fix: normalize malformed Bash tool arguments from OpenAI-compatible providers (#385)

* fix: normalize malformed Bash tool arguments from OpenAI-compatible providers

* fix: keep invalid Bash tool args from becoming commands

* fix: preserve malformed Bash JSON literals

* test: stabilize rebased PR 385 checks

* test: isolate provider profile env assertions

* fix: extend tool argument normalization to all tools and harden edge cases

- Extend STRING_ARGUMENT_TOOL_FIELDS to normalize Read, Write, Edit,
  Glob, and Grep plain-string arguments (fixes "Invalid tool parameters"
  errors reported by VennDev)
- Normalize streaming Bash args regardless of finish_reason, not only
  when finish_reason is 'tool_calls'
- Broaden isLikelyStructuredObjectLiteral to catch malformed object-shaped
  strings like {command:"pwd"} and {'command':'pwd'} (fixes CR2 from
  Vasanthdev2004)
- Apply blank/object-literal guard to all tools, not just Bash
- Extract duplicated JSON repair suffix combinations into shared constant
- Add 32 isolated unit tests for toolArgumentNormalization

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: skip streaming normalization on finish_reason length

Truncated tool calls (finish_reason: 'length') now preserve the raw
buffer instead of normalizing into executable commands, preventing
incomplete commands from becoming runnable.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: comprehensive tool argument normalization hardening

- Remove all { raw: ... } returns that caused InputValidationError with
  z.strictObject schemas — return {} instead for clean Zod errors
- Extend normalizeAtStop buffering to all mapped tools (Read, Write,
  Edit, Glob, Grep) so streaming paths also get normalized
- Make repairPossiblyTruncatedObjectJson generic — repair any valid
  JSON object, not just ones with a command field
- Export hasToolFieldMapping for streaming normalizeAtStop decision
- Skip normalization on finish_reason: length to preserve raw truncated
  buffer
- Update all test expectations to match new behavior

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

src/services/api/toolArgumentNormalization.ts

@@ -0,0 +1,69 @@
+const STRING_ARGUMENT_TOOL_FIELDS: Record<string, string> = {
+  Bash: 'command',
+  Read: 'file_path',
+  Write: 'file_path',
+  Edit: 'file_path',
+  Glob: 'pattern',
+  Grep: 'pattern',
+}
+
+function isBlankString(value: string): boolean {
+  return value.trim().length === 0
+}
+
+function isLikelyStructuredObjectLiteral(value: string): boolean {
+  // Match object-like patterns with key-value syntax:
+  // {"key":, {key:, {'key':, { "key" :, etc.
+  // But NOT bash compound commands like { pwd; } or { echo hi; }
+  return /^\s*\{\s*['"]?\w+['"]?\s*:/.test(value)
+}
+
+function isRecord(value: unknown): value is Record<string, unknown> {
+  return typeof value === 'object' && value !== null && !Array.isArray(value)
+}
+
+function getPlainStringToolArgumentField(toolName: string): string | null {
+  return STRING_ARGUMENT_TOOL_FIELDS[toolName] ?? null
+}
+
+export function hasToolFieldMapping(toolName: string): boolean {
+  return toolName in STRING_ARGUMENT_TOOL_FIELDS
+}
+
+function wrapPlainStringToolArguments(
+  toolName: string,
+  value: string,
+): Record<string, string> | null {
+  const field = getPlainStringToolArgumentField(toolName)
+  if (!field) return null
+  return { [field]: value }
+}
+
+export function normalizeToolArguments(
+  toolName: string,
+  rawArguments: string | undefined,
+): unknown {
+  if (rawArguments === undefined) return {}
+
+  try {
+    const parsed = JSON.parse(rawArguments)
+    if (isRecord(parsed)) {
+      return parsed
+    }
+    // Parsed as a non-object JSON value (string, number, boolean, null, array)
+    if (typeof parsed === 'string' && !isBlankString(parsed)) {
+      return wrapPlainStringToolArguments(toolName, parsed) ?? parsed
+    }
+    // For blank strings, booleans, null, arrays — pass through as-is
+    // and let Zod schema validation produce a meaningful error
+    return parsed
+  } catch {
+    // rawArguments is not valid JSON — treat as a plain string
+    if (isBlankString(rawArguments) || isLikelyStructuredObjectLiteral(rawArguments)) {
+      // Blank or looks like a malformed object literal — don't wrap into
+      // a tool field to avoid turning garbage into executable input
+      return {}
+    }
+    return wrapPlainStringToolArguments(toolName, rawArguments) ?? {}
+  }
+}