You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
CodeBurn tracks token usage, cost, and performance across **18 AI coding tools**. It breaks down spending by task type, model, tool, project, and provider so you can see exactly where your budget goes.
16
+
CodeBurn tracks token usage, cost, and performance across **19 AI coding tools**. It breaks down spending by task type, model, tool, project, and provider so you can see exactly where your budget goes.
17
17
18
18
Everything runs locally. No wrapper, no proxy, no API keys. CodeBurn reads session data directly from disk and prices every call using [LiteLLM](https://github.com/BerriAI/litellm).
19
19
@@ -104,6 +104,7 @@ Arrow keys switch between Today, 7 Days, 30 Days, Month, and 6 Months (use `--fr
@@ -119,7 +120,7 @@ Arrow keys switch between Today, 7 Days, 30 Days, Month, and 6 Months (use `--fr
119
120
120
121
Each provider doc lists the exact data location, storage format, and known quirks. Linux and Windows paths are detected automatically. If a path has changed or is wrong, please [open an issue](https://github.com/getagentseal/codeburn/issues).
121
122
122
-
Provider logos are trademarks of their respective owners. The icon set was sourced from [tokscale](https://github.com/junhoyeo/tokscale) (MIT) plus official vendor assets, used under nominative fair use for the purpose of identifying supported tools.
123
+
Provider logos are trademarks of their respective owners. The icon set was sourced from [tokscale](https://github.com/junhoyeo/tokscale) (MIT), official vendor assets, and simple provider identifiers, used under nominative fair use for the purpose of identifying supported tools.
123
124
124
125
CodeBurn auto-detects which AI coding tools you use. If multiple providers have session data on disk, press `p` in the dashboard to toggle between them.
125
126
@@ -378,6 +379,8 @@ These are starting points, not verdicts. A 60% cache hit on a single experimenta
378
379
379
380
**OpenClaw** stores agent sessions as JSONL at `~/.openclaw/agents/*.jsonl`. Also checks legacy paths `.clawdbot`, `.moltbot`, `.moldbot`. Token usage comes from assistant message `usage` blocks; model from `modelId` or `message.model` fields.
380
381
382
+
**IBM Bob** stores IDE task history in `User/globalStorage/ibm.bob-code/tasks/<task-id>/` under the IBM Bob application data directory. CodeBurn reads `ui_messages.json` for API request token/cost records and `api_conversation_history.json` for the selected model, with support for both GA (`IBM Bob`) and preview (`Bob-IDE`) app data folders.
383
+
381
384
**Roo Code / KiloCode** are Cline-family VS Code extensions. CodeBurn reads `ui_messages.json` from each task directory in VS Code's `globalStorage`, filtering `type: "say"` entries with `say: "api_req_started"` to extract token counts.
382
385
383
386
CodeBurn deduplicates messages (by API message ID for Claude, by cumulative token cross-check for Codex, by conversation/timestamp for Cursor, by session ID for Gemini, by session+message ID for OpenCode, by responseId for Pi/OMP), filters by date range per entry, and classifies each turn.
- **Lazy**: `antigravity`, `goose`, `cursor`, `opencode`, `cursor-agent`, `crush`. Imported via dynamic `import()` so the heavy dependencies (SQLite, protobuf) do not touch users who do not have those tools installed.
135
135
136
136
Both lists hit the same `getAllProviders()` aggregator. A failed lazy import is silent and excludes that provider from the run.
137
137
138
-
`src/providers/vscode-cline-parser.ts` is a shared helper consumed by `kilo-code` and `roo-code`. It is not registered as a provider on its own.
138
+
`src/providers/vscode-cline-parser.ts` is a shared helper consumed by `ibm-bob`, `kilo-code`, and `roo-code`. It is not registered as a provider on its own.
139
139
140
140
For the per-provider data location, storage format, parser quirks, and test coverage, see `docs/providers/`.
| Windows |`%APPDATA%/IBM Bob/User/globalStorage/ibm.bob-code/`, `%APPDATA%/Bob-IDE/User/globalStorage/ibm.bob-code/`|
19
+
| Linux |`$XDG_CONFIG_HOME/IBM Bob/User/globalStorage/ibm.bob-code/`, `$XDG_CONFIG_HOME/Bob-IDE/User/globalStorage/ibm.bob-code/` with `~/.config` fallback |
20
+
21
+
The `Bob-IDE` paths cover the preview-era app name that some installs used before the GA `IBM Bob` directory.
22
+
23
+
## Storage Format
24
+
25
+
Each task is a directory under `tasks/<task-id>/` and must contain `ui_messages.json`.
26
+
27
+
CodeBurn parses the same Cline-family UI event format used by Roo Code and KiloCode:
28
+
29
+
-`ui_messages.json` entries with `type: "say"` and `say: "api_req_started"` contain serialized token/cost metrics.
30
+
-`ui_messages.json` user text entries seed the turn's first user message.
31
+
-`api_conversation_history.json` is optional and is used to extract the selected model from `<model>...</model>` environment details when present.
32
+
-`task_metadata.json` may exist upstream, but CodeBurn does not need it for usage math today.
33
+
34
+
If no model tag is present, the parser uses `ibm-bob-auto`, which is priced through the same conservative Sonnet fallback used for Cline-family auto modes.
35
+
36
+
## Caching
37
+
38
+
None at the provider level.
39
+
40
+
## Deduplication
41
+
42
+
Per `<providerName>:<taskId>:<apiRequestIndex>` via `vscode-cline-parser.ts`.
43
+
44
+
## Quirks
45
+
46
+
- IBM Bob has shipped under both `IBM Bob` and `Bob-IDE` application data folder names.
47
+
- This provider intentionally covers the IDE task-history format. Bob Shell's `~/.bob` checkpoint data is a separate storage surface and is not parsed until we have a stable usage schema fixture.
48
+
- The shared Cline parser does not currently extract individual tool names from UI messages, so tool breakdowns are empty for IBM Bob just like Roo Code and KiloCode.
49
+
50
+
## When Fixing A Bug Here
51
+
52
+
1. Check whether the install uses `IBM Bob` or `Bob-IDE` as the application data directory.
53
+
2. Confirm the task folder still contains `ui_messages.json` and `api_conversation_history.json`.
54
+
3. If the UI message schema changed, add a focused fixture to `tests/providers/ibm-bob.test.ts`.
55
+
4. If the change also affects Roo Code or KiloCode, update `src/providers/vscode-cline-parser.ts` and run all three provider test files.
-**Loading:** not a provider; imported by `kilo-code.ts` and `roo-code.ts`.
7
-
-**Test:** none directly. Coverage comes from `tests/providers/kilo-code.test.ts` and `tests/providers/roo-code.test.ts`.
6
+
-**Loading:** not a provider; imported by `ibm-bob.ts`, `kilo-code.ts`, and `roo-code.ts`.
7
+
-**Test:** none directly. Coverage comes from `tests/providers/ibm-bob.test.ts`, `tests/providers/kilo-code.test.ts`, and `tests/providers/roo-code.test.ts`.
8
8
9
9
## What it does
10
10
11
11
Two responsibilities:
12
12
13
-
1.`discoverClineTasks(extensionId)` walks VS Code's `globalStorage/<extensionId>/tasks/` directories and returns one source per task that has a `ui_messages.json` file (`vscode-cline-parser.ts:25-50`).
14
-
2.`createClineParser` reads each task's `ui_messages.json` and `api_conversation_history.json`, extracts model, tools, and token counts, and yields `ParsedProviderCall` objects.
13
+
1.`discoverClineTasks(extensionId)` walks VS Code's `globalStorage/<extensionId>/tasks/` directories and returns one source per task that has a `ui_messages.json` file.
14
+
2.`discoverClineTasksInBaseDirs(baseDirs)` does the same for non-VS Code apps with compatible task storage, such as IBM Bob.
15
+
3.`createClineParser` reads each task's `ui_messages.json` and `api_conversation_history.json`, extracts model and token counts, and yields `ParsedProviderCall` objects.
15
16
16
17
## Storage layout
17
18
@@ -25,25 +26,25 @@ Per task directory:
25
26
26
27
## Model resolution
27
28
28
-
The model is extracted from `api_conversation_history.json` by searching user message content blocks for a `<model>...</model>` tag (`vscode-cline-parser.ts:54-72`). Falls back to `cline-auto` if no tag is found.
29
+
The model is extracted from `api_conversation_history.json` by searching user message content blocks for a `<model>...</model>` tag. Falls back to the provider-supplied auto model (`cline-auto` by default) if no tag is found.
29
30
30
31
## Token extraction
31
32
32
-
From `api_req_started` entries inside `ui_messages.json`. Each such entry's `text` field is JSON-parsed; the parsed object holds `tokensIn`, `tokensOut`, `cacheReads`, `cacheWrites`, and (optionally) `cost` (`vscode-cline-parser.ts:119-134`).
33
+
From `api_req_started` entries inside `ui_messages.json`. Each such entry's `text` field is JSON-parsed; the parsed object holds `tokensIn`, `tokensOut`, `cacheReads`, `cacheWrites`, and (optionally) `cost`.
33
34
34
-
If `cost` is present, it is used directly. If not, `calculateCost` from `src/models.ts` computes it from tokens (`vscode-cline-parser.ts:139`).
35
+
If `cost` is present, it is used directly. If not, `calculateCost` from `src/models.ts` computes it from tokens.
35
36
36
37
## Deduplication
37
38
38
-
Per `<providerName>:<taskId>:<index>` where `index` is the position of the `api_req_started` entry within `ui_messages.json` (`vscode-cline-parser.ts:109`).
39
+
Per `<providerName>:<taskId>:<index>` where `index` is the position of the `api_req_started` entry within `ui_messages.json`.
39
40
40
41
## Quirks
41
42
42
-
- Only the **first** user message is emitted as `userMessage` in the `ParsedProviderCall` (`vscode-cline-parser.ts:157`). Subsequent user turns are accounted but not surfaced.
43
+
- Only the **first** user message is emitted as `userMessage` in the `ParsedProviderCall`. Subsequent user turns are accounted but not surfaced.
43
44
- The model regex looks inside content blocks, not at top-level fields. Some Cline-derivative extensions emit the model elsewhere; if you add support for one, branch on extension ID rather than rewriting the regex.
44
45
45
46
## When fixing a bug here
46
47
47
-
1. A change here ripples to **both**KiloCode and Roo Code. Run both test files (`tests/providers/kilo-code.test.ts` and `tests/providers/roo-code.test.ts`) before opening a PR.
48
+
1. A change here ripples to IBM Bob, KiloCode, and Roo Code. Run all three provider test files before opening a PR.
48
49
2. If you find that one of the two extensions emits a different shape, branch on the extension ID parameter that the discovery function already takes; do not duplicate the parser.
49
-
3. If you add support for a third Cline-derivative extension, register it as a thin wrapper file in the same shape as `kilo-code.ts` and `roo-code.ts`.
50
+
3. If you add support for another Cline-family task store, register it as a thin wrapper file in the same shape as `ibm-bob.ts`, `kilo-code.ts`, and `roo-code.ts`.
0 commit comments