UC4 test times out in CI (5s default) because generateSummary's API
provider layer takes longer to fail on slow CI runners. Increase to 15s.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The setTimeout in runSubagentTask was never cleared when childAgent.run()
completed before the timeout. The dangling timer would later reject an
unobserved promise, causing an unhandled promise rejection crash in Node.js
v15+. Capture the timer and clear it in a .finally() block.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Delete sessions-spawn.ts, sessions-list.ts and their tests. Update CLI
to remove waitForSubagents polling workaround (delegate is synchronous).
Update UI, desktop IPC, SWE-bench, and system prompt tests to use the
new delegate tool name.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace the async sessions_spawn/sessions_list sub-agent system with a
single synchronous `delegate` tool. The new tool runs tasks in parallel
via Promise.all with per-task timeout, returning combined results directly
in the tool response. This eliminates the need for registry, announce queue,
persistence, and Hub involvement.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The pre-emptive truncation, tool result pruning, and summary fallback
only checked for Anthropic-style `role: "user"` messages with
`type: "tool_result"` blocks. The actual runtime uses pi-agent-core
format with `role: "toolResult"`, `toolCallId`, and `toolName` on the
message itself. This caused truncation and pruning to silently skip
all tool results in real agent runs.
Add handlers for the pi-agent-core format in all four affected modules:
- session-manager.ts: check both "user" and "toolResult" roles
- tool-result-truncation.ts: new handler for toolResult format
- tool-result-pruning.ts: new processToolResultMessage() + updated loops
- summary-fallback.ts: include "toolResult" in artifact ref extraction
Verified via agent-driven E2E tests (5 test sessions, 6 artifacts).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add real user messages for bootstrap protection in pruning tests
- Fix artifact directory path assertions (baseDir vs sessions/baseDir)
- Add cross-phase tests (Phase 1 truncation → Phase 2 pruning)
- Remove conditional assertion guards that could silently skip checks
- All 30 E2E integration tests now pass with mandatory assertions
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The extractArtifactRef regex only matched "Full result saved to" (from
pre-emptive truncation) but not "Full result available at" (from soft
trim). This caused hard clear to lose artifact references when preceded
by soft trim in the same pruning pass.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
SectionReport now includes truncated/originalChars fields for budget-controlled
sections. formatPromptReport shows estimated token count and truncation details.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Workspace.md content is capped at 20k chars and skills prompt at 12k chars.
Oversized content is intelligently truncated (head 70% + marker + tail 20%)
with newline-boundary snapping. Inspired by OpenClaw's bootstrap budget system.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Soft trim and hard clear now detect and preserve artifact references
in their markers. Summary instructions include guidance to note artifact
paths. Plain-text fallback extracts and lists all artifact references
in a "Saved Artifacts" section.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Oversized tool results (>30% of context window) are now saved as artifacts
before being truncated in the session. The LLM sees a truncated version with
head+tail preservation and a marker pointing to the full artifact file,
which it can re-read on demand. This prevents information loss during
context window management.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Use absolute positioning for the step indicator to achieve true centering
regardless of left/right element widths. This is the standard approach for
header layouts where the center element must be centered relative to the
entire container width, not the remaining flex space.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add instructions for the agent to understand [Replying to: "..."] annotations
and to send brief acknowledgments before tool calls when messages come from
messaging channels.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Extract reply_to_message text from Telegram replies and prepend as
[Replying to: "..."] context so the agent can reference specific messages
- Replace edit-message pattern with new messages for each tool narration,
improving clarity in the chat flow
- Remove dead code: sendOrEditStatus, editFormatted, statusMessages map
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Multi-turn test script for compaction behavior with low context window.
Runs 4 turns of file reading to push context pressure and outputs
run-log analysis.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Remove compactMessagesWithSummary (~100 lines, never called; only
the Chunked variant was used)
- Remove compactMessagesByCount, findSafeCompactionPoint, and all
count-mode references (~90 lines)
- Narrow CompactionResult.reason to "tokens" | "summary" | "pruning"
- Narrow compactionMode to "tokens" | "summary" (was "count" | ...)
- Simplify session-manager: remove maxMessages/keepLast params,
enable tool result pruning by default
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Pre-flight compaction runs in-memory only (not persisted), so tool
result pruning in this path was wasted work — results were thrown away
after the LLM call. Post-turn compaction still handles pruning and
persists the results. Only Phase 2 (emergency message drop) remains
as a safety net in pre-flight.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- estimateSystemPromptTokens now uses estimateTokens() (chars/4) instead
of chars/2, eliminating the 2x overestimate that caused pre-flight
compaction to fire on every LLM call at small context windows
- ESTIMATION_SAFETY_MARGIN reduced from 1.5 to 1.2, increasing usable
context from ~53% to ~73% before compaction triggers
At 200k context, effective usable tokens before compaction improved from
~86k to ~120k message tokens (39% increase).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
resolveContextWindowInfo now uses config > model > default priority so
explicit --context-window flag overrides model defaults. Also adds
--context-window CLI option to the run command.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Track the last assistant message saved by the message_end event handler
and skip saving it again in the abort handler. This prevents the
duplicate assistant entries in session.jsonl that caused the
"tool_call_id is not found" bug.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When a session is aborted mid-tool-execution, the assistant message can
be persisted twice (once by message_end, once by the abort handler).
The repair logic failed to handle this: it generated a synthetic tool
result for the first copy but deduplicated the result for the second,
leaving an orphaned tool call that caused "tool_call_id is not found"
errors on all subsequent API calls.
Detect and remove duplicate assistant messages whose tool call IDs
have all already been paired with results from an earlier copy.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Login page: replace full-container drag region with a dedicated header
bar, matching the pattern used across the app. The previous approach
applied -webkit-app-region: drag to the entire content container which
could interfere with child element interactions.
Onboarding steps 1-4: move drag region from a tiny 80px left strip to
the entire header element, and mark the ModeToggle as no-drag so it
remains clickable.
Closes MUL-241
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
In CLI mode, the parent Agent is not registered with the Hub, so the
normal announce flow can't deliver sub-agent results. Added polling
mechanism that waits for sub-agents to complete and prints their
findings directly to stdout.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- SKILL.md: python → python3 (macOS has no `python` binary)
- skills/index.ts: inject skill directory path so agent can resolve
relative paths like scripts/recalc.py to absolute paths
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
LLM often invents custom groupId strings that don't exist in the
registry, causing "group not found" errors. Now auto-creates the
group instead, matching the behavior when `next` is provided.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
toolsOptions spread `options` which had sessionId undefined for
auto-generated sessions. This caused sessions_list and sessions_spawn
to fail with "No session ID available" — breaking sub-agent orchestration.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace sequential for+await tool dispatch with Promise.allSettled for
parallel execution. All tool_execution_start events emit immediately,
tools run concurrently, results are processed in original order.
Also fix run-log toolStartTimes to key by toolCallId instead of toolName
to prevent collisions with parallel same-name tools.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Grouped runs now display findings for completed sub-agents (up to 4000
chars). Ungrouped runs increased truncation from 200 to 4000 chars. All
status lines include full runId for subsequent API queries.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Return error: true (boolean) with code field instead of error: "string_code"
to match ToolErrorPayload convention. Also update runner.ts formatRunLogToolSummary
to prefer details.code for error categorization.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Covers the full pipeline: dataset download, agent execution,
result analysis, and official Docker evaluation. Includes
runner options, output format, known limitations, and initial
benchmark results.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Always initialize Hub in CLI run mode to match the Desktop environment
where Hub is always active. This enables sessions_spawn (sub-agent
creation), cron tasks, channel plugins, and other Hub-dependent
features during E2E testing.
Hub constructor is non-blocking — gateway connection failures are
handled gracefully with auto-reconnect. hub.shutdown() in finally
block ensures clean teardown on exit.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Enrich tool_end events with result_chars, result_summary, and
error_type fields. Since run-log.jsonl is append-only and never
compacted, this preserves tool result metadata that would otherwise
be lost when session.jsonl undergoes compaction.
New fields:
- result_chars: total character count of result content
- result_summary: short tool-specific summary (e.g. "10 results",
"12.5KB", "finance/get_price_snapshot")
- error_type: error category for tool errors (e.g. "fetch_failed")
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- download-dataset.py: fetches SWE-bench Lite/Verified/Full from HuggingFace
- run.ts: core runner that clones repos, runs Agent, collects git diff patches
- evaluate.sh: wrapper for official SWE-bench Docker evaluation harness
- analyze.ts: summarizes run results with per-repo and timing breakdowns
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When SMC_DATA_DIR is set (e.g., for E2E tests), the credentials lookup
now falls back to ~/.super-multica/credentials.json5 if the custom
data dir doesn't have its own credentials file. This mirrors the
existing fallback pattern in auth-store.ts and removes the need for
the SMC_CREDENTIALS_PATH workaround in E2E tests.
Lookup order:
1. SMC_CREDENTIALS_PATH env var (explicit override)
2. {DATA_DIR}/credentials.json5 (current data dir)
3. ~/.super-multica/credentials.json5 (default location fallback)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
