chore(futuresearch-python): bump version to 0.8.0 (#5133)

## Summary
- Bump SDK + MCP version from 0.7.0 to 0.8.0 across all packages and
manifests
- Updates 9 files: 4 pyproject.toml, manifest.json, server.json,
plugin.json, marketplace.json, gemini-extension.json

### New features since 0.7.0:
- `document_query_llm` param for `agent_map` / `agent_map_async`
- `llm` param for `dedupe` / `dedupe_async`
- Session rename support (`session_name` + `session_id` together)
- `conversation_id` param in `create_session`
- MCP: widget UX fixes, activity rehydration, deferred polling
instructions, active worker counts

## Test plan
- [ ] CI passes (version consistency test validates all version strings
match)
- [ ] After merge, sync action copies to futuresearch-python repo
- [ ] Create GitHub Release with tag `v0.8.0` on futuresearch-python to
trigger PyPI publish

🤖 Generated with [Claude Code](https://claude.com/claude-code)

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Sourced from commit 0176763f6a305c167e2cb4768b5189e4e9dddcdb

Author: RafaelPo

.claude-plugin/marketplace.json

@@ -11,7 +11,7 @@
       "name": "futuresearch",
       "source": "./",
       "description": "Give Claude Code a research team. Forecast, score, classify, or research every row of a dataset.",
-      "version": "0.7.0"
+      "version": "0.8.0"
     }
   ]
 }

.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "futuresearch",
   "description": "Give Claude Code a research team. Forecast, score, classify, or research every row of a dataset.",
-  "version": "0.7.0",
+  "version": "0.8.0",
   "author": {
     "name": "FutureSearch"
   },

CITATION.cff

@@ -4,7 +4,7 @@ type: software
 title: "futuresearch"
 abstract: "A researcher for every row. Run web research agents at scale to forecast, score, classify, deduplicate, merge, or enrich entire datasets."
 license: MIT
-version: 0.7.0
+version: 0.8.0
 date-released: 2026-02-24
 repository-code: "https://github.com/futuresearch/everyrow-sdk"
 url: "https://futuresearch.ai"

README.md

@@ -262,7 +262,7 @@ Built by [FutureSearch](https://futuresearch.ai).
   author       = {FutureSearch},
   title        = {futuresearch},
   url          = {https://github.com/futuresearch/futuresearch-python},
-  version      = {0.7.0},
+  version      = {0.8.0},
   year         = {2026},
   license      = {MIT}
 }

futuresearch-mcp/manifest.json

@@ -2,7 +2,7 @@
   "manifest_version": "0.4",
   "name": "futuresearch-mcp",
   "display_name": "FutureSearch MCP Server",
-  "version": "0.7.0",
+  "version": "0.8.0",
   "description": "Give your AI a research team. Forecast, score, classify, or research every row of a dataset.",
   "long_description": "MCP server for futuresearch: give your AI a research team. Each operation dispatches web research agents across a dataset to forecast, score, classify, deduplicate, merge, or research at scale.",
   "author": {

futuresearch-mcp/pyproject.toml

@@ -1,12 +1,12 @@
 [project]
 name = "futuresearch-mcp"
-version = "0.7.0"
+version = "0.8.0"
 description = "MCP server for futuresearch: a researcher for every row"
 readme = "README.md"
 requires-python = ">=3.12"
 dependencies = [
     "PyJWT[crypto]>=2.8.0",
-    "futuresearch>=0.7.0",
+    "futuresearch>=0.8.0",
     "httpx>=0.27.0",
     "jsonschema>=4.0.0",
     "mcp[cli]>=1.0.0",
@@ -39,6 +39,7 @@ dev = [
 
 [tool.uv]
 exclude-newer = "7 days"
+exclude-newer-package = { futuresearch = false, futuresearch-mcp = false }
 
 [tool.basedpyright]
 venvPath = ".."

futuresearch-mcp/server.json

@@ -9,13 +9,13 @@
     "subfolder": "futuresearch-mcp"
   },
   "websiteUrl": "https://github.com/futuresearch/everyrow-sdk/tree/main/futuresearch-mcp",
-  "version": "0.7.0",
+  "version": "0.8.0",
   "packages": [
     {
       "registryType": "pypi",
       "registryBaseUrl": "https://pypi.org",
       "identifier": "futuresearch-mcp",
-      "version": "0.7.0",
+      "version": "0.8.0",
       "runtimeHint": "uvx",
       "transport": {
         "type": "stdio"

gemini-extension.json

@@ -1,7 +1,7 @@
 {
   "name": "futuresearch",
   "description": "Gemini extension for the futuresearch SDK - AI-powered data processing utilities for transforming, deduping, merging, ranking, and classifying dataframes",
-  "version": "0.7.0",
+  "version": "0.8.0",
   "mcpServers": {
     "futuresearch": {
       "command": "uvx",

pyproject.toml

@@ -1,5 +1,6 @@
 [tool.uv]
 exclude-newer = "7 days"
+exclude-newer-package = { futuresearch = false, futuresearch-mcp = false }
 
 [tool.uv.workspace]
 members = ["futuresearch-mcp"]
@@ -9,7 +10,7 @@ futuresearch = { workspace = true }
 
 [project]
 name = "futuresearch"
-version = "0.7.0"
+version = "0.8.0"
 description = "A researcher for every row. Forecast, score, classify, or research entire datasets."
 readme = "README.md"
 requires-python = ">=3.12"

stubs/everyrow-mcp/pyproject.toml

@@ -1,10 +1,10 @@
 [project]
 name = "everyrow-mcp"
-version = "0.7.0"
+version = "0.8.0"
 description = "Renamed to futuresearch-mcp. This package is a compatibility shim."
 readme = "README.md"
 requires-python = ">=3.12"
-dependencies = ["futuresearch-mcp>=0.7.0"]
+dependencies = ["futuresearch-mcp>=0.8.0"]
 
 [tool.hatch.build.targets.wheel]
 packages = ["src/everyrow_mcp"]