chore(release): bump workspace to v0.8.34 and clean repo root

- Bump workspace.package.version 0.8.33 -> 0.8.34 across all 14 crates
- Bump npm wrapper version + deepseekBinaryVersion pin
- Update docs/TOOL_SURFACE.md "Current surface" + docs/ARCHITECTURE.md
  current-surface references; historical "removed_in"/"v0.8.33 began
  moving" wording stays as fact
- Update web/lib/facts.generated.ts version pin
- Draft [0.8.34] CHANGELOG section covering the 135 commits since 0.8.33
  (prefix-cache stability, bundled skills, Kitty/Ghostty notifications,
  theme picker, chunked tool dispatch, MCP session-id persistence,
  cost-calc reasoning tokens, and the in-flight internal cleanup)
- Remove stale repo-root development artifacts:
  * TAKEOVER_PROMPT.md (v0.8.6 handoff, 3 minors stale)
  * PROMPT_ANALYSIS.md (v0.8.13-era prompt audit doc)
  * DEPENDENCY_GRAPH.md (claimed monolith layout, predates 14-crate split)
  docs/ARCHITECTURE.md already contains the live crate map.
- Update CONTRIBUTING.md to reference docs/ARCHITECTURE.md for build
  ordering instead of the removed DEPENDENCY_GRAPH.md

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

docs/ARCHITECTURE.md

@@ -7,7 +7,7 @@ Current boundary note (v0.8.6):
 - Other workspace crates are being split out incrementally, but they are not yet the sole runtime source of truth.
 - The LSP subsystem (`crates/tui/src/lsp/`) is fully wired into the engine's post-tool-execution path
   (`core/engine/lsp_hooks.rs`), providing inline diagnostics after every edit_file/apply_patch/write_file.
-- The swarm agent system was removed in v0.8.5. The active v0.8.33 orchestration surface is persistent sub-agent sessions (`agent_open` / `agent_eval` / `agent_close`) and persistent RLM sessions (`rlm_open` / `rlm_eval` / `rlm_configure` / `rlm_close`).
+- The swarm agent system was removed in v0.8.5. The active v0.8.34 orchestration surface is persistent sub-agent sessions (`agent_open` / `agent_eval` / `agent_close`) and persistent RLM sessions (`rlm_open` / `rlm_eval` / `rlm_configure` / `rlm_close`).
   No model-visible swarm tool remains in the active codebase.
 
 ## High-Level Overview

docs/TOOL_SURFACE.md

@@ -15,7 +15,7 @@ chosen over the available shell equivalent. Companion to `crates/tui/src/prompts
   for the same backing operation are a model trap — the LLM will alternate
   between them and the cache hit rate suffers.
 
-## Current surface (v0.8.33)
+## Current surface (v0.8.34)
 
 ### File operations
 
@@ -138,7 +138,7 @@ Large logs and command outputs should be artifacts with compact summaries in the
 
 ### Sub-agents
 
-v0.8.33 begins moving large tool outputs toward symbolic handles: tools return
+v0.8.33 began moving large tool outputs toward symbolic handles: tools return
 small `var_handle` objects, and `handle_read` retrieves bounded slices, counts,
 or JSON projections from the backing environment. This keeps the parent
 transcript small while preserving a recovery path to the full payload.
@@ -224,7 +224,7 @@ slots.
 
 ## Removed legacy aliases and surfaces
 
-v0.8.33 removes the old model-facing sub-agent fan-out surface from active
+v0.8.33 removed the old model-facing sub-agent fan-out surface from active
 prompting and tool catalogs. Do not use these names in new active guidance:
 `agent_spawn`, `agent_wait`, `agent_result`, `agent_send_input`,
 `agent_assign`, `agent_resume`, `agent_list`, `spawn_agent`,
@@ -269,7 +269,7 @@ rg -n '"handle_read"|"rlm_open"|"rlm_eval"|"rlm_configure"|"rlm_close"|"agent_op
 rg -n 'handle_read|rlm_open|rlm_eval|rlm_configure|rlm_close|agent_open|agent_eval|agent_close' docs crates/tui/src/prompts crates/tui/src/tools
 ```
 
-The canonical v0.8.33 live names are:
+The canonical v0.8.34 live names are:
 
 - `handle_read`
 - `rlm_open`, `rlm_eval`, `rlm_configure`, `rlm_close`