SAS compute tools (#14)

* Correct typo

* Add basic compute server related tools

* Add comments to Compute Server related tools

* Use return_items

* feat!: reusable compute sessions, reset tool, and compute discovery tools

Add Tier 6 compute tools (list_compute_contexts, list_compute_libraries,
list_compute_tables, list_compute_columns) and a reset_compute_session
tool. Compute sessions are now pooled per authenticated user and compute
context so repeat calls skip the slow session spin-up; cached sessions
are validated before reuse, transparently recreated if Viya reaps them,
and deleted on server shutdown via a FastMCP lifespan.

BREAKING CHANGE: execute_sas_code now runs in a reusable session, so SAS
state (WORK tables, macro variables, assigned librefs) persists across
successive calls instead of being discarded per call. Use
reset_compute_session to start from a clean session.

Also harden get_context_id/create_session with raise_for_status, encode
the context-name query parameter, add unit and live integration coverage
for the new tools (including an end-to-end reuse/reset/recreate test),
update the README and CHANGELOG, and bump the version to 1.2.0.

Assisted by Claude Code.

---------

Signed-off-by: sbxxab <xavier.bizoux@sas.com>
Signed-off-by: David Weik <david.weik@sas.com>

Author: xavierBizoux

CHANGELOG.md

@@ -1,5 +1,23 @@
 # Changelog
 
+## [1.2.0] - 2026-06-15
+
+### Added
+- **Compute service discovery tools** — `list_compute_contexts`, `list_compute_libraries`, `list_compute_tables`, `list_compute_columns` — browse compute contexts and the SAS libraries/tables/columns visible inside a compute session. Brings the tool count to 32.
+- **`reset_compute_session` tool** — deletes the cached compute session for the caller and compute context, discarding its SAS state (WORK tables, macro variables, assigned librefs) so the next call starts from a fresh session. Defaults to the configured execution context.
+- **Reusable, per-user compute session cache** (`_ComputeSessionCache` in `viya_utils.py`) — one warm compute session is kept per authenticated user and compute context, so repeat calls skip the slow session spin-up. Keyed by the JWT `sub` claim (falling back to other identity claims, then a token hash) so multi-user HTTP deployments never share a session. Cached sessions are validated before reuse and transparently recreated if Viya has reaped them for inactivity.
+- **Compute session shutdown cleanup** — both server entry points register a FastMCP `lifespan` that deletes all cached compute sessions on shutdown (best effort), so warm sessions don't linger until Viya's idle reaper collects them.
+- **Integration coverage for every new tool** — `test_compute_discovery_workflow` and `test_compute_session_reuse_and_reset` (which proves reuse, deletion, and recreation end to end against a live Viya), wired into the `test_every_tool_has_integration_coverage` guard.
+- **`return_items` helper** (`viya_client.py`) — shared field-projection used by the compute discovery tools.
+
+### Changed — BREAKING
+- **`execute_sas_code` is now stateful across calls.** It runs in the reusable per-user compute session, so SAS WORK tables, macro variables, and assigned librefs persist between successive calls instead of being discarded with a per-call session. Call `reset_compute_session` to start from a clean session. (Previously every call created and tore down its own session.)
+
+### Changed
+- `get_context_id` and `create_session` now call `raise_for_status()`, so an auth/permission failure surfaces as a real `HTTPStatusError` instead of a misleading "compute context not found" or a `KeyError`.
+- `get_context_id` builds its query with httpx `params=` instead of string interpolation, so compute context names containing reserved characters (`&`, `+`, `#`) are encoded correctly.
+- The compute session lifecycle (resolve context → create → reuse/reset/teardown) is centralised in `_ComputeSessionCache`; `run_one_snippet` and the compute tools now share it, and `delete_session` was extracted as a reusable helper.
+
 ## [1.1.0] - 2026-05-31
 
 ### Changed — BREAKING

README.md

@@ -4,7 +4,7 @@ A Model Context Protocol (MCP) server for executing SAS code, training AutoML pr
 
 ## Features
 
-- 20+ Tools spanning the Analytics Life Cycle across SAS Viya
+- 30+ Tools spanning the Analytics Life Cycle across SAS Viya
 - Prompt Templates for improving your SAS Code
 - OAuth2 authentication with PKCE flow
 - HTTP-based MCP server compatible with MCP clients
@@ -135,7 +135,7 @@ The server validates the token against Viya's JWKS and uses it upstream as-is, b
 ### Available Tools
 
 #### Code Execution
-- **execute_sas_code**: Execute SAS code snippets and retrieve execution results (log and listing output)
+- **execute_sas_code**: Execute SAS code snippets and retrieve execution results (log and listing output). Runs in a reusable, per-user compute session that is kept warm across calls, so SAS state (WORK tables, macro variables, assigned librefs) persists between successive calls — use **reset_compute_session** to start fresh.
 
 #### Data Discovery (CAS Management)
 - **list_cas_servers**: List available CAS servers
@@ -173,6 +173,13 @@ The server validates the token against Viya's JWKS and uses it upstream as-is, b
 - **list_models_and_decisions**: List published MAS modules
 - **score_data**: Score data against a published model
 
+#### Compute Contexts & Code Execution
+- **list_compute_contexts**: List available compute contexts
+- **list_compute_libraries**: List the SAS libraries (librefs) assigned in a compute context
+- **list_compute_tables**: List the tables in a SAS library within a compute context
+- **list_compute_columns**: List the columns of a table in a SAS library
+- **reset_compute_session**: Delete the cached compute session for a context, discarding its SAS state and forcing a fresh session on the next call
+
 ### Prompt Templates
 
 - **debug_sas_log**: Analyze SAS log for errors with root-cause explanations
@@ -293,7 +300,7 @@ Integration tests call every tool against a live Viya environment. They require
 ./run_tests.sh --integration-only
 ```
 
-Every one of the 27 tools and 8 prompt templates has an integration test, enforced by the
+Every one of the 32 tools and 8 prompt templates has an integration test, enforced by the
 `test_every_tool_has_integration_coverage` / `test_every_prompt_has_integration_coverage`
 guards — adding a new tool or prompt without integration coverage fails the suite. The
 resource-dependent tests discover real targets on the instance: `score_data` scores the most
@@ -326,7 +333,7 @@ gh gist create reports/integration.xml                          # full XML as a
 
 | File | Description |
 |---|---|
-| `tests/test_tool_payloads.py` | Payload assertions for all 27 tools (URL paths, JSON body, query params, headers) plus error-path coverage |
+| `tests/test_tool_payloads.py` | Payload assertions for all 32 tools (URL paths, JSON body, query params, headers) plus error-path coverage |
 | `tests/test_integration.py` | End-to-end workflow tests against a real Viya instance |
 | `tests/test_tools.py` | Unit tests for the generic Viya REST helpers in `viya_client` (`get_json`, `post_json`, `make_client`, …) |
 | `tests/test_viya_utils.py` | Unit tests for Viya compute session and job orchestration |