Flow visualization improvements:
- Add dynamic minZoom that adapts to card count (see all cards at min zoom)
- Fix maxZoom at 1.5x for readable card text regardless of card count
- Align scroll wheel zoom speed between minimap and canvas (~9 clicks)
- Add translateExtent to constrain panning within node bounds
- Add status-based MiniMap colors (blue=running, green=success, red=error)

Scroll and layout fixes:
- Fix page-level scrolling by adding overflow:hidden to html/body/SidebarProvider
- Fix auto-scroll on page load (scrollIntoView block:'nearest')
- Add overscroll-contain to ChatHistory to prevent scroll chaining

Swim lane layout (flow-utils.ts):
- Rewrite layout algorithm for fixed-width swim lanes per agent
- Increase node fallback dimensions for better readability
- Add minimum dimension enforcement in getNodeSize()

Files changed:
- FlowView.tsx: zoom config, MiniMap styling, ReactFlowProvider wrapper
- ChatLayout.tsx: overflow-hidden on panels
- Workspace.tsx: overflow-hidden on container
- ChatHistory.tsx: overscroll-contain
- flow-utils.ts: swim lane algorithm
- globals.css: html/body overflow hidden
- layout.tsx: SidebarProvider height constraints
- r/page.tsx: scrollIntoView fix

Associates that output JSON deliverables without calling `finish_flow`
would have their work lost, as the system only triggers deliverable
extraction when `finish_flow` is invoked. Live session analysis
revealed this caused re-dispatching.

The `generate_message_summary` instructional prompt told agents "DO NOT
call any tools" after outputting JSON, but `finish_flow` IS required to
trigger `_extract_deliverables_from_messages()` and capture the work.

- Updated instructional prompt to explicitly describe the 3-response
  sequence: generate_message_summary → JSON output → finish_flow
- Added critical warning about deliverable capture requirement

- Added "Finish Protocol" section documenting the completion sequence
- Updated self-reflection to detect JSON-without-finish_flow state
- Fixed observation text to match actual trigger conditions

- Added "CRITICAL CHECK" for JSON deliverable detection
- Updated instructions to guide agents through finish protocol
- Fixed incomplete sentence ("MUST synthesis" → proper guidance)

- Updated Deliver step to mention `finish_flow` requirement

- Analyzed production runs confirming the JSON → finish_flow
 sequence across all completed work modules
- All unit tests pass
- No regressions expected - changes are corrective/additive

Flow visualization now groups disconnected subgraphs into time-sorted
epochs, ensuring timestamps always flow top-to-bottom (swimlane style).

Changes:
- Detect epochs via flood-fill of disconnected turn subgraphs
- Sort epochs by earliest timestamp for chronological ordering
- Add epoch separator nodes between epochs with proper labels
- Add "Epoch 1" header when multiple epochs exist
- Create edges connecting separators to adjacent epoch roots/leaves
- Filter Partner and user_turn before epoch detection
- Add epoch_separator nodeType to frontend FlowView component
- Update FlowViewModel documentation in API reference
- Add comprehensive unit tests for epoch detection logic

Fixes issue where cards from re-dispatched work modules appeared
out of chronological order in the flow visualization.

- Detect disconnected subgraphs as epochs, sort by timestamp
- Add epoch separator nodes with edges to adjacent epochs
- Show "Epoch N" headers only when multiple epochs exist
- Filter Partner/user_turn before epoch detection
- Update frontend to render epoch_separator nodeType
- Update API docs for FlowViewModel epoch fields

Core Fixes:
- Add tool conflict resolution to prioritize finish_flow when called
  with other tools (prevents silent data loss from juicy-winged-adder)
- Add synchronous completion handler ensuring deliverables propagate
  to Partner inbox before session save
- Add /api/reports/{project_id}/{filename} endpoint for report downloads

Port Configuration:
- Consolidate all port config to core/.env as single source of truth
- Update commonground.sh to read BACKEND_PORT/FRONTEND_PORT from .env
- Update run_server.py to use .env defaults for host/port
- Update analysis scripts to read from .env instead of hardcoding

Pagination Enhancements:
- Add work module archive pagination to get_paginated_run_snapshot
- Support work_module_id and archive_index params for deep inspection
- Update message_handlers.py to pass new pagination params
- Update live_session_query.py to reconstruct archives with pagination

Frontend:
- Fix heartbeat/reconnect message format to use data wrapper
- Increase heartbeat tolerance (30s interval, 4 missed max)

Tests & Docs:
- Add test_tool_conflict_resolution.py (10 tests)
- Add TestTeamStatePagination tests (7 tests)
- Add context-management-fixes.md design document
- Restore DEFAULT_API_KEY/DEFAULT_BASE_URL in env.sample

…tion

- Add `allowed_at_critical` parameter to tool registry for budget-aware filtering
- User prompts (USER_PROMPT, PARTNER_DIRECTIVE, PRINCIPAL_COMPLETED) bypass
  circuit breaker to use reserved 15% headroom
- Restrict Partner tools to read-only at CRITICAL/EXCEEDED thresholds
- Mark flow-terminating tools (finish_flow, generate_message_summary) and
  GetPrincipalStatusSummaryTool as critical-safe
- Add filter_tools_for_critical_budget() in agent_strategy_helpers
- Add --output flag to analyze_session.py and live_session_query.py

Tests: 13 new tests for strategy helpers, 4 for guardian bypass, 6 for registry