@fuzzle/opencode-accountant 0.4.6-next.1 → 0.4.6

package/docs/tools/classify-statements.md

@@ -18,8 +18,6 @@ This tool is **restricted to the accountant agent only**.
 - `{paths.pending}` = `import/pending`
 - `{paths.unrecognized}` = `import/unrecognized`
 
-**Note on Context IDs:** Each classified file receives a unique `contextId` (UUID). This ID references an import context file stored in `.memory/{uuid}.json` that tracks the file's metadata and progress through the import pipeline. The context is used by subsequent tools (`import-statements`, `reconcile-statement`) to locate files and retrieve metadata. See [Import Context Architecture](../architecture/import-context.md) for details.
-
 ### Success - All Files Classified
 
 When all CSV files are successfully classified:
@@ -32,15 +30,13 @@ When all CSV files are successfully classified:
       "filename": "transactions-ubs-2026-02.csv",
       "provider": "ubs",
       "currency": "chf",
-      "targetPath": "{paths.pending}/ubs/chf/transactions-ubs-2026-02.csv",
-      "contextId": "f47ac10b-58cc-4372-a567-0e02b2c3d479"
+      "targetPath": "{paths.pending}/ubs/chf/transactions-ubs-2026-02.csv"
     },
     {
       "filename": "account-statement_2026-02.csv",
       "provider": "revolut",
       "currency": "eur",
-      "targetPath": "{paths.pending}/revolut/eur/account-statement_2026-02.csv",
-      "contextId": "8b3e9c21-1a4f-4d89-b123-9f8e7d6c5b4a"
+      "targetPath": "{paths.pending}/revolut/eur/account-statement_2026-02.csv"
     }
   ],
   "unrecognized": [],
@@ -65,8 +61,7 @@ When provider config includes `renamePattern` with metadata extraction:
       "originalFilename": "export.csv",
       "provider": "ubs",
       "currency": "chf",
-      "targetPath": "{paths.pending}/ubs/chf/transactions-ubs-0235-90250546.csv",
-      "contextId": "a1b2c3d4-5e6f-7g8h-9i0j-k1l2m3n4o5p6"
+      "targetPath": "{paths.pending}/ubs/chf/transactions-ubs-0235-90250546.csv"
     }
   ],
   "unrecognized": [],
@@ -92,8 +87,7 @@ When some files cannot be classified:
       "filename": "transactions-ubs-2026-02.csv",
       "provider": "ubs",
       "currency": "chf",
-      "targetPath": "{paths.pending}/ubs/chf/transactions-ubs-2026-02.csv",
-      "contextId": "f47ac10b-58cc-4372-a567-0e02b2c3d479"
+      "targetPath": "{paths.pending}/ubs/chf/transactions-ubs-2026-02.csv"
     }
   ],
   "unrecognized": [
@@ -213,74 +207,13 @@ ubs:
 
 This extracts metadata from the CSV (e.g., account number from row 0, column 1) and uses it in the output filename.
 
-## Import Context
-
-Each classified file gets an **import context** - a JSON file stored in `.memory/{contextId}.json` that tracks the file's metadata and progress through the import pipeline.
-
-### What Gets Stored in the Context
-
-When a CSV is classified, the context is created with:
-
-- **File tracking**: filename, file path, original filename (if renamed)
-- **Provider detection**: provider, currency, account number
-- **CSV metadata**: transaction date range (from-date, until-date), opening/closing balances
-- **Timestamps**: creation and last update times
-
-### Example Context File
-
-`.memory/f47ac10b-58cc-4372-a567-0e02b2c3d479.json`:
-
-```json
-{
-  "id": "f47ac10b-58cc-4372-a567-0e02b2c3d479",
-  "createdAt": "2026-02-28T10:30:00.000Z",
-  "updatedAt": "2026-02-28T10:30:00.000Z",
-
-  "filename": "ubs-0235-90250546.1-transactions-2026-02-22-to-2026-02-24.csv",
-  "filePath": "import/pending/ubs/chf/ubs-0235-90250546.1-transactions-2026-02-22-to-2026-02-24.csv",
-  "originalFilename": "transactions-0235-90250546.1-2026-02.csv",
-
-  "provider": "ubs",
-  "currency": "chf",
-  "accountNumber": "0235-90250546.1",
-
-  "fromDate": "2026-02-22",
-  "untilDate": "2026-02-24",
-  "openingBalance": "4001.55",
-  "closingBalance": "9001.55"
-}
-```
-
-### Context Lifecycle
-
-1. **Created by classify-statements**: Initial context with provider/currency/metadata
-2. **Updated by import-statements**: Adds rules file, year journal, transaction count
-3. **Updated by reconcile-statement**: Adds reconciliation results
-4. **Persisted**: Remains in `.memory/` for audit/debugging
-
-### Why Context IDs Matter
-
-Context IDs solve the **multi-account problem**: when you have multiple accounts from the same provider/currency (e.g., UBS checking `.0` and savings `.1`), the context ID ensures each file is tracked independently and reconciled against the correct account.
-
-**Without contexts**: Tools would select CSVs by timestamp → wrong account reconciled ❌
-
-**With contexts**: Each CSV has an `accountNumber` in its context → correct account reconciled ✓
-
-See [Import Context Architecture](../architecture/import-context.md) for complete technical details.
-
 ## Directory Structure
 
 ```
 your-project/
-├── .memory/                        # Import context files (created by classify-statements)
-│   ├── f47ac10b-58cc-4372-a567-0e02b2c3d479.json  # Context for UBS checking
-│   ├── 8b3e9c21-1a4f-4d89-b123-9f8e7d6c5b4a.json  # Context for UBS savings
-│   └── a1b2c3d4-5e6f-7g8h-9i0j-k1l2m3n4o5p6.json  # Context for Revolut EUR
-│
 ├── config/
 │   └── import/
 │       └── providers.yaml          # Defines all paths and detection rules
-│
 ├── {paths.import}/                 # Drop CSV files here (default: import/incoming)
 │   ├── bank1.csv
 │   └── bank2.csv
@@ -291,8 +224,7 @@ your-project/
 │   │       └── classified.csv
 │   ├── ubs/
 │   │   └── chf/
-│   │       ├── ubs-0235-90250546.0-transactions-2026-02.csv  # Checking
-│   │       └── ubs-0235-90250546.1-transactions-2026-02.csv  # Savings
+│   │       └── transactions-ubs-0235-90250546.csv
 │   └── revolut/
 │       └── eur/
 │           └── account-statement_2026-02.csv
@@ -301,13 +233,6 @@ your-project/
     └── mystery-bank.csv
 ```
 
-**Note on `.memory/` directory:**
-
-- Contains import context JSON files (one per classified CSV)
-- Each context tracks metadata and progress through the pipeline
-- Files persist for audit/debugging (not auto-deleted)
-- Directory is gitignored (contexts are local/temporary)
-
 ## Typical Workflow
 
 ### Scenario 1: Successful Classification
@@ -315,10 +240,8 @@ your-project/
 1. Drop CSV files into `{paths.import}/` (e.g., `import/incoming/`)
 2. Run `classify-statements` tool (no arguments)
 3. Check output - all files classified successfully
-4. **Each file gets a unique contextId** stored in `.memory/{uuid}.json`
-5. Files organized in `{paths.pending}/<provider>/<currency>/`
-6. **Context IDs are passed automatically to subsequent steps** when using `import-pipeline`
-7. Proceed to `import-statements` or `import-pipeline` tool
+4. Files organized in `{paths.pending}/<provider>/<currency>/`
+5. Proceed to `import-statements` tool
 
 ### Scenario 2: Handling Unrecognized Files
 

package/docs/tools/import-statements.md

@@ -5,8 +5,6 @@ The `import-statements` tool imports classified CSV bank statements into hledger
 - **Check mode** (`checkOnly: true`, default): Validates transactions and reports any that cannot be categorized
 - **Import mode** (`checkOnly: false`): Imports validated transactions and moves processed files to the done directory
 
-**Important**: This tool requires a `contextId` from a prior `classify-statements` run. The context provides the file path and metadata needed for import. See [Import Context Architecture](../architecture/import-context.md) for details.
-
 ## Year-Based Journal Routing
 
 Transactions are automatically routed to year-specific journal files based on transaction dates:
@@ -21,47 +19,13 @@ Transactions are automatically routed to year-specific journal files based on tr
 
 **Constraint:** Each CSV file must contain transactions from a single year. CSVs with transactions spanning multiple years are rejected during check mode with an error message listing the years found.
 
-## Using Context IDs
-
-The tool uses import contexts to locate CSV files and access metadata:
-
-### How It Works
-
-1. **classify-statements** creates a context for each CSV with a unique ID
-2. **import-statements** receives the contextId (via import-pipeline or manual invocation)
-3. Tool loads the context from `.memory/{contextId}.json`
-4. Context provides the file path to the CSV (no need to search by provider/currency)
-5. After import, tool updates context with results (rules file, year journal, transaction count)
-
-### Manual Invocation Example
-
-```bash
-# Step 1: Classify statements
-classify-statements
-# Output: { "classified": [{ "contextId": "abc123-...", ... }] }
-
-# Step 2: Import using contextId
-import-statements --contextId "abc123-..." --checkOnly false
-```
-
-### Automatic Invocation via Pipeline
-
-When using `import-pipeline`, context IDs are passed automatically:
-
-```bash
-# Pipeline handles everything
-import-pipeline
-# Internally: classify → get contextIds → import each context → reconcile each context
-```
-
 ## Arguments
 
-| Argument    | Type    | Required | Default | Description                                        |
-| ----------- | ------- | -------- | ------- | -------------------------------------------------- |
-| `contextId` | string  | Yes      | -       | Context ID from `classify-statements` (e.g., UUID) |
-| `checkOnly` | boolean | No       | `true`  | If true, only validate without importing           |
-
-**Note**: When called via `import-pipeline`, the `contextId` is passed automatically. For manual invocation, get the `contextId` from `classify-statements` output.
+| Argument    | Type    | Default | Description                                 |
+| ----------- | ------- | ------- | ------------------------------------------- |
+| `provider`  | string  | -       | Filter by provider (e.g., `revolut`, `ubs`) |
+| `currency`  | string  | -       | Filter by currency (e.g., `chf`, `eur`)     |
+| `checkOnly` | boolean | `true`  | If true, only validate without importing    |
 
 ## Output Format
 
@@ -97,8 +61,6 @@ When all transactions have matching rules:
 }
 ```
 
-**Note**: When invoked via `import-pipeline`, the CSV file path comes from the import context (loaded via `contextId`). The context also provides metadata like account number and closing balance.
-
 ### Check Mode - Unknown Postings Found
 
 When transactions don't match any `if` pattern in the rules file, the tool returns the full CSV row data for each unknown posting to provide context for classification:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@fuzzle/opencode-accountant",
-  "version": "0.4.6-next.1",
+  "version": "0.4.6",
   "description": "An OpenCode accounting agent, specialized in double-entry-bookkepping with hledger",
   "author": {
     "name": "ali bengali",
@@ -28,7 +28,8 @@
     "docs"
   ],
   "dependencies": {
-    "@opencode-ai/plugin": "^1.2.6",
+    "@opencode-ai/plugin": "latest",
+    "convert-csv-to-json": "^3.20.0",
     "glob": "^10.3.10",
     "js-yaml": "^4.1.0",
     "minimatch": "^9.0.3",
@@ -43,7 +44,7 @@
     "@types/uuid": "^11.0.0",
     "@typescript-eslint/eslint-plugin": "8.47.0",
     "@typescript-eslint/parser": "8.47.0",
-    "bun-types": "^1.3.9",
+    "bun-types": "latest",
     "eslint": "^9.39.1",
     "eslint-config-prettier": "10.1.8",
     "eslint-plugin-prettier": "^5.1.3",