copilot-session-usage 0.7.7__tar.gz → 0.8.0__tar.gz

{copilot_session_usage-0.7.7 → copilot_session_usage-0.8.0}/.github/skills/gh-release-notes/SKILL.md

@@ -44,7 +44,7 @@ The skill includes `scripts/generate_release_notes.py`, a standalone Python scri
 - precomputes the commit log and complete diff locally so generation also works
 	when the Copilot CLI cannot inspect Git history inside its tool environment;
 - invokes the Copilot CLI with `/gh-release-notes`;
-- writes the requested output file; and
+- captures the final Markdown response and writes the requested output file; and
 - verifies only that the requested output file is readable and non-empty. The
 	script does not normalize Markdown or decide user impact, categorize changes,
 	discover documentation, infer breaking changes, or require examples; those

{copilot_session_usage-0.7.7 → copilot_session_usage-0.8.0}/.github/skills/gh-release-notes/scripts/generate_release_notes.py

@@ -90,8 +90,10 @@ def build_prompt(
     prompt = (
         f"Use the /{SKILL_NAME} skill. Generate release notes for the exact Git range "
         f"{from_ref}..{to_ref} in {repo}. The skill is authoritative for analysis, "
-        f"classification, wording, documentation, and Markdown format. Write only "
-        f"the final release-note Markdown to {output}; do not summarize it in your response. "
+        f"classification, wording, documentation, and Markdown format. Return only "
+        f"the final release-note Markdown in your response; the wrapper writes it to {output}. "
+        "Do not create or edit the output file through tools, and do not summarize it in "
+        "your response. "
         "Before writing, enforce the skill's final output contract: render every "
         "documentation URL as concise inline Markdown such as "
         "See the [pricing reference for details](https://example.com/pricing), never as a "
@@ -126,10 +128,8 @@ def build_copilot_command(
         "--output-format",
         "text",
         "--disable-builtin-mcps",
-        "--available-tools=read,create,edit,bash",
-        "--allow-tool=read",
-        "--allow-tool=write",
-        "--allow-tool=shell(git:*)",
+        "--available-tools=read",
+        "--allow-all-tools",
     ]
     if model:
         command.extend(["--model", model])
@@ -203,8 +203,8 @@ def run_copilot(
     repo: Path,
     prompt: str,
     model: str | None,
-) -> None:
-    """Run Copilot CLI and fail with its captured diagnostics when needed."""
+) -> str:
+    """Run Copilot CLI and return its final response."""
     result = subprocess.run(
         build_copilot_command(prompt, model),
         cwd=repo,
@@ -215,10 +215,11 @@ def run_copilot(
     if result.returncode != 0:
         output = f"{result.stdout}\n{result.stderr}".strip()
         raise RuntimeError(f"Copilot CLI failed with exit code {result.returncode}:\n{output}")
+    return result.stdout
 
 
 def validate_output(output: Path) -> None:
-    """Verify that Copilot created a readable, non-empty output file."""
+    """Verify that generated release notes are readable and non-empty."""
     try:
         content = output.read_text(encoding="utf-8")
     except OSError as error:
@@ -247,11 +248,12 @@ def generate_release_notes(
     require_copilot_token()
     run_skill_check(repo)
     git_context = build_git_context(repo, from_ref, to_ref)
-    run_copilot(
+    release_notes = run_copilot(
         repo,
         build_prompt(from_ref, to_ref, repo, output, git_context),
         model,
     )
+    output.write_text(release_notes, encoding="utf-8")
 
     validate_output(output)
     print(f"Release notes written to {output}")

{copilot_session_usage-0.7.7 → copilot_session_usage-0.8.0}/AGENTS.md

@@ -1,7 +1,7 @@
 # AGENTS.md — copilot-session-usage
 
 `copilot-session-usage` is a PyPI-installable Python package that extracts usage and
-cost analytics from local VS Code Copilot and Copilot CLI session logs.
+cost analytics from local VS Code Copilot, Copilot CLI, and Copilot App session logs.
 
 Read [`CONSTITUTION.md`](CONSTITUTION.md) before changing code, tests, packaging,
 release automation, or knowledge. It contains the durable project rules. This file
@@ -37,7 +37,7 @@ src/copilot_session_usage/
 ├── cli.py                    Click CLI entry point
 ├── _internal/core.py         Session parsing, cost analysis, and shaping
 ├── _internal/vscode.py       VS Code workspace discovery
-├── _internal/copilot_cli.py  Future Copilot CLI provider stub
+├── _internal/copilot_cli.py  Copilot CLI/App discovery and event parsing
 └── data/                     Bundled model and pricing data
 tests/                        Pytest suite
 scripts/                      Maintenance scripts, including pricing refresh

{copilot_session_usage-0.7.7 → copilot_session_usage-0.8.0}/CONSTITUTION.md

@@ -24,8 +24,8 @@ Python package, usable from automation, and honest about unavailable evidence.
 - Public API belongs in `src/copilot_session_usage/api.py`; internal implementation
   belongs under `src/copilot_session_usage/_internal/`.
 - Public API functions retain the optional `agent` parameter used for provider
-  routing. The supported provider values are `vscode` and `cli`; the CLI provider
-  remains explicitly unsupported until implemented.
+  routing. The supported provider values are `vscode`, `cli`, and the explicit
+  combined mode `all`.
 - Keep provider discovery separate from parsing, pricing, shaping, and presentation.
 - Do not expose internal modules as public API merely to avoid a proper API change.
 

{copilot_session_usage-0.7.7 → copilot_session_usage-0.8.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: copilot-session-usage
-Version: 0.7.7
+Version: 0.8.0
 Summary: Usage and cost analytics for GitHub Copilot and Copilot-CLI session logs
 Project-URL: Homepage, https://github.com/gsemet/copilot-session-usage
 Project-URL: Documentation, https://copilot-session-usage.readthedocs.io/en/stable/
@@ -27,7 +27,8 @@ Description-Content-Type: text/markdown
 [![Type checked](https://img.shields.io/badge/type%20checked-mypy%2Fty-blue.svg)](./)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
-Extract VS Code Copilot session cost KPIs (tokens, estimated USD, model, duration) from local debug logs.
+Extract Copilot session cost KPIs (tokens, estimated USD, model, duration) from local
+VS Code Copilot debug logs and/or local Copilot CLI/Copilot App session logs.
 
 **Full documentation:** [copilot-session-usage.readthedocs.io](https://copilot-session-usage.readthedocs.io/en/stable/)
 
@@ -56,8 +57,8 @@ models without providing a reproducible split of tokens and dollars by model or
 
 ### What this project adds
 
-`copilot-session-usage` reads the original VS Code Copilot debug logs and turns them into
-repeatable reports. It provides:
+`copilot-session-usage` reads the original VS Code Copilot debug logs and local
+Copilot CLI/App event logs and turns them into repeatable reports. It provides:
 
 | Need | Chronicle | `copilot-session-usage` |
 | --- | --- | --- |
@@ -84,6 +85,38 @@ breakdown for it.
 Use Chronicle for **“What did I do?”** and use this project for **“How much did it cost,
 which model or subagent consumed it, and can I export the evidence?”**
 
+## Providers
+
+`copilot-session-usage` supports two local session sources, selected explicitly
+with `--agent` (default `vscode`):
+
+- **`vscode`** (default) — VS Code Copilot Chat debug logs.
+- **`cli`** — Copilot CLI and Copilot App local sessions, stored under
+  `~/.copilot/session-state/<session-id>/events.jsonl`. The macOS Copilot App
+  runs a bundled Copilot CLI runtime and uses the same session-state layout.
+- **`all`** — an explicit, opt-in combined mode that discovers and
+  aggregates sessions from both providers, deduplicated by session UUID.
+  Commands never mix providers unless `--agent all` is passed. Missing
+  provider roots are ignored, including when both roots are absent.
+
+Both providers share the same model catalog, pricing data, cache rules, and
+estimated-USD calculation. Copilot CLI/App sessions additionally expose
+provider-native counters (`provider_usage`: nanoAiu, premium requests) as
+separate fields, and never turn missing evidence (for example, a session that
+has not shut down yet) into a fabricated zero — see `diagnostics` in the
+output when data is unavailable.
+
+```bash
+# Analyze the latest Copilot CLI/App session
+copilot-session-usage --agent cli latest
+
+# Analyze a specific Copilot CLI/App session by its session-state directory
+copilot-session-usage --agent cli analyze ~/.copilot/session-state/<uuid>
+
+# List and aggregate sessions from both VS Code and Copilot CLI/App
+copilot-session-usage --agent all list --format table
+```
+
 ## Installation
 
 ```bash
@@ -105,6 +138,12 @@ copilot-session-usage list
 # Batch analyze the last 10 sessions
 copilot-session-usage batch 10
 
+# Compact total/model/session report for a date span
+copilot-session-usage --agent all span \
+  --since 2026-07-01T00:00:00Z \
+  --until 2026-07-08T00:00:00Z \
+  --format table
+
 # Aggregate cost across all sessions matching a PRD path
 copilot-session-usage analyze --name "PRD: /path/to/prd" --aggregate --format table
 
@@ -118,6 +157,7 @@ copilot-session-usage list --dir /path/to/debug-logs --format table
 - **Multi-model sessions** — correctly handles sessions that call multiple models (e.g. Claude + Kimi)
 - **Threshold-aware pricing** — long-context tier switching (e.g. GPT-5.4 > 272k tokens)
 - **Subagent cost attribution** — tracks `runSubagent` calls and their token usage
+- **VS Code and Copilot CLI/App providers** — `--agent vscode` (default), `--agent cli`, or the opt-in combined `--agent all`
 - **Cross-platform** — macOS, Linux, Windows, WSL2
 - **Three output formats** — `json` (default), `table`, `detailed`
 - **Three detail levels** — `minimal`, `compact`, `full`
@@ -125,7 +165,7 @@ copilot-session-usage list --dir /path/to/debug-logs --format table
 - **Session filtering** — regex match by name, date-range filtering
 - **Aggregation** — roll up costs across many sessions in one command
 - **Skill-aware cost attribution** — detect skills, attribute LLM and tool calls to the active skill
-- **Skill cost breakdown** — per-skill token counts and estimated cost
+- **Skill cost breakdown** — per-skill token counts and estimated cost (VS Code provider)
 - **Tool-call attribution** — per-skill/per-subagent tool-call counts
 - **Title filtering** — find sessions by title substring
 - **Efficiency summaries** — cache ratio, model split, cost per 1M tokens
@@ -133,6 +173,8 @@ copilot-session-usage list --dir /path/to/debug-logs --format table
 
 ## How it works
 
+### VS Code provider (`--agent vscode`, default)
+
 `copilot-session-usage` reads VS Code Copilot debug logs stored in
 `~/Library/Application Support/Code/User/workspaceStorage/` (macOS),
 `%APPDATA%\Code\User\workspaceStorage\` (Windows), or
@@ -146,6 +188,44 @@ switching), and estimates the session cost in USD.
 Subagent calls (`runSubagent`) are tracked separately so you can see how much
 token usage was delegated to helper agents.
 
+### Copilot CLI/App provider (`--agent cli`)
+
+Copilot CLI and the Copilot App store one directory per session under
+`~/.copilot/session-state/<session-id>/` (override with `--session-root`).
+Each session directory has a structured `events.jsonl` event log — the
+primary evidence source — plus an optional `workspace.yaml` sidecar with
+title, working directory, git branch, and timestamps.
+
+`copilot-session-usage` also accepts an explicit session directory or a
+relocated/exported `events.jsonl` file directly (for example
+`copilot-session-usage --agent cli analyze /path/to/exported/events.jsonl`),
+without requiring auto-discovery. An explicit source is only analyzed when it
+contains recognizable Copilot CLI event records and a canonical session UUID
+can be determined (from the directory name or a `session.start` event) —
+otherwise it is rejected with an actionable error instead of being analyzed
+with a fabricated identity.
+
+Per-model token totals and cost come from the session's final
+`session.shutdown` event and use the same shared, token-based pricing
+calculation as the VS Code provider. GitHub Copilot's own `totalNanoAiu`
+billing figure is kept separate under `provider_usage.total_nano_aiu` and
+never substituted into the shared cost calculation. For a session that has
+not shut down yet (still active, or interrupted), only provider-native
+counters from the last usage checkpoint are available; token totals and cost
+are reported as unavailable (`null`) via the shared `total` block, with
+`diagnostics` explaining why, rather than as fabricated zeros. Tool calls and
+skill attribution are scoped to the subagent that made them, using
+`subagent.started`/`subagent.completed` events and each event's `agentId`;
+`provider_usage.subagents` separately preserves the raw per-subagent evidence
+available (name, model, tool-call count, reported tokens, duration). Parsing
+tolerates unrecognized event types and schema versions other than the one
+currently validated, recording a diagnostic instead of failing.
+
+Pricing lookups for `--agent cli`/`--agent all` are local-only by default
+(no runtime pricing refresh attempt over the network), unlike the `vscode`
+provider's default daily refresh attempt. Run
+`copilot-session-usage pricing refresh` to update pricing explicitly.
+
 ## Knowledge base
 
 This project includes an OKF knowledge bundle in `knowledge/` with structured
@@ -167,6 +247,7 @@ just knowledge-validate
 | `id SESSION_ID` | Analyze a session by exact UUID |
 | `list` | List recent sessions (metadata only by default) |
 | `batch N` | Analyze the N most recent sessions in one pass |
+| `span` | Emit a compact total, per-model, and per-session date-span report |
 | `skills` | List skills used across sessions with aggregated cost |
 
 ### Analysis options
@@ -177,6 +258,7 @@ just knowledge-validate
 | `--title SUBSTRING` | Filter sessions by title substring (case-insensitive) |
 | `--since DATE` | Only sessions created after DATE (ISO 8601 with timezone) |
 | `--until DATE` | Only sessions created before DATE (ISO 8601 with timezone) |
+| `--last DURATION` | Use a rolling window such as `7d`, `24h`, or `30m` with `span` |
 | `--workspace PATH` | Only sessions from this workspace folder |
 | `--aggregate` | Aggregate all matching sessions into one summary |
 | `--summary` | Output a cost-efficiency summary |
@@ -190,8 +272,9 @@ just knowledge-validate
 
 | Option | Description |
 |--------|-------------|
-| `--workspace-storage PATH` | Override workspaceStorage directory (auto-detected by default) |
-| `--agent {vscode,cli}` | Provider to use (`cli` not yet implemented) |
+| `--workspace-storage PATH` | Override workspaceStorage directory (auto-detected by default). Used by `--agent vscode`/`all` |
+| `--session-root PATH` | Override the Copilot CLI/App session-state root (default: `~/.copilot/session-state`). Used by `--agent cli`/`all` |
+| `--agent {vscode,cli,all}` | Provider for session discovery: `vscode` (default), `cli`, or the explicit opt-in combined mode `all` |
 | `--detail {minimal,compact,full}` | Detail level (default: `compact`) |
 | `--format {json,table,detailed}` | Output format (default: `json`) |
 | `--output PATH` | Write output to file instead of stdout |
@@ -322,6 +405,11 @@ sessions = list_sessions(
     since="2026-07-01T00:00:00Z",
     until="2026-07-07T00:00:00Z",
 )
+
+# Analyze a Copilot CLI/App session, or discover/aggregate across all
+# providers with the explicit opt-in agent="all"
+cli_result = analyze_session(Path("~/.copilot/session-state/<uuid>"), agent="cli")
+combined = list_sessions(agent="all")
 ```
 
 ## Development

{copilot_session_usage-0.7.7 → copilot_session_usage-0.8.0}/README.md

@@ -9,7 +9,8 @@
 [![Type checked](https://img.shields.io/badge/type%20checked-mypy%2Fty-blue.svg)](./)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
-Extract VS Code Copilot session cost KPIs (tokens, estimated USD, model, duration) from local debug logs.
+Extract Copilot session cost KPIs (tokens, estimated USD, model, duration) from local
+VS Code Copilot debug logs and/or local Copilot CLI/Copilot App session logs.
 
 **Full documentation:** [copilot-session-usage.readthedocs.io](https://copilot-session-usage.readthedocs.io/en/stable/)
 
@@ -38,8 +39,8 @@ models without providing a reproducible split of tokens and dollars by model or
 
 ### What this project adds
 
-`copilot-session-usage` reads the original VS Code Copilot debug logs and turns them into
-repeatable reports. It provides:
+`copilot-session-usage` reads the original VS Code Copilot debug logs and local
+Copilot CLI/App event logs and turns them into repeatable reports. It provides:
 
 | Need | Chronicle | `copilot-session-usage` |
 | --- | --- | --- |
@@ -66,6 +67,38 @@ breakdown for it.
 Use Chronicle for **“What did I do?”** and use this project for **“How much did it cost,
 which model or subagent consumed it, and can I export the evidence?”**
 
+## Providers
+
+`copilot-session-usage` supports two local session sources, selected explicitly
+with `--agent` (default `vscode`):
+
+- **`vscode`** (default) — VS Code Copilot Chat debug logs.
+- **`cli`** — Copilot CLI and Copilot App local sessions, stored under
+  `~/.copilot/session-state/<session-id>/events.jsonl`. The macOS Copilot App
+  runs a bundled Copilot CLI runtime and uses the same session-state layout.
+- **`all`** — an explicit, opt-in combined mode that discovers and
+  aggregates sessions from both providers, deduplicated by session UUID.
+  Commands never mix providers unless `--agent all` is passed. Missing
+  provider roots are ignored, including when both roots are absent.
+
+Both providers share the same model catalog, pricing data, cache rules, and
+estimated-USD calculation. Copilot CLI/App sessions additionally expose
+provider-native counters (`provider_usage`: nanoAiu, premium requests) as
+separate fields, and never turn missing evidence (for example, a session that
+has not shut down yet) into a fabricated zero — see `diagnostics` in the
+output when data is unavailable.
+
+```bash
+# Analyze the latest Copilot CLI/App session
+copilot-session-usage --agent cli latest
+
+# Analyze a specific Copilot CLI/App session by its session-state directory
+copilot-session-usage --agent cli analyze ~/.copilot/session-state/<uuid>
+
+# List and aggregate sessions from both VS Code and Copilot CLI/App
+copilot-session-usage --agent all list --format table
+```
+
 ## Installation
 
 ```bash
@@ -87,6 +120,12 @@ copilot-session-usage list
 # Batch analyze the last 10 sessions
 copilot-session-usage batch 10
 
+# Compact total/model/session report for a date span
+copilot-session-usage --agent all span \
+  --since 2026-07-01T00:00:00Z \
+  --until 2026-07-08T00:00:00Z \
+  --format table
+
 # Aggregate cost across all sessions matching a PRD path
 copilot-session-usage analyze --name "PRD: /path/to/prd" --aggregate --format table
 
@@ -100,6 +139,7 @@ copilot-session-usage list --dir /path/to/debug-logs --format table
 - **Multi-model sessions** — correctly handles sessions that call multiple models (e.g. Claude + Kimi)
 - **Threshold-aware pricing** — long-context tier switching (e.g. GPT-5.4 > 272k tokens)
 - **Subagent cost attribution** — tracks `runSubagent` calls and their token usage
+- **VS Code and Copilot CLI/App providers** — `--agent vscode` (default), `--agent cli`, or the opt-in combined `--agent all`
 - **Cross-platform** — macOS, Linux, Windows, WSL2
 - **Three output formats** — `json` (default), `table`, `detailed`
 - **Three detail levels** — `minimal`, `compact`, `full`
@@ -107,7 +147,7 @@ copilot-session-usage list --dir /path/to/debug-logs --format table
 - **Session filtering** — regex match by name, date-range filtering
 - **Aggregation** — roll up costs across many sessions in one command
 - **Skill-aware cost attribution** — detect skills, attribute LLM and tool calls to the active skill
-- **Skill cost breakdown** — per-skill token counts and estimated cost
+- **Skill cost breakdown** — per-skill token counts and estimated cost (VS Code provider)
 - **Tool-call attribution** — per-skill/per-subagent tool-call counts
 - **Title filtering** — find sessions by title substring
 - **Efficiency summaries** — cache ratio, model split, cost per 1M tokens
@@ -115,6 +155,8 @@ copilot-session-usage list --dir /path/to/debug-logs --format table
 
 ## How it works
 
+### VS Code provider (`--agent vscode`, default)
+
 `copilot-session-usage` reads VS Code Copilot debug logs stored in
 `~/Library/Application Support/Code/User/workspaceStorage/` (macOS),
 `%APPDATA%\Code\User\workspaceStorage\` (Windows), or
@@ -128,6 +170,44 @@ switching), and estimates the session cost in USD.
 Subagent calls (`runSubagent`) are tracked separately so you can see how much
 token usage was delegated to helper agents.
 
+### Copilot CLI/App provider (`--agent cli`)
+
+Copilot CLI and the Copilot App store one directory per session under
+`~/.copilot/session-state/<session-id>/` (override with `--session-root`).
+Each session directory has a structured `events.jsonl` event log — the
+primary evidence source — plus an optional `workspace.yaml` sidecar with
+title, working directory, git branch, and timestamps.
+
+`copilot-session-usage` also accepts an explicit session directory or a
+relocated/exported `events.jsonl` file directly (for example
+`copilot-session-usage --agent cli analyze /path/to/exported/events.jsonl`),
+without requiring auto-discovery. An explicit source is only analyzed when it
+contains recognizable Copilot CLI event records and a canonical session UUID
+can be determined (from the directory name or a `session.start` event) —
+otherwise it is rejected with an actionable error instead of being analyzed
+with a fabricated identity.
+
+Per-model token totals and cost come from the session's final
+`session.shutdown` event and use the same shared, token-based pricing
+calculation as the VS Code provider. GitHub Copilot's own `totalNanoAiu`
+billing figure is kept separate under `provider_usage.total_nano_aiu` and
+never substituted into the shared cost calculation. For a session that has
+not shut down yet (still active, or interrupted), only provider-native
+counters from the last usage checkpoint are available; token totals and cost
+are reported as unavailable (`null`) via the shared `total` block, with
+`diagnostics` explaining why, rather than as fabricated zeros. Tool calls and
+skill attribution are scoped to the subagent that made them, using
+`subagent.started`/`subagent.completed` events and each event's `agentId`;
+`provider_usage.subagents` separately preserves the raw per-subagent evidence
+available (name, model, tool-call count, reported tokens, duration). Parsing
+tolerates unrecognized event types and schema versions other than the one
+currently validated, recording a diagnostic instead of failing.
+
+Pricing lookups for `--agent cli`/`--agent all` are local-only by default
+(no runtime pricing refresh attempt over the network), unlike the `vscode`
+provider's default daily refresh attempt. Run
+`copilot-session-usage pricing refresh` to update pricing explicitly.
+
 ## Knowledge base
 
 This project includes an OKF knowledge bundle in `knowledge/` with structured
@@ -149,6 +229,7 @@ just knowledge-validate
 | `id SESSION_ID` | Analyze a session by exact UUID |
 | `list` | List recent sessions (metadata only by default) |
 | `batch N` | Analyze the N most recent sessions in one pass |
+| `span` | Emit a compact total, per-model, and per-session date-span report |
 | `skills` | List skills used across sessions with aggregated cost |
 
 ### Analysis options
@@ -159,6 +240,7 @@ just knowledge-validate
 | `--title SUBSTRING` | Filter sessions by title substring (case-insensitive) |
 | `--since DATE` | Only sessions created after DATE (ISO 8601 with timezone) |
 | `--until DATE` | Only sessions created before DATE (ISO 8601 with timezone) |
+| `--last DURATION` | Use a rolling window such as `7d`, `24h`, or `30m` with `span` |
 | `--workspace PATH` | Only sessions from this workspace folder |
 | `--aggregate` | Aggregate all matching sessions into one summary |
 | `--summary` | Output a cost-efficiency summary |
@@ -172,8 +254,9 @@ just knowledge-validate
 
 | Option | Description |
 |--------|-------------|
-| `--workspace-storage PATH` | Override workspaceStorage directory (auto-detected by default) |
-| `--agent {vscode,cli}` | Provider to use (`cli` not yet implemented) |
+| `--workspace-storage PATH` | Override workspaceStorage directory (auto-detected by default). Used by `--agent vscode`/`all` |
+| `--session-root PATH` | Override the Copilot CLI/App session-state root (default: `~/.copilot/session-state`). Used by `--agent cli`/`all` |
+| `--agent {vscode,cli,all}` | Provider for session discovery: `vscode` (default), `cli`, or the explicit opt-in combined mode `all` |
 | `--detail {minimal,compact,full}` | Detail level (default: `compact`) |
 | `--format {json,table,detailed}` | Output format (default: `json`) |
 | `--output PATH` | Write output to file instead of stdout |
@@ -304,6 +387,11 @@ sessions = list_sessions(
     since="2026-07-01T00:00:00Z",
     until="2026-07-07T00:00:00Z",
 )
+
+# Analyze a Copilot CLI/App session, or discover/aggregate across all
+# providers with the explicit opt-in agent="all"
+cli_result = analyze_session(Path("~/.copilot/session-state/<uuid>"), agent="cli")
+combined = list_sessions(agent="all")
 ```
 
 ## Development

{copilot_session_usage-0.7.7 → copilot_session_usage-0.8.0}/docs/articles/presentation.md

@@ -1,12 +1,13 @@
 ## Title
 
-I built `copilot-session-usage`: inspect the token usage and estimated cost of VS Code Copilot sessions
+I built `copilot-session-usage`: inspect the token usage and estimated cost of VS Code, Copilot CLI, and Copilot App sessions
 
 ## Post
 
-I’ve released [`copilot-session-usage`](https://github.com/gsemet/copilot-session-usage), an open-source Python CLI for analyzing VS Code Copilot sessions.
+I’ve released [`copilot-session-usage`](https://github.com/gsemet/copilot-session-usage), an open-source Python CLI for analyzing VS Code Copilot, Copilot CLI, and Copilot App sessions.
 
-VS Code’s UI does not provide a detailed per-session cost report. This tool reads the local Copilot debug logs and reports:
+VS Code and Copilot CLI/App do not provide a detailed per-session cost report.
+This tool reads local Copilot logs and reports:
 
 - Input, output, and cached token counts
 - Models used during a session
@@ -17,13 +18,18 @@ VS Code’s UI does not provide a detailed per-session cost report. This tool re
 - JSON output for scripts and a Python API for integration
 - Optional Git commit trailers containing session usage
 
-It supports multi-model sessions, cache-aware pricing, long-context pricing tiers, macOS, Linux, Windows, and WSL2. For Copilot-plan models, it uses the usage value recorded by VS Code when available. For externally billed Azure-hosted models, it falls back to token-based pricing, so reports should be treated as estimates.
+It supports multi-model sessions, cache-aware pricing, long-context pricing tiers,
+macOS, Linux, Windows, and WSL2. The VS Code provider reads workspace debug
+logs; the Copilot CLI/App provider reads local `events.jsonl` session logs.
+For Copilot-plan models, it uses the usage value recorded by VS Code when
+available. For externally billed Azure-hosted models, it falls back to
+token-based pricing, so reports should be treated as estimates.
 
 
 ## What this project adds
 
-`copilot-session-usage` reads the original VS Code Copilot debug logs and turns them into
-repeatable reports. It provides:
+`copilot-session-usage` reads the original VS Code Copilot debug logs and local
+Copilot CLI/App event logs and turns them into repeatable reports. It provides:
 
 | Need | Chronicle | `copilot-session-usage` |
 | --- | --- | --- |
@@ -43,6 +49,11 @@ repeatable reports. It provides:
 | Pricing provenance and custom model rates | ⚠️ Only for aggregated costs | ✅ |
 | Git commit cost trailers | ❌ | ✅ |
 
+For CLI/App sessions, provider-native counters are preserved separately from
+shared token-based cost totals. Per-skill cost and validated per-subagent cost
+breakdowns are available only when the source log contains the required
+per-request evidence.
+
 ## Example
 
 A typical workflow is simply: