v0.39.1: re-verify field matrix against CC 2.1.161 + correct workflow claim (#35)

User updated Claude Code 2.1.131 → 2.1.161. Re-grepped the new bundle.

Two corrections:

1. The three fields that were absent on 2.1.131 are now present on
   2.1.161: reloadSkills (6), continueOnBlock (3), MessageDisplay (28).
   docs/reference/cc-undocumented-fields.md updated to mark them
   present. Still NOT built — none has a compelling token-pilot use
   case yet (skills are static; post-hooks are advisory not blocking;
   tp-* output is already terse). Recorded, not adopted — building
   them now would be feature-for-feature's-sake.

2. CORRECTED a speculative claim. `/workflow` exists in 2.1.161 but
   does NOT export a per-workflow id env var to subagents — the bundle
   has only `CLAUDE_CODE_WORKFLOWS` (feature flag) and an internal
   `WorkflowId`. There is no `CLAUDE_CODE_WORKFLOW_ID`. The v0.38.0
   README + workflow.ts comment claimed token-pilot would "compose
   with CC /workflow" via that var — that bridge does not exist.
   Corrected README + the activeWorkflowId() doc comment to state
   the truth: token-pilot's fleet workflows are independent
   (TOKEN_PILOT_WORKFLOW_ID); the extra env probes are a harmless
   forward-compat fallback, not a working integration.

No behaviour change — activeWorkflowId() already returned null for the
non-existent var and fell back to our own. Docs-only accuracy fix.

Tests: 1319/1319 pass.

Author: Shahinyanm

.claude-plugin/marketplace.json

@@ -6,14 +6,14 @@
   },
   "metadata": {
     "description": "Token Pilot \u2014 save 60-90% tokens when AI reads code",
-    "version": "0.39.0"
+    "version": "0.39.1"
   },
   "plugins": [
     {
       "name": "token-pilot",
       "source": "./",
       "description": "Reduces token consumption by 60-90% via AST-aware lazy file reading, structural symbol navigation, and cross-session tool-usage analytics. 22 MCP tools + 19 subagents + budget watchdog hooks.",
-      "version": "0.39.0",
+      "version": "0.39.1",
       "author": {
         "name": "Digital-Threads"
       },

.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "token-pilot",
-  "version": "0.39.0",
+  "version": "0.39.1",
   "description": "Saves 60-90% tokens on AI code reading. AST-aware lazy reads, symbol navigation, find_usages, structural git diff/log, edit-safety guard, Task-routing matcher, cross-session telemetry (errors + diagnostics), 25 tp-* subagents tiered to haiku/sonnet/opus with budget watchdog.",
   "author": {
     "name": "Digital-Threads",

README.md

@@ -304,9 +304,12 @@ While a workflow is active:
 - The window title switches to `[TP] wf · N tasks · X%` so a long run
   shows live progress.
 
-If Claude Code ever sets its own workflow-id env var
-(`CLAUDE_CODE_WORKFLOW_ID`), token-pilot reads that too — no config
-change needed.
+Claude Code's own `/workflow` (2.1.154+) does **not** expose a
+per-workflow id env var to subagents (verified against the 2.1.161
+bundle — it has only a `CLAUDE_CODE_WORKFLOWS` feature flag). So
+token-pilot's workflows are independent: they rely on our own
+`TOKEN_PILOT_WORKFLOW_ID`. If CC adds a per-workflow env var later,
+`activeWorkflowId()` already probes for it — no config change needed.
 
 ## Troubleshooting
 

agents/tp-api-surface-tracker.md

@@ -9,7 +9,7 @@ tools:
   - mcp__token-pilot__read_symbol
   - Bash
 model: haiku
-token_pilot_version: "0.39.0"
+token_pilot_version: "0.39.1"
 token_pilot_body_hash: dd184501203fa7f3c73f419c4ffbe33c4be75400cb64a7a51733a3fe23f6e085
 requiredMcpServers:
   - "token-pilot"

agents/tp-audit-scanner.md

@@ -11,7 +11,7 @@ tools:
   - Grep
   - Read
 model: sonnet
-token_pilot_version: "0.39.0"
+token_pilot_version: "0.39.1"
 token_pilot_body_hash: d172f600bf32277ea6eb4cbbee4542ddd698a986dcd96997d33930561964569b
 requiredMcpServers:
   - "token-pilot"

agents/tp-commit-writer.md

@@ -8,7 +8,7 @@ tools:
   - mcp__token-pilot__test_summary
   - mcp__token-pilot__outline
   - Bash
-token_pilot_version: "0.39.0"
+token_pilot_version: "0.39.1"
 token_pilot_body_hash: de64a406b5176de19f7422619c7de7949b1f28865f225402c9cea9255f377428
 requiredMcpServers:
   - "token-pilot"

agents/tp-context-engineer.md

@@ -13,7 +13,7 @@ tools:
   - Edit
   - Glob
 model: sonnet
-token_pilot_version: "0.39.0"
+token_pilot_version: "0.39.1"
 token_pilot_body_hash: 68b32af2dacd82ebe52c4eec93edb903d452688274c3065218270627c564d8b0
 requiredMcpServers:
   - "token-pilot"

agents/tp-dead-code-finder.md

@@ -11,7 +11,7 @@ tools:
   - Grep
   - Read
 model: sonnet
-token_pilot_version: "0.39.0"
+token_pilot_version: "0.39.1"
 token_pilot_body_hash: d9b7f5b7ae6f4ae21305c775361bcab097cc774370a6d976c093571d46d55021
 requiredMcpServers:
   - "token-pilot"

agents/tp-debugger.md

@@ -12,7 +12,7 @@ tools:
   - Read
   - Bash
 model: sonnet
-token_pilot_version: "0.39.0"
+token_pilot_version: "0.39.1"
 token_pilot_body_hash: 052413de8d92377edcde6ae5c823f5378db304baccfa29e8866467f42553a500
 requiredMcpServers:
   - "token-pilot"

agents/tp-dep-health.md

@@ -9,7 +9,7 @@ tools:
   - Bash
   - Read
 model: haiku
-token_pilot_version: "0.39.0"
+token_pilot_version: "0.39.1"
 token_pilot_body_hash: e14dc57493d816f8c2e017963e2ef5f66bea50fd0b805a80e8a0d97c968427e7
 requiredMcpServers:
   - "token-pilot"