594 Commits

Author	SHA1	Message	Date
drew	6178be3aa7	feat(models): single-source model registry via models.yaml + sync_models.py ... .opencode/models/models.yaml is now the ONE file humans edit to assign a model to an agent. tools/sync_models.py regenerates every derived surface — the .opencode/models/*.txt files, opencode.json's `agent` block, and each non-tier agent's .md `model:` frontmatter — so an assignment cannot drift across surfaces. `--check` verifies with no writes and is enforced in CI by test_model_registry_in_sync_with_manifest. Hardened after adversarial review: - Deletes orphan <agent>.txt files left behind when an override is dropped from the manifest. The dispatcher's resolver reads <agent>.txt before default.txt, so a stale file would silently pin the old model. Tier .txt files are left to sync_tier_models.py. - Rejects a manifest key that does not name a real agent (no matching .opencode/agents/<name>.md) instead of silently appending a bogus opencode.json entry and leaving the real agent on the default model. - Validates the regenerated opencode.json BEFORE writing it, so a bad render aborts cleanly instead of corrupting the file on disk. Tier-ladder agents (task-implementor-tier-*) remain governed separately by tiers.yaml + sync_tier_models.py and are passed through untouched. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>	2026-05-22 07:33:18 -04:00
drew	2658deee94	feat(auto-agents): PR State Warmer substrate + supporting infra ... Adds a long-lived sidecar (pr_state_warmer.py) that polls Forgejo's /pulls endpoint every 30s and writes the full PR snapshot to a shared SQLite store, eliminating the dispatcher's per-cycle cold-cache stalls (24-30s rebuilds on flaky cycles) and the silent 50-PR pagination cap on the legacy single-page fetch. Substrate - tools/_pr_state_cache.py — SQLite store with (owner, repo) PK, WAL mode, additive v2→v3 migration (comments_refreshed_updated_at), bounded fcntl.flock migration lock, threading.Lock for per-process init, @_with_reheal decorator (catches OperationalError no-such- table + DatabaseError corruption with file quarantine), atomic TEMP-table chunking for >32k seen-set, _normalize_updated_at to canonicalize Forgejo tz-marker drift - tools/pr_state_warmer.py — poll/upsert/vanish/comments-refresh loop with fcntl.flock singleton (rejects second warmer), bounded comments-refresh cap, persistent deferral via SQL pending query, PermissionError-tolerant lock setup, cold-start log suppression - tools/_pr_classification_cache.py — three-layer fall-through (warmer cache → list cache → live fetch) with staleness gate (PR_STATE_WARMER_STALE_AFTER_S floored at 30s in prod) Comments cache hardening - Bot-filter at write time drops bot status/claim/release/sentinel while preserving **Implementation Attempt** markers (94.6% reduction on bot-heavy PRs like #30's 19k-comment thread) - _normalize_since_cursor strips microsecond precision before building ?since= query (fixes the live-observed Forgejo HTTP 422 bug on PRs #25 + #28); handles uppercase Z, lowercase z, ±HH:MM offsets (including non-zero like +05:30), naive ISO - Lazy migration of legacy null-key by_author entries on _read_cache - _newest_cursor walks tail-back skipping malformed entries Supporting infrastructure (cumulative dmpipeline-v2 work) - Telemetry server: SSE live tail, run-sessions enumeration, cost/token tracking, app.js UI rewrite with collapsible sections - MCP servers (mcp_ci_server, mcp_forgejo_server, mcp_git_server, mcp_handoff_server, mcp_graphify_server) for opencode worker context access - Live log writer (tools/live_log_writer.py) — SSE-streaming dispatcher event log - Tier-dispatcher escalation flow with prompts trimmed for budget - Shared bot-logins resolver (tools/_bot_logins.py) replacing two drift-prone copies - token_usage_audit.py for opencode cost analysis Tests - 2259 passing across 65 changed/new files - New suites: test_pr_state_cache, test_pr_state_warmer, test_pr_state_warmer_integration, test_pr_classification_cache, test_pr_list_cache_backoff, test_mcp_* (5 servers), test_live_log_writer_sse, test_telemetry_run_sessions, test_review_post_ready_label - Test_pr_comments_cache expanded with bot-filter coverage, cursor-normalization regression pins, format-drift, atomicity, failed-comments-not-stamped (silent-data-loss class) - Parametrized @_with_reheal coverage across 7 wrapped APIs - Real fault-inject atomicity test for chunked mark_vanished path via Connection wrapper class - Subprocess-based singleton flock test (cross-process contract) - Event-driven SIGTERM-mid-poll test (no fixed-sleep flake) Architecture notes - Schema v3 migration is additive (ALTER ADD COLUMN); v0/v1 still need destructive rebuild because pre-v2 column shape lacks owner/repo. Cross-process drop-table-ping-pong prevented by the fcntl migration lock + per-process _initialized flag. - Comments-refresh deferral is persistent via comments_refreshed_updated_at column — survives warmer restart, picks up next cycle even if PR didn't change again. Replaces in-memory changed_numbers list. - Rollback path: PR_STATE_WARMER_PREFER=0 bypasses the warmer cache and reverts to live-fetch behavior. PR_STATE_CACHE_DISABLE=1 short-circuits the warmer process at startup. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>	2026-05-17 10:02:53 -04:00
drew	1eac4ea233	refactor(auto-agents): manifest-driven tier-model registry, slot-based naming ... Replace the scattered per-agent .txt-file mapping (whose names embedded model-family identity like tier-qwen-med and tier-kimi and went stale the moment a model was swapped) with a single source-of-truth manifest at .opencode/models/tiers.yaml. The four tier slots get model-agnostic slot-based names (tier-min, tier-0, tier-1, tier-2); the model in each slot is configured ONLY in the manifest. Derived artifacts (per-agent .txt files and the mapping table block in tier-dispatcher.md) are now generated by tools/sync_tier_models.py. A drift-detection test in tests/auto_agents/test_tier_model_registry.py fails CI if any derived file diverges from the manifest, if an agent referenced by the manifest lacks an agent file, if the manifest cites a provider not declared in opencode.json, or if opencode.json carries a stale tier-* entry. To swap a model in a slot: edit tiers.yaml -> run python3 tools/sync_tier_models.py -> commit. The runtime dispatcher re-reads the .txt files per cycle (no restart); the static OpenCode config path needs a server restart. Tier rename mapping (escalation_tier integers UNCHANGED): tier-qwen-small -> tier-min (slot -1) tier-qwen-med -> tier-0 (slot 0, default first attempt) tier-qwen-large -> tier-1 (slot 1) tier-kimi -> tier-2 (slot 2) Vestigial tier-* agents removed (declared but never in the active mapping): tier-haiku, tier-sonnet, tier-opus, tier-codex, tier-gpt5-mini, tier-gpt5-nano, tier-o4-mini. estimator-implementation.md now reasons in capability descriptors (cheapest / default / advanced / complex) instead of model-family labels (qwen-small / qwen-med / qwen-large / kimi), so the estimator stays correct across model swaps. The stale "default tier = gpt-5-mini" docstring claim (already drifted to claude-haiku-4-5) is removed. Companion prose updates across every consumer of tier names: - Agent prompts: tier-dispatcher.md, implementation-worker.md, estimator-implementation.md - Skills: implementer-pr-context, implementer-workspace - Python: dispatch_implementer.py, _opencode_worker.py, _pr_context_sentinel.py, implementer_workspace.py, setup_auto_labels.py, _attempt_history.py - Tests: test_worker_permissions.py (parametrize list + byte-identity test now covers 4 slot files instead of 3 family-named files), test_opencode_worker_models.py (synthetic-fixture names updated) - Docs: .opencode/models/README.md, docs/development/models.md, docs/development/agent-system-specification.md, docs/development/auto-agents-tier-2-3-plan.md, docs/development/implementer-in-cycle-escalation-plan.md, docs/development/final-working-harvest-plan.md Validation: 1625 tests pass (+6 net new from the tier-registry test file), 3 skipped. python3 tools/sync_tier_models.py --check exits 0. local_ci_gate.sh --gate lint PASS. Files: 9 added, 22 deleted, 18 modified. The drift-detection test ran green on every step of the refactor, catching one out-of-sync .txt file before commit. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>	2026-05-15 12:49:31 -04:00
drew	d3d66f3726	feat(auto-agents): in-cycle implementer tier escalation 0→1→2 ... Adds a flag-gated escalation loop to the implementer dispatcher (`IMPLEMENTER_ESCALATION_ENABLED=1`, default OFF). When the worker fails in a way the predicate determines escalation can help, the dispatcher holds the claim, resets the worktree to the prefetched head_sha, refreshes the TTL via _claim_runtime.claim_pr, applies the next-tier label, and re-runs the worker at the next tier — all within the same cycle. Bounded by per-failure-class budgets in _implementer_escalation.BUDGET_PER_FAILURE_CLASS. Tier 2 (tier-kimi) is default-ON with a kill-switch flag (IMPLEMENTER_ESCALATION_TIER2_ENABLED=0). Cross-cycle resumption: the dispatcher reads auto/last-attempt-tier-N at cycle start and seeds start_tier = min(N+1, max_tier) so crash recovery skips known-failed tiers. Worker holds release across the cycle via the new release_claim_on_exit: false directive — eliminates the inter-tier claim-absent race window. Behaviour preservation: flag=0 path is byte-equivalent to the pre-feature build (worker prompt unchanged, Phase 4 row schema unchanged, status-comment fingerprint unchanged). Issue work (new_issue work group) always takes the legacy path even with the flag on. Supersedes the cross-cycle-only Phase 5c scheme in auto-agents-tier-2-3-plan.md (now updated to point at the new plan doc and the dual-role label semantics). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>	2026-05-12 12:15:39 -04:00
drew	0150c4fbc0	feat(auto-agents): Tier 1+2 follow-ups from 2026-05-11 post-mortem ... R1: bake 20-min bash timeout into quality-gates skill recipes so the first cold-cache --fast call no longer trips OpenCode's 120 s default (recovered ~2 min that was lost on the 2026-05-11 PR #30 cycle to timeout-and-retry). R2: plumb subagent_max_depth from _archive_subagent_tree's BFS walk through SessionResult -> SessionContext -> extract_phase4_ telemetry so the field stops landing as null on real multi-tier cycles. Distinguishes None (walk failed / unknown) from 0 (measured-flat). +7 behavioural tests, 4 existing tests updated to consume the new (paths, max_depth) tuple. R3: throttled operator-visible "worker still in-flight" log line every 120 s (configurable via DISPATCHER_HEARTBEAT_LOG_INTERVAL_SECONDS) so a 20-min worker turn emits ~10 status lines instead of going completely silent between session-start and session-end. +5 tests covering env-var override, defaults, garbage-rejection, end-to-end emission, and short-cycle suppression. R4: triaged 25 errored steps in fork-local unit_tests -- conclusive finding that they're caused by Rich Console defaulting to 80-col width in non-TTY CliRunner mode, truncating asserted column headers. Pre-existing on every branch, unrelated to auto-agents. Documented in the Tier 2/3 plan so future operators don't re-spend the diagnostic time. R5: short-circuit tier-dispatcher's estimator call on first attempts via new optional escalation_tier_hint parameter; implementation-worker now hard-codes hint=0. Saves ~30-60 s wall-clock per cycle on the common case (estimator's recommendation converged on Tier 0 in every observed cycle to date; sample too small for a confidence interval). Future-proof: the hint becomes dynamic when the auto/last-attempt-tier-N label scheme lands. +2 static lint tests pin the contract. Pre-commit polish (P0/P1/P2 from the consolidated critique): - Renumber tier-dispatcher CRITICAL rules 6,9,7,8 -> 6,7,8,9 - End-to-end pin tests for the R2 closure-mutation chain (subagent_max_depth=1 and =None paths) - Deterministic time.monotonic mock in heartbeat tests so they no longer depend on real-clock timing - Reject bool from extract_phase4_telemetry's int check (bool is subclass of int in Python -- would slip True/False through as 1/0) - Replace d.get("_subagent_depth") or 0 footgun with int(d.get(..., 0)) - Document DISPATCHER_HEARTBEAT_LOG_INTERVAL_SECONDS as a startup-only knob - Calibrate the "~95% Tier 0" claim to "Tier 0 in every observed cycle, n=1" - Document the reviewer-side R2 asymmetry (SessionContext carries the field; reviewer telemetry sink doesn't emit yet) - Add R5 rollback procedure - Trim duplicated R5 rationale prose in implementation-worker.md - Add reviewer back-compat test for SessionContext with the new subagent_max_depth field Tests: 1238 passed (+3 net-new), 3 skipped. Lint + typecheck clean. Validated via the local_ci_gate.sh wrapper.	2026-05-12 08:37:01 -04:00
drew	132a5a2269	feat(auto-agents): centralise model registry under .opencode/models with session-create model stamp ... Every agent's model assignment now lives in a single-line text file at .opencode/models/<name>.txt; default.txt is the 27-agent catch-all. opencode.json's agent.<name>.model uses {file:./.opencode/models/<name>.txt} interpolation, and tools/_opencode_worker.py reads the same files at session-create to stamp the resolved model on the session record (observability + drift sentinel; OpenCode does NOT propagate session-level model to prompt_async — schema for that is undocumented and deferred to Stage 2). 39 .md frontmatter `model:` lines stripped; the two intentional inheritors (task-implementor, agent-evolution-pool-supervisor) keep their model-less frontmatter. Operator workflow for swapping a model is now: edit .opencode/models/<role>.txt, restart OpenCode so opencode.json's {file:...} re-resolves, run the dispatcher. Live-swap without restart was attempted (override on prompt_async); OpenCode 0.x silently dropped those requests (200 OK, no assistant message) and the prompt_async override was reverted. The session-create override remains for observability + drift detection. End-to-end validation (2026-05-10): dispatch_review.py on PR #25 with default.txt=openai/gpt-5-mini produced a clean REQUEST_CHANGES review in 26 s for ~$0.016; dispatch_implementer.py on PR #30 with tier-qwen-* files remapped to openai/{gpt-5-nano, gpt-5-mini, gpt-5-codex} ran the full implementation-worker → tier-dispatcher → estimator-implementation → tier-qwen-med → task-implementor → git-isolator-util chain in 16 min with model=gpt-5-mini end-to-end. Also documents the printenv VAR form as the only allowed env-read in implementation-worker.md and task-implementor.md (live testing showed the worker burning 2–4 turns on permission-denied trial-and-error trying printf and echo variants). Tests: 21 in tests/auto_agents/test_opencode_worker_models.py (resolver semantics with caplog assertions on every malformed-input path; session-create body shape; prompt_async body never carries model; three repo-level invariants — every {file:...} reference resolves, every .md is wired or in the inheritor allowlist, no .md has a model: frontmatter). 1027 auto_agents tests pass / 3 skipped. Note: .opencode/models/default.txt and the three tier-qwen-*.txt files are committed with their OpenAI swaps in place (gpt-5-mini, gpt-5-nano, gpt-5-mini, gpt-5-codex respectively) because the CleverThis HuggingFace endpoints are paused. Revert with `git diff HEAD~1 -- .opencode/models/*.txt | git apply -R` if/when they come back. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-05-10 17:23:06 -04:00
drew	355af84fb1	refactor(auto-agents): hard-switch supervisor decommission + implementer parity ... Combines the 2026-05-09 hard-switch decommissioning of the LLM implementation/pr-review supervisors with the Phase 2/3/4/5b implementer parity work (prefetch + preclone + telemetry + operator- status comments) and the third/fourth-round critique cleanup. Removed - .opencode/agents/implementation-supervisor.md (340 LoC) - .opencode/agents/pr-review-supervisor.md (348 LoC) - _dispatch_runtime.assert_no_legacy_supervisor + detect_legacy_supervisor_sessions and the SUPERVISOR_TAGS / SUPERVISOR_OVERRIDE_ENV plumbing in both dispatchers, along with the five supervisor-coexistence tests in test_dispatch_runtime.py - _watchdog_helpers.parse_truthy_env + watchdog_check.py --check-env mode + their dedicated unit tests (the legacy DISPATCHERS_RUNNING gate had no callers after the watchdog rewrite became unconditional) Added - tools/_implementer_prefetch.py — pre-dispatch Forgejo fetches (PR/issue body, diff, CI status, comments, reviews, linked issues, Epic) per work group - tools/_implementer_prompt.py — pure-function prompt assembly with UNTRUSTED CONTENT fences and shared PR_COMPLIANCE_CHECKLIST / OUTPUT_CONTRACT - tools/_phase4_telemetry.py — extractor + JSONL sink for the Phase 4 plan metrics - tools/_status_comments.py — per-fingerprint operator-status comment substrate, namespaced for reviewer + implementer - _dispatch_runtime.SessionContext dataclass + SIGTERM/SIGINT cooperative claim release with synchronous handler - TestSupervisorAgentsDecommissioned and TestAutoAgentsMdIsWatchdogOnly anti-regression lints (glob over *supervisor*.md in .opencode/agents/, plus body keyword bans and bash allow-list lint) - pyproject.toml `slow` marker registration for the subprocess SIGTERM smoke test - tests/auto_agents/fixtures/{phase4-acceptance.yaml, phase4-session-output-sample.txt} Rewritten - .opencode/agents/auto-agents.md from supervisor-fleet manager (~545 LoC) to dispatcher heartbeat watchdog (~184 LoC); host init system / process manager (systemd / runit / docker) is now the explicit restart authority instead of "host-level process supervisor" - AGENTS.md production-launch story (Shells A-D) reflects the deterministic-Python orchestration boundary; the bot-identity fork-mode paragraph reads from FORGEJO_OWNER / FORGEJO_REPO env vars instead of the deleted hard-coded supervisor flags - tools/launch_fork.sh header documents three host-level entry points (dispatchers-launcher.sh, opencode-builder.sh, merge_drive.py) - worker self-descriptions (implementation-worker.md, pr-review-worker.md) refer to the dispatcher / merge driver instead of the deleted supervisors; session-health-quick-util.md and async-agent-util.md treat -SUP-suffixed sessions as flag-and-escalate signals Tests: 1006 passed, 3 skipped, 0 failed under tests/auto_agents/. Lint: zero new ruff errors on touched files; three pre-existing errors in tools/_pr_diff.py at lines blamed to 2026-05-07. Operator note: the only in-process rollback knob for prefetch issues is IMPLEMENTER_DISPATCHER_PREFETCH=0 (and the matching IMPLEMENTER_DISPATCHER_PRECLONE=0). Anything beyond that is git revert of this commit. Residual doc surface in the auto-agents-system and supervised-workers skill READMEs is documentation-only; the agent files those READMEs reference no longer exist. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-05-10 16:03:43 -04:00
drew	720b633b1d	docs: flag dispatcher throughput regression as immediate post-soak follow-up ... The 2026-05-09 parity audit against agents/final-working surfaced one HIGH-severity regression in the new dispatcher: workers run strictly serially (no ThreadPoolExecutor / asyncio anywhere in _dispatch_runtime.py), where the legacy LLM supervisors ran max_workers=4 concurrent workers. ~4x wallclock throughput penalty on backlog burndown. Document this in docs/development/auto-agents-tier-2-3-plan.md as a new Tracking subsection ("Open - immediate follow-up after dispatcher soak") with full acceptance criteria (--workers N flag wrapping the per-item cycle loop in ThreadPoolExecutor, default 1 for safety; six concrete test cases; cycle_failure_budget must remain cycle-level not per-worker) so the fix is ready to pick up the moment the serial dispatcher demonstrates >= 1 week of clean production runtime. The soak-first ordering is deliberate: known-good serial baseline makes concurrency bugs much easier to attribute. Operator-side multi-process fallback (sharding via distinct LOCK_PATH/HEARTBEAT_PATH per process) also documented for hosts that cannot wait for the in-process fix. Cross-referenced from the existing "Cross-cutting work" section so a reader scanning the plan top-to-bottom sees the dependency before reaching Tracking. CHANGELOG updated. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-05-09 12:09:28 -04:00
drew	2f1be34d12	feat(auto-agents): implementer parity — verify-invariant verifiers, implementer-helpers skill, watchdog gate, _opencode_worker audit ... Closes the four open items in `docs/development/auto-agents-tier-2-3-plan.md` § "Revised remaining scope (2026-05-08)" plus three rounds of fresh-eyes critique fold-in (rounds 3, 5, and post-round-5 polish). Highlights: - New continuous invariant verifiers on a shared `_verify_common.py` substrate: `verify_review_invariant.py` (R1: approval-without-CI) and `verify_implementer_invariant.py` (I1: head-commit fails commit-lint, I2: PR description missing Epic reference). Strictly additive cron-job- shaped scripts that open idempotent `auto/invariant-violation` issues; safe to run every 15 minutes in production. - New `implementer-helpers` skill at `.opencode/skills/implementer-helpers/SKILL.md` + CLI at `tools/implementer_validate.py` (4 subcommands: validate-commit-message, validate-pr-compliance, validate-file-budget, validate-changelog). Mirrors the reviewer side; `tools/_commit_lint.py` is shared so a future change to commit policy updates one place. - `auto-agents.md` watchdog gate: `DISPATCHERS_RUNNING=1` puts the primary orchestrator into watchdog-only mode. Heartbeat resolution + age computation factored into `tools/_watchdog_helpers.py` + the CLI `tools/watchdog_check.py` so the agent only needs `python3 tools/watchdog_check.py *` and `sleep *` bash permissions. The reader honours the env-var override first, then falls back to a freshest-mtime scan across `/var/run` / `$XDG_RUNTIME_DIR` / `/tmp` (deliberately diverging from the dispatcher's first-existing fallback to guard against stale heartbeats from previous root-owned sessions masking healthy user-mode heartbeats). - `_opencode_worker.py` audit: structured `error_kind` classification at every transport-error / timeout return site, plumbed through `_dispatch_runtime.py` into the cycle-log; new `_request_read` retry helper (3 × 0.5s linear backoff, transport-only) wrapping every idempotent read in a worker session so a single transient flap on a polling GET cannot trash a 10-minute worker session. - Static heredoc lint at `tests/auto_agents/test_prompt_heredoc_lint.py` glob-walks every agent prompt and skill recipe markdown, rejecting any heredoc bash recipe in a fenced code block (per `bash-commands.md` rule 2 — heredocs fail at OpenCode's permission-engine parse time). - `bash-commands.md` rule 2 + its fix-it advice both lead with apostrophe-safe `printf "%s" "<body>"` (double-quoted) form; single-quoted form documented as the fragile JSON-only fallback. - `CHANGELOG.md` carries the full multi-round narrative (round 3 CRITICAL/HIGH/MEDIUM/LOW fold-in, round 5 docstring drift + telemetry refactor + broader heredoc lint scope, post-round-5 doc-drift polish). Net delta: +911 passing tests / 3 skipped (was 825 / 3); ruff clean on every new file; pre-existing lint debt in `_dispatch_runtime.py`, `_opencode_worker.py`, `conftest.py`, `_commit_lint.py` unchanged and out of scope for this commit. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-05-09 11:48:12 -04:00
drew	ed8dd31b35	docs(plan): mark Tier 2/3 dispatcher work shipped; revise remaining scope ... The reviewer/implementer dispatchers and the review-helpers skill landed between 2026-05-04 and 2026-05-08. The plan document still read as a deferred forward-looking design. Update it to mark every shipped deliverable with a status entry + module pointer, explain how the skill pattern (a second deterministic surface inside the worker session) changed the architectural calculus, and replace the original Tier-3 deliverable list with a four-item revised remaining scope: verify-*-invariant cron jobs, implementer-helpers skill, auto-agents.md watchdog gate, _opencode_worker.py audit (~5 engineering days total). Co-authored-by: Cursor <cursoragent@cursor.com>	2026-05-08 10:56:18 -04:00
drew	703a7c9090	feat(auto-agents): Phase A — conflict_drive.py deterministic conflict-resolution driver ... Implement Tier 1.5 conflict resolution as a peer driver to merge_drive.py that honours the same hard invariant: every commit on master came from a SHA whose CI passed against the exact current master. New components - tools/conflict_drive.py: deterministic driver that picks PRs labelled auto/needs-conflict-resolution, claims them via the shared auto/claimed-merge label, attempts a deterministic rebase with deepen-on-demand fallback, dispatches conflict-resolver-worker on conflict, force-pushes with --force-with-lease, and clears the label for merge_drive to re-pick. Includes 24h retry budget, escalation to auto/needs-implementer, single-instance lock + heartbeat, opt-in TOCTOU mitigations (CONFLICT_DRIVER_CYCLE_JITTER_SECONDS, CONFLICT_DRIVER_VERIFY_CLAIM), startup TTL constraint and required- labels assertions, and full SQLite telemetry. - tools/_claim_runtime.py: shared HTTP/lock/heartbeat/claim primitives extracted from merge_drive.py (driver-aware claim/release markers, injectable op_label_map). merge_drive re-exports for back-compat. - tools/_opencode_worker.py: blocking Python client for the OpenCode HTTP API with O(N) string-aware bracket matcher for tolerant JSON extraction from worker output. - .opencode/agents/conflict-resolver-worker.md: subagent definition with tight permissions and "always finish, never abort, never --skip" doctrine. - tools/inject_synthetic_conflict.py: CLI that creates PRs on a test fork with guaranteed conflicts (trivial / multi-commit / unresolvable) for end-to-end testing. Telemetry & dashboard - tools/_forgejo_cache.py: new conflict_drive_cycles table, cycle-level escalated_count, indexed retry-budget query, mark_*_escalated helper. - tools/render-pr-velocity.py + pr-velocity.canvas.template.tsx: conflict-resolution activity section showing 7-day cycle counts, resolved/escalated/timeout/push-rejected breakdowns. Open-issue dependency check - tools/merge_drive.py: pr_is_eligible now consults Forgejo's blocks endpoint and applies auto/blocked-by-deps when any open dependency exists. Read-only predicate _pr_has_open_dependencies; label mutations live with the eligibility caller. - tools/setup_auto_labels.py: provisions auto/blocked-by-deps. Documentation - docs/development/conflict-drive-plan.md: full plan including TOCTOU race documentation (§3.3.1) with implementation/test pointers. - AGENTS.md: operator-facing section on conflict_drive.py and the expanded label registry. Tests - 300 unit tests pass / 1 skipped (opt-in fork integration test). - Coverage includes JSON extractor fuzz, push-stderr classification, PAT scrub, deepen-on-demand fallback, retry budget escalation, cycle-level escalated_count stamping, claim collision detection (latest-claim-only with marker-primary identity), jitter wiring, and verify_claim_after_apply plumbing. Quality invariant unchanged: conflict_drive.py only operates on PR head branches, never on master. CI gating on the train-merge SHA continues to enforce the exact-current-master rule for everything that lands. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-05-06 01:28:41 -04:00
drew	f358cb7363	feat(auto-agents): Tier 1 mutual-respect claim contract ... Extend the deterministic merge driver's auto/claimed-merge contract to a three-way symmetric mutex covering all auto-agents fleet workers, so the merge driver, reviewer pool, and implementer pool stop racing on the same PRs and orphaned claims are bounded by a TTL-based sweep. Patch A — wrapper opt-in (7 files): Add excludeClaimed: true to every list_prs_*.ts wrapper used by pr-review-supervisor and implementation-supervisor. Reviewer / implementer pools now never see PRs carrying any auto/claimed-* label, closing the "comments on a mid-train PR" race. Worker claim/release wiring: pr-review-worker.md (Startup step 3 / 1800 s TTL) and implementation-worker.md (Startup step 5 / 7200 s TTL, pr_fix only) invoke claim_pr.ts at start-of-work and through a new "Release and Exit" subsection at every termination path. Adds one bash permission (npx --yes tsx*claim_pr.ts*) and one skill allow each. Driver sweep coverage: merge_drive.py grows ALL_CLAIM_LABELS and sweep_all_expired_claims; sweep_expired_claims gains an optional label parameter (default = CLAIM_LABEL, backward compatible). run_one_cycle exposes swept_by_label per cycle so operators see per-label orphan rates. Foreign labels are swept with an empty session-exclusion set because the driver never owns them. Tests: Four new tests in tests/auto_agents/test_merge_drive.py covering the parameterised sweep, the all-labels iterator, per-label sweep results, and the ALL_CLAIM_LABELS <-> registry contract. Full auto_agents suite: 176 -> 180 tests, 100% pass. Docs: - AGENTS.md: new "Tier 1 mutual-respect claim contract" subsection; auto-* label registry rows for claimed-implementer / claimed-reviewer updated to reflect new owners and sweep coverage. - CHANGELOG.md: detailed Added entry under [Unreleased]. - docs/development/auto-agents-tier-2-3-plan.md: new plan capturing deferred Tier 2 (shared claim-runtime module + deterministic dispatchers) and Tier 3 (full deterministic drivers analogous to merge_drive.py) with concrete deliverables and decision gates. What this Tier deliberately does NOT do: replace LLM supervisor sessions, change worker dispatch, or touch the actual review / implementation logic. The supervisors still poll wrappers and dispatch workers; the workers still do the real LLM work. Only the orchestration bookkeeping around them gained a deterministic claim contract. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-05-04 21:15:05 -04:00
HAL9000	dde71cf8e2	docs(milestone): split advanced-concepts and tui docs into sub-documents ... Split docs/advanced-concepts.md (554 lines) into four sub-documents under docs/advanced-concepts/ and docs/tui.md (634 lines) into four sub-documents under docs/tui/, each under the 500-line limit per CONTRIBUTING.md. Advanced Concepts sub-documents: - docs/advanced-concepts/index.md: Overview, context strategies, LLM backends - docs/advanced-concepts/resource-types.md: Resource types, A2A rename - docs/advanced-concepts/container-tools.md: Container tools, scope chain, budgets, safety - docs/advanced-concepts/e2e-tests-and-plugins.md: E2E tests, code review, plugins TUI sub-documents: - docs/tui/index.md: Overview, getting started, main screen layout - docs/tui/sidebar-and-personas.md: Sidebar states, persona system - docs/tui/input-and-sessions.md: Reference/command input, session management - docs/tui/configuration-and-integration.md: Config, key bindings, theme, integration Updated mkdocs.yml navigation to reflect new sub-document structure. Updated CONTRIBUTORS.md with contribution entry for PR #9903. ISSUES CLOSED: #10533	2026-05-03 01:11:03 +00:00
HAL9000	7ece6f1530	docs(spec): rename checkpoint triggers on_tool_write → before/after_tool_execute ... Update the Automatic Checkpoint Triggers table and configuration reference in docs/specification.md to use the trigger names that match the actual implementation in ToolRunner and config_service.py: - on_tool_write → before_tool_execute - on_tool_write_complete → after_tool_execute The implementation (PR #3474) chose before_/after_ prefix pattern for consistency with event naming conventions and because _execute is more precise than _write. The spec was not updated at that time. ISSUES CLOSED: #4745	2026-04-30 17:48:19 +00:00
HAL9000	d7f03ee0a6	docs: add CHANGELOG.md and CONTRIBUTING.md to docs tree ... Add mirrored versions of root CHANGELOG.md and CONTRIBUTING.md to the docs tree. Add migration headers noting these are mirrors of the authoritative root files. Update mkdocs.yml navigation to include both new pages between FAQ and Reference.	2026-04-30 14:26:39 +00:00
HAL9000	0ade2526eb	docs(cli): update agents validation attach synopsis to use --key value named option format ... Update docs/specification.md to clarify that agents validation attach extra arguments use --key value named option format (not positional [<ARGS>...] format). Updates synopsis, argument description, and all inline references across the specification. ISSUES CLOSED: #4747	2026-04-29 17:08:17 +00:00
HAL9000	ab15eec673	docs(showcase): add audit log and security commands example to registry ... Register the existing audit-log-and-security.md example in the showcase registry (examples.json) so it appears alongside other CLI tool examples. Includes 17 audit commands covering list, show, count, and prune operations with all filter options. Closes #10824	2026-04-28 20:47:15 +00:00
HAL9000	ba53d2723b	docs(timeline): update schedule adherence Day 99 (2026-04-09)	2026-04-28 11:02:38 +00:00
HAL9000	98bc7c6b5d	docs(spec): align checkpoint trigger names and config key path with implementation ... - Update trigger names from 'on_tool_write' and 'on_tool_write_complete' to 'before_tool_execute' and 'after_tool_execute' to match the actual implementation in config_service.py - Correct config key path from 'core.checkpoints.auto_create_on' to 'checkpoints.auto_create_on' to match the actual configuration structure - Update TOML configuration examples to use comma-separated string format instead of array format, matching the actual ConfigService implementation - Update references to trigger names in the CLI Usage section to use the correct names	2026-04-28 08:20:42 +00:00
HAL9000	581dff6b43	spec(acms): add comprehensive ACMS v1 specification section (v3.4.0) ... Adds a comprehensive ACMS v1 (Advanced Context Management System) specification section covering all aspects of the context management architecture for milestone v3.4.0 — ACMS v1 + Context Scaling. Sections included: - Overview and design goals - Architecture: UKO (Unified Knowledge Ontology), CRP (Context Request Protocol), Context Pipeline, Storage Tiers (hot/warm/cold) - Module Definitions across all 4 architecture layers (Domain, Application, Infrastructure, Presentation) - Data Models: ContextFragment, ContextBudget, ProjectContextPolicy, ContextView, AssembledContext/ContextPayload, IndexMetadata - Key Interfaces: ACMSPipeline, ContextBudgetEnforcer, UKOStore, ContextTierService, RepoIndexingService - 10-Component Pipeline Architecture (3 phases: Strategy Orchestration, Fragment Fusion, Context Finalization) - Context Strategies: 6 built-in strategies with fallback degradation path - CLI Commands: agents context list/add/show/clear and agents project context set/show/inspect/simulate - Integration Points: Plan Lifecycle, Resource System, Actor/Agent, Configuration, DI Container - Database Schema: repo_indexes and indexed_files tables - v1 Known Limitations with planned conformance path - Acceptance Criteria for milestone v3.4.0 Replaces stuck [AUTO-ARCH-19] worker from Cycle 26. [AUTO-ARCH-20] Cycle 27 # Conflicts: # docs/specification.md	2026-04-26 18:45:44 +00:00
HAL9000	3975ad244c	docs(spec): fix invariant reconciliation, add ACMS thread safety, v3.6.0 section, ADR-049 ... - Fix invariant glossary entry: reconciliation now documented as occurring at each phase boundary (before Strategize, Execute, Apply, and after Apply) rather than only at start of Strategize (closes #9899) - Add Multi-Phase Invariant Enforcement note to Plan Lifecycle section - Add ACMS Thread Safety subsection documenting threading.RLock concurrency contract for ContextAssemblyPipeline and all context stores (closes #9859) - Append M7: Advanced Concepts and Deferred Features (v3.6.0) milestone spec section covering advanced invariant lifecycle, ACMS observability, plan hierarchy enhancements, and CLI communication pattern migration - Add ADR-049: CLI Communication Pattern documenting local CLI exemption from A2A boundary requirement and M9 migration path	2026-04-26 17:09:22 +00:00
HAL9000	0f0efe02e3	docs: update examples.json index with actor management workflow entry ... ISSUES CLOSED: #7539	2026-04-26 16:52:36 +00:00
HAL9000	4f2122cd9e	docs: add action module API reference, update CHANGELOG and nav ... - Add docs/api/action.md: full API reference for ActionConfigSchema and ActionArgumentSchema — field tables, factory methods, camelCase compat mapping, env-var interpolation, database integrity note, and complete YAML example - Update docs/api/index.md: add cleveragents.action entry to module index - Update mkdocs.yml: add 'Action Schema: api/action.md' to the API Reference nav - Update CHANGELOG.md [Unreleased] Fixed: document plan use UNIQUE constraint violation fix (#4174, #4197) - Clarify from_yaml_file ValueError semantics, document inputs_schema type as dict[str, Any] | None, and update A2A ASV benchmarks to pass method= requests after JSON-RPC migration ISSUES CLOSED: #7472	2026-04-26 09:39:17 +00:00
HAL9000	663a6d2397	docs(decomposition): enhance docstrings and add spec section for selective subtree recomputation	2026-04-24 08:26:59 +00:00
HAL9000	dddfa48eb4	docs(spec): extend diagnostics example to cover all providers ... - update agents diagnostics examples to show all provider checks across rich, plain, JSON, and YAML formats - refresh error scenario samples to reflect the expanded provider coverage and recommendation counts - align CLI diagnostics output with the spec by adding explicit provider display names and consistent ordering Closes #5320	2026-04-24 03:51:32 +00:00
HAL9000	afc17b22c5	feat(architecture-pool-supervisor): add milestone assignment to spec PRs ... Restore original permission structure and model configuration while adding only the changes needed for issue #7521: forgejo_update_pull_request permission and PR Workflow for Major Changes documentation section. Fixes addressed: - Restore flat permission format (was incorrectly restructured to nested) - Restore model to claude-haiku-4-5 with reasoningEffort max - Restore removed critical rules (6: label delegation, 7: pagination) - Restore removed permission denials (*, doom_loop, question, etc.) - Add CHANGELOG.md entry for this feature - Restore CONTRIBUTORS.md to master (remove unrelated changes) ISSUES CLOSED: #7521 # Conflicts: # CONTRIBUTORS.md	2026-04-24 02:04:54 +00:00
HAL9000	44fc7411f9	ci: move benchmark regression job out of default PR workflow ... Extract the benchmark-regression job from the default PR CI workflow into a dedicated scheduled workflow (.forgejo/workflows/benchmark-scheduled.yml). The benchmark job was blocking PR feedback for 99-132 minutes even when lint/typecheck/tests passed in under 20 minutes. The new workflow runs: - Nightly regression tests (2 AM UTC) comparing HEAD against master - Weekly full benchmark suite (3 AM UTC Sundays) for trend analysis - Manual dispatch trigger for ad-hoc benchmark validation AWS S3 integration stores benchmark results for historical trend analysis. Documentation updated in docs/development/ci-cd.md. CONTRIBUTORS.md updated with benchmark workflow separation contribution. ISSUES CLOSED: #9040 # Conflicts: # CONTRIBUTORS.md # Conflicts: # CONTRIBUTORS.md	2026-04-23 14:24:09 +00:00
HAL9000	00d12c844d	[AUTO-TIME-2] Day 103 Timeline Update — Cycle 3 (2026-04-13 ~22:02 UTC) ... Update docs/timeline.md with Cycle 3 milestone status: - ALERT: Scope expanding faster than closing (+110 open in 60 min, only +2 closed) - M2 v3.1.0: 5 open (was 3) — scope expanding in closed milestone - M3 v3.2.0: 802 open (was 776), 269 closed — 25.1% completion - M4 v3.3.0: 157 open (was 148), 109 closed — 41.0% completion - M5 v3.4.0: 242 open (was 233), 139 closed — 36.5% completion - M6 v3.5.0: 1052 open (was 1032), 212 closed — 16.8% completion - M7 v3.6.0: 314 open (was 296), 152 closed — 32.6% completion - M8 v3.7.0: 574 open (was 548), 427 closed — 42.6% completion Added scope expansion alert section and Cycle 3 schedule adherence entries.	2026-04-21 20:32:34 +00:00
CoreRasurae	e19af527e6	revert 4e86ffe596 ... revert docs: document LLM provider fallback behavior (Anthropic Sonnet fallback) [AUTO-DOCS-7]	2026-04-21 19:44:48 +00:00
HAL9000	4e86ffe596	docs: document LLM provider fallback behavior (Anthropic Sonnet fallback) [AUTO-DOCS-7]	2026-04-21 17:26:19 +00:00
HAL9000	1f95ea0c2a	Update timeline: milestone status for 2026-04-19	2026-04-19 04:00:21 +00:00
HAL9000	89baa0a525	Update timeline: milestone status for 2026-04-19	2026-04-19 03:59:35 +00:00
CoreRasurae	0c5b140d29	fix(database): include alembic files in package distribution ... Move alembic configuration and migration files from repository root into the Python package structure to ensure they are included in the wheel distribution. This fix resolves the FileNotFoundError when running `agents init` in Docker containers or any environment using the built wheel distribution. Changes: - Move alembic/ directory from repo root to src/cleveragents/infrastructure/database/migrations/ - Move alembic.ini to the same new location and update script_location setting - Update MigrationRunner._find_alembic_ini() to search from the new canonical location within the package - Update create_template_db.py to point to the new alembic.ini location - Update documentation references to reflect new migration file locations - Create __init__.py for migrations package - The env.py file is imported when running tests that verify all modules can be imported without errors. However, context.config is only available when alembic is actually running migrations, not during normal module imports. This caused an AttributeError when the test tried to import the migrations.env module. - Fix by using getattr() with a default value to safely access context.config, and guard all code that uses config with None checks. This allows the module to be safely imported while still functioning correctly during migrations. Testing: - Verified MigrationRunner can locate alembic.ini in new location - Tested agents init succeeds in creating project with database - Template database creation works correctly - All migration tests should pass without changes Alembic files now follow standard Python packaging conventions, making them automatically included in wheel distributions without special configuration. ISSUES CLOSED: #4180	2026-04-17 17:40:00 +00:00
HAL9000	835bc580e2	spec: document JSON-RPC 2.0 A2A wire format (AUTO-ARCH-8) ... Updates the A2A Protocol section to reflect the rename of A2aRequest/ A2aResponse fields to standard JSON-RPC 2.0 names (method, id, result, error). Documents A2aVersionNegotiator for backward compatibility. Closes #8787	2026-04-15 08:44:55 +00:00
HAL9000	0d6b197504	docs(timeline): update schedule adherence Day 104 (2026-04-14) [AUTO-TIME-1]	2026-04-14 17:51:15 +00:00
HAL9000	510cb03d99	docs(spec): add v3.8.0 Server Implementation milestone plan and update status table (#7701) ... Co-authored-by: CleverThis <hal9000@cleverthis.com> Co-committed-by: CleverThis <hal9000@cleverthis.com>	2026-04-14 16:46:31 +00:00
HAL9000	df863f169b	docs(api): add ACMS/UKO API reference and update nav ... Add comprehensive API documentation for the cleveragents.acms package, covering the four-layer UKO ontology hierarchy (Layer 0-3), all public types (VocabularyRegistry, ProvenanceInfo, UKOClass, UKOProperty, UKOVocabulary, Layer2Dependency, ParadigmVocabulary), detail level maps (DetailLevelMapBuilder, build_detail_level_map, build_effective_map, resolve_detail_level), and all Layer 3 language vocabulary types for Python, TypeScript, Rust, and Java. - Add docs/api/acms.md with full API reference and usage example - Update docs/api/index.md to include ACMS/UKO in the module index - Update mkdocs.yml nav to include the new ACMS/UKO page - Update CHANGELOG.md [Unreleased] with the documentation addition	2026-04-14 15:45:11 +00:00
CleverAgents Bot	9db348e5f6	docs(timeline): update schedule adherence Day 102 (2026-04-12)	2026-04-14 14:56:10 +00:00
HAL9000	6559a0e9df	docs: integrate docs-writer automation tracking workflows ... - document docs-writer responsibilities and automation tracking requirements\n- enforce automation tracking label validation and clean coverage regression tags\n\nISSUES CLOSED: #7616 # Conflicts: # CHANGELOG.md # docs/development/automation-tracking.md # docs/development/docs-writer.md # mkdocs.yml	2026-04-14 14:11:47 +00:00
clever-agent	c5820266fd	Build: improced merge agent logic to ensure faster and more effective merging into master	2026-04-13 15:30:00 -04:00
HAL9000	978849412d	docs(reference): align A2A facade API with implementation ... Fixes docs/reference/a2a.md Local Facade section. Issues #6620 and #6624. Fixes #6620 Fixes #6624 Automatically merged by PR Merge Pool Supervisor [AUTO-PRMRG-SUP] --- **Automated by CleverAgents Bot** Supervisor: PR Merge | Agent: pr-merge-pool-supervisor Co-authored-by: CleverThis <hal9000@cleverthis.com> Co-committed-by: CleverThis <hal9000@cleverthis.com>	2026-04-13 08:10:03 +00:00
clever-agent	56a430d31f	refactor(agents): rename backlog-grooming to grooming, fix tier selector dispatch ... Renamed backlog-grooming-pool-supervisor to grooming-pool-supervisor and backlog-grooming-worker to grooming-worker. The grooming agents now analyze all open issues AND pull requests (not just the backlog). Workers perform a full 10-point quality analysis on a single item instead of processing batches. PRs with unaddressed reviews are prioritized. PR labels are synced from linked issues. Workers post [GROOMED] markers for tracking. Fixed critical issue: implementation-pool-supervisor now correctly dispatches workers through tier selectors (tier-haiku/codex/sonnet/opus) instead of launching implementation-worker directly, ensuring the escalation model actually sets the correct model tier. Added implementation-worker to all four tier selector task permissions. Updated session tags from AUTO-BLOG to AUTO-GROOM. Updated specification sections 4.2.1, 5.5, 5.5.1, 9.7, and architecture diagram. ISSUES CLOSED: n/a	2026-04-12 22:33:40 -04:00
HAL9000	a3094dea2b	docs(spec): clarify path containment, datetime, and plugin security contracts ... Three implementation contracts clarified in response to security/correctness bugs surfaced by the bug hunt pool: 1. Path containment: Sandbox path validation MUST use Path.is_relative_to() not string prefix comparison. String prefix allows /tmp/sandboxmalicious to pass a /tmp/sandbox root check. Canonical implementation provided. 2. Datetime handling: All stored ISO timestamp comparisons MUST parse back to timezone-aware datetime objects before comparing. String comparison of ISO timestamps is incorrect when timezone offsets differ in format. Canonical parse_utc_ts() pattern provided. 3. Plugin protocol validation: Protocol compliance MUST be checked structurally via issubclass() — never by instantiating the plugin class. Instantiation runs __init__ side effects before the plugin is approved. These are minor clarifications (implementation contracts, not architectural changes) added to the existing Security and Extensibility sections. Refs: BUG-HUNT issues #7336 (path traversal), #7341 (datetime comparison), #7331 (plugin instantiation)	2026-04-13 00:44:44 +00:00
clever-agent	8692bb46e5	build: Refactored agent definitions to be simpler and less contention	2026-04-12 19:24:50 -04:00
HAL9000	48532de1cd	docs: add context hydration and git worktree sandbox module docs ... - Add docs/modules/context-hydration.md: documents the ACMS context hydration pipeline (context_tier_hydrator) that fixes the empty ContextTierService bug (#1028). Covers hydrate_tiers_from_project, hydrate_tiers_for_plan, file listing strategies, limits, and fragment metadata. - Add docs/modules/git-worktree-sandbox.md: documents the GitWorktreeSandbox class that isolates plan apply changes in a dedicated git branch/worktree and merges back on commit (#4454). Covers full lifecycle, error types, branch naming, and fallback for non-git projects. - Update docs/architecture.md: add Git Worktree Sandbox Apply section and extend ACMS section with context hydration note. - Update mkdocs.yml: add both new module pages to the Modules nav. ISSUES CLOSED: #6841	2026-04-12 16:42:19 +00:00
clever-agent	b89b781881	docs(spec): add Section 22 — Division of Responsibilities and Redundancy Model ... Add comprehensive responsibility-first analysis of the entire agent system covering 144 named responsibilities (R-01 through R-144) organized into 8 categories with 29 sub-categories and complete bidirectional cross-references. Key additions: - Section 22.0: Categorized Responsibility Index with navigation guide - Section 7.9: Universal Supervisor Responsibilities (13 shared baseline) - Section 22.145: Redundancy Analysis Summary with depth distribution, highest-redundancy items, most cross-referenced agents, and 5 named redundancy patterns - 30 agent back-reference tables covering ~50 individual agents - Category introductions explaining scope and significance - 6th foundational principle (Defense-in-Depth) added to Section 1.1 Categories: A (Development Lifecycle, 50 items), B (Quality Assurance), C (Ticket Hygiene), D (Architecture), E (Operational Health), F (Human Interaction), G (Strategic Governance), H (Project Standards). ISSUES CLOSED: N/A	2026-04-11 23:03:56 -04:00
HAL9000	157b0d6b8c	docs(timeline): update schedule adherence Day 100 (2026-04-10) ... Refresh Day 100 entries using Forgejo telemetry across both cycle snapshots to capture scope expansion, milestone progress, and active session data.\n\n- Update today marker and Gantt update log for Day 100\n- Capture scope expansion metrics and milestone completion percentages\n- Refresh risk register, status summary, and track/milestone forecasts\n- Append Day 100 cycle-2 schedule adherence tables for teams and milestones\n- Note infrastructure changes (review requirement, supervisor additions)\n\nISSUES CLOSED: #6975	2026-04-11 02:52:50 +00:00
HAL9000	c76433f756	docs(tracking): document automation-tracking-manager centralization	2026-04-11 00:40:19 +00:00
HAL9000	39b6fb3fa8	docs: harden backup script example	2026-04-10 23:37:56 +00:00
HAL9000	6523034cb0	docs: add actor context management showcase (remove, export, import) ... Document the CLI-based lifecycle for removing, exporting, and importing named contexts, including JSON import limitations and scripting examples. ISSUES CLOSED: #4409	2026-04-10 23:37:56 +00:00