docs: complete tool catalog, trajectory types, and browser automation details

docs/ls-binary-analysis.md

@@ -690,17 +690,162 @@ MODEL_STATUS_INFO
 MODEL_STATUS_WARNING
 ```
 
-### Cortex Step Types
+### Cortex Step Types (Complete Tool Catalog)
 
-These are the internal names for the agent's tool-use steps:
+Every tool the agent can invoke, organized by category:
+
+**File Operations:**
 
 ```
-CORTEX_STEP_TYPE_CODE_ACTION
-CORTEX_STEP_TYPE_COMMAND_STATUS
-CORTEX_STEP_TYPE_COMPILE_TOOL_PYLINT
-CORTEX_STEP_TYPE_GREP_SEARCH
-CORTEX_STEP_TYPE_RUN_COMMAND
-CORTEX_STEP_TYPE_VIEW_CODE_ITEM
+CODE_ACTION          — edit/create files
+VIEW_FILE            — read file contents
+VIEW_FILE_OUTLINE    — view file structure
+VIEW_CODE_ITEM       — view specific code symbol
+VIEW_CONTENT_CHUNK   — view document chunk
+LIST_DIRECTORY       — list directory contents
+FIND                 — find files
+GREP_SEARCH          — search file contents
+CODE_SEARCH          — semantic code search
+FIND_ALL_REFERENCES  — find all references to symbol
+FILE_CHANGE          — track file changes
+DELETE_DIRECTORY      — delete directory
+MOVE                 — move/rename files
+```
+
+**Terminal / Commands:**
+
+```
+RUN_COMMAND          — execute shell command
+COMMAND_STATUS       — check command status
+SEND_COMMAND_INPUT   — send input to running command
+READ_TERMINAL        — read terminal output
+SHELL_EXEC           — execute shell (lightweight variant)
+DEFINE_NEW_ENV_VARIABLE — set environment variable
+```
+
+**Browser Automation:**
+
+```
+OPEN_BROWSER_URL     — navigate to URL
+READ_BROWSER_PAGE    — read current page
+BROWSER_CLICK_ELEMENT     — click element
+BROWSER_INPUT             — type into element
+BROWSER_SELECT_OPTION     — select dropdown option
+BROWSER_PRESS_KEY         — keyboard press
+BROWSER_SCROLL / _UP / _DOWN — scroll page
+BROWSER_REFRESH_PAGE      — refresh
+BROWSER_RESIZE_WINDOW     — resize viewport
+BROWSER_MOVE_MOUSE        — move cursor
+BROWSER_MOUSE_DOWN / _UP  — mouse events
+BROWSER_MOUSE_WHEEL       — scroll wheel
+BROWSER_DRAG_PIXEL_TO_PIXEL — drag and drop
+CLICK_BROWSER_PIXEL       — click at pixel coordinates
+CAPTURE_BROWSER_SCREENSHOT — screenshot
+CAPTURE_BROWSER_CONSOLE_LOGS — console output
+BROWSER_GET_DOM           — get DOM tree
+BROWSER_LIST_NETWORK_REQUESTS — list network requests
+BROWSER_GET_NETWORK_REQUEST   — get specific request
+EXECUTE_BROWSER_JAVASCRIPT    — run JS in page
+LIST_BROWSER_PAGES       — list open pages
+BROWSER_SUBAGENT         — spawn browser sub-agent
+```
+
+**Web & External:**
+
+```
+SEARCH_WEB           — web search
+READ_URL_CONTENT     — fetch URL
+READ_RESOURCE        — read MCP resource
+LIST_RESOURCES       — list MCP resources
+MCP_TOOL             — invoke MCP tool
+```
+
+**Git & PR:**
+
+```
+GIT_COMMIT           — create commit
+POST_PR_REVIEW       — post PR review
+```
+
+**Knowledge & Memory:**
+
+```
+MEMORY               — store memory
+RETRIEVE_MEMORY      — recall memory
+KNOWLEDGE_GENERATION — generate knowledge item
+KNOWLEDGE_ARTIFACTS  — manage knowledge artifacts
+KI_INSERTION         — insert knowledge item
+BRAIN_UPDATE         — update brain state
+RETRIEVE_CONTENT     — retrieve stored content
+CONVERSATION_HISTORY — access conversation history
+```
+
+**Planning & Control Flow:**
+
+```
+PLANNER_RESPONSE     — planner output
+PLAN_INPUT           — plan step input
+TASK_BOUNDARY        — mark task boundary
+CHECKPOINT           — checkpoint state
+TRAJECTORY_CHOICE    — choose trajectory branch
+TRAJECTORY_SEARCH    — search trajectories
+TOOL_CALL_CHOICE     — choose tool call
+TOOL_CALL_PROPOSAL   — propose tool call
+PROPOSE_CODE         — propose code change
+CODE_ACKNOWLEDGEMENT — acknowledge code change
+MANAGER_FEEDBACK     — agent manager feedback
+PROPOSAL_FEEDBACK    — proposal feedback
+CRITIQUE             — self-critique step
+FINISH               — mark completion
+WAIT                 — wait/pause
+```
+
+**Media & UI:**
+
+```
+GENERATE_IMAGE       — generate image
+SUGGESTED_RESPONSES  — suggest user responses
+NOTIFY_USER          — notify user
+EPHEMERAL_MESSAGE    — temporary message
+ERROR_MESSAGE        — error display
+SYSTEM_MESSAGE       — system message
+ADD_ANNOTATION       — add UI annotation
+CLIPBOARD            — clipboard access
+```
+
+**Code Quality:**
+
+```
+COMPILE              — compile/build
+COMPILE_APPLET       — compile applet
+LINT_DIFF            — lint changes
+LINT_APPLET          — lint applet
+FINDINGS             — code findings
+```
+
+**Workspace & Deployment:**
+
+```
+WORKSPACE_API        — workspace operations
+RESTART_DEV_SERVER   — restart dev server
+SET_UP_FIREBASE      — Firebase setup
+DEPLOY_FIREBASE      — Firebase deployment
+INSTALL_APPLET_DEPENDENCIES — install deps
+INSTALL_APPLET_PACKAGE      — install package
+RUN_EXTENSION_CODE          — run VS Code extension code
+```
+
+**Google-Internal (corp only):**
+
+```
+INTERNAL_SEARCH      — internal search (Moma?)
+MOMA                 — Google Moma system
+MQUERY               — Google MQuery
+BLAZE_BUILD_TARGETS  — Blaze build
+BLAZE_TEST_TARGETS   — Blaze test
+BUILD_CLEANER        — build cleaning
+CIDER_AGENT_DUMMY    — Cider agent placeholder
+AGENCY_TOOL_CALL     — agency tool
 ```
 
 ### Cortex Generation Types
@@ -718,7 +863,49 @@ CORTEX_GENERATION_TYPE_STATIC_TRAJECTORY
 CORTEX_GENERATION_TYPE_VERIFY
 ```
 
----
+### Cortex Trajectory Types
+
+Different "modes" the agent can operate in:
+
+```
+CASCADE                 — standard cascade (user-initiated)
+INTERACTIVE_CASCADE     — interactive cascade (multi-turn)
+AUTO_CASCADE            — auto-triggered cascade
+AUTO_CASCADE_MANAGER    — manages auto-cascades
+BACKGROUND_RESEARCH     — background research thread
+BROWSER                 — browser automation trajectory
+DEEP_THINK              — extended reasoning mode
+KNOWLEDGE_GENERATION    — knowledge item generation
+APPLIER                 — code application trajectory
+BRAIN_UPDATE            — brain/memory update
+CHECKPOINT              — state checkpoint
+CUSTOM_TOOL             — custom tool execution
+LLM_JUDGE               — LLM-as-judge evaluation
+PASSIVE_CODER           — passive coding assistance
+RETRIEVE_MEMORY         — memory retrieval
+SUPERCOMPLETE           — tab-completion trajectory
+TOOL_CALL_PROPOSAL      — tool call proposal
+TRAJECTORY_CHOICE       — trajectory branching
+USER_MAINLINE           — user's main trajectory
+USER_GRANULAR           — granular user trajectory
+ARTIFACT_SUMMARY        — artifact summary generation
+```
+
+### Cortex Trajectory Sources
+
+Where trajectories originate from:
+
+```
+INTERACTIVE_CASCADE     — user-initiated cascade
+CASCADE_CLIENT          — cascade client
+REFACTOR_FUNCTION       — refactor action
+EXPLAIN_PROBLEM         — explain/debug action
+PASSIVE_CODER           — passive coding
+REPLAY                  — trajectory replay
+SDK / PYTHON_SDK        — API/SDK access
+EVAL / EVAL_TASK        — evaluation system
+ASYNC_CF / ASYNC_SL / ASYNC_CM / ASYNC_PRD / ASYNC_PRR — async operations
+```
 
 ## Hardcoded URLs