Add Kimi provider

docs/architecture.md

@@ -128,9 +128,9 @@ type Provider = {
 }
 ```
 
-`src/providers/index.ts` registers eighteen providers across two tiers:
+`src/providers/index.ts` registers nineteen providers across two tiers:
 
-- **Eager**: `claude`, `codex`, `copilot`, `droid`, `gemini`, `kilo-code`, `kiro`, `openclaw`, `pi`, `omp`, `qwen`, `roo-code`. Imported at module load.
+- **Eager**: `claude`, `codex`, `copilot`, `droid`, `gemini`, `kilo-code`, `kiro`, `openclaw`, `pi`, `omp`, `qwen`, `kimi`, `roo-code`. Imported at module load.
 - **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.
 
 Both lists hit the same `getAllProviders()` aggregator. A failed lazy import is silent and excludes that provider from the run.
@@ -181,7 +181,7 @@ The `prepublishOnly` hook in `package.json` runs `npm run build` so `npm publish
 
 - `tests/` root (27 files) covers CLI, parser, optimize, cache, format, models, plans.
 - `tests/security/` (1 file) covers prototype-pollution guards.
-- `tests/providers/` (14 files) covers per-provider parsing.
+- `tests/providers/` (15 files) covers per-provider parsing.
 - `tests/fixtures/` holds redacted real-world session data.
 
 Five providers ship without dedicated test files today: `antigravity`, `claude`, `gemini`, `goose`, `qwen`. Closing this gap is a standing good-first-issue.

docs/providers/README.md

@@ -17,6 +17,7 @@ For the architectural picture, see `../architecture.md`.
 | [Gemini](gemini.md) | JSON / JSONL | `src/providers/gemini.ts` | none |
 | [KiloCode](kilo-code.md) | JSON | `src/providers/kilo-code.ts` | `tests/providers/kilo-code.test.ts` |
 | [Kiro](kiro.md) | JSON | `src/providers/kiro.ts` | `tests/providers/kiro.test.ts` |
+| [Kimi](kimi.md) | JSONL | `src/providers/kimi.ts` | `tests/providers/kimi.test.ts` |
 | [OpenClaw](openclaw.md) | JSONL | `src/providers/openclaw.ts` | `tests/providers/openclaw.test.ts` |
 | [Pi](pi.md) | JSONL | `src/providers/pi.ts` | `tests/providers/pi.test.ts` |
 | [OMP](omp.md) | JSONL | `src/providers/pi.ts` | `tests/providers/omp.test.ts` |

docs/providers/kimi.md

@@ -0,0 +1,62 @@
+# Kimi
+
+Kimi Code CLI session parser.
+
+- **Source:** `src/providers/kimi.ts`
+- **Loading:** eager (`src/providers/index.ts`)
+- **Test:** `tests/providers/kimi.test.ts`
+
+## Where it reads from
+
+`$KIMI_SHARE_DIR/sessions/` if set, otherwise `~/.kimi/sessions/`.
+
+Kimi stores sessions by work-directory hash:
+
+```text
+~/.kimi/
+  kimi.json
+  config.toml
+  sessions/
+    <workdir-md5>/
+      <session-id>/
+        context.jsonl
+        wire.jsonl
+        state.json
+        subagents/
+          <agent-id>/
+            context.jsonl
+            wire.jsonl
+```
+
+`kimi.json` maps each work-directory hash back to the original working path. CodeBurn uses that to display the project basename; if the metadata file is missing, the hash directory name is used.
+
+## Storage Format
+
+CodeBurn reads `wire.jsonl`. Each data line is a persisted wire record:
+
+```json
+{"timestamp":1776162403,"message":{"type":"StatusUpdate","payload":{"message_id":"msg-1","token_usage":{"input_other":100,"input_cache_read":25,"input_cache_creation":10,"output":40}}}}
+```
+
+`TurnBegin` / `SteerInput` provide the user prompt, `ToolCall` / `ToolCallRequest` provide tool names and shell commands, and `StatusUpdate.token_usage` provides the billable token counts.
+
+## Caching
+
+None.
+
+## Deduplication
+
+Per `kimi:<session-id>:<message_id>`, falling back to the status-update line index if the message id is absent.
+
+## Quirks
+
+- Kimi's official `TokenUsage` separates `input_other`, `input_cache_read`, `input_cache_creation`, and `output`. CodeBurn maps those directly into input, cache read, cache write, and output.
+- The current Kimi wire schema does not persist the model on every usage update. CodeBurn uses `KIMI_MODEL_NAME` when set, then the active `~/.kimi/config.toml` default model, then `kimi-auto`.
+- `kimi-auto`, `kimi-code`, and `kimi-for-coding` are priced as `kimi-k2-thinking` so managed Kimi Code sessions do not show as `$0` when the exact backend model is hidden.
+- Subagent sessions are discovered from `subagents/<agent-id>/wire.jsonl` and parsed as separate Kimi sessions under the same project.
+
+## When Fixing A Bug Here
+
+1. Reproduce with a tiny `wire.jsonl` fixture in `tests/providers/kimi.test.ts`.
+2. If token totals look wrong, inspect `StatusUpdate.token_usage` first; `context.jsonl` only stores context checkpoints and cumulative counts, not per-step billing detail.
+3. If tools are missing, check whether Kimi emitted `ToolCall`, `ToolCallRequest`, or nested `SubagentEvent`; CodeBurn intentionally counts subagent wire files separately to avoid double-counting parent mirrors.