && /tmp/codex-usage-pipx-bin/codex-usage-tracker --version`.
+- [x] Verify the current public PyPI version is visible as `0.10.1`: `python -c "import json, urllib.request; print(json.load(urllib.request.urlopen('https://pypi.org/pypi/codex-usage-tracking/json'))['info']['version'])"`.
+- [x] Verify public venv install for `0.10.1`: `python -m venv /tmp/codex-usage-pypi-smoke && . /tmp/codex-usage-pypi-smoke/bin/activate && python -m pip install codex-usage-tracking==0.10.1 && codex-usage-tracker --version`.
+- [x] Verify public pipx install path for `0.10.1`: `PIPX_HOME=/tmp/codex-usage-pipx-home PIPX_BIN_DIR=/tmp/codex-usage-pipx-bin pipx install codex-usage-tracking==0.10.1 && /tmp/codex-usage-pipx-bin/codex-usage-tracker --version`.
 - [x] Verify installed package resources from a built wheel: `python scripts/smoke_installed_package.py`.
 - [x] Verify installed package resources in Linux Docker: `python scripts/smoke_installed_package.py --docker`.
-- [x] Verify public PyPI package in Docker: `python scripts/smoke_installed_package.py --docker --from-pypi --version 0.10.0`.
+- [x] Verify public PyPI package in Docker: `python scripts/smoke_installed_package.py --docker --from-pypi --version 0.10.1`.
 - [x] Verify PyPI metadata names remain unchanged: `python scripts/check_release.py`.
 - [x] Add Python 3.14 as an official support target after CI, package classifiers, docs, and installed-package smoke coverage were added. Docker smoke coverage uses `python:3.14-slim` by default. Track this in issue #12.
 
@@ -134,14 +134,14 @@ Not guaranteed:
 
 ## Evidence References
 
-These references are the concrete proof behind completed checklist items. Public package smoke commands are version-specific to `0.10.0`; all repo tests use synthetic or aggregate-only data.
+These references are the concrete proof behind completed checklist items. Public package smoke commands are version-specific to `0.10.1`; all repo tests use synthetic or aggregate-only data.
 
 ### Public Install And Package Metadata
 
 - Public PyPI version, public venv install, and public pipx install are proven by the exact public-install commands in section 1.
 - Built-wheel and installed-resource coverage is proven by `scripts/smoke_installed_package.py` and `tests/test_cli_release.py::test_installed_package_smoke_checks_help_for_stable_commands`.
 - Linux package-resource coverage is proven by `scripts/smoke_installed_package.py --docker`.
-- Public PyPI Docker coverage is proven by `scripts/smoke_installed_package.py --docker --from-pypi --version 0.10.0`.
+- Public PyPI Docker coverage is proven by `scripts/smoke_installed_package.py --docker --from-pypi --version 0.10.1`.
 - PyPI metadata, package/distribution names, package resources, source/wheel member names, Python 3.10-3.14 support metadata, CI workflow requirements, publish workflow safety text, and tracked secret patterns are proven by `scripts/check_release.py`, `scripts/check_release.py --dist`, and `tests/test_cli_release.py::test_release_check_script_passes`.
 
 ### Upgrade And Migration
@@ -219,8 +219,8 @@ These references are the concrete proof behind completed checklist items. Public
 - Publish workflow package name, Trusted Publishing, TestPyPI/PyPI job presence, event guards, no push/PR publishing, no token/password publishing, and manual PyPI main/tag preflight are proven by `scripts/check_release.py::_check_publish_workflow`.
 - The GitHub `pypi` environment gate is proven by `gh api repos/douglasmonsky/codex-usage-tracker/environments/pypi`, which reports a `required_reviewers` protection rule and `can_admins_bypass=false`.
 - Dist filename and wheel/sdist member checks are proven by `python -m build`, `python -m twine check dist/*`, and `python scripts/check_release.py --dist`.
-- TestPyPI publish process is proven by a workflow-dispatch run on `main`, followed by TestPyPI metadata and clean virtualenv install checks for `codex-usage-tracking==0.10.0`.
-- PyPI publish process is proven by a workflow-dispatch run on `main`, protected `pypi` environment approval, PyPI metadata visibility, clean virtualenv install, temporary pipx install, and Docker public-package smoke for `codex-usage-tracking==0.10.0`.
+- TestPyPI publish process is proven by a workflow-dispatch run on `main`, followed by TestPyPI metadata and clean virtualenv install checks for `codex-usage-tracking==0.10.1`.
+- PyPI publish process is proven by a workflow-dispatch run on `main`, protected `pypi` environment approval, PyPI metadata visibility, clean virtualenv install, temporary pipx install, and Docker public-package smoke for `codex-usage-tracking==0.10.1`.
 - Release recovery documentation is proven by `scripts/check_release.py` required-file and docs checks.
 
 ### Known Limitations

{codex_usage_tracking-0.10.0 → codex_usage_tracking-0.10.1}/docs/privacy.md

@@ -41,7 +41,7 @@ Diagnostic snapshots are not live recomputed during ordinary dashboard or usage
 
 ## On-Demand Context
 
-`usage_call_context`, `codex-usage-tracker context`, and the `serve-dashboard` context endpoint read a single source JSONL file only when explicitly requested. Returned context is redacted for common secret patterns and capped in size by default for CLI/MCP requests. The call investigator uses the same endpoint at runtime and requests quick redacted evidence for the selected call when the local context API is enabled; that still does not persist raw context into SQLite, CSV, support bundles, or generated dashboard HTML.
+`usage_call_context`, `codex-usage-tracker context`, and the `serve-dashboard` context endpoint read a single source JSONL file only when explicitly requested. Returned context is redacted for common secret patterns and capped in size by default for CLI/MCP requests. The call investigator uses the same endpoint at runtime and requests quick redacted evidence for the selected call when the local context API is enabled; that still does not persist raw context into SQLite, CSV, support bundles, or generated dashboard HTML. Per-entry action timing in this evidence response is derived from already-read entry timestamps and contains numeric durations only; it does not add a second scan or store raw transcript content.
 
 Tool output is omitted by default for CLI/MCP and dashboard investigator context requests. The call investigator offers `Show tool output` when redacted, size-limited tool output is needed. Full serialized JSONL group analysis is also opt-in through `mode=full` / `Run full serialized analysis`; default quick mode returns only a fast serialized upper-bound estimate. Compacted replacement history remains omitted by default everywhere. Compaction metadata can show that replacement history exists, its entry count, and the source line, but the replacement text is returned only when explicitly requested for that selected call and is redacted before display.
 

{codex_usage_tracking-0.10.0 → codex_usage_tracking-0.10.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "codex-usage-tracking"
-version = "0.10.0"
+version = "0.10.1"
 description = "Unofficial local Codex plugin and dashboard for investigating aggregate token usage, costs, caching, and thread patterns."
 readme = "README.md"
 requires-python = ">=3.10"

{codex_usage_tracking-0.10.0 → codex_usage_tracking-0.10.1}/scripts/check_release.py

@@ -82,6 +82,7 @@ REQUIRED_FILES = [
     "docs/assets/dashboard-calls-preview.png",
     "docs/assets/dashboard-threads.png",
     "docs/assets/dashboard-diagnostics.png",
+    "docs/assets/dashboard-diagnostics-git-expanded.png",
     "docs/assets/dashboard-details.png",
     "docs/assets/dashboard-call-investigator.png",
     "docs/assets/dashboard-call-investigator-preview.png",
@@ -134,6 +135,7 @@ REQUIRED_FILES = [
     "src/codex_usage_tracker/plugin_data/docs/assets/dashboard-calls-preview.png",
     "src/codex_usage_tracker/plugin_data/docs/assets/dashboard-threads.png",
     "src/codex_usage_tracker/plugin_data/docs/assets/dashboard-diagnostics.png",
+    "src/codex_usage_tracker/plugin_data/docs/assets/dashboard-diagnostics-git-expanded.png",
     "src/codex_usage_tracker/plugin_data/docs/assets/dashboard-details.png",
     "src/codex_usage_tracker/plugin_data/docs/assets/dashboard-call-investigator.png",
     "src/codex_usage_tracker/plugin_data/docs/assets/dashboard-call-investigator-preview.png",
@@ -179,6 +181,7 @@ WHEEL_REQUIRED_MEMBERS = {
     "codex_usage_tracker/plugin_data/docs/assets/dashboard-calls-preview.png",
     "codex_usage_tracker/plugin_data/docs/assets/dashboard-threads.png",
     "codex_usage_tracker/plugin_data/docs/assets/dashboard-diagnostics.png",
+    "codex_usage_tracker/plugin_data/docs/assets/dashboard-diagnostics-git-expanded.png",
     "codex_usage_tracker/plugin_data/docs/assets/dashboard-details.png",
     "codex_usage_tracker/plugin_data/docs/assets/dashboard-call-investigator.png",
     "codex_usage_tracker/plugin_data/docs/assets/dashboard-call-investigator-preview.png",

{codex_usage_tracking-0.10.0 → codex_usage_tracking-0.10.1}/scripts/smoke_installed_package.py

@@ -110,6 +110,7 @@ RESOURCE_PATHS = [
     "docs/assets/dashboard-calls-preview.png",
     "docs/assets/dashboard-threads.png",
     "docs/assets/dashboard-diagnostics.png",
+    "docs/assets/dashboard-diagnostics-git-expanded.png",
     "docs/assets/dashboard-details.png",
     "docs/assets/dashboard-call-investigator.png",
     "docs/assets/dashboard-call-investigator-preview.png",

{codex_usage_tracking-0.10.0 → codex_usage_tracking-0.10.1}/skills/codex-usage-tracker/scripts/run_mcp.py

@@ -15,9 +15,9 @@ from pathlib import Path
 
 PACKAGE_SPEC = os.environ.get(
     "CODEX_USAGE_TRACKER_PACKAGE_SPEC",
-    "codex-usage-tracking==0.10.0",
+    "codex-usage-tracking==0.10.1",
 )
-RUNTIME_VERSION = "0.10.0"
+RUNTIME_VERSION = "0.10.1"
 PACKAGE_SPEC_MARKER = ".codex-usage-tracker-package-spec"
 MODULE_CHECK = (
     "import importlib.metadata; "

{codex_usage_tracking-0.10.0 → codex_usage_tracking-0.10.1}/src/codex_usage_tracker/__init__.py

@@ -2,6 +2,6 @@
 
 from codex_usage_tracker.models import UsageEvent
 
-__version__ = "0.10.0"
+__version__ = "0.10.1"
 
 __all__ = ["UsageEvent", "__version__"]

{codex_usage_tracking-0.10.0 → codex_usage_tracking-0.10.1}/src/codex_usage_tracker/context.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import json
+from datetime import datetime, timezone
 from functools import lru_cache
 from math import ceil
 from pathlib import Path
@@ -92,7 +93,14 @@ def load_call_context(
 
     target_turn_id = _optional_str(row.get("turn_id"))
     source_scan_started = perf_counter()
-    entries, omitted, estimate_entries, serialized_estimate, serialized_estimate_ms = (
+    (
+        entries,
+        omitted,
+        estimate_entries,
+        serialized_estimate,
+        serialized_estimate_ms,
+        action_timing,
+    ) = (
         _read_context_entries(
             path=source_file,
             token_line=line_number,
@@ -126,6 +134,7 @@ def load_call_context(
         "visible_token_estimate": visible_estimate["visible_token_estimate"],
         "visible_token_estimator": visible_estimate["visible_token_estimator"],
         "serialized_evidence": serialized_estimate,
+        "action_timing": action_timing,
         "record": {
             "record_id": row.get("record_id"),
             "session_id": row.get("session_id"),
@@ -187,7 +196,14 @@ def _read_context_entries(
     include_compaction_history: bool,
     model: str | None,
     context_mode: str,
-) -> tuple[list[dict[str, Any]], dict[str, Any], list[dict[str, Any]], dict[str, Any], float]:
+) -> tuple[
+    list[dict[str, Any]],
+    dict[str, Any],
+    list[dict[str, Any]],
+    dict[str, Any],
+    float,
+    dict[str, Any],
+]:
     candidates: list[dict[str, Any]] = []
     raw_entries: list[dict[str, Any]] = []
     field_buckets: dict[str, dict[str, Any]] = {}
@@ -341,11 +357,12 @@ def _read_context_entries(
         )
     serialized_estimate_ms = _elapsed_ms(serialized_started)
     candidates = _dedupe_chat_message_echoes(candidates)
+    action_timing = _annotate_action_timing(candidates)
     limited, omitted = _limit_entries(candidates, max_chars=max_chars, max_entries=max_entries)
     omitted["parse_errors"] = omitted_parse_errors
     omitted["target_turn_id"] = target_turn_id
     omitted["total_entries"] = len(candidates)
-    return limited, omitted, candidates, serialized_estimate, serialized_estimate_ms
+    return limited, omitted, candidates, serialized_estimate, serialized_estimate_ms, action_timing
 
 
 def _collect_serialized_envelope(
@@ -438,6 +455,7 @@ def _summarized_context_entry(
         compaction=summarized.get("compaction")
         if isinstance(summarized.get("compaction"), dict)
         else None,
+        action_duration_ms=_nonnegative_float(summarized.get("action_duration_ms")),
     )
 
 
@@ -675,11 +693,15 @@ def _summarize_safe_structured_event(
         value = payload.get(key)
         if _is_safe_structured_scalar(value):
             compact[key] = value
-    return {
+    summary: dict[str, Any] = {
         "label": event_type,
         "text": _jsonish(compact),
         "carry_into_next_turn": True,
     }
+    duration_ms = _nonnegative_float(payload.get("duration_ms"))
+    if duration_ms is not None:
+        summary["action_duration_ms"] = duration_ms
+    return summary
 
 
 def _is_safe_structured_scalar(value: object) -> bool:
@@ -715,6 +737,7 @@ def _context_entry(
     tool_output_omitted: bool = False,
     token_usage: dict[str, Any] | None = None,
     compaction: dict[str, Any] | None = None,
+    action_duration_ms: float | None = None,
 ) -> dict[str, Any]:
     entry = {
         "line_number": line_number,
@@ -730,9 +753,79 @@ def _context_entry(
         entry["token_usage"] = token_usage
     if compaction:
         entry["compaction"] = compaction
+    if action_duration_ms is not None:
+        entry["action_timing"] = {
+            "reported_duration_ms": _normalize_millisecond_value(action_duration_ms),
+            "duration_source": "event.duration_ms",
+        }
     return entry
 
 
+def _annotate_action_timing(entries: list[dict[str, Any]]) -> dict[str, Any]:
+    first_ms: float | None = None
+    previous_ms: float | None = None
+    last_ms: float | None = None
+    timed_entries = 0
+    slowest_gap_ms = 0.0
+
+    for entry in entries:
+        timestamp_ms = _timestamp_epoch_ms(entry.get("timestamp"))
+        if timestamp_ms is None:
+            continue
+        if first_ms is None:
+            first_ms = timestamp_ms
+        existing_timing = entry.get("action_timing")
+        action_timing = dict(existing_timing) if isinstance(existing_timing, dict) else {}
+        action_timing["since_turn_start_ms"] = _duration_between_ms(first_ms, timestamp_ms)
+        if previous_ms is not None:
+            gap_ms = _duration_between_ms(previous_ms, timestamp_ms)
+            action_timing["since_previous_entry_ms"] = gap_ms
+            slowest_gap_ms = max(slowest_gap_ms, float(gap_ms))
+        action_timing["timestamp_source"] = "entry.timestamp"
+        entry["action_timing"] = action_timing
+        previous_ms = timestamp_ms
+        last_ms = timestamp_ms
+        timed_entries += 1
+
+    total_elapsed_ms = (
+        _duration_between_ms(first_ms, last_ms)
+        if first_ms is not None and last_ms is not None
+        else 0
+    )
+    return {
+        "available": timed_entries > 1,
+        "scope": "selected_turn_evidence_entries",
+        "source": "entry_timestamps",
+        "timed_entry_count": timed_entries,
+        "total_elapsed_ms": total_elapsed_ms,
+        "slowest_gap_ms": _normalize_millisecond_value(slowest_gap_ms),
+    }
+
+
+def _timestamp_epoch_ms(value: object) -> float | None:
+    if not isinstance(value, str) or not value.strip():
+        return None
+    normalized = value.strip()
+    if normalized.endswith("Z"):
+        normalized = f"{normalized[:-1]}+00:00"
+    try:
+        parsed = datetime.fromisoformat(normalized)
+    except ValueError:
+        return None
+    if parsed.tzinfo is None:
+        parsed = parsed.replace(tzinfo=timezone.utc)
+    return parsed.timestamp() * 1000
+
+
+def _duration_between_ms(start_ms: float, end_ms: float) -> int | float:
+    return _normalize_millisecond_value(max(0.0, end_ms - start_ms))
+
+
+def _normalize_millisecond_value(value: float) -> int | float:
+    rounded = round(value, 3)
+    return int(rounded) if rounded.is_integer() else rounded
+
+
 def _limit_entries(
     entries: list[dict[str, Any]],
     max_chars: int,
@@ -977,5 +1070,13 @@ def _nonnegative_int(value: object) -> int | None:
     return number if number >= 0 else None
 
 
+def _nonnegative_float(value: object) -> float | None:
+    try:
+        number = float(value)  # type: ignore[arg-type]
+    except (TypeError, ValueError):
+        return None
+    return number if number >= 0 else None
+
+
 def _optional_str(value: object) -> str | None:
     return value if isinstance(value, str) and value else None

{codex_usage_tracking-0.10.0 → codex_usage_tracking-0.10.1}/src/codex_usage_tracker/plugin_data/dashboard/dashboard.js

@@ -1357,6 +1357,7 @@
       escapeHtml,
       short,
       formatTimestamp,
+      formatDuration,
       t,
       tf,
       moneyText,

{codex_usage_tracking-0.10.0 → codex_usage_tracking-0.10.1}/src/codex_usage_tracker/plugin_data/dashboard/dashboard_call_investigator.js

@@ -6,6 +6,7 @@
       escapeHtml,
       short,
       formatTimestamp,
+      formatDuration,
       t,
       tf,
       moneyText,
@@ -753,6 +754,31 @@
       `;
     }
 
+    function formatTimingValue(milliseconds) {
+      const value = Number(milliseconds);
+      if (!Number.isFinite(value) || value < 0) return '';
+      return formatDuration(value / 1000, '');
+    }
+
+    function renderContextTimingMeta(entry) {
+      const timing = entry?.action_timing || {};
+      if (!timing || typeof timing !== 'object') return '';
+      const chips = [];
+      const sinceStart = formatTimingValue(timing.since_turn_start_ms);
+      const sincePrevious = formatTimingValue(timing.since_previous_entry_ms);
+      const reportedDuration = formatTimingValue(timing.reported_duration_ms);
+      if (sinceStart) {
+        chips.push(`<span class="context-entry-timing" title="Elapsed from selected turn start">T+${escapeHtml(sinceStart)}</span>`);
+      }
+      if (sincePrevious) {
+        chips.push(`<span class="context-entry-timing" title="Gap since previous evidence entry">+${escapeHtml(sincePrevious)}</span>`);
+      }
+      if (reportedDuration) {
+        chips.push(`<span class="context-entry-timing duration" title="Duration reported by this event">${escapeHtml(t('table.duration'))} ${escapeHtml(reportedDuration)}</span>`);
+      }
+      return chips.join('');
+    }
+
     function contextEntryWindow(entries, payload) {
       const sourceLine = Number(payload?.source?.line_number || 0);
       const selectedIndex = entries.findIndex(entry => sourceLine && Number(entry.line_number || 0) === sourceLine);
@@ -795,7 +821,11 @@
       const entryWindow = contextEntryWindow(entries, payload);
       const body = entries.map((entry, index) => {
         const entryKey = contextEntryKey(entry, index);
-        const meta = [formatTimestamp(entry.timestamp, ''), entry.line_number ? tf('context.line', { line: entry.line_number }) : ''].filter(Boolean).join(' - ');
+        const metaParts = [
+          formatTimestamp(entry.timestamp, ''),
+          entry.line_number ? tf('context.line', { line: entry.line_number }) : '',
+        ].filter(Boolean);
+        const timingMeta = renderContextTimingMeta(entry);
         const outputAction = entry.tool_output_omitted && !payload.include_tool_output
           ? `<button class="context-entry-action" type="button" data-context-entry-load-output>${escapeHtml(t('button.show_tool_output'))}</button>`
           : '';
@@ -806,7 +836,8 @@
           <div class="context-entry-header">
             <span class="context-entry-title">${escapeHtml(entry.label || entry.type || 'entry')}</span>
             <span class="context-entry-meta">
-              ${meta ? `<span>${escapeHtml(meta)}</span>` : ''}
+              ${metaParts.length ? `<span>${escapeHtml(metaParts.join(' - '))}</span>` : ''}
+              ${timingMeta}
               ${outputAction}
             </span>
           </div>
@@ -821,7 +852,10 @@
             <details class="context-entry context-entry-collapsed" data-context-entry-key="${escapeHtml(entryKey)}">
               <summary class="context-entry-summary">
                 <span class="context-entry-title">${escapeHtml(entry.label || entry.type || 'entry')}</span>
-                <span class="context-entry-meta">${meta ? escapeHtml(meta) : ''}</span>
+                <span class="context-entry-meta">
+                  ${metaParts.length ? `<span>${escapeHtml(metaParts.join(' - '))}</span>` : ''}
+                  ${timingMeta}
+                </span>
               </summary>
               ${bodyHtml}
             </details>

{codex_usage_tracking-0.10.0 → codex_usage_tracking-0.10.1}/src/codex_usage_tracker/plugin_data/dashboard/dashboard_detail.css

@@ -271,6 +271,25 @@
       margin-left: auto;
       text-align: right;
     }
+    .context-entry-timing {
+      display: inline-flex;
+      align-items: center;
+      min-height: 20px;
+      padding: 2px 6px;
+      border: 1px solid #bfdbfe;
+      border-radius: 999px;
+      background: #eff6ff;
+      color: #1d4ed8;
+      font-size: 10px;
+      font-weight: 780;
+      line-height: 1.2;
+      white-space: nowrap;
+    }
+    .context-entry-timing.duration {
+      border-color: #bbf7d0;
+      background: #ecfdf5;
+      color: #065f46;
+    }
     .context-entry-action {
       display: inline-flex;
       align-items: center;

{codex_usage_tracking-0.10.0 → codex_usage_tracking-0.10.1}/src/codex_usage_tracker/plugin_data/docs/dashboard-guide.html

@@ -133,7 +133,7 @@ codex-usage-tracker serve-dashboard --open</code></pre>
 
     <h2>Call Investigator</h2>
     <img src="assets/dashboard-call-investigator.png" alt="Call investigator showing exact token accounting, cache/accounting deltas, context estimates, and runtime evidence.">
-    <p>Clicking a Calls row opens <code>dashboard.html?view=call&amp;record=&lt;record_id&gt;</code> for one model call. It separates exact callback counts, derived previous/next deltas, visible-context estimates, serialized local JSONL upper bounds, candidate serialized-overhead buckets, and redacted evidence loaded at runtime for the selected call. When the localhost context API is enabled, the investigator automatically loads a bounded turn-log evidence window with tool output included; use <code>Hide tool output</code> for a quieter evidence stream, and expand or load older surrounding evidence explicitly when needed. Visible evidence token estimates are calculated from the full selected-turn evidence set before display limiting, using <code>tiktoken</code> when available and a conservative character fallback only when the tokenizer is unavailable. The serialized upper bound tokenizes a redacted raw-JSON representation of the same selected-turn log slice. It can explain why visible text is much smaller than exact uncached input, but it can overcount because local JSONL includes client metadata that may not be prompt text. Bucket labels such as encrypted reasoning/state, local goal metadata, token callback metadata, and rate-limit metadata are counts only; raw text is not returned. <code>encrypted_content</code> is an opaque encrypted field found on some reasoning response items. The tracker cannot decrypt it and treats it as serialized state, not readable prompt, assistant, or tool text. Previous and next buttons move chronologically within the same resolved thread. Cache diagnostics label warm cache reuse, cold resume or stale cache, partial cache miss, uncached spike, and post-compaction without claiming exact cached text spans.</p>
+    <p>Clicking a Calls row opens <code>dashboard.html?view=call&amp;record=&lt;record_id&gt;</code> for one model call. It separates exact callback counts, derived previous/next deltas, visible-context estimates, serialized local JSONL upper bounds, candidate serialized-overhead buckets, and redacted evidence loaded at runtime for the selected call. When the localhost context API is enabled, the investigator automatically loads a bounded turn-log evidence window with tool output included; use <code>Hide tool output</code> for a quieter evidence stream, and expand or load older surrounding evidence explicitly when needed. Evidence entries include lightweight action timing derived from timestamps already read during that same source-log scan, shown as elapsed time from the selected turn start, gap since the previous evidence entry, and reported event duration when the log provides one. Visible evidence token estimates are calculated from the full selected-turn evidence set before display limiting, using <code>tiktoken</code> when available and a conservative character fallback only when the tokenizer is unavailable. The serialized upper bound tokenizes a redacted raw-JSON representation of the same selected-turn log slice. It can explain why visible text is much smaller than exact uncached input, but it can overcount because local JSONL includes client metadata that may not be prompt text. Bucket labels such as encrypted reasoning/state, local goal metadata, token callback metadata, and rate-limit metadata are counts only; raw text is not returned. <code>encrypted_content</code> is an opaque encrypted field found on some reasoning response items. The tracker cannot decrypt it and treats it as serialized state, not readable prompt, assistant, or tool text. Previous and next buttons move chronologically within the same resolved thread. Cache diagnostics label warm cache reuse, cold resume or stale cache, partial cache miss, uncached spike, and post-compaction without claiming exact cached text spans.</p>
 
     <h2>Details And Context</h2>
     <img src="assets/dashboard-details.png" alt="Calls view with a selected usage row and the compact Call Details rail collapsed.">

{codex_usage_tracking-0.10.0 → codex_usage_tracking-0.10.1}/src/codex_usage_tracking.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: codex-usage-tracking
-Version: 0.10.0
+Version: 0.10.1
 Summary: Unofficial local Codex plugin and dashboard for investigating aggregate token usage, costs, caching, and thread patterns.
 Author: Douglas Monsky
 License-Expression: MIT
@@ -107,6 +107,10 @@ Diagnostics surfaces on-demand snapshot reports for tool output, commands, Git i
 
 ![Diagnostics view showing stored snapshot panels for tool output, commands, Git interactions, file modifications, and concentration.](docs/assets/dashboard-diagnostics.png?v=readme-drilldown)
 
+The Git Interactions panel expands the safe Git and GitHub CLI operation families without storing command text, branch names, release notes, or patch content.
+
+![Diagnostics Git Interactions panel showing aggregate Git and GitHub CLI operation counts.](docs/assets/dashboard-diagnostics-git-expanded.png?v=readme-diagnostics-git)
+
 Insights still gives a fast triage layer for costly threads, low cache reuse, context bloat, and pricing gaps.
 
 ![Insights view with ranked Needs Attention cards, investigation presets, and top threads by attention score.](docs/assets/dashboard-insights.png?v=readme-drilldown)

{codex_usage_tracking-0.10.0 → codex_usage_tracking-0.10.1}/src/codex_usage_tracking.egg-info/SOURCES.txt

@@ -27,6 +27,7 @@ docs/assets/dashboard-call-investigator.png
 docs/assets/dashboard-calls-preview.png
 docs/assets/dashboard-calls.png
 docs/assets/dashboard-details.png
+docs/assets/dashboard-diagnostics-git-expanded.png
 docs/assets/dashboard-diagnostics.png
 docs/assets/dashboard-insights.png
 docs/assets/dashboard-threads.png
@@ -139,6 +140,7 @@ src/codex_usage_tracker/plugin_data/docs/assets/dashboard-call-investigator.png
 src/codex_usage_tracker/plugin_data/docs/assets/dashboard-calls-preview.png
 src/codex_usage_tracker/plugin_data/docs/assets/dashboard-calls.png
 src/codex_usage_tracker/plugin_data/docs/assets/dashboard-details.png
+src/codex_usage_tracker/plugin_data/docs/assets/dashboard-diagnostics-git-expanded.png
 src/codex_usage_tracker/plugin_data/docs/assets/dashboard-diagnostics.png
 src/codex_usage_tracker/plugin_data/docs/assets/dashboard-insights.png
 src/codex_usage_tracker/plugin_data/docs/assets/dashboard-threads.png