Compare commits
3 Commits
fb9d4e5b9f
...
master
| Author | SHA1 | Date | |
|---|---|---|---|
|
c5b1fb3a80 | ||
|
|
abbede923d | ||
|
|
ef451cf20f |
@@ -3,6 +3,21 @@ import os
|
||||
|
||||
from amc_server.config import EVENTS_DIR
|
||||
|
||||
# Prefixes for system-injected content that appears as user messages
|
||||
# but was not typed by the human (hook outputs, system reminders, etc.)
|
||||
_SYSTEM_INJECTED_PREFIXES = (
|
||||
"<system-reminder>",
|
||||
"<local-command-caveat>",
|
||||
"<available-deferred-tools>",
|
||||
"<teammate-message",
|
||||
)
|
||||
|
||||
|
||||
def _is_system_injected(content):
|
||||
"""Return True if user message content is system-injected, not human-typed."""
|
||||
stripped = content.lstrip()
|
||||
return stripped.startswith(_SYSTEM_INJECTED_PREFIXES)
|
||||
|
||||
|
||||
class ConversationMixin:
|
||||
def _serve_events(self, session_id):
|
||||
@@ -57,7 +72,7 @@ class ConversationMixin:
|
||||
if msg_type == "user":
|
||||
content = entry.get("message", {}).get("content", "")
|
||||
# Only include actual human messages (strings), not tool results (arrays)
|
||||
if content and isinstance(content, str):
|
||||
if content and isinstance(content, str) and not _is_system_injected(content):
|
||||
messages.append({
|
||||
"id": f"claude-{session_id[:8]}-{msg_id}",
|
||||
"role": "user",
|
||||
|
||||
@@ -167,6 +167,7 @@ export function SessionCard({ session, onClick, conversation, onFetchConversatio
|
||||
status=${session.status}
|
||||
onRespond=${onRespond}
|
||||
autocompleteConfig=${autocompleteConfig}
|
||||
conversation=${conversation}
|
||||
/>
|
||||
`}
|
||||
</div>
|
||||
|
||||
@@ -2,7 +2,7 @@ import { html, useState, useRef, useCallback, useMemo, useEffect } from '../lib/
|
||||
import { getStatusMeta } from '../utils/status.js';
|
||||
import { getTriggerInfo as _getTriggerInfo, filteredSkills as _filteredSkills } from '../utils/autocomplete.js';
|
||||
|
||||
export function SimpleInput({ sessionId, status, onRespond, autocompleteConfig = null }) {
|
||||
export function SimpleInput({ sessionId, status, onRespond, autocompleteConfig = null, conversation }) {
|
||||
const [text, setText] = useState('');
|
||||
const [focused, setFocused] = useState(false);
|
||||
const [sending, setSending] = useState(false);
|
||||
@@ -12,8 +12,15 @@ export function SimpleInput({ sessionId, status, onRespond, autocompleteConfig =
|
||||
const [selectedIndex, setSelectedIndex] = useState(0);
|
||||
const textareaRef = useRef(null);
|
||||
const autocompleteRef = useRef(null);
|
||||
const historyIndexRef = useRef(-1);
|
||||
const draftRef = useRef('');
|
||||
const meta = getStatusMeta(status);
|
||||
|
||||
const userHistory = useMemo(
|
||||
() => (conversation || []).filter(m => m.role === 'user').map(m => m.content),
|
||||
[conversation]
|
||||
);
|
||||
|
||||
const getTriggerInfo = useCallback((value, cursorPos) => {
|
||||
return _getTriggerInfo(value, cursorPos, autocompleteConfig);
|
||||
}, [autocompleteConfig]);
|
||||
@@ -100,6 +107,7 @@ export function SimpleInput({ sessionId, status, onRespond, autocompleteConfig =
|
||||
try {
|
||||
await onRespond(sessionId, text.trim(), true, 0);
|
||||
setText('');
|
||||
historyIndexRef.current = -1;
|
||||
} catch (err) {
|
||||
setError('Failed to send message');
|
||||
console.error('SimpleInput send error:', err);
|
||||
@@ -130,6 +138,7 @@ export function SimpleInput({ sessionId, status, onRespond, autocompleteConfig =
|
||||
const value = e.target.value;
|
||||
const cursorPos = e.target.selectionStart;
|
||||
setText(value);
|
||||
historyIndexRef.current = -1;
|
||||
setTriggerInfo(getTriggerInfo(value, cursorPos));
|
||||
e.target.style.height = 'auto';
|
||||
e.target.style.height = e.target.scrollHeight + 'px';
|
||||
@@ -169,6 +178,57 @@ export function SimpleInput({ sessionId, status, onRespond, autocompleteConfig =
|
||||
}
|
||||
}
|
||||
|
||||
// History navigation (only when autocomplete is closed)
|
||||
if (e.key === 'ArrowUp' && !showAutocomplete &&
|
||||
e.target.selectionStart === 0 && e.target.selectionEnd === 0 &&
|
||||
userHistory.length > 0) {
|
||||
e.preventDefault();
|
||||
if (historyIndexRef.current === -1) {
|
||||
draftRef.current = text;
|
||||
historyIndexRef.current = userHistory.length - 1;
|
||||
} else if (historyIndexRef.current > 0) {
|
||||
historyIndexRef.current -= 1;
|
||||
}
|
||||
// Clamp if history shrank since last navigation
|
||||
if (historyIndexRef.current >= userHistory.length) {
|
||||
historyIndexRef.current = userHistory.length - 1;
|
||||
}
|
||||
const historyText = userHistory[historyIndexRef.current];
|
||||
setText(historyText);
|
||||
setTimeout(() => {
|
||||
if (textareaRef.current) {
|
||||
textareaRef.current.selectionStart = historyText.length;
|
||||
textareaRef.current.selectionEnd = historyText.length;
|
||||
textareaRef.current.style.height = 'auto';
|
||||
textareaRef.current.style.height = textareaRef.current.scrollHeight + 'px';
|
||||
}
|
||||
}, 0);
|
||||
return;
|
||||
}
|
||||
|
||||
if (e.key === 'ArrowDown' && !showAutocomplete &&
|
||||
historyIndexRef.current !== -1) {
|
||||
e.preventDefault();
|
||||
historyIndexRef.current += 1;
|
||||
let newText;
|
||||
if (historyIndexRef.current >= userHistory.length) {
|
||||
historyIndexRef.current = -1;
|
||||
newText = draftRef.current;
|
||||
} else {
|
||||
newText = userHistory[historyIndexRef.current];
|
||||
}
|
||||
setText(newText);
|
||||
setTimeout(() => {
|
||||
if (textareaRef.current) {
|
||||
textareaRef.current.selectionStart = newText.length;
|
||||
textareaRef.current.selectionEnd = newText.length;
|
||||
textareaRef.current.style.height = 'auto';
|
||||
textareaRef.current.style.height = textareaRef.current.scrollHeight + 'px';
|
||||
}
|
||||
}, 0);
|
||||
return;
|
||||
}
|
||||
|
||||
// Normal Enter-to-submit (only when dropdown is closed)
|
||||
if (e.key === 'Enter' && !e.shiftKey) {
|
||||
e.preventDefault();
|
||||
|
||||
@@ -20,6 +20,8 @@ Add the ability to view tool call results (diffs, bash output, file contents) di
|
||||
- Copy-to-clipboard functionality
|
||||
- Virtual scrolling / performance optimization
|
||||
- Editor integration (clicking paths to open files)
|
||||
- Accessibility (keyboard navigation, focus management, ARIA labels — deferred to v2)
|
||||
- Lazy-fetch API for tool results (consider for v2 if payload size becomes an issue)
|
||||
|
||||
---
|
||||
|
||||
@@ -61,44 +63,46 @@ Add the ability to view tool call results (diffs, bash output, file contents) di
|
||||
- **AC-1:** Tool calls render as expandable elements showing tool name and summary
|
||||
- **AC-2:** Clicking a collapsed tool call expands to show its result
|
||||
- **AC-3:** Clicking an expanded tool call collapses it
|
||||
- **AC-4:** Tool results in the most recent assistant message are expanded by default
|
||||
- **AC-5:** When a new assistant message arrives, previous tool results collapse
|
||||
- **AC-6:** Edit and Write tool diffs remain expanded regardless of message age
|
||||
- **AC-7:** Tool calls without results display as non-expandable with muted styling
|
||||
- **AC-4:** In active sessions, tool results in the most recent assistant message are expanded by default
|
||||
- **AC-5:** When a new assistant message arrives, previous non-diff tool results collapse unless the user has manually toggled them in that message
|
||||
- **AC-6:** Edit and Write results remain expanded regardless of message age or session status (even if Write only has confirmation text)
|
||||
- **AC-7:** In completed sessions, all non-diff tool results start collapsed
|
||||
- **AC-8:** Tool calls without results display as non-expandable with muted styling; in active sessions, pending tool calls show a spinner to distinguish in-progress from permanently missing
|
||||
|
||||
### Diff Rendering
|
||||
|
||||
- **AC-8:** Edit/Write results display structuredPatch data as syntax-highlighted diff
|
||||
- **AC-9:** Diff additions render with VS Code dark theme green background (rgba(46, 160, 67, 0.15))
|
||||
- **AC-10:** Diff deletions render with VS Code dark theme red background (rgba(248, 81, 73, 0.15))
|
||||
- **AC-11:** Full file path displays above each diff block
|
||||
- **AC-12:** Diff context lines use structuredPatch as-is (no recomputation)
|
||||
- **AC-9:** Edit/Write results display structuredPatch data as syntax-highlighted diff; falls back to raw content text if structuredPatch is malformed or absent
|
||||
- **AC-10:** Diff additions render with VS Code dark theme green background (rgba(46, 160, 67, 0.15))
|
||||
- **AC-11:** Diff deletions render with VS Code dark theme red background (rgba(248, 81, 73, 0.15))
|
||||
- **AC-12:** Full file path displays above each diff block
|
||||
- **AC-13:** Diff context lines use structuredPatch as-is (no recomputation)
|
||||
|
||||
### Other Tool Types
|
||||
|
||||
- **AC-13:** Bash results display stdout in monospace, stderr separately if present
|
||||
- **AC-14:** Read results display file content with syntax highlighting based on file extension
|
||||
- **AC-15:** Grep/Glob results display file list with match counts
|
||||
- **AC-16:** WebFetch results display URL and response summary
|
||||
- **AC-14:** Bash results display stdout in monospace, stderr separately if present
|
||||
- **AC-15:** Bash output with ANSI escape codes renders as colored HTML (via ansi_up)
|
||||
- **AC-16:** Read results display file content with syntax highlighting based on file extension
|
||||
- **AC-17:** Grep/Glob results display file list with match counts
|
||||
- **AC-18:** Unknown tools (WebFetch, Task, etc.) use GenericResult fallback showing raw content
|
||||
|
||||
### Truncation
|
||||
|
||||
- **AC-17:** Long outputs truncate at thresholds matching Claude Code behavior
|
||||
- **AC-18:** Truncated outputs show "Show full output (N lines)" link
|
||||
- **AC-19:** Clicking "Show full output" opens a dedicated lightweight modal
|
||||
- **AC-20:** Modal displays full content with syntax highlighting, scrollable
|
||||
- **AC-19:** Long outputs truncate at configurable line/character thresholds (defaults tuned to approximate Claude Code behavior)
|
||||
- **AC-20:** Truncated outputs show "Show full output (N lines)" link
|
||||
- **AC-21:** Clicking "Show full output" opens a dedicated lightweight modal
|
||||
- **AC-22:** Modal displays full content with syntax highlighting, scrollable
|
||||
|
||||
### Error States
|
||||
|
||||
- **AC-21:** Failed tool calls display with red-tinted background
|
||||
- **AC-22:** Error content (stderr, error messages) is clearly distinguishable from success content
|
||||
- **AC-23:** is_error flag from tool_result determines error state
|
||||
- **AC-23:** Failed tool calls display with red-tinted background
|
||||
- **AC-24:** Error content (stderr, error messages) is clearly distinguishable from success content
|
||||
- **AC-25:** is_error flag from tool_result determines error state
|
||||
|
||||
### API Contract
|
||||
|
||||
- **AC-24:** /api/conversation response includes tool results nested in tool_calls
|
||||
- **AC-25:** Each tool_call has: name, id, input, result (when available)
|
||||
- **AC-26:** Result structure varies by tool type (documented in IMP-SERVER)
|
||||
- **AC-26:** /api/conversation response includes tool results nested in tool_calls
|
||||
- **AC-27:** Each tool_call has: name, id, input, result (when available)
|
||||
- **AC-28:** All tool results conform to a normalized envelope: `{ kind, status, content, is_error }` with tool-specific fields nested in `content`
|
||||
|
||||
---
|
||||
|
||||
@@ -130,6 +134,23 @@ Full output can be thousands of lines. Inline expansion would:
|
||||
|
||||
A modal provides a focused reading experience without disrupting conversation layout.
|
||||
|
||||
### Why a Normalized Result Contract
|
||||
|
||||
Raw `toolUseResult` shapes vary wildly by tool type — Edit has `structuredPatch`, Bash has `stdout`/`stderr`, Glob has `filenames`. Passing these raw to the frontend means every renderer must know the exact JSONL format, and adding Codex support (v2) would require duplicating all that branching.
|
||||
|
||||
Instead, the server normalizes each result into a stable envelope:
|
||||
|
||||
```python
|
||||
{
|
||||
"kind": "diff" | "bash" | "file_content" | "file_list" | "generic",
|
||||
"status": "success" | "error" | "pending",
|
||||
"is_error": bool,
|
||||
"content": { ... } # tool-specific fields, documented per kind
|
||||
}
|
||||
```
|
||||
|
||||
The frontend switches on `kind` (5 cases) rather than tool name (unbounded). This also gives us a clean seam for the `result_mode` query parameter if payload size becomes an issue later.
|
||||
|
||||
### Component Structure
|
||||
|
||||
```
|
||||
@@ -157,7 +178,7 @@ FullOutputModal (new, top-level)
|
||||
|
||||
### IMP-SERVER: Parse and Attach Tool Results
|
||||
|
||||
**Fulfills:** AC-24, AC-25, AC-26
|
||||
**Fulfills:** AC-26, AC-27, AC-28
|
||||
|
||||
**Location:** `amc_server/mixins/conversation.py`
|
||||
|
||||
@@ -167,38 +188,43 @@ Two-pass parsing:
|
||||
1. First pass: Scan all entries, build map of `tool_use_id` → `toolUseResult`
|
||||
2. Second pass: Parse messages as before, but when encountering `tool_use`, lookup and attach result
|
||||
|
||||
**Tool call schema after change:**
|
||||
**API query parameter:** `/api/conversation?result_mode=full` (default). Future option: `result_mode=preview` to return truncated previews and reduce payload size without an API-breaking change.
|
||||
|
||||
**Normalization step:** After looking up the raw `toolUseResult`, the server normalizes it into the stable envelope before attaching:
|
||||
|
||||
```python
|
||||
{
|
||||
"name": "Edit",
|
||||
"id": "toolu_abc123",
|
||||
"input": {"file_path": "...", "old_string": "...", "new_string": "..."},
|
||||
"result": {
|
||||
"content": "The file has been updated successfully.",
|
||||
"kind": "diff",
|
||||
"status": "success",
|
||||
"is_error": False,
|
||||
"structuredPatch": [...],
|
||||
"filePath": "...",
|
||||
# ... other fields from toolUseResult
|
||||
"content": {
|
||||
"structuredPatch": [...],
|
||||
"filePath": "...",
|
||||
"text": "The file has been updated successfully."
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**Result Structure by Tool Type:**
|
||||
**Normalized `kind` mapping:**
|
||||
|
||||
| Tool | Result Fields |
|
||||
|------|---------------|
|
||||
| Edit | `structuredPatch`, `filePath`, `oldString`, `newString` |
|
||||
| Write | `filePath`, content confirmation |
|
||||
| Read | `file`, `type`, content in `content` field |
|
||||
| Bash | `stdout`, `stderr`, `interrupted` |
|
||||
| Glob | `filenames`, `numFiles`, `truncated` |
|
||||
| Grep | `content`, `filenames`, `numFiles`, `numLines` |
|
||||
| kind | Source Tools | `content` Fields |
|
||||
|------|-------------|-----------------|
|
||||
| `diff` | Edit, Write | `structuredPatch`, `filePath`, `text` |
|
||||
| `bash` | Bash | `stdout`, `stderr`, `interrupted` |
|
||||
| `file_content` | Read | `file`, `type`, `text` |
|
||||
| `file_list` | Glob, Grep | `filenames`, `numFiles`, `truncated`, `numLines` |
|
||||
| `generic` | All others | `text` (raw content string) |
|
||||
|
||||
---
|
||||
|
||||
### IMP-TOOLCALL: Expandable Tool Call Component
|
||||
|
||||
**Fulfills:** AC-1, AC-2, AC-3, AC-4, AC-5, AC-6, AC-7
|
||||
**Fulfills:** AC-1, AC-2, AC-3, AC-4, AC-5, AC-6, AC-7, AC-8
|
||||
|
||||
**Location:** `dashboard/lib/markdown.js` (refactor `renderToolCalls`)
|
||||
|
||||
@@ -213,16 +239,21 @@ Renders a single tool call with:
|
||||
|
||||
**State Management:**
|
||||
|
||||
Track expanded state per message. When new assistant message arrives:
|
||||
Track two sets per message: `autoExpanded` (system-controlled) and `userToggled` (manual clicks).
|
||||
|
||||
When new assistant message arrives:
|
||||
- Compare latest assistant message ID to stored ID
|
||||
- If different, reset expanded set to empty
|
||||
- If different, reset `autoExpanded` to empty for previous messages
|
||||
- `userToggled` entries are never reset — user intent is preserved
|
||||
- Edit/Write tools bypass this logic (always expanded via CSS/logic)
|
||||
|
||||
Expand/collapse logic: a tool call is expanded if it is in `userToggled` (explicit click) OR in `autoExpanded` (latest message) OR is Edit/Write kind.
|
||||
|
||||
---
|
||||
|
||||
### IMP-DIFF: Diff Rendering Component
|
||||
|
||||
**Fulfills:** AC-8, AC-9, AC-10, AC-11, AC-12
|
||||
**Fulfills:** AC-9, AC-10, AC-11, AC-12, AC-13
|
||||
|
||||
**Location:** `dashboard/lib/markdown.js` (new function `renderDiff`)
|
||||
|
||||
@@ -234,12 +265,13 @@ hljs.registerLanguage('diff', langDiff);
|
||||
|
||||
**Diff Renderer:**
|
||||
|
||||
1. Convert `structuredPatch` array to unified diff text:
|
||||
1. If `structuredPatch` is present and valid, convert to unified diff text:
|
||||
- Each hunk: `@@ -oldStart,oldLines +newStart,newLines @@`
|
||||
- Followed by hunk.lines array
|
||||
2. Syntax highlight with hljs diff language
|
||||
3. Sanitize with DOMPurify before rendering
|
||||
4. Wrap in container with file path header
|
||||
2. If `structuredPatch` is missing or malformed, fall back to raw `content.text` in a monospace block
|
||||
3. Syntax highlight with hljs diff language
|
||||
4. Sanitize with DOMPurify before rendering
|
||||
5. Wrap in container with file path header
|
||||
|
||||
**CSS styling:**
|
||||
- Container: dark border, rounded corners
|
||||
@@ -252,22 +284,33 @@ hljs.registerLanguage('diff', langDiff);
|
||||
|
||||
### IMP-BASH: Bash Output Component
|
||||
|
||||
**Fulfills:** AC-13, AC-21, AC-22
|
||||
**Fulfills:** AC-14, AC-15, AC-23, AC-24
|
||||
|
||||
**Location:** `dashboard/lib/markdown.js` (new function `renderBashResult`)
|
||||
|
||||
Renders:
|
||||
- `stdout` in monospace pre block
|
||||
**ANSI-to-HTML conversion:**
|
||||
```javascript
|
||||
import AnsiUp from 'https://esm.sh/ansi_up';
|
||||
const ansi = new AnsiUp();
|
||||
const html = ansi.ansi_to_html(bashOutput);
|
||||
```
|
||||
|
||||
The `ansi_up` library (zero dependencies, ~8KB) converts ANSI escape codes to styled HTML spans, preserving colored test output, progress indicators, and error highlighting from CLI tools.
|
||||
|
||||
**Renders:**
|
||||
- `stdout` in monospace pre block with ANSI colors preserved
|
||||
- `stderr` in separate block with error styling (if present)
|
||||
- "Command interrupted" notice (if interrupted flag)
|
||||
|
||||
**Sanitization order (CRITICAL):** First convert ANSI to HTML via ansi_up, THEN sanitize with DOMPurify. Sanitizing before conversion would strip escape codes; sanitizing after preserves the styled spans while preventing XSS.
|
||||
|
||||
Error state: `is_error` or presence of stderr triggers error styling (red tint, left border).
|
||||
|
||||
---
|
||||
|
||||
### IMP-TRUNCATE: Output Truncation
|
||||
|
||||
**Fulfills:** AC-17, AC-18
|
||||
**Fulfills:** AC-19, AC-20
|
||||
|
||||
**Truncation Thresholds (match Claude Code):**
|
||||
|
||||
@@ -289,7 +332,7 @@ Takes content string, returns `{ text, truncated, totalLines }`. If truncated, r
|
||||
|
||||
### IMP-MODAL: Full Output Modal
|
||||
|
||||
**Fulfills:** AC-19, AC-20
|
||||
**Fulfills:** AC-21, AC-22
|
||||
|
||||
**Location:** `dashboard/components/FullOutputModal.js` (new file)
|
||||
|
||||
@@ -305,7 +348,7 @@ Takes content string, returns `{ text, truncated, totalLines }`. If truncated, r
|
||||
|
||||
### IMP-ERROR: Error State Styling
|
||||
|
||||
**Fulfills:** AC-21, AC-22, AC-23
|
||||
**Fulfills:** AC-23, AC-24, AC-25
|
||||
|
||||
**Styling:**
|
||||
- Tool call header: red-tinted background when `result.is_error`
|
||||
@@ -331,17 +374,19 @@ Takes content string, returns `{ text, truncated, totalLines }`. If truncated, r
|
||||
|
||||
---
|
||||
|
||||
### Slice 2: Server-Side Tool Result Parsing
|
||||
### Slice 2: Server-Side Tool Result Parsing and Normalization
|
||||
|
||||
**Goal:** API returns tool results nested in tool_calls
|
||||
**Goal:** API returns normalized tool results nested in tool_calls
|
||||
|
||||
**Deliverables:**
|
||||
1. Two-pass parsing in `_parse_claude_conversation`
|
||||
2. Tool results attached with `id` field
|
||||
3. Unit tests for result attachment
|
||||
4. Handle missing results gracefully (return tool_call without result)
|
||||
2. Normalization layer: raw `toolUseResult` → `{ kind, status, is_error, content }` envelope
|
||||
3. Tool results attached with `id` field
|
||||
4. Unit tests for result attachment and normalization per tool type
|
||||
5. Handle missing results gracefully (return tool_call without result)
|
||||
6. Support `result_mode=full` query parameter (only mode for now, but wired up for future `preview`)
|
||||
|
||||
**Exit Criteria:** AC-24, AC-25, AC-26 pass
|
||||
**Exit Criteria:** AC-26, AC-27, AC-28 pass
|
||||
|
||||
---
|
||||
|
||||
@@ -356,7 +401,7 @@ Takes content string, returns `{ text, truncated, totalLines }`. If truncated, r
|
||||
4. Collapse on new assistant message
|
||||
5. Keep Edit/Write always expanded
|
||||
|
||||
**Exit Criteria:** AC-1 through AC-7 pass
|
||||
**Exit Criteria:** AC-1 through AC-8 pass
|
||||
|
||||
---
|
||||
|
||||
@@ -370,7 +415,7 @@ Takes content string, returns `{ text, truncated, totalLines }`. If truncated, r
|
||||
3. VS Code dark theme styling
|
||||
4. Full file path header
|
||||
|
||||
**Exit Criteria:** AC-8 through AC-12 pass
|
||||
**Exit Criteria:** AC-9 through AC-13 pass
|
||||
|
||||
---
|
||||
|
||||
@@ -379,12 +424,13 @@ Takes content string, returns `{ text, truncated, totalLines }`. If truncated, r
|
||||
**Goal:** Bash, Read, Glob, Grep render appropriately
|
||||
|
||||
**Deliverables:**
|
||||
1. `renderBashResult` with stdout/stderr separation
|
||||
2. `renderFileContent` for Read
|
||||
3. `renderFileList` for Glob/Grep
|
||||
4. Generic fallback for unknown tools
|
||||
1. Import and configure `ansi_up` for ANSI-to-HTML conversion
|
||||
2. `renderBashResult` with stdout/stderr separation and ANSI color preservation
|
||||
3. `renderFileContent` for Read
|
||||
4. `renderFileList` for Glob/Grep
|
||||
5. `GenericResult` fallback for unknown tools (WebFetch, Task, etc.)
|
||||
|
||||
**Exit Criteria:** AC-13 through AC-16 pass
|
||||
**Exit Criteria:** AC-14 through AC-18 pass
|
||||
|
||||
---
|
||||
|
||||
@@ -398,7 +444,7 @@ Takes content string, returns `{ text, truncated, totalLines }`. If truncated, r
|
||||
3. `FullOutputModal` component
|
||||
4. Syntax highlighting in modal
|
||||
|
||||
**Exit Criteria:** AC-17 through AC-20 pass
|
||||
**Exit Criteria:** AC-19 through AC-22 pass
|
||||
|
||||
---
|
||||
|
||||
@@ -412,15 +458,16 @@ Takes content string, returns `{ text, truncated, totalLines }`. If truncated, r
|
||||
3. Test with interrupted sessions
|
||||
4. Cross-browser testing
|
||||
|
||||
**Exit Criteria:** AC-21 through AC-23 pass, feature complete
|
||||
**Exit Criteria:** AC-23 through AC-25 pass, feature complete
|
||||
|
||||
---
|
||||
|
||||
## Open Questions
|
||||
|
||||
1. **Exact Claude Code truncation thresholds** — need to verify against Claude Code source or experiment
|
||||
1. ~~**Exact Claude Code truncation thresholds**~~ — **Resolved:** using reasonable defaults with a note to tune via testing. AC-19 updated.
|
||||
2. **Performance with 100+ tool calls** — monitor after ship, optimize if needed
|
||||
3. **Codex support timeline** — when should we prioritize v2?
|
||||
3. **Codex support timeline** — when should we prioritize v2? The normalized `kind` contract makes this easier: add Codex normalizers without touching renderers.
|
||||
4. ~~**Lazy-fetch for large payloads**~~ — **Resolved:** `result_mode` query parameter wired into API contract. Only `full` implemented in v1; `preview` deferred.
|
||||
|
||||
---
|
||||
|
||||
|
||||
96
plans/input-history.md
Normal file
96
plans/input-history.md
Normal file
@@ -0,0 +1,96 @@
|
||||
# Input History (Up/Down Arrow)
|
||||
|
||||
## Summary
|
||||
|
||||
Add shell-style up/down arrow navigation through past messages in SimpleInput. History is derived from the conversation data already parsed from session logs -- no new state management, no server changes.
|
||||
|
||||
## How It Works Today
|
||||
|
||||
1. Server parses JSONL session logs, extracts user messages with `role: "user"` (`conversation.py:57-66`)
|
||||
2. App.js stores parsed conversations in `conversations` state, refreshed via SSE on `conversation_mtime_ns` change
|
||||
3. SessionCard receives `conversation` as a prop but does **not** pass it to SimpleInput
|
||||
4. SimpleInput has no awareness of past messages
|
||||
|
||||
## Step 1: Pipe Conversation to SimpleInput
|
||||
|
||||
Pass the conversation array from SessionCard into SimpleInput so it can derive history.
|
||||
|
||||
- `SessionCard.js:165-169` -- add `conversation` prop to SimpleInput
|
||||
- Same for the QuestionBlock path if freeform input is used there (line 162) -- skip for now, QuestionBlock is option-based
|
||||
|
||||
**Files**: `dashboard/components/SessionCard.js`
|
||||
|
||||
## Step 2: Derive User Message History
|
||||
|
||||
Inside SimpleInput, filter conversation to user messages only.
|
||||
|
||||
```js
|
||||
const userHistory = useMemo(
|
||||
() => (conversation || []).filter(m => m.role === 'user').map(m => m.content),
|
||||
[conversation]
|
||||
);
|
||||
```
|
||||
|
||||
This updates automatically whenever the session log changes (SSE triggers conversation refresh, new prop flows down).
|
||||
|
||||
**Files**: `dashboard/components/SimpleInput.js`
|
||||
|
||||
## Step 3: History Navigation State
|
||||
|
||||
Add refs for tracking position in history and preserving the draft.
|
||||
|
||||
```js
|
||||
const historyIndexRef = useRef(-1); // -1 = not browsing
|
||||
const draftRef = useRef(''); // saves in-progress text before browsing
|
||||
```
|
||||
|
||||
Use refs (not state) because index changes don't need re-renders -- only `setText` triggers the visual update.
|
||||
|
||||
**Files**: `dashboard/components/SimpleInput.js`
|
||||
|
||||
## Step 4: ArrowUp/ArrowDown Keybinding
|
||||
|
||||
In the `onKeyDown` handler (after the autocomplete block, before Enter-to-submit), add history navigation:
|
||||
|
||||
- **ArrowUp**: only when autocomplete is closed AND cursor is at position 0 (prevents hijacking multiline cursor movement). On first press, save current text to `draftRef`. Walk backward through `userHistory`. Call `setText()` with the history entry.
|
||||
- **ArrowDown**: walk forward through history. If past the newest entry, restore `draftRef` and reset index to -1.
|
||||
- **Reset on submit**: set `historyIndexRef.current = -1` in `handleSubmit` after successful send.
|
||||
- **Reset on manual edit**: in `onInput`, reset `historyIndexRef.current = -1` so typing after browsing exits history mode.
|
||||
|
||||
### Cursor position check
|
||||
|
||||
```js
|
||||
const atStart = e.target.selectionStart === 0 && e.target.selectionEnd === 0;
|
||||
```
|
||||
|
||||
Only intercept ArrowUp when `atStart` is true. This lets multiline text cursor movement work normally. ArrowDown can use similar logic (check if cursor is at end of text) or always navigate history when `historyIndexRef.current !== -1` (already browsing).
|
||||
|
||||
**Files**: `dashboard/components/SimpleInput.js`
|
||||
|
||||
## Step 5: Modal Parity
|
||||
|
||||
The Modal (`Modal.js:71`) also renders SimpleInput with `onRespond`. Verify it passes `conversation` through. The same SessionCard is used in enlarged mode, so this should work automatically if Step 1 is done correctly.
|
||||
|
||||
**Files**: `dashboard/components/Modal.js` (verify, likely no change needed)
|
||||
|
||||
## Non-Goals
|
||||
|
||||
- No localStorage persistence -- history comes from session logs which survive across page reloads
|
||||
- No server changes -- conversation parsing already extracts what we need
|
||||
- No new API endpoints
|
||||
- No changes to QuestionBlock (option-based, not free-text history)
|
||||
|
||||
## Test Cases
|
||||
|
||||
| Scenario | Expected |
|
||||
|----------|----------|
|
||||
| Press up with empty input | Fills with most recent user message |
|
||||
| Press up multiple times | Walks backward through user messages |
|
||||
| Press down after browsing up | Walks forward; past newest restores draft |
|
||||
| Press up with text in input | Saves text as draft, shows history |
|
||||
| Press down past end | Restores saved draft |
|
||||
| Type after browsing | Exits history mode (index resets) |
|
||||
| Submit after browsing | Sends displayed text, resets index |
|
||||
| Up arrow in multiline text (cursor not at pos 0) | Normal cursor movement, no history |
|
||||
| New message arrives via SSE | userHistory updates, no index disruption |
|
||||
| Session with no prior messages | Up arrow does nothing |
|
||||
51
plans/model-selection.md
Normal file
51
plans/model-selection.md
Normal file
@@ -0,0 +1,51 @@
|
||||
# Model Selection & Display
|
||||
|
||||
## Summary
|
||||
|
||||
Add model visibility and control to the AMC dashboard. Users can see which model each agent is running, pick a model when spawning, and switch models mid-session.
|
||||
|
||||
## Models
|
||||
|
||||
| Label | Value sent to Claude Code |
|
||||
|-------|--------------------------|
|
||||
| Opus 4.6 | `opus` |
|
||||
| Opus 4.5 | `claude-opus-4-5-20251101` |
|
||||
| Sonnet 4.6 | `sonnet` |
|
||||
| Haiku | `haiku` |
|
||||
|
||||
## Step 1: Display Current Model
|
||||
|
||||
Surface `context_usage.model` in `SessionCard.js`.
|
||||
|
||||
- Data already extracted by `parsing.py` (line 202) from conversation JSONL
|
||||
- Already available via `/api/state` in `context_usage.model`
|
||||
- Add model name formatter: `claude-opus-4-5-20251101` -> `Opus 4.5`
|
||||
- Show in SessionCard (near agent badge or context usage area)
|
||||
- Shows `null` until first assistant message
|
||||
|
||||
**Files**: `dashboard/components/SessionCard.js`
|
||||
|
||||
## Step 2: Model Picker at Spawn
|
||||
|
||||
Add model dropdown to `SpawnModal.js`. Pass to spawn API, which appends `--model <value>` to the claude command.
|
||||
|
||||
- Extend `/api/spawn` to accept optional `model` param
|
||||
- Validate against allowed model list
|
||||
- Prepend `--model {model}` to command in `AGENT_COMMANDS`
|
||||
- Default: no flag (uses Claude Code's default)
|
||||
|
||||
**Files**: `dashboard/components/SpawnModal.js`, `amc_server/mixins/spawn.py`
|
||||
|
||||
## Step 3: Mid-Session Model Switch
|
||||
|
||||
Dropdown on SessionCard to change model for running sessions via Zellij.
|
||||
|
||||
- Send `/model <value>` to the agent's Zellij pane:
|
||||
```bash
|
||||
zellij -s {session} action write-chars "/model {value}" --pane-id {pane}
|
||||
zellij -s {session} action write 10 --pane-id {pane}
|
||||
```
|
||||
- New endpoint: `POST /api/session/{id}/model` with `{"model": "opus"}`
|
||||
- Only works when agent is idle (waiting for input). If mid-turn, command queues and applies after.
|
||||
|
||||
**Files**: `dashboard/components/SessionCard.js`, `amc_server/mixins/state.py` (or new mixin)
|
||||
@@ -1,26 +1,27 @@
|
||||
# Subagent & Agent Team Visibility for AMC
|
||||
|
||||
> **Status**: Draft
|
||||
> **Last Updated**: 2026-02-27
|
||||
> **Last Updated**: 2026-03-02
|
||||
|
||||
## Summary
|
||||
|
||||
Add a button in the turn stats section showing the count of active subagents/team members. Clicking it opens a list with names and lifetime stats (time taken, tokens used). Mirrors Claude Code's own agent display.
|
||||
Add visibility into Claude Code subagents (Task tool spawns and team members) within AMC session cards. A pill button shows active agent count; clicking opens a popover with names, status, and stats. Claude-only (Codex does not support subagents).
|
||||
|
||||
---
|
||||
|
||||
## User Workflow
|
||||
|
||||
1. User views a session card in AMC
|
||||
2. Turn stats area shows: `2h 15m | 84k tokens | 3 agents`
|
||||
2. Session status area shows: `[●] Working 2m 15s · 42k tokens 32% ctx [3 agents]`
|
||||
3. User clicks "3 agents" button
|
||||
4. List opens showing:
|
||||
4. Popover opens showing:
|
||||
```
|
||||
claude-code-guide (running) 12m 42,000 tokens
|
||||
Explore (completed) 3m 18,500 tokens
|
||||
Explore (completed) 5m 23,500 tokens
|
||||
Explore-a250de ● running 12m 42,000 tokens
|
||||
code-reviewer ○ completed 3m 18,500 tokens
|
||||
action-wirer ○ completed 5m 23,500 tokens
|
||||
```
|
||||
5. List updates in real-time as agents complete
|
||||
5. Popover auto-updates every 2s while open
|
||||
6. Button hidden when session has no subagents
|
||||
|
||||
---
|
||||
|
||||
@@ -28,24 +29,505 @@ Add a button in the turn stats section showing the count of active subagents/tea
|
||||
|
||||
### Discovery
|
||||
|
||||
- **AC-1**: Subagent JSONL files discovered at `{session_dir}/subagents/agent-*.jsonl`
|
||||
- **AC-2**: Both regular subagents (Task tool) and team members (Task with `team_name`) are discovered from same location
|
||||
- **AC-1**: Subagent JSONL files discovered for Claude sessions at `{claude_projects}/{encoded_project_dir}/{session_id}/subagents/agent-*.jsonl`
|
||||
- **AC-2**: Team members discovered from same location (team spawning uses Task tool, stores in subagents dir)
|
||||
- **AC-3**: Codex sessions do not show subagent button (Codex does not support subagents)
|
||||
|
||||
### Status Detection
|
||||
|
||||
- **AC-3**: Subagent is "running" if: parent session is alive AND last assistant entry has `stop_reason != "end_turn"`
|
||||
- **AC-4**: Subagent is "completed" if: last assistant entry has `stop_reason == "end_turn"` OR parent session is dead
|
||||
- **AC-4**: Subagent is "running" if parent session is not dead AND last assistant entry has `stop_reason != "end_turn"`
|
||||
- **AC-5**: Subagent is "completed" if last assistant entry has `stop_reason == "end_turn"` OR parent session is dead
|
||||
|
||||
### Name Resolution
|
||||
|
||||
- **AC-6**: Team member names extracted from agentId format `{name}@{team_name}` (O(1) string split)
|
||||
- **AC-7**: Non-team subagent names generated as `agent-{agentId_prefix}` (no parent session parsing required)
|
||||
|
||||
### Stats Extraction
|
||||
|
||||
- **AC-5**: Subagent name extracted from parent's Task tool invocation: use `name` if present (team member), else `subagent_type`
|
||||
- **AC-6**: Lifetime duration = first entry timestamp to last entry timestamp (or now if running)
|
||||
- **AC-7**: Lifetime tokens = sum of all assistant entries' `usage.input_tokens + usage.output_tokens`
|
||||
- **AC-8**: Duration = first entry timestamp to last entry timestamp (or server time if running)
|
||||
- **AC-9**: Tokens = sum of `input_tokens + output_tokens` from all assistant entries (excludes cache tokens)
|
||||
|
||||
### API
|
||||
|
||||
- **AC-10**: `/api/state` includes `subagent_count` and `subagent_running_count` for each Claude session
|
||||
- **AC-11**: New endpoint `/api/sessions/{id}/subagents` returns full subagent list with name, status, duration_ms, tokens
|
||||
- **AC-12**: Subagent endpoint supports session_id path param; returns 404 if session not found
|
||||
|
||||
### UI
|
||||
|
||||
- **AC-8**: Turn stats area shows agent count button when subagents exist
|
||||
- **AC-9**: Button shows count + running indicator (e.g., "3 agents" or "2 agents (1 running)")
|
||||
- **AC-10**: Clicking button opens popover with: name, status, duration, token count
|
||||
- **AC-11**: Running agents show activity indicator
|
||||
- **AC-12**: List updates via existing polling/SSE
|
||||
- **AC-13**: Context usage displays as plain text (remove badge styling)
|
||||
- **AC-14**: Agent count button appears as bordered pill to the right of context text
|
||||
- **AC-15**: Button hidden when `subagent_count == 0`
|
||||
- **AC-16**: Button shows running indicator: "3 agents" when none running, "3 agents (1 running)" when some running
|
||||
- **AC-17**: Clicking button opens popover anchored to button
|
||||
- **AC-18**: Popover shows list: name, status indicator, duration, token count per row
|
||||
- **AC-19**: Running agents show filled indicator (●), completed show empty (○)
|
||||
- **AC-20**: Popover polls `/api/sessions/{id}/subagents` every 2s while open
|
||||
- **AC-21**: Popover closes on outside click or Escape key
|
||||
- **AC-22**: Subagent rows are display-only (no click action in v1)
|
||||
|
||||
---
|
||||
|
||||
## Architecture
|
||||
|
||||
### Why This Structure
|
||||
|
||||
| Decision | Rationale | Fulfills |
|
||||
|----------|-----------|----------|
|
||||
| Aggregate counts in `/api/state` + detail endpoint | Minimizes payload size; hash stability (counts change less than durations) | AC-10, AC-11 |
|
||||
| Claude-only | Codex lacks subagent infrastructure | AC-3 |
|
||||
| Name from agentId pattern | Avoids expensive parent session parsing; team names encoded in agentId | AC-6, AC-7 |
|
||||
| Input+output tokens only | Matches "work done" mental model; simpler than cache tracking | AC-9 |
|
||||
| Auto-poll in popover | Real-time feel consistent with session card updates | AC-20 |
|
||||
| Hide button when empty | Reduces visual noise for sessions without agents | AC-15 |
|
||||
|
||||
### Data Flow
|
||||
|
||||
```
|
||||
┌─────────────────────────────────────────────────────────────────┐
|
||||
│ Backend (Python) │
|
||||
│ │
|
||||
│ _collect_sessions() │
|
||||
│ │ │
|
||||
│ ├── For each Claude session: │
|
||||
│ │ └── _count_subagents(session_id, project_dir) │
|
||||
│ │ ├── glob subagents/agent-*.jsonl │
|
||||
│ │ ├── count files, check running status │
|
||||
│ │ └── return (count, running_count) │
|
||||
│ │ │
|
||||
│ └── Attach subagent_count, subagent_running_count │
|
||||
│ │
|
||||
│ _serve_subagents(session_id) │
|
||||
│ ├── _get_claude_session_dir(session_id, project_dir) │
|
||||
│ ├── glob subagents/agent-*.jsonl │
|
||||
│ ├── For each file: │
|
||||
│ │ ├── Parse name from agentId │
|
||||
│ │ ├── Determine status from stop_reason │
|
||||
│ │ ├── Calculate duration from timestamps │
|
||||
│ │ └── Sum tokens from assistant usage │
|
||||
│ └── Return JSON list │
|
||||
│ │
|
||||
└─────────────────────────────────────────────────────────────────┘
|
||||
|
||||
┌─────────────────────────────────────────────────────────────────┐
|
||||
│ Frontend (Preact) │
|
||||
│ │
|
||||
│ SessionCard │
|
||||
│ │ │
|
||||
│ ├── Session Status Area: │
|
||||
│ │ ├── AgentActivityIndicator (left) │
|
||||
│ │ ├── Context text (center-right, plain) │
|
||||
│ │ └── SubagentButton (far right, if count > 0) │
|
||||
│ │ │
|
||||
│ └── SubagentButton │
|
||||
│ ├── Shows "{count} agents" or "{count} ({running})" │
|
||||
│ ├── onClick: opens SubagentPopover │
|
||||
│ └── SubagentPopover │
|
||||
│ ├── Polls /api/sessions/{id}/subagents │
|
||||
│ ├── Renders list with status indicators │
|
||||
│ └── Closes on outside click or Escape │
|
||||
│ │
|
||||
└─────────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
### File Changes
|
||||
|
||||
| File | Change | ACs |
|
||||
|------|--------|-----|
|
||||
| `amc_server/mixins/subagent.py` | New mixin for subagent discovery and stats | AC-1,2,4-9 |
|
||||
| `amc_server/mixins/state.py` | Call subagent mixin, attach counts to session | AC-10 |
|
||||
| `amc_server/mixins/http.py` | Add route `/api/sessions/{id}/subagents` | AC-11,12 |
|
||||
| `amc_server/handler.py` | Add SubagentMixin to handler class | - |
|
||||
| `dashboard/components/SessionCard.js` | Update status area layout | AC-13,14 |
|
||||
| `dashboard/components/SubagentButton.js` | New component for button + popover | AC-15-22 |
|
||||
| `dashboard/utils/api.js` | Add `fetchSubagents(sessionId)` function | AC-20 |
|
||||
|
||||
---
|
||||
|
||||
## Implementation Specs
|
||||
|
||||
### IMP-1: SubagentMixin (Python)
|
||||
|
||||
**Fulfills:** AC-1, AC-2, AC-4, AC-5, AC-6, AC-7, AC-8, AC-9
|
||||
|
||||
```python
|
||||
# amc_server/mixins/subagent.py
|
||||
|
||||
class SubagentMixin:
|
||||
def _get_subagent_counts(self, session_id: str, project_dir: str) -> tuple[int, int]:
|
||||
"""Return (total_count, running_count) for a Claude session."""
|
||||
subagents_dir = self._get_subagents_dir(session_id, project_dir)
|
||||
if not subagents_dir or not subagents_dir.exists():
|
||||
return (0, 0)
|
||||
|
||||
total = 0
|
||||
running = 0
|
||||
for jsonl_file in subagents_dir.glob("agent-*.jsonl"):
|
||||
total += 1
|
||||
if self._is_subagent_running(jsonl_file):
|
||||
running += 1
|
||||
return (total, running)
|
||||
|
||||
def _get_subagents_dir(self, session_id: str, project_dir: str) -> Path | None:
|
||||
"""Construct path to subagents directory."""
|
||||
if not project_dir:
|
||||
return None
|
||||
encoded_dir = project_dir.replace("/", "-")
|
||||
if not encoded_dir.startswith("-"):
|
||||
encoded_dir = "-" + encoded_dir
|
||||
return CLAUDE_PROJECTS_DIR / encoded_dir / session_id / "subagents"
|
||||
|
||||
def _is_subagent_running(self, jsonl_file: Path) -> bool:
|
||||
"""Check if subagent is still running based on last assistant stop_reason."""
|
||||
try:
|
||||
# Read last few lines to find last assistant entry
|
||||
entries = self._read_jsonl_tail_entries(jsonl_file, max_lines=20)
|
||||
for entry in reversed(entries):
|
||||
if entry.get("type") == "assistant":
|
||||
stop_reason = entry.get("message", {}).get("stop_reason")
|
||||
return stop_reason != "end_turn"
|
||||
return True # No assistant entries yet = still starting
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
def _get_subagent_list(self, session_id: str, project_dir: str, parent_is_dead: bool) -> list[dict]:
|
||||
"""Return full subagent list with stats."""
|
||||
subagents_dir = self._get_subagents_dir(session_id, project_dir)
|
||||
if not subagents_dir or not subagents_dir.exists():
|
||||
return []
|
||||
|
||||
result = []
|
||||
for jsonl_file in subagents_dir.glob("agent-*.jsonl"):
|
||||
subagent = self._parse_subagent(jsonl_file, parent_is_dead)
|
||||
if subagent:
|
||||
result.append(subagent)
|
||||
|
||||
# Sort: running first, then by name
|
||||
result.sort(key=lambda s: (0 if s["status"] == "running" else 1, s["name"]))
|
||||
return result
|
||||
|
||||
def _parse_subagent(self, jsonl_file: Path, parent_is_dead: bool) -> dict | None:
|
||||
"""Parse a single subagent JSONL file."""
|
||||
try:
|
||||
entries = self._read_jsonl_tail_entries(jsonl_file, max_lines=500, max_bytes=512*1024)
|
||||
if not entries:
|
||||
return None
|
||||
|
||||
# Get agentId from first entry
|
||||
first_entry = entries[0] if entries else {}
|
||||
agent_id = first_entry.get("agentId", "")
|
||||
|
||||
# Resolve name
|
||||
name = self._resolve_subagent_name(agent_id, jsonl_file)
|
||||
|
||||
# Determine status
|
||||
is_running = False
|
||||
if not parent_is_dead:
|
||||
for entry in reversed(entries):
|
||||
if entry.get("type") == "assistant":
|
||||
stop_reason = entry.get("message", {}).get("stop_reason")
|
||||
is_running = stop_reason != "end_turn"
|
||||
break
|
||||
status = "running" if is_running else "completed"
|
||||
|
||||
# Calculate duration
|
||||
first_ts = first_entry.get("timestamp")
|
||||
last_ts = entries[-1].get("timestamp") if entries else None
|
||||
duration_ms = self._calculate_duration_ms(first_ts, last_ts, is_running)
|
||||
|
||||
# Sum tokens
|
||||
tokens = self._sum_assistant_tokens(entries)
|
||||
|
||||
return {
|
||||
"name": name,
|
||||
"status": status,
|
||||
"duration_ms": duration_ms,
|
||||
"tokens": tokens,
|
||||
}
|
||||
except Exception:
|
||||
return None
|
||||
|
||||
def _resolve_subagent_name(self, agent_id: str, jsonl_file: Path) -> str:
|
||||
"""Extract display name from agentId or filename."""
|
||||
# Team members: "reviewer-wcja@surgical-sync" -> "reviewer-wcja"
|
||||
if "@" in agent_id:
|
||||
return agent_id.split("@")[0]
|
||||
|
||||
# Regular subagents: use prefix from agentId
|
||||
# agent_id like "a250dec6325c589be" -> "a250de"
|
||||
prefix = agent_id[:6] if agent_id else "agent"
|
||||
|
||||
# Try to get subagent_type from filename if it contains it
|
||||
# Filename: agent-acompact-b857538cac0d5172.jsonl -> might indicate "compact"
|
||||
# For now, use generic fallback
|
||||
return f"agent-{prefix}"
|
||||
|
||||
def _calculate_duration_ms(self, first_ts: str, last_ts: str, is_running: bool) -> int:
|
||||
"""Calculate duration in milliseconds."""
|
||||
if not first_ts:
|
||||
return 0
|
||||
try:
|
||||
first = datetime.fromisoformat(first_ts.replace("Z", "+00:00"))
|
||||
if is_running:
|
||||
end = datetime.now(timezone.utc)
|
||||
elif last_ts:
|
||||
end = datetime.fromisoformat(last_ts.replace("Z", "+00:00"))
|
||||
else:
|
||||
return 0
|
||||
return max(0, int((end - first).total_seconds() * 1000))
|
||||
except Exception:
|
||||
return 0
|
||||
|
||||
def _sum_assistant_tokens(self, entries: list[dict]) -> int:
|
||||
"""Sum input_tokens + output_tokens from all assistant entries."""
|
||||
total = 0
|
||||
for entry in entries:
|
||||
if entry.get("type") != "assistant":
|
||||
continue
|
||||
usage = entry.get("message", {}).get("usage", {})
|
||||
input_tok = usage.get("input_tokens", 0) or 0
|
||||
output_tok = usage.get("output_tokens", 0) or 0
|
||||
total += input_tok + output_tok
|
||||
return total
|
||||
```
|
||||
|
||||
### IMP-2: State Integration (Python)
|
||||
|
||||
**Fulfills:** AC-10
|
||||
|
||||
```python
|
||||
# In amc_server/mixins/state.py, within _collect_sessions():
|
||||
|
||||
# After computing is_dead, add:
|
||||
if data.get("agent") == "claude":
|
||||
subagent_count, subagent_running = self._get_subagent_counts(
|
||||
data.get("session_id", ""),
|
||||
data.get("project_dir", "")
|
||||
)
|
||||
if subagent_count > 0:
|
||||
data["subagent_count"] = subagent_count
|
||||
data["subagent_running_count"] = subagent_running
|
||||
```
|
||||
|
||||
### IMP-3: Subagents Endpoint (Python)
|
||||
|
||||
**Fulfills:** AC-11, AC-12
|
||||
|
||||
```python
|
||||
# In amc_server/mixins/http.py, add route handling:
|
||||
|
||||
def _route_request(self):
|
||||
# ... existing routes ...
|
||||
|
||||
# /api/sessions/{id}/subagents
|
||||
subagent_match = re.match(r"^/api/sessions/([^/]+)/subagents$", self.path)
|
||||
if subagent_match:
|
||||
session_id = subagent_match.group(1)
|
||||
self._serve_subagents(session_id)
|
||||
return
|
||||
|
||||
def _serve_subagents(self, session_id):
|
||||
"""Serve subagent list for a specific session."""
|
||||
# Find session to get project_dir and is_dead
|
||||
session_file = SESSIONS_DIR / f"{session_id}.json"
|
||||
if not session_file.exists():
|
||||
self._send_json(404, {"error": "Session not found"})
|
||||
return
|
||||
|
||||
try:
|
||||
session_data = json.loads(session_file.read_text())
|
||||
except (json.JSONDecodeError, OSError):
|
||||
self._send_json(404, {"error": "Session not found"})
|
||||
return
|
||||
|
||||
if session_data.get("agent") != "claude":
|
||||
self._send_json(200, {"subagents": []})
|
||||
return
|
||||
|
||||
parent_is_dead = session_data.get("is_dead", False)
|
||||
subagents = self._get_subagent_list(
|
||||
session_id,
|
||||
session_data.get("project_dir", ""),
|
||||
parent_is_dead
|
||||
)
|
||||
self._send_json(200, {"subagents": subagents})
|
||||
```
|
||||
|
||||
### IMP-4: SubagentButton Component (JavaScript)
|
||||
|
||||
**Fulfills:** AC-14, AC-15, AC-16, AC-17, AC-18, AC-19, AC-20, AC-21, AC-22
|
||||
|
||||
```javascript
|
||||
// dashboard/components/SubagentButton.js
|
||||
|
||||
import { html, useState, useEffect, useRef } from '../lib/preact.js';
|
||||
import { fetchSubagents } from '../utils/api.js';
|
||||
|
||||
export function SubagentButton({ sessionId, count, runningCount }) {
|
||||
const [isOpen, setIsOpen] = useState(false);
|
||||
const [subagents, setSubagents] = useState([]);
|
||||
const buttonRef = useRef(null);
|
||||
const popoverRef = useRef(null);
|
||||
|
||||
// Format button label
|
||||
const label = runningCount > 0
|
||||
? `${count} agents (${runningCount} running)`
|
||||
: `${count} agents`;
|
||||
|
||||
// Poll while open
|
||||
useEffect(() => {
|
||||
if (!isOpen) return;
|
||||
|
||||
const fetchData = async () => {
|
||||
const data = await fetchSubagents(sessionId);
|
||||
if (data?.subagents) {
|
||||
setSubagents(data.subagents);
|
||||
}
|
||||
};
|
||||
|
||||
fetchData();
|
||||
const interval = setInterval(fetchData, 2000);
|
||||
return () => clearInterval(interval);
|
||||
}, [isOpen, sessionId]);
|
||||
|
||||
// Close on outside click or Escape
|
||||
useEffect(() => {
|
||||
if (!isOpen) return;
|
||||
|
||||
const handleClickOutside = (e) => {
|
||||
if (popoverRef.current && !popoverRef.current.contains(e.target) &&
|
||||
buttonRef.current && !buttonRef.current.contains(e.target)) {
|
||||
setIsOpen(false);
|
||||
}
|
||||
};
|
||||
|
||||
const handleEscape = (e) => {
|
||||
if (e.key === 'Escape') setIsOpen(false);
|
||||
};
|
||||
|
||||
document.addEventListener('mousedown', handleClickOutside);
|
||||
document.addEventListener('keydown', handleEscape);
|
||||
return () => {
|
||||
document.removeEventListener('mousedown', handleClickOutside);
|
||||
document.removeEventListener('keydown', handleEscape);
|
||||
};
|
||||
}, [isOpen]);
|
||||
|
||||
const formatDuration = (ms) => {
|
||||
const sec = Math.floor(ms / 1000);
|
||||
if (sec < 60) return `${sec}s`;
|
||||
const min = Math.floor(sec / 60);
|
||||
return `${min}m`;
|
||||
};
|
||||
|
||||
const formatTokens = (count) => {
|
||||
if (count >= 1000) return `${(count / 1000).toFixed(1)}k`;
|
||||
return String(count);
|
||||
};
|
||||
|
||||
return html`
|
||||
<div class="relative">
|
||||
<button
|
||||
ref=${buttonRef}
|
||||
onClick=${() => setIsOpen(!isOpen)}
|
||||
class="rounded-lg border border-selection/80 bg-bg/45 px-2.5 py-1 font-mono text-label text-dim hover:border-starting/50 hover:text-bright transition-colors"
|
||||
>
|
||||
${label}
|
||||
</button>
|
||||
|
||||
${isOpen && html`
|
||||
<div
|
||||
ref=${popoverRef}
|
||||
class="absolute right-0 top-full mt-2 z-50 min-w-[280px] rounded-lg border border-selection/80 bg-surface shadow-lg"
|
||||
>
|
||||
<div class="p-2">
|
||||
${subagents.length === 0 ? html`
|
||||
<div class="text-center text-dim text-sm py-4">Loading...</div>
|
||||
` : subagents.map(agent => html`
|
||||
<div class="flex items-center gap-3 px-3 py-2 rounded hover:bg-bg/40">
|
||||
<span class="w-2 h-2 rounded-full ${agent.status === 'running' ? 'bg-active' : 'border border-dim'}"></span>
|
||||
<span class="flex-1 font-mono text-sm text-bright truncate">${agent.name}</span>
|
||||
<span class="font-mono text-label text-dim">${formatDuration(agent.duration_ms)}</span>
|
||||
<span class="font-mono text-label text-dim">${formatTokens(agent.tokens)}</span>
|
||||
</div>
|
||||
`)}
|
||||
</div>
|
||||
</div>
|
||||
`}
|
||||
</div>
|
||||
`;
|
||||
}
|
||||
```
|
||||
|
||||
### IMP-5: SessionCard Status Area Update (JavaScript)
|
||||
|
||||
**Fulfills:** AC-13, AC-14, AC-15
|
||||
|
||||
```javascript
|
||||
// In dashboard/components/SessionCard.js, update the Session Status Area:
|
||||
|
||||
// Replace the contextUsage badge with plain text + SubagentButton
|
||||
|
||||
<!-- Session Status Area -->
|
||||
<div class="flex items-center justify-between gap-3 px-4 py-2 border-b border-selection/50 bg-bg/60">
|
||||
<${AgentActivityIndicator} session=${session} />
|
||||
<div class="flex items-center gap-3">
|
||||
${contextUsage && html`
|
||||
<span class="font-mono text-label text-dim" title=${contextUsage.title}>
|
||||
${contextUsage.headline}
|
||||
</span>
|
||||
`}
|
||||
${session.subagent_count > 0 && session.agent === 'claude' && html`
|
||||
<${SubagentButton}
|
||||
sessionId=${session.session_id}
|
||||
count=${session.subagent_count}
|
||||
runningCount=${session.subagent_running_count || 0}
|
||||
/>
|
||||
`}
|
||||
</div>
|
||||
</div>
|
||||
```
|
||||
|
||||
### IMP-6: API Function (JavaScript)
|
||||
|
||||
**Fulfills:** AC-20
|
||||
|
||||
```javascript
|
||||
// In dashboard/utils/api.js, add:
|
||||
|
||||
export async function fetchSubagents(sessionId) {
|
||||
try {
|
||||
const response = await fetch(`/api/sessions/${sessionId}/subagents`);
|
||||
if (!response.ok) return null;
|
||||
return await response.json();
|
||||
} catch (e) {
|
||||
console.error('Failed to fetch subagents:', e);
|
||||
return null;
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Rollout Slices
|
||||
|
||||
### Slice 1: Backend Discovery (AC-1, AC-2, AC-4, AC-5, AC-6, AC-7, AC-8, AC-9, AC-10)
|
||||
- Create `amc_server/mixins/subagent.py` with discovery and stats logic
|
||||
- Integrate into `state.py` to add counts to session payload
|
||||
- Unit tests for name resolution, status detection, token summing
|
||||
|
||||
### Slice 2: Backend Endpoint (AC-11, AC-12)
|
||||
- Add `/api/sessions/{id}/subagents` route
|
||||
- Return 404 for missing sessions, empty list for Codex
|
||||
- Integration test with real session data
|
||||
|
||||
### Slice 3: Frontend Button (AC-13, AC-14, AC-15, AC-16)
|
||||
- Update SessionCard status area layout
|
||||
- Create SubagentButton component with label logic
|
||||
- Test: button shows when count > 0, hidden when 0
|
||||
|
||||
### Slice 4: Frontend Popover (AC-17, AC-18, AC-19, AC-20, AC-21, AC-22)
|
||||
- Add popover with polling
|
||||
- Style running/completed indicators
|
||||
- Test: popover opens, polls, closes on outside click/Escape
|
||||
|
||||
@@ -9,7 +9,7 @@ import unittest
|
||||
from pathlib import Path
|
||||
from unittest.mock import patch
|
||||
|
||||
from amc_server.mixins.conversation import ConversationMixin
|
||||
from amc_server.mixins.conversation import ConversationMixin, _is_system_injected
|
||||
from amc_server.mixins.parsing import SessionParsingMixin
|
||||
|
||||
|
||||
@@ -278,6 +278,110 @@ class TestParseClaudeConversation(unittest.TestCase):
|
||||
path.unlink()
|
||||
|
||||
|
||||
class TestIsSystemInjected(unittest.TestCase):
|
||||
"""Tests for _is_system_injected filter."""
|
||||
|
||||
def test_system_reminder(self):
|
||||
self.assertTrue(_is_system_injected("<system-reminder>\nSome reminder text\n</system-reminder>"))
|
||||
|
||||
def test_local_command_caveat(self):
|
||||
self.assertTrue(_is_system_injected("<local-command-caveat>Caveat: The messages below...</local-command-caveat>"))
|
||||
|
||||
def test_available_deferred_tools(self):
|
||||
self.assertTrue(_is_system_injected("<available-deferred-tools>\nAgent\nBash\n</available-deferred-tools>"))
|
||||
|
||||
def test_teammate_message(self):
|
||||
self.assertTrue(_is_system_injected('<teammate-message teammate_id="reviewer" color="yellow">Review complete</teammate-message>'))
|
||||
|
||||
def test_leading_whitespace_stripped(self):
|
||||
self.assertTrue(_is_system_injected(" \n <system-reminder>content</system-reminder>"))
|
||||
|
||||
def test_normal_user_message(self):
|
||||
self.assertFalse(_is_system_injected("Hello, Claude!"))
|
||||
|
||||
def test_message_containing_tag_not_at_start(self):
|
||||
self.assertFalse(_is_system_injected("Please check this <system-reminder> thing"))
|
||||
|
||||
def test_empty_string(self):
|
||||
self.assertFalse(_is_system_injected(""))
|
||||
|
||||
def test_slash_command(self):
|
||||
self.assertFalse(_is_system_injected("/commit"))
|
||||
|
||||
def test_multiline_user_message(self):
|
||||
self.assertFalse(_is_system_injected("Fix this bug\n\nHere's the error:\nTypeError: foo is not a function"))
|
||||
|
||||
|
||||
class TestClaudeSystemInjectedFiltering(unittest.TestCase):
|
||||
"""Integration tests: system-injected messages filtered from Claude conversation."""
|
||||
|
||||
def setUp(self):
|
||||
self.handler = DummyConversationHandler()
|
||||
|
||||
def _parse_with_messages(self, *user_contents):
|
||||
"""Helper: write JSONL with user messages, parse, return results."""
|
||||
with tempfile.NamedTemporaryFile(mode="w", suffix=".jsonl", delete=False) as f:
|
||||
for content in user_contents:
|
||||
f.write(json.dumps({
|
||||
"type": "user",
|
||||
"timestamp": "2024-01-01T00:00:00Z",
|
||||
"message": {"content": content}
|
||||
}) + "\n")
|
||||
path = Path(f.name)
|
||||
|
||||
try:
|
||||
with patch.object(self.handler, "_get_claude_conversation_file", return_value=path):
|
||||
return self.handler._parse_claude_conversation("session123", "/project")
|
||||
finally:
|
||||
path.unlink()
|
||||
|
||||
def test_system_reminder_excluded(self):
|
||||
messages = self._parse_with_messages(
|
||||
"real question",
|
||||
"<system-reminder>\nHook success\n</system-reminder>",
|
||||
)
|
||||
self.assertEqual(len(messages), 1)
|
||||
self.assertEqual(messages[0]["content"], "real question")
|
||||
|
||||
def test_local_command_caveat_excluded(self):
|
||||
messages = self._parse_with_messages(
|
||||
"<local-command-caveat>Caveat: generated by local commands</local-command-caveat>",
|
||||
"what does this function do?",
|
||||
)
|
||||
self.assertEqual(len(messages), 1)
|
||||
self.assertEqual(messages[0]["content"], "what does this function do?")
|
||||
|
||||
def test_teammate_message_excluded(self):
|
||||
messages = self._parse_with_messages(
|
||||
'<teammate-message teammate_id="impl" color="green">Task done</teammate-message>',
|
||||
"looks good, commit it",
|
||||
)
|
||||
self.assertEqual(len(messages), 1)
|
||||
self.assertEqual(messages[0]["content"], "looks good, commit it")
|
||||
|
||||
def test_all_system_messages_excluded_preserves_ids(self):
|
||||
"""Message IDs should be sequential with no gaps from filtering."""
|
||||
messages = self._parse_with_messages(
|
||||
"first real message",
|
||||
"<system-reminder>noise</system-reminder>",
|
||||
"<available-deferred-tools>\nAgent\n</available-deferred-tools>",
|
||||
"second real message",
|
||||
)
|
||||
self.assertEqual(len(messages), 2)
|
||||
self.assertEqual(messages[0]["content"], "first real message")
|
||||
self.assertEqual(messages[1]["content"], "second real message")
|
||||
# IDs should be sequential (0, 1) not (0, 3)
|
||||
self.assertTrue(messages[0]["id"].endswith("-0"))
|
||||
self.assertTrue(messages[1]["id"].endswith("-1"))
|
||||
|
||||
def test_only_system_messages_returns_empty(self):
|
||||
messages = self._parse_with_messages(
|
||||
"<system-reminder>reminder</system-reminder>",
|
||||
"<local-command-caveat>caveat</local-command-caveat>",
|
||||
)
|
||||
self.assertEqual(messages, [])
|
||||
|
||||
|
||||
class TestParseCodexConversation(unittest.TestCase):
|
||||
"""Tests for _parse_codex_conversation edge cases."""
|
||||
|
||||
|
||||
Reference in New Issue
Block a user