Repository navigation
fix(deepseek): warn when dsh is outside its tested release - #38651
Conversation
dsh-acp reports agentInfo.version 0.0.1 on every release, so the tested-range notice could not read deepseek from the handshake. The per-session spawn now reads dsh's own npm manifest (@deepseek-ai/dsh), and the notice reads that version against 0.2.x, the Real Adapter Contract lane pin (0.2.0-rc.2). An unreadable manifest gets no notice. Fixes #38323
UX Review (Opus 5.5) — ⏭️ skippedRevision |
Design Review (Opus 5.5) — ✅ PASSDesign-level review of Design-Verdict: PASS Nothing blocks: the change only adds a warning, it reuses the existing manifest reader and range check, and a revert undoes it cleanly. Notes
[DESIGN-REVIEWED] 92ff6bb Description read[DESCRIPTION-READ] 0170037c0e30ef48d8e71a73b40d1e0ed9f807fecf444b1c9e8a64c5b819ded6 That sha256 names everything this verdict read: the PR description, plus the 1 evidence file(s) the workflow collected from it and handed this review. It covers that evidence because the media strip replaces every attachment URL with the same placeholder, so an edit swapping one attachment for another would leave the description's captured text identical while what this review judged changed. Recompute it with |
First Principles Review (Opus 5.5) — ✅ PASSPremise-level review of First-Principles-Verdict: PASS Nothing blocks: the fix feeds deepseek into the existing tested-range check, using the manifest reader the Node adapters already share. Its one generalized form has a single member. Notes
What this change shipsInventory (5 items) — 4 justifiedIntent: a deepseek user running a dsh release Crew never tested gets the same one-time warning other harnesses already give (FIX, #38323).
[FIRST-PRINCIPLES-REVIEWED] 92ff6bb Description read[DESCRIPTION-READ] bbc5e67f5122402809e7d5b71c7e0b178c18981df87c1e3807a44b01010b2f6b That sha256 names the PR description this verdict read. Recompute it with |
Opus 5.5 Review — ✅ no blocking findingsReviewed Verdict parsed from the review's SHA-scoped output markers for commit False positive or not applicable? A repository writer can comment: |
GPT 6.1 Review — ✅ no blocking findingsGPT 6.1 completed its review of This comment is updated in place on each push. Review detailsNo findings. False positive or not applicable? A repository writer can comment: |
Code change approver recommendation: ApproveWhy: the decider estimates an 8% chance that this change introduces a defect, within the 12% limit for approving on its own, and every check passes. Adds a deepseek row to the tested-version table. dsh's handshake always reports 0.0.1, so the version is read from dsh's npm manifest at spawn (off the event loop, using the shared Node manifest reader) and fed into the existing range check. Verified: the reader follows symlinks and Windows .cmd shims; the 0.2.0-rc.2 pin parses inside 0.2.x; the install command is the deepseek launch row's; the new attribute has a default on both session types resolve_spawn writes to (per-session client and the shared runtime's probe session), so the write cannot fail; other backends and the KAS fallback are unchanged. Doc counts are consistent. New tests cover the range, the spawn-read version being used instead of the handshake, the manifest reader and the spawn recording. CI is green. Tier: 1, every tier gate passed. An automated recommendation, not a review: a maintainer still decides. It approves on its own only when the estimated chance of a defect is at most 12% and the change has at most 400 changed lines. Decider v3c (217fe607) · commit |
KiroCrewCaptain
left a comment
There was a problem hiding this comment.
Approved automatically by the code change approver, not by a person. The decider estimates an 8% chance that this change introduces a defect, within the 12% limit for approving on its own, and the change has at most 400 changed lines.
Adds a deepseek row to the tested-version table. dsh's handshake always reports 0.0.1, so the version is read from dsh's npm manifest at spawn (off the event loop, using the shared Node manifest reader) and fed into the existing range check. Verified: the reader follows symlinks and Windows .cmd shims; the 0.2.0-rc.2 pin parses inside 0.2.x; the install command is the deepseek launch row's; the new attribute has a default on both session types resolve_spawn writes to (per-session client and the shared runtime's probe session), so the write cannot fail; other backends and the KAS fallback are unchanged. Doc counts are consistent. New tests cover the range, the spawn-read version being used instead of the handshake, the manifest reader and the spawn recording. CI is green.
Tier: 1, every tier gate passed.
Criteria: no merge conflict, no owner block, no change request, the default branch, no security-sensitive path, no design document to agree on, the readiness status, the review lanes, the P0 history, the linked issues' tier, the review lessons, no concern label, the file count, a safe change category, not its own change, the decider, the security checklist, the change matches its title, no competing change.
Design documents ride along with the code (docs/architecture/harness-gap-analysis.md, docs/system-specs/modules/harness-parity.md): they were not reviewed as a design, and a person who changes what they decide should ask for that review.
Decider v3c (217fe607). To overrule it, request changes or dismiss this review.
Problem / Motivation
Goal: A deepseek chat running a dsh release outside the one Crew tested gets the same one-time "outside the tested range" notice that goose, codex, claude, pi and kiro-cli chats get.
Crew warns once per chat when a harness runs a release outside its tested range (
_TESTED_VERSION_RANGES, requirement R-LAU-3). deepseek had no entry, because the table reads the handshake'sagentInfo.version, and@deepseek-ai/dsh-acp0.2.0-rc.2 hardcodesversion: "0.0.1"(the live capturecrew-oauth-bridge-args-live.jsonlshows the same).dsh --versionprints nothing.Why it matters
A user who installs a newer or older dsh than the lane pin runs on an adapter Crew never measured and nothing says so. Silent upgrades are what caused #25171 and #36125 on other harnesses.
Not a goal
shortcut:comment atTESTED_VERSION_READ_AT_SPAWN.agent_versionitself: other readers still see what the handshake said.What changed (motivation → approach → change)
Handshake version is meaningless for dsh → read the release off disk, the way claude-agent-acp's and pi's are read → feed that version, not
agentInfo.version, into the existing range check.acp/harness/deepseek.py:_dsh_installed_versionreadsversionfrom the@deepseek-ai/dshnpm manifest beside the resolved binary (launch._node_adapter_manifest_version, the reader the Node adapters share).DeepseekLaunch.resolve_spawnrecords it off-loop on the session asharness_installed_version. A wrapper script or aDSH_BINoverride naming another file reads"".acp/client_turn_control.py:DEEPSEEK_DSH_TESTED_RANGEis 0.2.x (lane pin 0.2.0-rc.2; 0.x, so the minor line), with the launch row's install command.TESTED_VERSION_READ_AT_SPAWNnames the backends whose handshake version is not read.providers/acp.py:tested_version_noticereadsharness_installed_versionfor those backends, so0.0.1never reaches the range check.acp/client_deepseek.py: the attribute's""default.dashboard/chat_turn/turn_spec_hooks.py: docstring names deepseek among the harnesses with a tested-range row. Docs: R-LAU-3 for deepseek goes ❌ → ✅ inharness-gap-analysis.md(counts and ranked list updated), plus one sentence inharness-parity.md.Backwards compatibility
Compatible: one new notice row on a deepseek chat whose dsh manifest names a release outside 0.2.x; an unreadable manifest, and every other backend, behave as before.
Removes nothing: the diff adds a table entry, an attribute and a reader; no key, path or function is removed or renamed.
Tests
test/test_deepseek_tested_version_notice.py(new): outside 0.2.x warns with version, range andnpm i -g @deepseek-ai/dsh@0.2.0-rc.2; 0.2.0-rc.2, 0.2.x and unreadable versions are silent; the range is the lane pin intest/real_adapters/package.json; the provider notice reads the spawn-read version (one row), and a handshake0.0.1alone never warns; the manifest reader finds@deepseek-ai/dsh/lib/bin.js's package and reads""for a wrapper or a missing file;DeepseekLaunch.resolve_spawnrecords the version on the session (existing_DeepseekLaunchRig).test/test_goose_tested_version_notice.py: deepseek joins the backends excluded from "no notice at0.0.1", since it now has a range.Proof: not provable -- other: prove.py reports INCONCLUSIVE because reverting every production hunk removes the constants the new test imports, so collection errors. Reverted by hand on this head instead: main's
providers/acp.pymakes 4 tests fail (the handshake0.0.1warns); dropping the spawn read indeepseek.pymakestest_a_per_session_spawn_records_the_installed_versionfail.Run locally (Linux, Python 3.12): the new file plus the tested-range, deepseek, harness-parity, launch-golden, fixture-pin and line-cap suites, 1126 passed; every
test_*ratchet*.pyplus the tree-scan tests withGITHUB_BASE_REF=main FLAKE_RATCHET_BASE=<merge-base>, 4295 passed, 22 skipped;black,isort,flake8on changed files andmypyon the four changed source modules clean;scripts/docs_lint.pyclean. New tests use no clock and no sleeps.Manual verification
N/A — unit coverage sufficient: no dsh is installed on this host. The manifest layout (
bin: {dsh: 'lib/bin.js'}, name@deepseek-ai/dsh) was checked withnpm view @deepseek-ai/dsh@0.2.0-rc.2 name version bin.Related Issues
Fixes #38323
Sibling sweep
Swept: git grep -n "untested_version_issue|_TESTED_VERSION_RANGES" -- src/
Sibling: src/kiro_crew/providers/acp.py -- changed here
Sibling: src/kiro_crew/acp/harness/kas.py -- not affected -- KAS reads its kiro-cli version itself at spawn
Sibling: src/kiro_crew/agent_sdk/drivers/acp.py -- not affected -- codex-only doctor helper reading codex's own manifest
Pattern harvest
Not generalizable: deepseek is the only harness whose handshake reports a constant version; the others report their release.