12678c637b
fix(agent-chat): streaming state leak, document parser magic bytes, HITL flow
...
### Bugfixes — Agent Chat 'Думаю' State Leak
- fix(agent-chat): loadHistory() now resets streamingState/idle + cancels stale
submission — prevents 'Думаю' state leak across conversation switches
- fix(agent-chat): onDisconnected/onDisconnectedPermanent cascade to
streamingState — prevents permanent hang on connection loss during stream
- fix(agent-chat): guard on isLoadingHistory — prevents false commit
of 'agent unavailable' fallback when switching conversations
- fix(agent-chat): remove race in _sendNow empty-response check vs Svelte
microtask (duplicate logic removed, handles correctly)
- fix(stream-processor): confirm_resolved now appends msg.text to partialText
instead of dropping it
### Bugfixes — Backend PDF Upload
- fix(document-parser): _detect_format_by_magic() — reads file header magic
bytes as fallback when Gradio loses filename
- fix(document-parser): improved name extraction — tries orig_name, path stem
- fix(document-parser): @RELATION AgentChatTypes -> AgentChat.Types
### HITL Flow & Agent Chat Improvements
- feat(agent): HITL resume confirm/deny with userId/userJwt/envId propagation
- feat(agent): confirm_required metadata fallback via aget_state() after
'Event loop is closed' error during interrupt
- feat(agent): interrupt_before re-enabled via AGENT_CONFIRM_TOOLS env var
- feat(frontend): debug panel with connection/stream state monitoring
- feat(frontend): AgentChatModel constructor options + onBeforeSend callback
- feat(frontend): crypto.randomUUID() for local conversation ID on first send
### Backend Agent Refactoring
- refactor(agent): langgraph_setup — monkey-patch for PydanticSerializationError
- refactor(agent): tools.py — dual identity headers, expanded tool set
- refactor(agent): run.py — _find_free_port, Gradio server port fallback
- refactor(agent): app.py — file size validation, message truncation, HITL path
### Frontend
- feat(dashboard-hub): DashboardHubModel with filters, pagination, git actions
- feat(ui): DateRangeFilter component
- feat(i18n): new dashboard keys; cache tooltips fix
- fix(i18n): full run tooltips — cache is NOT ignored
### Semantic Protocol
- chore(agents): update all agents with canonical format
- chore(skills): sync semantics-core, semantics-contracts, molecular-cot-logging
### Housekeeping
- chore: remove stale semantic reports (10 files, Jan 2026)
- chore: update 033-gradio-agent-chat specs, contracts, UX, tasks, tests
- chore: add .agents/ directory (mirrors .opencode/ agent layouts)
- chore: update run.sh with DEV_MODE, port management
2026-06-29 17:15:25 +03:00
ec6421de35
rename ss-tools to superset-tools across the entire project
...
- Replace all occurrences of 'ss-tools' with 'superset-tools' in 104 files
- Rename git bundle file ss-tools.bundle → superset-tools.bundle
- Update .gitignore pattern accordingly
- Preserve variable names (hasSsTools etc.) and code identifiers
2026-06-16 11:15:19 +03:00
73e809e189
skills
2026-06-08 15:08:02 +03:00
4cef6af041
fix
2026-06-05 15:01:34 +03:00
4b6c47837f
agents skills
2026-05-25 13:25:35 +03:00
c617754cca
refactor(semantics): make complexity tiers descriptive, not gatekeeping
...
Why: tier rules forbidding @PRE/@POST on C2 cause agents to either
remove useful documentation or generate audit noise. Both outcomes are
worse than having slightly richer metadata.
Changed:
- Tier table in all 4 agent prompts: removed 'Forbidden' column,
replaced with 'descriptive signal, NOT gatekeeper'
- All tags (@PRE/@POST/@RATIONALE/@REJECTED) welcomed at any tier
- semantics-core: complexity table collapsed to descriptive
- qa-tester: removed tier-based reject rules from P1 and Phase 1
Hard rules preserved: CONTRACT-FIRST, ANCHOR SAFETY, FRACTAL LIMIT,
RESURRECTION BAN. Everything else is descriptive intent.
2026-05-20 15:15:52 +03:00
07cfaadee1
refactor(agents): inject CONTRACT MANDATE into all coder agent prompts
...
Why: agents kept forgetting #region contracts because the rationale
was hidden in loadable skills, not active in their system prompt.
Changed agent prompts (+RATIONALE-first):
- python-coder: +55 lines — 4 failure modes + operational rules
- fullstack-coder: +40 lines — same, with cross-stack emphasis
- svelte-coder: replaced PHYSICS OF ATTENTION with unified mandate
- qa-tester: +15 lines — QA-specific contract mandate
Compressed skills (reference-only):
- semantics-core: 174→110 lines (-37%) — rationale removed, syntax+tables kept
- semantics-contracts: 103→79 lines (-23%) — duplicates removed, methodology kept
Verification: 320 tests pass, 0 parse warnings, 0 semantic audit warnings
2026-05-20 15:02:29 +03:00
09d12b3b68
semantics
2026-05-20 09:59:03 +03:00
afe6c7e281
agents
2026-05-18 23:58:42 +03:00
8bea44f640
chore: update semantic index, agent configs, and app startup
2026-05-14 21:33:26 +03:00
a9a5eff518
fix(lint): apply QA-found gaps in agent instruction files
...
- python-coder.md: ruff check src/ tests/ → ruff check .
- speckit.test.md: add frontend npm run lint
- speckit.plan.md: ruff check . + frontend lint
- speckit.tasks.md: ruff check . + frontend lint
- fullstack-coder.md: move npm run lint to frontend block
2026-05-14 11:19:22 +03:00
9b8c485562
chore: configure ruff + eslint linters for agentic workflow
...
- Replace pylint with ruff (backend/ruff.toml)
- line-length=300, max-complexity=10, per-file-ignores for tests
- Exclude D (docstrings replaced by contracts) and ANN
- Add eslint flat config for frontend (eslint-plugin-svelte)
- Allow console.info/warn/error (belief-state protocol)
- Remove .pylintrc (references non-existent plugin)
- Update agent docs: ruff check . + npm run lint
- Add ruff>=0.11.0 to backend/requirements.txt
- Add eslint + plugins to frontend devDependencies
2026-05-14 10:28:30 +03:00
9ea177558b
agents
2026-05-12 19:37:22 +03:00
fefdee98d0
agents
2026-05-11 22:58:01 +03:00
