fix(api-tox): Codex P1+P2 followups on auto-rollback (PR #34) by dreamrec · Pull Request #36 · dreamrec/TDPilot_deepseekv4

dreamrec · 2026-05-11T14:35:18Z

Summary

Codex's automated review on PR #34 caught two real bugs in the v2.2.0 Phase 1.1 auto-rollback code I shipped earlier today. Both are real silent-correctness issues — neither crashes, both mislead the agent + user — and both have regression tests targeting the exact failure shapes Codex described.

This is the established v2.1.3→v2.1.4→v2.1.5 followup pattern carried into Phase 1.1.

The two bugs

P1 — `rollback_fired = True` claimed even when undo failed

AutoRollbackGuard.__exit__ set rollback_fired = True whenever auto_rollback_end was attempted, regardless of the handler's actual return value. Failure modes:

Dispatcher return	Pre-fix behaviour	Post-fix behaviour
Raises an exception	`rollback_fired = True` + "reverted" hint (lying)	`rollback_fired = False` + degraded hint with `(undo raised: ...)`
`{"error": "ui.undo.endBlock failed: ..."}`	same as above (lying)	`rollback_fired = False` + degraded hint with `(endBlock raised: ...)`
`{"ok": False, "undo_error": "..."}`	same as above (lying)	`rollback_fired = False` + degraded hint with the surfaced error
`{"ok": True, "rolled_back": True}`	`rollback_fired = True` (correct)	unchanged — correct

Worst case pre-fix: agent's follow-up decisions cascade on a corrupted graph while both the chat UI and the LLM's next tool_result show "reverted." Silent-correctness, not a crash — exactly the kind of bug that erodes trust without a clear repro.

P2 — hint dropped when undo block never opened

Agent._loop's inline hint-append condition gated on getattr(rollback_guard, "rollback_fired", False). In the degraded path (regression detected but undo block never opened — e.g. running outside TD, or auto_rollback_begin returned an error), the guard sets rollback_fired = False while still populating hint_text specifically to flag the failure. The condition dropped that hint entirely — leaving the LLM continuing from a broken graph in exactly the failure mode where it most needed feedback.

Fix: extracted the inline block into Agent._apply_rollback_hint (testable), condition now keys on hint_text presence instead of rollback_fired. Both success and degraded paths now surface the hint to LLM + chat UI uniformly.

Refactor

The inline hint-append logic became a method on Agent so the P2 path is unit-testable without urlopen mocking. Cleaner reuse surface for future Phase 1 features that also want to augment the per-batch results_block (e.g. Phase 1.3 mid-turn integrity check could fold its findings into the same callsite).

Files

Modified (3):

td_component/tdpilot_api_rollback.py — __exit__ inspects the dispatcher's return value before claiming success; new _format_end_failure helper produces the (undo raised: …) / (endBlock raised: …) detail clauses; format_hint gained an end_failure="" keyword for richer degraded-path hints.
td_component/tdpilot_api_agent.py — extracted _apply_rollback_hint; _loop calls it after the per-batch tool_use loop instead of inlining the condition.
tests/test_tdpilot_api_rollback.py — 12 new tests across two new classes (TestCodexP1RollbackFiredAccuracy × 5, TestCodexP2HintAppendInDegradedPath × 7).

Binary (2): td_component/tdpilot_API.tox (221,182 → 222,406 bytes), .tox-api-source-hash.json — rebuilt in TD via the canonical Textport recipe.

No source files added/removed → no _SOURCE_FILES / _API_TOX_SOURCE_FILES changes needed (PR #35's paired-list consolidation means there's only one list now anyway).

Test plan

uv run pytest tests/ --ignore=tests/agent_evals -q — 1772 passed (1760 prior + 12 new).
uv run --extra dev ruff format --check src tests scripts td_component — clean.
uv run --extra dev ruff check src tests scripts td_component — clean.
uv run python scripts/check_versions.py — in sync at v2.1.5.
uv run python scripts/check_tox_freshness.py — dpsk4 .tox fresh (not touched).
uv run python scripts/check_tox_api_freshness.py — API .tox fresh post-rebuild (hash 10ba287545a6f421...).
bash scripts/check_no_personal_paths.sh — clean.
CI all-green on push.

No version bump — Phase 1.1 stays unreleased; this is the same in-progress arc.

Why mock-only and not live-TD verification

The user's TD has TD_MCP_REQUIRE_AUTH=1 so my MCP client hits 401, blocking live verification through the dpsk4 MCP server. The 12 new mock-dispatcher tests model the exact failure shapes Codex flagged — higher coverage than a single hand-driven live test would give. If anything still slips, the Codex review pattern will catch it post-PR.

🤖 Generated with Claude Code

Two real bugs Codex caught on the v2.2.0 Phase 1.1 ship. P1 — `rollback_fired = True` claimed even when undo failed ========================================================= In `AutoRollbackGuard.__exit__`, pre-fix code set `rollback_fired = True` whenever `auto_rollback_end` was attempted, regardless of the handler's actual return value. Failure modes: * dispatcher raises (caught by `except Exception: pass`) * handler returns `{"error": "ui.undo.endBlock failed: ..."}` * handler returns `{"ok": False, "endblock_ok": True, "undo_error": "..."}` (the dpsk4-baked `handle_auto_rollback_end` explicitly returns this when `ui.undo.undo()` raises) * handler returns `{"ok": True}` (partial payload — defensive) …all of these reported "reverted" to both the user and the LLM while the network stayed broken. Silent-correctness bug, not a crash. Worst case: agent's follow-up decisions cascade on a corrupted graph while the chat UI shows a confident "reverted" message. Fix: capture the dispatcher's return value, only set rollback_fired = True when it's `{"ok": True, "rolled_back": True}`. Every other shape (raise, ok=False, partial) routes to the degraded hint with a short `(undo raised: ...)` / `(endBlock raised: ...)` detail clause appended so the LLM can decide whether to retry or escalate. P2 — hint dropped when undo block never opened ============================================== In `Agent._loop`, pre-fix the hint-append condition was: if (rollback_guard is not None and getattr(rollback_guard, "rollback_fired", False) and getattr(rollback_guard, "hint_text", "") and ...): ... The middle clause keyed on `rollback_fired`. But in the degraded path (regression detected but undo block didn't open), the guard sets `rollback_fired = False` while still populating `hint_text` specifically to flag the failure. The condition dropped that hint entirely — leaving the LLM continuing from a broken graph with zero feedback in exactly the failure mode where it most needed it. Fix: extracted the inline block into `Agent._apply_rollback_hint` (testable as a method), condition keys on `hint_text` presence instead of `rollback_fired`. Both success and degraded paths now surface the hint to LLM + chat UI uniformly. Tests ===== 12 new regression tests in `tests/test_tdpilot_api_rollback.py`: TestCodexP1RollbackFiredAccuracy (5 tests) - end-handler returns `{"ok": False, "undo_error": ...}` → rollback_fired stays False, hint contains "(undo raised: ...)" - end-handler returns `{"error": "endBlock failed: ..."}` → rollback_fired stays False, hint contains "(endBlock raised: ...)" - dispatcher raises during auto_rollback_end → rollback_fired stays False, degraded hint - end-handler returns `{"ok": True, "rolled_back": True}` (happy path) → rollback_fired = True, "reverted" hint (no regression on happy path) - end-handler returns `{"ok": True}` (partial) → rollback_fired stays False (defensive) TestCodexP2HintAppendInDegradedPath (7 tests) - hint appends with rollback_fired=False (the actual P2 fix-trigger) - hint appends with rollback_fired=True (happy path) - empty hint_text is a no-op - None guard is a no-op - empty results_block is a no-op - list-shaped tool_result.content gets a text-block appended - on_text raising doesn't break the LLM-side append Refactor ======== Extracted `Agent._loop`'s hint-append block into `Agent._apply_rollback_hint` so the P2 path is directly testable without urlopen mocking. Also clean reuse point for future Phase 1 features that need the same results_block-augmentation pattern (e.g. Phase 1.3 mid-turn integrity check might want to fold its findings into the same callsite). Local sweep: 1772 pytest passed (1760 prior + 12 new). Ruff format/check clean. Versions in sync. dpsk4 .tox freshness clean (not touched). API .tox freshness FAIL until rebuilt — that's the final pre-push step. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Bakes the rollback-success-gating fix (P1) and the extracted Agent._apply_rollback_hint method (P2) into the .tox so users get the corrected auto-rollback behaviour at COMP load time. 213,814 → 222,406 bytes (~+8.5KB delta from PR #34's tox — mostly the new private method body + the broadened format_hint). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(api-tox): v2.2.0 Phase 1.2 — cycle detection in tool chains Second feature of the v2.2.0 reliability phase (Phase 1.1 was auto-rollback; see PR #34 + Codex P1/P2 follow-up in PR #36). Pairs with 1.1 to cover the two high-impact reliability gaps: - 1.1 catches "agent broke things" → undo the batch - 1.2 catches "agent is stuck looping" → break the turn How it works ============ A ``CycleLedger`` is constructed once per turn in ``Agent._loop`` and tracks ``(tool_name, args_hash) -> count``. Each call to ``ledger.record(name, args)`` increments and returns the new count. The agent loop checks against the threshold (default 3) BEFORE dispatching: - count == 1: first time, dispatch. - count == 2: second time, dispatch. - count >= 3: ``CycleDetected`` raised; ``run_turn``'s catch fires ``on_error`` → ``EV_ERROR`` + ``EV_STATE: idle`` in the event stream → red banner in the chat UI with tool name + args preview. The threshold of 3 is conservative on purpose — 2 dispatches give the agent a chance to recover from a one-off failure before declaring the turn stuck. Args identity uses sorted-keys JSON so ``{"a":1,"b":2}`` and ``{"b":2,"a":1}`` collapse to the same key; nested dicts hash recursively; lists are order-sensitive (connect source/dest ordering matters). Disable via env var ``TDPILOT_DISABLE_CYCLE_DETECTION=1``. Implementation ============== - NEW td_component/tdpilot_api_cycle_detector.py — pure-Python: args_hash, CycleLedger, CycleDetected, env-var gate, factory builder. No TouchDesigner imports. - tdpilot_api_agent.py: - New cycle_ledger_factory ctor kwarg. - _loop builds one ledger per turn after model resolution. - Inner per-batch for-loop checks ledger.record() BEFORE on_tool_call/dispatch; raises CycleDetected at the threshold. - CycleDetected is **late-imported** from cycle_detector inside _loop to avoid a circular import (cycle_detector imports AgentError from agent at top-level). Cost: one dict lookup per turn after the import is cached. - tdpilot_api_runtime.py: - New _build_cycle_ledger_factory method honours TDPILOT_DISABLE_CYCLE_DETECTION=1. - AgentRuntime._build_agent passes the factory to Agent(). - build_tdpilot_api_tox.py: - Adds tdpilot_api_cycle_detector to _SOURCE_FILES so it's baked into the API .tox. (Post-#35 the freshness gate auto-imports this same list, so no parallel-list maintenance.) Tests (49 new) ============== - TestArgsHash (8) — order independence, normalization, nested ordering, list-order sensitivity, defensive paths. - TestCycleLedger (10) — threshold validation (>=2), increment, per-key isolation, peek/reset, len semantics. - TestCycleDetectedException (3) — metadata, message formatting, AgentError membership. - TestEnvVarGate (3) — truthy/falsy classification. - TestBuildCycleLedgerFactory (3) — env-disable, fresh instances, custom threshold. - TestUsagePattern (4) — the canonical check-then-dispatch flow. - TestFormatArgsSummary (3) — render rules. - TestAgentLoopCycleIntegration (3) — end-to-end with mocked urlopen, proving the late-import + raise + on_error path actually works in run_turn. Covers: enabled+stuck (raises on 3rd, dispatches 2), disabled-factory (no check, hits turn_budget), distinct-args (never triggers, completes cleanly). Local sweep =========== - pytest: 1821 passed (1772 prior + 49 new). - ruff format + check: clean. - check_versions: in sync at v2.1.5 (no bump on this PR). - check_tox_freshness (dpsk4): fresh — that .tox not touched. - check_tox_api_freshness (chat-pipe): EXPECTED FAIL until the user rebuilds the .tox via the canonical Textport recipe. - check_no_personal_paths: clean. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore: rebuild tdpilot_API.tox for Phase 1.2 cycle detection --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

First milestone of the v2.2.0→v3.0 roadmap (see docs/ROADMAP.md). Phase 1 ships in full; the chat-pipe agent is now safe to leave unsupervised on complex builds, two failure modes have automatic recovery, and drag-and-go finally works for new users out of the box. Bundled in this release ======================= - 1.1 Auto-rollback on error regression (PR #34 + #36) - 1.2 Cycle detection in tool chains (PR #37) - 1.2.1 Drag-and-go UX polish — Authmode COMP param, auto-save+auto-reload on Apikey change, 401 reconnect banner (PR #38) - 1.2.2 Build scripts auto-mirror .tox into main repo on rebuild, eliminating stale-symlink footgun (PR #39) - PR #35 paired source-file-list refactor (build-script + freshness- check now share a single source of truth) 136 new tests since v2.1.5. Total suite at release: 1848 passing. Headline behaviour change for end users ======================================= Default chat-pipe webserver auth posture changes from token-required to origin-allowlist-only (Authmode=open default). The origin allowlist still rejects cross-origin browser CSRF, so this is safe on TouchDesigner's typical single-user dev/perform usage profile. Users sharing .toe files across machines should set Authmode=token on the COMP for that deployment. The MCP-server tdpilot-dpsk4.tox (port 9985) auth model is UNCHANGED — TD_MCP_SHARED_SECRET still required. Bumps + rebuilt artifacts ========================= All 10 versioned files (7 manifests + 3 doc titles) bumped from 2.1.5 to 2.2.0 (scripts/check_versions.py enforces sync). API_VERSION in td_component/callbacks/_header.py also bumped; this invalidated both .tox source-hashes, both rebuilt inside TouchDesigner via the canonical recipe. Auto-mirror (Phase 1.2.2, just landed) propagated the rebuilt .tox files to the main repo's td_component/ automatically. Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(api-tox): Codex P1+P2 followups on auto-rollback (PR #34) Two real bugs Codex caught on the v2.2.0 Phase 1.1 ship. P1 — `rollback_fired = True` claimed even when undo failed ========================================================= In `AutoRollbackGuard.__exit__`, pre-fix code set `rollback_fired = True` whenever `auto_rollback_end` was attempted, regardless of the handler's actual return value. Failure modes: * dispatcher raises (caught by `except Exception: pass`) * handler returns `{"error": "ui.undo.endBlock failed: ..."}` * handler returns `{"ok": False, "endblock_ok": True, "undo_error": "..."}` (the dpsk4-baked `handle_auto_rollback_end` explicitly returns this when `ui.undo.undo()` raises) * handler returns `{"ok": True}` (partial payload — defensive) …all of these reported "reverted" to both the user and the LLM while the network stayed broken. Silent-correctness bug, not a crash. Worst case: agent's follow-up decisions cascade on a corrupted graph while the chat UI shows a confident "reverted" message. Fix: capture the dispatcher's return value, only set rollback_fired = True when it's `{"ok": True, "rolled_back": True}`. Every other shape (raise, ok=False, partial) routes to the degraded hint with a short `(undo raised: ...)` / `(endBlock raised: ...)` detail clause appended so the LLM can decide whether to retry or escalate. P2 — hint dropped when undo block never opened ============================================== In `Agent._loop`, pre-fix the hint-append condition was: if (rollback_guard is not None and getattr(rollback_guard, "rollback_fired", False) and getattr(rollback_guard, "hint_text", "") and ...): ... The middle clause keyed on `rollback_fired`. But in the degraded path (regression detected but undo block didn't open), the guard sets `rollback_fired = False` while still populating `hint_text` specifically to flag the failure. The condition dropped that hint entirely — leaving the LLM continuing from a broken graph with zero feedback in exactly the failure mode where it most needed it. Fix: extracted the inline block into `Agent._apply_rollback_hint` (testable as a method), condition keys on `hint_text` presence instead of `rollback_fired`. Both success and degraded paths now surface the hint to LLM + chat UI uniformly. Tests ===== 12 new regression tests in `tests/test_tdpilot_api_rollback.py`: TestCodexP1RollbackFiredAccuracy (5 tests) - end-handler returns `{"ok": False, "undo_error": ...}` → rollback_fired stays False, hint contains "(undo raised: ...)" - end-handler returns `{"error": "endBlock failed: ..."}` → rollback_fired stays False, hint contains "(endBlock raised: ...)" - dispatcher raises during auto_rollback_end → rollback_fired stays False, degraded hint - end-handler returns `{"ok": True, "rolled_back": True}` (happy path) → rollback_fired = True, "reverted" hint (no regression on happy path) - end-handler returns `{"ok": True}` (partial) → rollback_fired stays False (defensive) TestCodexP2HintAppendInDegradedPath (7 tests) - hint appends with rollback_fired=False (the actual P2 fix-trigger) - hint appends with rollback_fired=True (happy path) - empty hint_text is a no-op - None guard is a no-op - empty results_block is a no-op - list-shaped tool_result.content gets a text-block appended - on_text raising doesn't break the LLM-side append Refactor ======== Extracted `Agent._loop`'s hint-append block into `Agent._apply_rollback_hint` so the P2 path is directly testable without urlopen mocking. Also clean reuse point for future Phase 1 features that need the same results_block-augmentation pattern (e.g. Phase 1.3 mid-turn integrity check might want to fold its findings into the same callsite). Local sweep: 1772 pytest passed (1760 prior + 12 new). Ruff format/check clean. Versions in sync. dpsk4 .tox freshness clean (not touched). API .tox freshness FAIL until rebuilt — that's the final pre-push step. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore: rebuild tdpilot_API.tox for Codex P1+P2 followups Bakes the rollback-success-gating fix (P1) and the extracted Agent._apply_rollback_hint method (P2) into the .tox so users get the corrected auto-rollback behaviour at COMP load time. 213,814 → 222,406 bytes (~+8.5KB delta from PR #34's tox — mostly the new private method body + the broadened format_hint). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(api-tox): v2.2.0 Phase 1.2 — cycle detection in tool chains Second feature of the v2.2.0 reliability phase (Phase 1.1 was auto-rollback; see PR #34 + Codex P1/P2 follow-up in PR #36). Pairs with 1.1 to cover the two high-impact reliability gaps: - 1.1 catches "agent broke things" → undo the batch - 1.2 catches "agent is stuck looping" → break the turn How it works ============ A ``CycleLedger`` is constructed once per turn in ``Agent._loop`` and tracks ``(tool_name, args_hash) -> count``. Each call to ``ledger.record(name, args)`` increments and returns the new count. The agent loop checks against the threshold (default 3) BEFORE dispatching: - count == 1: first time, dispatch. - count == 2: second time, dispatch. - count >= 3: ``CycleDetected`` raised; ``run_turn``'s catch fires ``on_error`` → ``EV_ERROR`` + ``EV_STATE: idle`` in the event stream → red banner in the chat UI with tool name + args preview. The threshold of 3 is conservative on purpose — 2 dispatches give the agent a chance to recover from a one-off failure before declaring the turn stuck. Args identity uses sorted-keys JSON so ``{"a":1,"b":2}`` and ``{"b":2,"a":1}`` collapse to the same key; nested dicts hash recursively; lists are order-sensitive (connect source/dest ordering matters). Disable via env var ``TDPILOT_DISABLE_CYCLE_DETECTION=1``. Implementation ============== - NEW td_component/tdpilot_api_cycle_detector.py — pure-Python: args_hash, CycleLedger, CycleDetected, env-var gate, factory builder. No TouchDesigner imports. - tdpilot_api_agent.py: - New cycle_ledger_factory ctor kwarg. - _loop builds one ledger per turn after model resolution. - Inner per-batch for-loop checks ledger.record() BEFORE on_tool_call/dispatch; raises CycleDetected at the threshold. - CycleDetected is **late-imported** from cycle_detector inside _loop to avoid a circular import (cycle_detector imports AgentError from agent at top-level). Cost: one dict lookup per turn after the import is cached. - tdpilot_api_runtime.py: - New _build_cycle_ledger_factory method honours TDPILOT_DISABLE_CYCLE_DETECTION=1. - AgentRuntime._build_agent passes the factory to Agent(). - build_tdpilot_api_tox.py: - Adds tdpilot_api_cycle_detector to _SOURCE_FILES so it's baked into the API .tox. (Post-#35 the freshness gate auto-imports this same list, so no parallel-list maintenance.) Tests (49 new) ============== - TestArgsHash (8) — order independence, normalization, nested ordering, list-order sensitivity, defensive paths. - TestCycleLedger (10) — threshold validation (>=2), increment, per-key isolation, peek/reset, len semantics. - TestCycleDetectedException (3) — metadata, message formatting, AgentError membership. - TestEnvVarGate (3) — truthy/falsy classification. - TestBuildCycleLedgerFactory (3) — env-disable, fresh instances, custom threshold. - TestUsagePattern (4) — the canonical check-then-dispatch flow. - TestFormatArgsSummary (3) — render rules. - TestAgentLoopCycleIntegration (3) — end-to-end with mocked urlopen, proving the late-import + raise + on_error path actually works in run_turn. Covers: enabled+stuck (raises on 3rd, dispatches 2), disabled-factory (no check, hits turn_budget), distinct-args (never triggers, completes cleanly). Local sweep =========== - pytest: 1821 passed (1772 prior + 49 new). - ruff format + check: clean. - check_versions: in sync at v2.1.5 (no bump on this PR). - check_tox_freshness (dpsk4): fresh — that .tox not touched. - check_tox_api_freshness (chat-pipe): EXPECTED FAIL until the user rebuilds the .tox via the canonical Textport recipe. - check_no_personal_paths: clean. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore: rebuild tdpilot_API.tox for Phase 1.2 cycle detection --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

First milestone of the v2.2.0→v3.0 roadmap (see docs/ROADMAP.md). Phase 1 ships in full; the chat-pipe agent is now safe to leave unsupervised on complex builds, two failure modes have automatic recovery, and drag-and-go finally works for new users out of the box. Bundled in this release ======================= - 1.1 Auto-rollback on error regression (PR #34 + #36) - 1.2 Cycle detection in tool chains (PR #37) - 1.2.1 Drag-and-go UX polish — Authmode COMP param, auto-save+auto-reload on Apikey change, 401 reconnect banner (PR #38) - 1.2.2 Build scripts auto-mirror .tox into main repo on rebuild, eliminating stale-symlink footgun (PR #39) - PR #35 paired source-file-list refactor (build-script + freshness- check now share a single source of truth) 136 new tests since v2.1.5. Total suite at release: 1848 passing. Headline behaviour change for end users ======================================= Default chat-pipe webserver auth posture changes from token-required to origin-allowlist-only (Authmode=open default). The origin allowlist still rejects cross-origin browser CSRF, so this is safe on TouchDesigner's typical single-user dev/perform usage profile. Users sharing .toe files across machines should set Authmode=token on the COMP for that deployment. The MCP-server tdpilot-dpsk4.tox (port 9985) auth model is UNCHANGED — TD_MCP_SHARED_SECRET still required. Bumps + rebuilt artifacts ========================= All 10 versioned files (7 manifests + 3 doc titles) bumped from 2.1.5 to 2.2.0 (scripts/check_versions.py enforces sync). API_VERSION in td_component/callbacks/_header.py also bumped; this invalidated both .tox source-hashes, both rebuilt inside TouchDesigner via the canonical recipe. Auto-mirror (Phase 1.2.2, just landed) propagated the rebuilt .tox files to the main repo's td_component/ automatically. Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

dreamrec and others added 2 commits May 11, 2026 17:33

dreamrec merged commit 5603d71 into main May 11, 2026
6 checks passed

dreamrec mentioned this pull request May 11, 2026

feat(api-tox): v2.2.0 Phase 1.2 — cycle detection in tool chains #37

Merged

8 tasks

dreamrec mentioned this pull request May 11, 2026

release: 2.2.0 — Phase 1 reliability foundation + drag-and-go UX #40

Merged

9 tasks

dreamrec deleted the claude/v2.2.0-feature-1.1.1-codex-followup branch May 11, 2026 22:48

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

fix(api-tox): Codex P1+P2 followups on auto-rollback (PR #34) - #36

fix(api-tox): Codex P1+P2 followups on auto-rollback (PR #34)#36
dreamrec merged 2 commits into
mainfrom
claude/v2.2.0-feature-1.1.1-codex-followup

dreamrec commented May 11, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Conversation

dreamrec commented May 11, 2026

Summary

The two bugs

P1 — rollback_fired = True claimed even when undo failed

P2 — hint dropped when undo block never opened

Refactor

Files

Test plan

Why mock-only and not live-TD verification

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

P1 — `rollback_fired = True` claimed even when undo failed