diff --git a/CHANGELOG.md b/CHANGELOG.md
index b5c0f65..2a5e92c 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,12 +1,16 @@
 # Changelog
 
-## Unreleased
+## 0.7.6 - 2026-10-06
 
 - Correct the display input price for `stepfun/Step-3.5-Flash` to $0.09 per million tokens and add the `Qwen/Qwen3.6-Plus` long-context tier above 256K tokens, verified against the official pricing page on 2026-10-06. Mark the unchanged, expired `qwen-3.7-max-2x-usage` badge as reviewed in the pricing checker while keeping it visible in reports; changed deal terms and price drift still require review.
 - Restore incremental reasoning on the Provider API OpenAI Responses wire by translating Command Code's non-standard `response.reasoning.delta` events into the canonical `response.reasoning_text.delta` before they reach pi-ai, including valid trailing frames without a final blank line. Reasoning now streams while the reasoning item is still open instead of appearing only at `response.output_item.done`. Unsupported reasoning event shapes remain unchanged and produce a content-free warning in `/commandcode-status`. Reproduced with `deepseek/deepseek-v4.1-flash-fast`; standard Responses events, Chat Completions, Anthropic Messages, and the generate fallback are unchanged.
 - Add a read-only `npm run check:commandcode-pricing` command that compares the live Provider API catalog and the official pricing page against `MODEL_COSTS`, reporting missing local prices, changed base rates and context tiers, time-policy drift, and expired promotions. It runs in the daily catalog workflow and applicable pull requests, publishes its report to the Actions summary, and never edits prices.
 - Add reviewed display pricing for the October catalog additions — `claude-sonnet-5-5`, `gpt-6.1-sol` (with its 272K long-context tier), `deepseek/deepseek-v4.1-flash-fast`, and the free `inclusionai/ling-3.1-flash:free`. Apply the DeepSeek V4 weekday peak-pricing window to `deepseek/deepseek-v4.1-flash-fast`. Models absent from `MODEL_COSTS` silently fall back to a zero display cost, so the snapshot now covers all 85 advertised models.
 
+### Contributors
+
+- @sandexzx — added October catalog display pricing (#135), built the pricing-drift checker (#136), and restored incremental Responses reasoning (#138).
+
 ## 0.7.5 - 2026-10-06
 
 - Harden the `test-pi-local.mjs` temp-home cleanup against transient `ENOTEMPTY` when RPC children flush session files while exiting: poll with fresh removal attempts instead of relying on `maxRetries`, whose behavior on `ENOTEMPTY` varies across Node versions. Test-only change; the 0.7.4 release run failed on this cleanup after all tests had passed.
diff --git a/package-lock.json b/package-lock.json
index 846dcef..a9e2357 100644
--- a/package-lock.json
+++ b/package-lock.json
@@ -1,12 +1,12 @@
 {
   "name": "pi-commandcode-provider",
-  "version": "0.7.5",
+  "version": "0.7.6",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "pi-commandcode-provider",
-      "version": "0.7.5",
+      "version": "0.7.6",
       "license": "MIT",
       "devDependencies": {
         "@types/node": "25.6.0",
diff --git a/package.json b/package.json
index d0b54a0..87eaec1 100644
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
 {
   "name": "pi-commandcode-provider",
-  "version": "0.7.5",
+  "version": "0.7.6",
   "description": "pi custom provider for Command Code API (commandcode.ai)",
   "type": "module",
   "keywords": [