Skip to content

fix(coding-agent): restart dead kernels on ensure() and read mcp>=2 tool schemas - #2034

Closed
snimu wants to merge 4 commits into
mainfrom
fix/python-runtime-defects
Closed

fix(coding-agent): restart dead kernels on ensure() and read mcp>=2 tool schemas#2034
snimu wants to merge 4 commits into
mainfrom
fix/python-runtime-defects

Conversation

@snimu

@snimu snimu commented Sep 4, 2026

Copy link
Copy Markdown
Contributor

Summary

Two Python-runtime defects:

  • A dead kernel no longer wedges the session. IpythonKernelProvisioner.ensure() memoizes the started kernel and cleared that memo only on startup failure, dispose, or kill. A kernel that died after a successful startup (OOM kill, os._exit, crash) was handed to every later Python call forever — each one failing against a dead process until the session restarted. ensure() now drops the memo when the started kernel is no longer running, so the existing startup path (snapshot restore included) reruns on the next call. Fixes the defect reported in discussion [Bug] v0.8.0 stopped IPython kernel remains permanently cached after unexpected exit #1659.
  • Skill-MCP tools advertise their real input schemas again. mcp>=2 renamed the Tool schema field to input_schema (with inputSchema as the wire alias); pydantic attribute access is by field name, so mcp_base.py's getattr(t, "inputSchema", ...) was always None and every skill-MCP tool advertised an empty {} schema — models called tools blind. The lookup now mirrors the dual lookup its sibling mcp.py already uses. Fixes the defect reported in discussion Fix: McpIntegration.list_tools() always returns empty inputSchema (#1073) #1757.

Validation

  • two pins, each verified fail-unfixed: a memoized not-running kernel forces a restart (pre-fix: the dead memo is returned and no restart happens), and a Tool exposing only snake_case input_schema surfaces its schema through list_tools() (pre-fix: {})
  • suites: ipython-provisioner (20) and test_mcp_base (18 via uv run python -m unittest) — green
  • root npm run check passes via the pre-commit hook

LOC

Total src: +20/−5 (net +15); tests: +50/−0 (net +50).
Src +14/−5 (both point fixes; the kernel fix is a 4-line liveness check ahead of the existing memo, the schema fix mirrors the sibling module's lookup). Tests +42, changelog 1 fragment.

Linear: RES-1266 https://linear.app/primeintellect/issue/RES-1266


Note

Medium Risk
Touches kernel lifecycle memoization and MCP tool metadata; behavior changes on post-crash recovery and tool listing, but scope is narrow with targeted tests.

Overview
Fixes two runtime bugs where sessions could get stuck on a dead Python kernel and skill-MCP tools could advertise empty parameter schemas.

Dead kernel memo: IpythonKernelProvisioner.ensure() now clears its cached manager when startedManager.isDefunct is true (new KernelClient / ReplKernelManager flag for terminal shutdown). The next Python call goes through the normal startup path—including snapshot restore—instead of reusing a process that died after a successful boot. Managers that are merely not running but still repairing stay memoized so a second kernel does not race on the snapshot dir.

MCP tool schemas: McpIntegration._ensure_tools in mcp_base.py resolves tool parameters via input_schema first, then inputSchema, matching mcp.py and restoring real inputSchema metadata under mcp>=2 instead of always {}.

Reviewed by Cursor Bugbot for commit 749e216. Bugbot is set up for automated code reviews on this repo. Configure here.

Note

Fix dead kernel restart on ensure() and read input_schema for mcp>=2 tools

  • Adds ReplKernelManager.isDefunct and the required KernelClient.isDefunct property so callers can detect a terminal-shutdown kernel. IpythonKernelProvisioner.ensure() now drops the memoized manager and its startup promise when defunct, forcing a fresh kernel on the next call; non-defunct managers stay memoized.
  • Reworks McpIntegration._ensure_tools to read input_schema first and fall back to inputSchema for older MCP objects, keeping only dictionary schemas and substituting empty schemas otherwise.
  • Risk: KernelClient implementers must now provide the read-only isDefunct property; any out-of-tree implementation missing it will fail the interface contract.

Macroscope summarized 749e216.

…ool schemas

IpythonKernelProvisioner.ensure() cleared its memo only on startup failure, dispose, or kill; a kernel that died after a successful startup (OOM kill, os._exit) was handed out forever, wedging every later Python call. The memo now drops when the started kernel is no longer running, so the existing startKernel path (snapshot restore included) reruns. Separately, mcp>=2 renamed the Tool schema field to input_schema; mcp_base.py read only the inputSchema alias, so every skill-MCP tool advertised an empty schema. It now mirrors mcp.py's dual lookup.

@cursor cursor Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Cursor Bugbot has reviewed your changes and found 1 potential issue.

Fix All in Cursor

❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.

Reviewed by Cursor Bugbot for commit b94d987. Configure here.

Comment thread packages/coding-agent/src/core/tools/ipython.ts
Protocol repair cycles the same manager through idle/starting while it respawns its child; the broad !isRunning check would abandon it and start a second kernel over the same snapshot directory. The memo now drops only for a defunct (shutdown-state) manager - the state an unexpected child exit parks in permanently.
sethkarten added a commit that referenced this pull request Sep 7, 2026
@sethkarten

Copy link
Copy Markdown
Contributor

Included in #2028: #2028

@sethkarten sethkarten closed this Sep 7, 2026
sethkarten added a commit that referenced this pull request Sep 7, 2026
)

* refactor(coding-agent): move the semantic-edge ledger onto the event-log substrate

The recorder's private append/replay/repair IO is deleted; EventLog owns it, the same move #1987 made for the RLM spawn ledger. One durability rule is unified in the substrate rather than dropped: an unterminated final line is an uncommitted append, skipped on read and truncated before the next append — never newline-completed and never surfaced to a consumer whose next append destroys it.

* fix(coding-agent): make the explicit ledger reader's ENOENT contract atomic

readSemanticEdgeLedger probed with statSync before reading through EventLog, which swallows ENOENT; a ledger deleted between the two returned [] instead of throwing. The missing-file decision now lives at the single open (replaySync missingFileThrows), so no check-then-read window exists.

* docs(coding-agent): state the event-log tail rule once

The unterminated-tail contract was restated four times (module doc, replaySync doc, two test comments). It now lives once in the module doc; the method doc keeps only its own parse/missing-file semantics and the test comments reference the contract.

* fix(coding-agent): write event-log appends fully and gate appends on tail repair

writeSync may write short (ENOSPC after a prefix); appendSync now loops until the payload is fully on disk so write-before-action callers never act on a torn record reported as success. A tail-repair failure (e.g. append-only ACL permitting O_APPEND but not r+) now propagates instead of being swallowed: writing through an unrepaired torn tail would weld it to the new record as permanent interior corruption. ENOENT and the concurrent-writer instability path keep their existing semantics.

* fix(coding-agent): reclaim short event-log writes instead of completing them

The rlm spawn ledger is multi-writer by documented design (supervisor plus each worker over one file), so completing a short O_APPEND write with a second write could interleave with a rival append and weld two records. A short write now truncates its own torn prefix back off (only while this writer still owns the tail) and fails the append; a torn tail is read-tolerated, a weld is permanent corruption. The append fd opens a+ so the ownership check can read the tail.

* fix(coding-agent): leave the torn tail on a short write instead of reclaiming it

The tail-match reclaim could truncate a rival's committed record whose final bytes coincide with our torn prefix - committed-data loss, strictly worse than the torn tail it prevented. A short write now just fails the append: the torn tail is the one tolerated shape, skipped on read and truncated by any writer's next repair (verified for both topologies: a resumed single-writer recorder repairs on its first append; every rlm-ledger writer repairs before each append).

* refactor(coding-agent): compress event-log comments

* fix(ai): omit the default service tier, reprice cache writes from message_delta, repoint the zai default

Incorporates #2032 at f82c7fa.

* fix(tui,coding-agent): survive lone surrogates in table cells and terminate the WebP EXIF scan

Incorporates #2033 at a3d1139.

* fix(coding-agent): restart dead kernels on ensure() and read mcp>=2 tool schemas

Incorporates #2034 at 749e216.

* fix: one crash-safe owner for durable state writes

Incorporates #2035 at f0f02d2.

* fix(coding-agent): one zombie-aware process-liveness probe

Incorporates #2041 at 92a0eac.

* fix(coding-agent): snapshot transfer ids from the materialized cursor; mismatches settle the transfer, not the worker channel

Incorporates #2044 at 5af3bbe.

* fix(coding-agent): failed workers recover on touch; roster gaps answer a structured recovering error

Incorporates #2047 at 77b747a.

* fix(coding-agent): seven session and IO correctness defects

Incorporates #2037 at 41b5d72.

* fix(coding-agent): coalesce child-usage attribution and gate agent-status persistence on real changes

Incorporates #2050 at 6b0af5d.

* fix(coding-agent): incremental single-flight session metadata scans

Incorporates #2043 at df032c1.

* fix(coding-agent): memoize the passive RLM topology derivation

Incorporates #2051 at 0ee114c.

* fix(coding-agent): preserve accounting and metadata across deferred updates

Keep durable child-usage aggregates separate from pending sibling usage. Retry optional topology metadata after transient reads. Completes #2050 and #2051 integration.

* fix: preserve session accounting and read-only persistence boundaries

---------

Co-authored-by: Seth <seth@primeintellect.ai>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants