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>
- 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>
- 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>
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>
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>
web_search and data tools authenticate via auth.json (sid + deviceId).
When SMC_DATA_DIR is set (e.g. for E2E tests), the auth file may not
exist in the custom dir. Now getLocalAuth() falls back to
~/.super-multica-dev/auth.json, which is created by pnpm dev:local
Desktop login and valid for the dev backend (api-dev.copilothub.ai).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add --run-log CLI flag to enable structured run logging without env var.
Print session directory path to stderr when run-log is enabled so Coding
Agents can easily locate log files for analysis.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Compaction was reporting only 189 tokens removed for 6 messages because
Phase 1 (tool result pruning) hollowed out messages before Phase 2
(summary compaction) measured them. Now captures pre-pruning token count
and reports combined savings from both phases.
Also threads RunLog through SessionManager to emit tool_result_pruning
and compaction_detail events, and adds preflight pruning stats logging.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The transformContext pipeline ran sanitizeToolUseResultPairing() before
preflightCompact(), but compaction (pruneToolResults + compactMessagesTokenAware)
can break tool_use/tool_result pairing by dropping assistant messages while
keeping their tool_result blocks. This caused 400 errors from the Anthropic API:
"unexpected tool_use_id found in tool_result blocks".
Add a second sanitizeToolUseResultPairing() call after preflightCompact()
to repair any orphaned tool_result blocks created during compaction.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Instead of only protecting .env files, use cpSync with force:true to
overlay bundle files onto the existing directory. This preserves any
user-created files (credentials.json, token.json, etc.) that don't
exist in the bundle, rather than deleting and re-copying the entire
directory.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove hardcoded service API key hints from getApiKeyHint() — skill-specific
hints should be discovered dynamically by the agent via web_search/web_fetch
at runtime. Only keep LLM provider hints which are system-level. Update
skill-creator instructions accordingly.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add buildIneligibleSkillsSummary() to SkillManager that surfaces skills
with actionable issues (missing env vars, binaries) in the agent's system
prompt. Expand getApiKeyHint() with common service API providers. Update
buildSkillsSection() to guide the agent to suggest activating inactive
skills when they match user intent.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove centralized skills.env.json5 in favor of per-skill .env files.
Clean up CredentialManager by removing hasEnv/getEnv/getResolvedEnvSnapshot
methods and skills env loading. Update CLI credentials and skills commands.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Move skill environment variables from centralized skills.env.json5 to
per-skill .env files within each skill's directory. This makes credential
management more intuitive and self-contained.
- Fix parser to handle metadata.requires, always, os, skillKey, install
- Add minimal .env parser (dotenv.ts) and load .env at skill parse time
- Add env field to Skill type for per-skill environment variables
- Update eligibility checker to use skill.env instead of CredentialManager
- Preserve user .env files across bundled skill upgrades in loader
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Move LoadingIndicator from ChatView into MessageList for consistent padding
- Add isLoading and hasPendingApprovals props to MessageList
- Adjust message spacing (my-1 → my-2) for better visual balance
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Create LoadingIndicator component with "generating" and "streaming" variants
- Remove inline loading indicator from StreamingMarkdown (empty content returns empty fragment)
- Use unified LoadingIndicator in ChatView with consistent positioning
- Eliminates layout shift between different loading states
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Use container utility class consistently across chat components
- Change container max-width from 5xl to 4xl for better readability
- Adjust message bubble padding (p-3 -> p-2)
- Fix logout dropdown alignment and add destructive variant
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Use TipTap's getText({ blockSeparator: '\n' }) instead of doc.textContent
to preserve newlines between paragraphs when submitting messages
- Add whitespace-pre-wrap CSS to user message bubbles to render newlines
- Add className prop support to StreamingMarkdown component
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Replace scattered API_URL, MAIN_VITE_API_URL, and RENDERER_VITE_API_URL
with a single MULTICA_API_URL across all apps and packages.
- Desktop: use envPrefix to expose MULTICA_* to main process, rename
RENDERER_VITE_API_URL → RENDERER_VITE_MULTICA_API_URL, remove
MAIN_VITE_API_URL (now read directly via MULTICA_API_URL)
- Web: add .env.development with MULTICA_API_URL, enforce required check
in next.config.ts, update .gitignore to allow .env.development
- Core: make MULTICA_API_URL required in api-client (no silent fallback)
- Scripts: pass MULTICA_API_URL in dev-local.sh for web process
- Turbo: update globalEnv from API_URL to MULTICA_API_URL
- Docs: update references to the new env var name
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
These fields were only checked during eligibility but never injected
at runtime via credentialManager.getEnv(). Remove the half-implemented
per-skill credential config to reduce confusion.
API key configuration remains supported via skills.env.json5 and
process.env.
Refs: MUL-246, MUL-255
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
When the user sends a message and the agent hasn't started streaming
yet, the chat area showed no visual feedback. Now a "Generating..."
spinner appears between message send and the first streaming content,
matching the existing indicator style used in StreamingMarkdown.
Closes MUL-224
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Move the shared office/ directory (pack/unpack, validators, schemas,
soffice wrapper) to skills/_shared/office/ and replace the three
identical copies with symlinks. Update skill loader to dereference
symlinks during copy to managed directory, and skip _-prefixed
directories in the bundled skills scan.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Allows isolating dev and prod data by setting SMC_DATA_DIR (e.g.
~/.super-multica-dev). Also fixes cron/store.ts which bypassed
DATA_DIR with a hardcoded path.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add an `active` flag so that message_update/message_end events are
ignored after reset() until the next message_start, preventing stale
accumulated text from being re-emitted as a block.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Lazy-read process.env at call time instead of module import time.
This ensures the env bridge in the Electron main process has time to
set process.env.MULTICA_API_URL before the first API request.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The hasToolUse() function was checking for "tool_use" (raw Anthropic format)
but pi-ai normalizes tool call blocks to type "toolCall". This made tool
narration non-functional in the ChannelManager (Desktop/embedded) path.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The Telegram bot is handled entirely by the Gateway
(apps/gateway/telegram/). The Desktop channel plugin was never
registered (commented out in initChannels) and is dead code.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Instead of silently discarding tool narration or spamming separate
messages, send a single editable Telegram message that updates in-place
as the agent works. First tool narration sends a reply; subsequent
narrations edit the same message. The final answer is sent as a new
message.
- Add replyTextEditable/editText to ChannelOutboundAdapter interface
- Implement editFormatted + editable methods in Telegram plugin
- Track statusMessageId in ChannelManager, clear on agent_end/error
- Add sendOrEditStatus to Gateway TelegramService with same behavior
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When the agent uses tools (web search, etc.), it generates intermediate
narration text like "Let me search..." before each tool call. These were
being sent as separate Telegram messages, causing message spam. Now we
detect tool_use blocks in the message content and skip sending those
intermediate messages — only the final answer reaches the user.
Applied to both Desktop channel plugin and Gateway Telegram service.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Telegram doesn't support HTML tables, so pipe-delimited Markdown tables
were rendered as hard-to-read plain text on mobile. This converts tables
to a vertical "Header: Value" format with bold first column before
sending to Telegram.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove the user-facing ability to create custom Telegram bots via BotFather.
Non-technical users should only need to message @multica_bot on Telegram.
- Disable telegramChannel plugin registration in initChannels()
- Remove ConnectStep from onboarding flow (Privacy → Provider → Start)
- Replace TelegramCard with simple text pointing to @multica_bot
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- store.test.ts: use baseDir option instead of mocking paths.js
- session-file-repair.test.ts: remove write-lock mock, assert behavior
- announce-findings.test.ts: use real storage with temp dirs
- sessions-list.test.ts: use real registry with seed helper
- compaction.test.ts: mock only third-party pi-coding-agent, use real
context-window internals
All tests exercise real code paths, improving confidence in actual
behavior per the strict mock policy.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add AuthStoreOptions with baseDir to auth-profiles/store.ts functions,
add baseDir option to announce.ts readLatestAssistantReply, and add
seedSubagentRunForTests helper to registry.ts. These enable tests to
use real implementations with temp directories instead of mocking
internal modules.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Introduce a RunLog system that records agent execution events as
structured JSONL to ~/.super-multica/sessions/{id}/run-log.jsonl.
Enable via MULTICA_RUN_LOG=1 env var or AgentOptions.enableRunLog.
Logs: run lifecycle, LLM calls, tool execution timing, context
overflow recovery, auth profile rotation, error classification,
and compaction events.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Prefer markdown responses from servers that support Cloudflare's Markdown
for Agents feature, reducing token usage by ~80% when available. Non-supporting
servers fall back to HTML as before.
- Update Accept header to prefer text/markdown in web_fetch requests
- Add text/markdown content-type handling to skip HTML parsing pipeline
- Capture x-markdown-tokens response header in WebFetchResult
- Add extractMarkdownTitle() helper for native markdown title extraction
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
