Commit Graph

279 Commits

Author SHA1 Message Date
TheArchitectit
b43a6f2d29 feat: auto-compact and retry on context window errors
Adds automatic compaction and retry when context window is exceeded.
2026-05-25 11:24:44 +09:00
TheArchitectit
f1a55a211e fix: /resume latest searches all workspaces
Fixes /resume latest to search all workspaces instead of just the current one.
2026-05-25 11:24:41 +09:00
TheArchitectit
cef45efc16 feat: interactive provider wizard with fast model selection
Adds interactive provider setup wizard.
2026-05-25 11:24:20 +09:00
TheArchitectit
7149bbc3d9 fix: streaming robustness — OpenAI parsing, error detection, reasoning content
Improves SSE parsing with raw JSON error detection, HTML response detection (for misconfigured endpoints), thinking/reasoning content from provider-specific delta fields, #[serde(default)] on streaming types for lenient deserialization, compact session boundary guard, and /team slash command. Adds install.sh convenience script.
2026-05-25 11:22:47 +09:00
joshbowyer
5a9550d388 fix: flatten prior compaction highlights to prevent nesting compounding
Instead of re-nesting prior highlights under '- Previously compacted context:', flatten them directly into the top-level list with '- ' prefix. This prevents each compaction cycle from adding a nesting layer, which inflated the summary by ~depth * overhead per turn.
2026-05-25 11:22:27 +09:00
Heo, Sung
1c62116e25 feat: truncate oversized git diff in system prompt
Adds MAX_GIT_DIFF_CHARS (50_000) limit and truncate_diff() function to prevent oversized git diffs from blowing up the system prompt. Truncation respects UTF-8 character boundaries and appends a clear truncation notice. Includes unit tests.
2026-05-25 11:21:30 +09:00
bellman
04c2abb412 Stabilize final gate before release checkpoint
Resolve the G012 evidence gate by fixing permission-mode regressions, platform-sensitive tests, and the clippy surface that blocked an all-targets verification run.

Constraint: G012 final gate required docs, board, full workspace tests, and clippy -D warnings evidence before checkpointing.

Rejected: documenting the worker-2 gate failure as an accepted gap | the failing tests and lints were locally reproducible and fixable.

Confidence: high

Scope-risk: moderate

Directive: Preserve read-only permission requirements for read/glob/grep tools; write/edit remain workspace-write or danger-full-access when outside the workspace.

Tested: python3 .github/scripts/check_doc_source_of_truth.py; python3 .github/scripts/check_release_readiness.py; python3 scripts/validate_cc2_board.py --board .omx/cc2/board.json; python3 .omx/cc2/validate_issue_parity_intake.py .omx/cc2/issue-parity-intake.json; cargo fmt --manifest-path rust/Cargo.toml --all -- --check; cargo check --manifest-path rust/Cargo.toml --workspace; cargo test --manifest-path rust/Cargo.toml --workspace -- --nocapture; cargo clippy --manifest-path rust/Cargo.toml --workspace --all-targets -- -D warnings

Not-tested: live network provider smoke tests and remote PR/issue mutations.
2026-05-15 13:34:57 +09:00
bellman
c9b34a2947 omx(team): auto-checkpoint worker-1 [1] 2026-05-15 11:07:21 +09:00
bellman
5e0cf62be5 omx(team): auto-checkpoint worker-1 [1] 2026-05-15 11:05:44 +09:00
bellman
51fa5a7048 omx(team): auto-checkpoint worker-3 [unknown] 2026-05-15 11:05:40 +09:00
bellman
33ac5c30d3 omx(team): auto-checkpoint worker-1 [1] 2026-05-15 11:05:36 +09:00
bellman
89d1052f3a omx(team): auto-checkpoint worker-3 [unknown] 2026-05-15 11:03:45 +09:00
bellman
fc35dc878c omx(team): auto-checkpoint worker-1 [1] 2026-05-15 11:03:35 +09:00
bellman
557ab8a9dd surface required MCP server semantics
Expose MCP server requiredness through config parsing, inventory reports, config hashes, and degraded startup failure context so orchestrators can distinguish optional degradation from required startup breakage.

Constraint: G007-plugin-mcp Task 3 requires required vs optional MCP behavior and must not mutate .omx/ultragoal.

Rejected: Treating all MCP failures as equivalent | it preserves the existing opacity that prevents required-server failures from being escalated differently.

Confidence: high

Scope-risk: moderate

Directive: Preserve required=false as the backward-compatible default; keep required surfaced in JSON/text inventory and degraded failure context when extending MCP lifecycle states.

Tested: cargo test -p runtime parses_typed_mcp_and_oauth_config -- --nocapture; cargo test -p runtime manager_discovery_report_keeps_healthy_servers_when_one_server_fails -- --nocapture; cargo test -p runtime manager_records_unsupported_non_stdio_servers_without_panicking -- --nocapture; cargo test -p commands renders_mcp_reports -- --nocapture; cargo check --workspace; cargo fmt --all -- --check

Not-tested: cargo clippy -p runtime -p commands -- -D warnings is blocked by pre-existing runtime/src/policy_engine.rs LaneContext clippy::struct_excessive_bools.

Co-authored-by: OmX <omx@oh-my-codex.dev>
2026-05-15 10:06:39 +09:00
bellman
0bcab573f3 omx(team): auto-checkpoint worker-1 [1] 2026-05-15 10:05:46 +09:00
bellman
4a76632f6c omx(team): auto-checkpoint worker-1 [1] 2026-05-15 10:05:42 +09:00
bellman
9910d5805e omx(team): auto-checkpoint worker-1 [1] 2026-05-15 10:01:44 +09:00
bellman
686cc89a36 omx(team): auto-checkpoint worker-1 [1] 2026-05-15 10:00:40 +09:00
bellman
18805b565a omx(team): auto-checkpoint worker-2 [2] 2026-05-15 09:45:29 +09:00
bellman
65a144c3f7 Keep G006 packet regressions aligned with shipped schema
Constraint: G006 worker auto-checkpoints added useful regression coverage after the pushed leader schema.\nRejected: Reapply later worker policy/lane merges | they produced duplicate definitions and syntax failures during shutdown integration.\nConfidence: high\nScope-risk: narrow\nDirective: Preserve the shipped G006 packet schema shape unless a future migration updates callers and tests together.\nTested: cargo fmt --manifest-path rust/Cargo.toml --all -- --check; cargo check --manifest-path rust/Cargo.toml -p runtime -p tools -p rusty-claude-cli; cargo test --manifest-path rust/Cargo.toml -p runtime task_packet -- --nocapture; cargo test --manifest-path rust/Cargo.toml -p tools run_task_packet -- --nocapture; cargo test --manifest-path rust/Cargo.toml -p runtime task_registry -- --nocapture; cargo test --manifest-path rust/Cargo.toml -p runtime session_heartbeat -- --nocapture; cargo test --manifest-path rust/Cargo.toml -p runtime policy_engine -- --nocapture; cargo test --manifest-path rust/Cargo.toml -p rusty-claude-cli status_json_surfaces -- --nocapture; git diff --check\nNot-tested: full workspace test suite\n\nCo-authored-by: OmX <omx@oh-my-codex.dev>
2026-05-15 09:41:38 +09:00
bellman
6d809cb278 omx(team): auto-checkpoint worker-1 [1] 2026-05-15 09:37:18 +09:00
bellman
f7235ca932 Make G006 task policy state machine executable
Typed task packets, policy decisions, lane board status, and session liveness now have concrete runtime contracts and focused regressions for Stream 4.

Constraint: G006 requires task/lane operation without pane scraping while preserving legacy task packet callers.
Rejected: waiting on stale worker worktrees | all G006 worker worktrees remained at main with no commits, so leader integrated the verified slice directly.
Confidence: high
Scope-risk: moderate
Directive: Keep task packet serde defaults when adding fields so older packets continue to deserialize.
Tested: git diff --check; cargo fmt --manifest-path rust/Cargo.toml --all -- --check; cargo check --manifest-path rust/Cargo.toml -p runtime -p tools -p rusty-claude-cli; cargo test --manifest-path rust/Cargo.toml -p runtime task_packet -- --nocapture; cargo test --manifest-path rust/Cargo.toml -p runtime policy_engine -- --nocapture; cargo test --manifest-path rust/Cargo.toml -p runtime task_registry -- --nocapture; cargo test --manifest-path rust/Cargo.toml -p runtime session_heartbeat -- --nocapture; cargo test --manifest-path rust/Cargo.toml -p tools run_task_packet_creates_packet_backed_task -- --nocapture; cargo test --manifest-path rust/Cargo.toml -p tools lane_completion -- --nocapture; cargo test --manifest-path rust/Cargo.toml -p rusty-claude-cli status_json_surfaces -- --nocapture
Not-tested: full workspace test suite; PR/issue reconciliation deferred to G011/G012

Co-authored-by: OmX <omx@oh-my-codex.dev>
2026-05-15 09:29:26 +09:00
bellman
d2b5f5d498 require provenance for green contracts
Promote merge-ready green contracts from a level-only check to explicit provenance requirements for test commands, base freshness, recovery-attempt context, and known blocking flakes. This preserves simple level contracts while giving policy code a single satisfied-contract signal to require before merge decisions.\n\nConstraint: Task scope was limited to green_contract.rs, policy_engine.rs if needed, and narrow tests; stale_* and recovery_recipes.rs were not edited.\nRejected: Adding more boolean fields to GreenContract | clippy flagged the shape and a requirement list is more explicit.\nConfidence: high\nScope-risk: narrow\nDirective: Treat raw test level as insufficient for merge readiness unless green contract evidence is satisfied.\nTested: cargo check --manifest-path rust/Cargo.toml -p runtime; cargo test --manifest-path rust/Cargo.toml -p runtime; cargo clippy --manifest-path rust/Cargo.toml -p runtime -- -D warnings; focused green_contract, policy_engine, and integration tests.\nNot-tested: full workspace cargo test due pre-existing rusty-claude-cli session_lifecycle_prefers_running_process_over_idle_shell failure observed before this slice.
2026-05-14 18:33:51 +09:00
bellman
d3f8ff9916 omx(team): auto-checkpoint worker-1 [1] 2026-05-14 18:28:21 +09:00
bellman
5c40d4e778 omx(team): auto-checkpoint worker-3 [4] 2026-05-14 18:26:55 +09:00
bellman
6a37442ee1 omx(team): auto-checkpoint worker-2 [3] 2026-05-14 18:24:51 +09:00
bellman
0bca524c8c omx(team): auto-checkpoint worker-1 [1] 2026-05-14 18:22:37 +09:00
bellman
1fbde9f47f omx(team): auto-checkpoint worker-1 [1] 2026-05-14 18:21:26 +09:00
bellman
0b0d55d7ec omx(team): auto-checkpoint worker-1 [1] 2026-05-14 18:11:53 +09:00
bellman
7214573f35 Keep approval token contracts in their own runtime module
Constraint: G004 task 3 now owns approval-token contracts through rust/crates/runtime/src/approval_tokens.rs, while auto-integration left a duplicate unused copy in permissions.rs.\nRejected: suppressing dead-code warnings | the duplicate implementation was obsolete after the dedicated module landed.\nConfidence: high\nScope-risk: narrow\nDirective: Keep permission-mode authorization in permissions.rs and approval-token policy handoff in approval_tokens.rs.\nTested: cargo fmt --manifest-path rust/Cargo.toml --all -- --check; cargo check --manifest-path rust/Cargo.toml -p runtime; cargo test --manifest-path rust/Cargo.toml -p runtime approval_token -- --nocapture; cargo test --manifest-path rust/Cargo.toml -p runtime --test g004_conformance -- --nocapture\nNot-tested: full workspace test suite; G004 tasks 2/4/5 remain non-terminal.\n\nCo-authored-by: OmX <omx@oh-my-codex.dev>
2026-05-14 18:11:20 +09:00
bellman
dcf11f8190 harden report contract projection identity
Add a runtime report schema v1 contract so downstream consumers can negotiate structured fields, verify canonical report identity, and audit projection redactions without reverse-engineering prose.\n\nConstraint: Task 2 scope was limited to report schema/projection/redaction modules/docs/tests and prohibited .omx/ultragoal mutation.\nRejected: Wiring into broader CLI report emitters | kept this slice focused on the reusable contract and deterministic fixtures.\nConfidence: high\nScope-risk: narrow\nDirective: Future report emitters should build canonical payloads through CanonicalReportV1 before projecting audience-specific views.\nTested: cargo test -p runtime report_schema -- --nocapture; cargo test -p runtime lane_events -- --nocapture; cargo check -p runtime\nNot-tested: cargo clippy -p runtime --all-targets -- -D warnings remains blocked by pre-existing non-task warnings in compact.rs, file_ops.rs, policy_engine.rs, sandbox.rs.
2026-05-14 18:09:36 +09:00
bellman
e1641aa010 Prove G004 contract bundles are machine-checkable
Constraint: Task 6 needed a regression harness without overwriting Task 1-4 implementation files.\nRejected: Editing lane_events/report-schema/approval-token owners directly | would create shared-file conflicts with active lanes.\nConfidence: high\nScope-risk: narrow\nDirective: Keep this harness as a consumer-facing conformance layer; extend fixtures after Task 2/3 land schema/token producers.\nTested: cd rust && cargo test -p runtime --test g004_conformance -- --nocapture; cd rust && cargo check -p runtime; cd rust && cargo fmt --check; git diff --check\nNot-tested: cargo clippy -p runtime --tests -- -D warnings fails on pre-existing runtime lint debt outside changed files.
2026-05-14 18:07:11 +09:00
bellman
5cebdd999d omx(team): auto-checkpoint worker-2 [3] 2026-05-14 18:07:05 +09:00
bellman
bf533d77a7 task: approval token chain
Add a runtime approval-token ledger so policy-blocked actions can require scoped owner grants, consume one-time tokens, reject replay, and retain delegation traceability.\n\nConstraint: Task 3 scope is the G004 approval-token chain for runtime event/report contract families.\nRejected: Extending the existing permission prompt path directly | the token contract can be tested independently without changing live tool authorization behavior.\nConfidence: high\nScope-risk: narrow\nDirective: Keep approval grants scoped to policy/action/repo/branch before wiring them into external execution paths.\nTested: cargo check --manifest-path rust/Cargo.toml --workspace; cargo test --manifest-path rust/crates/runtime/Cargo.toml; cargo test --manifest-path rust/crates/runtime/Cargo.toml approval_token -- --nocapture\nNot-tested: cargo clippy --manifest-path rust/crates/runtime/Cargo.toml --all-targets -- -D warnings is blocked by pre-existing warnings in compact.rs, file_ops.rs, policy_engine.rs, and sandbox.rs.
2026-05-14 18:07:03 +09:00
bellman
e34209ff7f omx(team): auto-checkpoint worker-2 [3] 2026-05-14 18:07:00 +09:00
bellman
ff37d395bb Stabilize G004 contract integration after worker merges
Constraint: G004 worker integrations introduced unparseable approval-token tests and a conformance path bug that blocked leader verification.\nRejected: waiting for another auto-integration cycle | local leader verification had exact parse and fixture failures to repair safely.\nConfidence: high\nScope-risk: moderate\nDirective: Keep approval-token regression tests in cfg(test) modules or integration tests, never inside type definitions.\nTested: cargo fmt --manifest-path rust/Cargo.toml --all -- --check; cargo check --manifest-path rust/Cargo.toml -p runtime; cargo test --manifest-path rust/Cargo.toml -p runtime approval_token -- --nocapture; cargo test --manifest-path rust/Cargo.toml -p runtime --test g004_conformance -- --nocapture; python3 .github/scripts/check_doc_source_of_truth.py\nNot-tested: full workspace test suite; remaining G004 tasks 1-5 still non-terminal.\n\nCo-authored-by: OmX <omx@oh-my-codex.dev>
2026-05-14 18:06:14 +09:00
bellman
f8d744bb37 omx(team): auto-checkpoint worker-1 [1] 2026-05-14 18:05:26 +09:00
bellman
c8c936ede1 omx(team): auto-checkpoint worker-3 [6] 2026-05-14 18:00:23 +09:00
bellman
57b3e3258b omx(team): auto-checkpoint worker-2 [3] 2026-05-14 18:00:19 +09:00
bellman
06e545325d omx(team): auto-checkpoint worker-1 [1] 2026-05-14 18:00:16 +09:00
bellman
f4e08d0ecf omx(team): auto-checkpoint worker-2 [3] 2026-05-14 17:58:46 +09:00
bellman
16d6525de4 omx(team): auto-checkpoint worker-2 [3] 2026-05-14 17:57:59 +09:00
bellman
8c11dd16f4 task: preserve startup no-evidence timestamp evidence
Lock the startup-no-evidence contract so prompt timestamps remain the original send time while lifecycle and pane timestamps prove timeout ordering.

Constraint: task 4 scope limited changes to runtime worker boot/session/startup modules and tests; .omx/ultragoal not mutated.

Rejected: CLI-surface changes | runtime evidence contract already exposes the typed worker.startup_no_evidence payload.

Confidence: high

Scope-risk: narrow

Directive: Keep startup timeout evidence timestamps stable across later lifecycle observations.

Tested: cargo test -p runtime worker_boot -- --nocapture; cargo check --workspace

Not-tested: cargo clippy -p runtime --tests -- -D warnings is blocked by pre-existing runtime warnings in compact.rs, file_ops.rs, policy_engine.rs, and sandbox.rs.
2026-05-14 17:50:33 +09:00
bellman
9ec4d8398e omx(team): auto-checkpoint worker-3 [unknown] 2026-05-14 17:46:13 +09:00
bellman
087e31d190 Keep G003 integrated runtime tests compiling
Constraint: G003 worker outputs added config and startup evidence fields that must compile under focused runtime validation before leader push.
Rejected: pushing auto-checkpoints without leader validation | integrated tests initially failed to compile due missing imports and stale StartupEvidenceBundle fixtures.
Confidence: high
Scope-risk: narrow
Directive: When extending StartupEvidenceBundle, update all in-crate fixtures in the same change.
Tested: git diff --check; cargo fmt --manifest-path rust/Cargo.toml --all -- --check; cargo test --manifest-path rust/Cargo.toml -p runtime trusted_roots -- --nocapture; cargo test --manifest-path rust/Cargo.toml -p runtime startup -- --nocapture; cargo test --manifest-path rust/Cargo.toml -p runtime worker_boot -- --nocapture; cargo test --manifest-path rust/Cargo.toml -p tools path_scope -- --nocapture; cargo check --manifest-path rust/Cargo.toml --workspace
Not-tested: full cargo test --workspace remains deferred during active G003 team work.

Co-authored-by: OmX <omx@oh-my-codex.dev>
2026-05-14 17:45:46 +09:00
bellman
a6ee51baab omx(team): auto-checkpoint worker-3 [unknown] 2026-05-14 17:40:32 +09:00
bellman
6df60a4683 omx(team): auto-checkpoint worker-2 [unknown] 2026-05-14 17:40:29 +09:00
bellman
713ca7aee4 omx(team): auto-checkpoint worker-1 [1] 2026-05-14 17:27:18 +09:00
bellman
f789525839 omx(team): auto-checkpoint worker-1 [1] 2026-05-14 17:22:06 +09:00
bellman
9ab569e626 omx(team): auto-checkpoint worker-2 [3] 2026-05-14 17:18:55 +09:00