@jaguilar87/gaia 5.0.8 → 5.0.9

package/dist/gaia-ops/hooks/user_prompt_submit.py

@@ -194,6 +194,26 @@ if __name__ == "__main__":
             else:
                 logger.info("Could not extract user prompt from stdin, skipping routing")
 
+            # Per-turn VERIFIED pending approvals. Lets the orchestrator present
+            # a pending approval for consent directly from injected context,
+            # WITHOUT dispatching a subagent to derive/verify it (that dispatch's
+            # SubagentStop caused a pending-revocation bug). Emits "" when there
+            # are no verified pendings, so a turn with nothing pending injects
+            # nothing -- this is what keeps the per-turn injection quiet, unlike
+            # the one-shot SessionStart summary it deliberately does not re-emit.
+            try:
+                from modules.session.session_manifest import (
+                    build_per_turn_pending_approvals_block,
+                )
+                pending_block = build_per_turn_pending_approvals_block()
+                if pending_block:
+                    context_parts.append(pending_block)
+            except Exception as _pa_exc:
+                logger.debug(
+                    "per-turn pending approvals injection failed (non-fatal): %s",
+                    _pa_exc,
+                )
+
         additional_context = "\n\n".join(context_parts)
         logger.info("Context injected: %s mode (%d chars)", mode, len(additional_context))
 

package/dist/gaia-ops/skills/agent-approval-protocol/SKILL.md

@@ -14,6 +14,20 @@ through the hook layer, to the orchestrator when a T3 command is blocked: the
 the status and event vocabularies, and how to confirm a grant is active. The
 tables below are the canonical schema -- relay them verbatim, do not author them.
 
+The orchestrator presents this contract to the user from a **trusted source**,
+never by dispatching a subagent to verify or derive it (it has no shell). The
+primary source is the per-turn `[PENDING-APPROVALS-VERIFIED]` block injected at
+`UserPromptSubmit` (`build_verified_pending_approvals` in
+`hooks/modules/session/session_manifest.py`), which carries every pending that
+has survived >= 1 turn, each already DB-read and fingerprint-verified
+(`verified: true`). For a pending emitted in the current turn -- not yet in the
+block -- the fallback is the subagent's relayed `approval_request`. The
+**integrity boundary is grant activation**, not presentation:
+`verify_fingerprint` (`gaia/approvals/chain.py`) runs when the user selects the
+Approve label, so a tampered payload fails to form a grant regardless of how it
+was presented. See `Skill('orchestrator-present-approval')` for the presentation
+discipline.
+
 For the universal response envelope (`plan_status` states, `evidence_report`),
 see `agent-protocol`. For the deep mechanics -- fingerprint canonicalization,
 the hash chain, grant activation, reading a granted approval from Python -- see
@@ -27,10 +41,12 @@ For a **singular** T3 approval (the hook-block path),
 verbatim. For a **plan-first `COMMAND_SET`** the id is instead **content-derived**
 by `store.derive_command_set_id()`: `P-<first 32 hex of
 sha256(canonical(command strings))>`. The two share the `P-` prefix and 32-hex
-length but differ in origin -- the command_set id is deterministic so the
-orchestrator reproduces it from the command_set (via `gaia approvals derive-id`)
-with no DB search; the singular id is random because the subagent relays it
-directly. The `P-` prefix is mandatory in both cases: without it the PostToolUse
+length but differ in origin -- the command_set id is deterministic (minted at
+SubagentStop intake), and once the pending has survived a turn the orchestrator
+reads that id directly from the injected `[PENDING-APPROVALS-VERIFIED]` block
+(no derive-dispatch, no DB search); the singular id is random and the subagent
+relays it directly for the same-turn case. The `P-` prefix is mandatory in both
+cases: without it the PostToolUse
 hook cannot do targeted grant activation. The first 8 hex chars after `P-` are
 the nonce prefix shown in option labels: `[P-b1bdfbb0]`.
 
@@ -106,9 +122,13 @@ whose command never ran, or that ran through the redirect-sanitized path.
 - `SHOWN` precedes `APPROVED`; the activation path writes them together.
 - `approval_events` is append-only -- the `bu_approval_events_immutable` and
   `bd_approval_events_immutable` triggers `RAISE(ABORT)` on UPDATE/DELETE.
-- The orchestrator MUST re-verify a relayed payload via
-  `chain.verify_fingerprint(approval_id, payload_json, con)` before presenting;
-  a mismatch raises `ChainTamperError` and the approval aborts.
+- The payload's integrity is enforced at grant **activation**, not at
+  presentation: `chain.verify_fingerprint(approval_id, payload_json, con)` runs
+  when the user selects the Approve label, and a mismatch raises
+  `ChainTamperError` so the grant never forms. The orchestrator presents from a
+  trusted source (the injected `[PENDING-APPROVALS-VERIFIED]` block, already
+  fingerprint-verified by the hook; or a same-turn relayed `approval_request`)
+  and never dispatches a subagent to verify or derive the approval.
 
 For the grant activation walk-through, fingerprint internals, reading a granted
 approval from Python, and the retry-blocked-again diagnosis, see `reference.md`.

package/dist/gaia-ops/skills/agent-approval-protocol/reference.md

@@ -12,12 +12,17 @@ canonical string. `store.insert_requested()` stores both the canonical JSON
 (`payload_json`) and the hex fingerprint on the `approvals` row and on the
 `REQUESTED` event.
 
-The orchestrator MUST re-verify via
-`chain.verify_fingerprint(approval_id, payload_json, con)` before presenting.
-That function re-parses and re-canonicalizes the relayed `payload_json`,
-recomputes the fingerprint, and compares it against the fingerprint stored on
-the `REQUESTED` event. A mismatch raises `ChainTamperError` and the approval
-aborts -- this is a security boundary, not a recoverable UX issue.
+The fingerprint is verified at grant **activation**, not at presentation.
+`chain.verify_fingerprint(approval_id, payload_json, con)` re-parses and
+re-canonicalizes the payload, recomputes the fingerprint, and compares it
+against the fingerprint stored on the `REQUESTED` event; a mismatch raises
+`ChainTamperError` and the grant never forms -- a security boundary, not a
+recoverable UX issue. The per-turn `[PENDING-APPROVALS-VERIFIED]` builder
+(`build_verified_pending_approvals`) applies the same check when assembling the
+injected block, so only fingerprint-clean pendings reach the orchestrator marked
+`verified: true`. The orchestrator therefore presents from that already-verified
+block (or a same-turn relayed `approval_request`) and never dispatches to verify
+the payload itself.
 
 ## Hash chain
 

package/dist/gaia-ops/skills/gaia-patterns/reference.md

@@ -109,7 +109,7 @@ The package ships a single `gaia` binary (`bin/gaia.js`) that dispatches to Pyth
 | `gaia memory` | `bin/cli/memory.py` | Episodic memory: FTS5 search, show episode, health checks |
 | `gaia metrics` | `bin/cli/metrics.py` | Usage analytics: tier classification, agent invocations, anomaly counters |
 | `gaia paths` | `bin/cli/paths.py` | Inspect canonical Gaia storage paths (DB, plugin root, workspace) |
-| `gaia plans` | `bin/cli/plans.py` | List and display briefs/plans with status info |
+| `gaia plan` | `bin/cli/plan.py` | Manage plans (one per brief, DB-canonical): save, show, list, status |
 | `gaia workspace` | `bin/cli/workspace.py` | Workspace identity and consolidate operations |
 | `gaia scan` | `bin/cli/scan.py` | In-process project scan: detect stack, sync results to ~/.gaia/gaia.db (DB-canonical; no project-context.json written) |
 | `gaia status` | `bin/cli/status.py` | Quick installation snapshot: version, mode, DB path, registered workspace, last scan |
@@ -289,7 +289,7 @@ After `npm install -g @jaguilar87/gaia` (or via the local symlink) the dispatche
 | `gaia history` | Session history viewer | Debugging past sessions |
 | `gaia memory` | Episodic memory inspect/search | Recall past episodes, memory health |
 | `gaia approvals` | List/accept/reject pending T3 approvals | Approval workflow |
-| `gaia brief` / `gaia plans` | Brief and plan management against the DB substrate | Planning, brief lifecycle |
+| `gaia brief` / `gaia plan` | Brief and plan management against the DB substrate | Planning, brief lifecycle |
 | `gaia context` | Display and refresh project context | Audit context state |
 | `gaia paths` | Print resolved storage paths | Path debugging |
 | `gaia workspace` | Workspace identity and consolidate operations | Multi-workspace setups |

package/dist/gaia-ops/skills/orchestrator-present-approval/SKILL.md

@@ -15,11 +15,13 @@ names the specific action. No exceptions. No brevity shortcuts.
 ```
 
 `orchestrator-present-approval` is the discipline the orchestrator follows when
-a subagent emits `APPROVAL_REQUEST` with an `approval_id`: relay the
-`sealed_payload` into AskUserQuestion -- fingerprint check, mandatory fields in
-the question, mandatory nonce in the option label. For the subagent side that
-produced the payload see `subagent-request-approval`; for the data contract
-itself see `agent-approval-protocol`.
+an approval needs the user's consent: relay the sealed fields into
+AskUserQuestion -- mandatory fields in the question, mandatory nonce in the
+option label. The orchestrator has no shell, so it never dispatches a subagent
+to derive or verify an approval; it presents from a trusted source it already
+holds. For the subagent side that produced the payload see
+`subagent-request-approval`; for the data contract itself see
+`agent-approval-protocol`.
 
 ## Mental Model
 
@@ -27,25 +29,53 @@ The orchestrator sits between the subagent and the user. The user cannot make
 an informed decision on data they have not seen -- a summary, a reference to
 "the plan above", or an offer to show details on request all push the decision
 without the data needed to decide. The job is **verbatim relay, not
-re-authoring**: rewriting any of the 7 sealed fields breaks the fingerprint and
-`verify_fingerprint` (`gaia/approvals/chain.py`) raises `ChainTamperError`.
-
-## Step 0 -- Verify the approval against the DB (mandatory before SHOWN)
-
-A subagent's reported `approval_id` is an unverified claim, not a fact. The agent runs in its own context and can relay an id that is stale, from another session, or simply wrong -- and a stale id presented as a fresh block walks the user into consenting to nothing real (or to a grant that no longer exists). The DB is the source of truth; the agent's report is a pointer into it that you must resolve, never the authority itself.
-
-So before AskUserQuestion, two checks against the DB, in order:
-
-1. **The approval exists, is fresh, and is from the current session.** Query `gaia approvals pending --session "$CLAUDE_SESSION_ID"` (or `--json` for parsing). The reported `approval_id` MUST appear in that result. If it appears only under `--all-sessions` but not the current session, it is leakage from another session (a test session such as `e2e-sim`, a prior run) -- **do not present**. If it does not appear at all, it does not exist or was already consumed/rejected -- **do not present**. Freshness is the `created_at` of the pending row plus its presence as still-`pending`; an id the agent reports that is not currently pending in *this* session is not a fresh block, whatever the agent says.
-2. **The payload is untampered.** Call `verify_fingerprint(approval_id, payload_json, con) -> bool` from `gaia/approvals/chain.py`. It raises `ChainTamperError` if the payload was modified between subagent emission and your relay (security boundary, do not present), and `ValueError` if no REQUESTED event exists for this `approval_id`. Either case: **do not present**, report the failure, stop.
-
-**For a `command_set` (plan-first batch) the agent does not know the id at all -- so you DERIVE it deterministically, you do not search the DB.** The hook mints the `approval_id` at SubagentStop (`_intake_command_set_pending` -- see Rule 3) from the **content** of the command_set, not from a uuid4. The id is `P-<first 32 hex of sha256(canonical(command list))>` (`derive_command_set_id` in `gaia/approvals/store.py`). Because it is content-derived, you reproduce the EXACT minted id from the `command_set` you already hold in the contract -- with **no `gaia approvals pending --session` search**. Run:
-
-```
-gaia approvals derive-id --commands-json '<the command_set from the contract>'
-```
-
-It applies the SAME mutative filter the intake used and prints the `P-...` id (the same function `derive_command_set_id` the hook minted with). This closes the cross-session miss: the SubagentStop output never reaches the parent (Claude Code issue #5812), so a random id could not be recovered across sessions -- a content-derived one needs no recovery at all. Having derived the id, run Step 0's existence/fingerprint checks against it exactly as for a singular id (the row is now findable by that exact id). The shape: the DB mints content-derived, the orchestrator re-derives, the agent never owns the id and no search is needed.
+re-authoring**: rewriting any of the sealed fields would change the consent
+surface from what was recorded. Integrity of the payload is enforced at grant
+**activation** (`verify_fingerprint` in `gaia/approvals/chain.py`, called when
+the user selects the Approve label), not at presentation -- so presentation
+itself never needs a verify-dispatch.
+
+## Step 0 -- Present from a trusted source; never dispatch to verify or derive
+
+The orchestrator has no shell. It MUST NOT dispatch a subagent solely to derive
+or verify an approval before presenting -- that dispatch is both unnecessary
+(the integrity check runs at activation, below) and harmful (its SubagentStop
+can sweep the very pending being verified). Instead, present from one of two
+**trusted** sources:
+
+1. **Primary -- the injected `[PENDING-APPROVALS-VERIFIED]` block.** A per-turn
+   hook (`hooks/modules/session/session_manifest.py`) injects, on every
+   `UserPromptSubmit`, every pending that has survived >= 1 turn. Each row in
+   that block has already been DB-read and fingerprint-verified by the hook
+   (`build_verified_pending_approvals` -- only rows whose payload re-canonicalizes
+   to the fingerprint stored on their `REQUESTED` event appear, each marked
+   `verified: true`). **Present directly from this block** -- the fields, the
+   full `approval_id`, and (for batches) the whole `command_set` with its minted
+   id are all there. No DB query, no `derive-id`, no dispatch.
+2. **Fallback -- same-turn relay.** A pending a subagent emits during the
+   CURRENT turn will not be in this turn's block yet: the block is built at
+   `UserPromptSubmit`, before the subagent ran. For that case present from the
+   subagent's relayed `approval_request`. This is justified because the pending
+   was freshly minted in THIS session by a trusted dispatch, AND integrity is
+   enforced at grant **activation** (`verify_fingerprint` fires when the user
+   selects the Approve label), not at presentation. The old pre-presentation
+   verify was redundant belt-and-suspenders; it is removed.
+
+Once the pending survives a turn it appears in the injected block, so the relay
+is only ever needed for the same-turn case.
+
+**For a `command_set` (plan-first batch) you do not derive the id -- you read it
+from the block.** The hook mints the `approval_id` at SubagentStop
+(`_intake_command_set_pending` -- see Rule 3) from the **content** of the
+command_set (`derive_command_set_id` in `gaia/approvals/store.py`,
+`P-<first 32 hex of sha256(canonical(command list))>`). Once that pending has
+survived a turn, the `[PENDING-APPROVALS-VERIFIED]` block carries it with its
+minted `approval_id` and all N commands already attached -- so you read the id
+and the commands straight from the block. **No `gaia approvals derive-id`
+dispatch is needed.** For a command_set emitted in the CURRENT turn (not yet in
+the block), present from the subagent's relayed `approval_request`, which carries
+the same `command_set`; the content-derived id reaches you when the pending
+appears in the next turn's block.
 
 ## Mandatory presentation -- 5 labeled fields + nonce-suffixed label
 
@@ -72,7 +102,13 @@ whose `id` starts with `P-{prefix}`. Without the suffix no grant is created.
 See `template.md` for the canonical layout and `reference.md` -> "GOOD vs BAD
 Examples" for full presentations.
 
-Fields above are extracted from the DB-stored canonical payload (`payload_json` on the REQUESTED row), not from the subagent's relayed `approval_request` — that's why `rollback_hint` is the field name here while the subagent contract uses `rollback`.
+Fields above are extracted from your trusted source. From the injected
+`[PENDING-APPROVALS-VERIFIED]` block (the primary path) they appear under the
+canonical names shown here (`operation`, `exact_content`, `scope`, `risk_level`,
+`rationale`, `rollback_hint`). From a same-turn relayed `approval_request` (the
+fallback) the rollback field arrives under the key `rollback` -- map it to
+ROLLBACK the same way. Either way you copy values verbatim; you do not re-author
+them.
 
 ## Rules
 
@@ -90,7 +126,12 @@ Fields above are extracted from the DB-stored canonical payload (`payload_json`
    `APPROVAL_REQUEST` carrying a `command_set` of >= 2 `{command, rationale}`
    items and **no** `approval_id`, the SubagentStop processor
    (`handoff_persister._intake_command_set_pending`) mints ONE pending
-   `COMMAND_SET` with one `approval_id`. You present that single approval: list
+   `COMMAND_SET` with one content-derived `approval_id`. Once that pending has
+   survived a turn it appears in the injected `[PENDING-APPROVALS-VERIFIED]`
+   block with its minted `approval_id` and all N commands -- **read the id and
+   commands from the block; do not dispatch `gaia approvals derive-id`.** (A
+   command_set emitted in the current turn is presented from the subagent's
+   relayed `approval_request`.) You present that single approval: list
    **all N commands** in the question body, but use **one** Approve label with
    **one** `[P-{nonce8}]` suffix -- one consent covers the whole batch. On
    approval, `activate_db_pending_by_prefix` Step 3b creates a single
@@ -126,5 +167,5 @@ wording, see `reference.md` -> "GOOD vs BAD Examples", "Option Label Patterns",
 | "Similar command, slightly different path -- I'll reuse / wrap it" | Grants match the statement signature byte-for-byte. Any wrapper, redirect, flag, or path drift is a different signature and a fresh re-block. |
 | "The same command emitted a new approval_id" | Grants are single-use and consumed on the first retry. A second run is a new APPROVAL_REQUEST -- approve again. |
 | "I'll set batch_scope to approve many at once" | `batch_scope` is ignored -- but a real batch path exists: a plan-first `command_set` (>= 2 items, no `approval_id`) is intaken into ONE pending `COMMAND_SET`. Present that single approval (N commands shown, one `[P-...]` nonce, one consent), not N separate approvals. |
-| "I can paraphrase a field before relaying" | The fingerprint covers all 7 sealed fields; any modification raises `ChainTamperError` in Step 0 and the presentation is refused. |
-| **"The agent reported an `approval_id`, so it's a real fresh block"** -- trusting a nonce relayed by the subagent | The agent's reported id is an unverified pointer, not a fact. It can be stale or belong to another session -- subagents have presented a STALE nonce from a test session (`e2e-sim`) as if it were a fresh block. Resolve every reported id against `gaia approvals pending --session "$CLAUDE_SESSION_ID"` (Step 0): it must be currently pending in *this* session. Visible only under `--all-sessions`, or absent entirely, means do not present. For `command_set` the hook mints the id and the agent never has one -- you **derive** it deterministically from the command_set via `gaia approvals derive-id` (content-derived, no DB search), then run the same existence/fingerprint checks. |
+| "I can paraphrase a field before relaying" | The fingerprint covers all sealed fields and is checked at grant **activation** (`verify_fingerprint`, when the user selects the Approve label); a paraphrase there raises `ChainTamperError` and the grant never forms. Relay verbatim so activation succeeds. |
+| **"I'll dispatch a subagent to verify or derive the approval before presenting"** | The orchestrator has no shell and must NEVER dispatch to verify or derive an approval. The pending arrives **already verified** in the injected `[PENDING-APPROVALS-VERIFIED]` block (DB-read + fingerprint-checked by the per-turn hook, `verified: true`) -- present from it. For a same-turn pending not yet in the block, present from the subagent's relayed `approval_request`. A verify/derive dispatch is unnecessary (integrity is enforced at activation) and harmful (its SubagentStop can sweep the very pending). For `command_set`, read the minted `approval_id` and all commands from the block -- do not run `gaia approvals derive-id`. |

package/dist/gaia-ops/skills/orchestrator-present-approval/reference.md

@@ -151,6 +151,16 @@ commands** in the question body, with **one** Approve label carrying **one**
 `[P-{nonce8}]` suffix. The user gives one consent; each command then runs on its
 own retry within the 60-minute window. You do NOT issue N separate approvals.
 
+**Reading the batch id and commands -- from the block, not by dispatch.** Once
+the minted `COMMAND_SET` pending has survived a turn, it appears in the injected
+`[PENDING-APPROVALS-VERIFIED]` block with its content-derived `approval_id` and
+all N commands attached (`build_verified_pending_approvals` in
+`hooks/modules/session/session_manifest.py`). Read the id and the commands
+straight from that block -- the orchestrator has no shell and must NOT dispatch
+`gaia approvals derive-id` or any verify command. For a command_set emitted in
+the CURRENT turn (not yet in the block), present from the subagent's relayed
+`approval_request`, which carries the same `command_set`.
+
 ## Grant Activation Mechanics
 
 When the hook blocks a T3 Bash command in subagent context,
@@ -161,9 +171,12 @@ generates a `P-{uuid4_hex}` `approval_id`, fingerprints the payload, inserts an
 message ends with `approval_id: P-{...}` (`build_t3_blocked_denial_message` in
 `hooks/modules/security/approval_messages.py`).
 
-The subagent relays that `approval_id` in its `approval_request`. The
-orchestrator presents via AskUserQuestion with the `[P-xxxxxxxx]` label. When
-the user selects the Approve label, the **ElicitationResult hook**
+The orchestrator presents via AskUserQuestion with the `[P-xxxxxxxx]` label,
+reading the `approval_id` and fields from the injected
+`[PENDING-APPROVALS-VERIFIED]` block (primary) or, for a same-turn pending not
+yet in the block, from the subagent's relayed `approval_request` (fallback). It
+does not dispatch to verify or derive. When the user selects the Approve label,
+the **ElicitationResult hook**
 (`hooks/elicitation_result.py`) fires and calls
 `activate_db_pending_by_prefix()`, which:
 

package/dist/gaia-ops/skills/orchestrator-present-approval/template.md

@@ -1,8 +1,12 @@
 # AskUserQuestion Template
 
 Use this layout verbatim when presenting an approval to the user. Replace
-`{...}` placeholders with values extracted from the subagent's `sealed_payload`
-and `approval_request`. Do not paraphrase, summarize, or omit any field.
+`{...}` placeholders with values read from your trusted source -- the injected
+`[PENDING-APPROVALS-VERIFIED]` block (primary; already DB-read and
+fingerprint-verified by the per-turn hook) or, for a same-turn pending not yet
+in the block, the subagent's relayed `approval_request` (fallback). Never
+dispatch a subagent to derive or verify the approval. Do not paraphrase,
+summarize, or omit any field.
 
 ## Standard Approval (single command)
 
@@ -23,8 +27,9 @@ AskUserQuestion(
 )
 ```
 
-Where `approval_id_prefix8` is the first 8 characters of the `approval_id`
-field from the subagent's `approval_request` (after the `P-` prefix).
+Where `approval_id_prefix8` is the first 8 characters (after the `P-` prefix) of
+the `approval_id` read from the `[PENDING-APPROVALS-VERIFIED]` block, or from the
+subagent's `approval_request` for a same-turn pending.
 
 ## Batch template (COMMAND_SET)
 
@@ -47,4 +52,4 @@ ignored -- the signal is the presence of `command_set` in the contract.
 | SCOPE | `sealed_payload.scope` |
 | RIESGO | `sealed_payload.risk_level` + `sealed_payload.rationale` |
 | ROLLBACK | `sealed_payload.rollback_hint` (null -> "NOT REVERSIBLE") |
-| Option nonce suffix | `approval_request.approval_id` first 8 chars after `P-` |
+| Option nonce suffix | `approval_id` first 8 chars after `P-` (from the `[PENDING-APPROVALS-VERIFIED]` block, or `approval_request.approval_id` for a same-turn pending) |

package/dist/gaia-ops/skills/pending-approvals/SKILL.md

@@ -37,7 +37,7 @@ report "rejected" when nothing actually changed.
 | `gaia approvals list` | DB grants + filesystem pendings | `cmd_list` (mixed) |
 | `gaia approvals reject NONCE` | filesystem only | `reject_pending` in `hooks/modules/security/approval_grants.py` |
 | `gaia approvals reject-all` | filesystem only | loops `reject_pending` |
-| `gaia approvals clean` | filesystem only | `cleanup_expired_grants` |
+| `gaia approvals clean` | DB (cross-session stale pendings) + filesystem | `cmd_clean` in `bin/cli/approvals.py`: calls `store.list_pending(all_sessions=True)`, transitions every pending older than `DEFAULT_PENDING_TTL_MINUTES` (24 h) to `revoked` via `store.revoke()`, then calls `cleanup_expired_grants` for filesystem files |
 
 The practical consequence: `revoke` is the DB-aware single-id verb; `reject` and
 `reject-all` only touch the legacy filesystem queue. If you need to mark a DB
@@ -105,15 +105,19 @@ Offer bulk cleanup when the user says "limpia todos los pendings", "borra los
 pendientes", or when SessionStart surfaces 5+ orphaned pendings the user has
 not engaged with.
 
-- `gaia approvals reject-all` -- bulk reject across the **filesystem** queue.
-  Returns "0 rejected" when the queue is empty.
-- `gaia approvals clean` -- removes expired/stale **filesystem** files.
+- `gaia approvals reject-all` -- bulk soft-reject across the **filesystem** queue.
+  Returns "0 rejected" when the queue is empty. Does not touch DB rows.
+- `gaia approvals clean` -- the first-class cross-session bulk drain for stale
+  DB pendings: `cmd_clean` calls `store.list_pending(all_sessions=True)` and
+  transitions every pending older than 24 h (`DEFAULT_PENDING_TTL_MINUTES`) to
+  `revoked` via `store.revoke()`, then runs `cleanup_expired_grants` to clean
+  expired filesystem grant files. Runs without a T3 prompt (consent-reducing,
+  listed in `CONSENT_REDUCING_SUBCOMMAND_EXCEPTIONS`). Use this when
+  `gaia approvals pending --all-sessions` shows a backlog of stale rows.
 
-There is no first-class bulk-revoke for the DB queue. If `gaia approvals
-pending --all-sessions` shows rows that need clearing, either revoke each by id
-or call `store.revoke()` in a short Python loop. Do not report "bulk cleanup
-done" after `reject-all` if the DB queue still has pending rows -- check
-`gaia approvals pending --all-sessions` to confirm.
+Do not report "bulk cleanup done" after `reject-all` alone -- it only clears
+the filesystem queue. Run `gaia approvals clean` to drain the DB backlog, then
+confirm with `gaia approvals pending --all-sessions`.
 
 Do not offer `reject-all` when there are active same-session pendings the user
 may still want to approve.
@@ -123,8 +127,9 @@ may still want to approve.
 - Approving without showing the exact COMANDO -- the user consents on the
   verbatim string, not a summary. The full presentation discipline lives in
   `orchestrator-present-approval`; this skill does not restate it.
-- Treating `gaia approvals reject-all` as a DB cleanup -- it operates on the
-  filesystem queue only. DB rows survive the call.
+- Treating `gaia approvals reject-all` as a full cleanup -- it operates on the
+  filesystem queue only; DB rows survive the call. Use `gaia approvals clean`
+  to drain the DB backlog.
 - Reporting "rechazado" without verifying the store -- `revoke` returns
   `not_found` for filesystem-only pendings; the inverse happens for `reject` on
   DB rows. Pick the verb by store, or be ready to fall back.

package/dist/gaia-ops/skills/subagent-request-approval/SKILL.md

@@ -44,9 +44,20 @@ Add an `approval_request` to your `agent_contract_handoff`, copying the hook's f
 
 The `approval_request` schema is canonical in `agent-approval-protocol` — relay the sealed_payload fields verbatim (the hook built them) and add `verification` (your own success criteria) + `approval_id` (the literal token from the denial). See `agent-approval-protocol/SKILL.md` for the full field list and types.
 
-The `approval_id` is the `P-{...}` token the orchestrator uses to find the
-`REQUESTED` row in the DB and validate the fingerprint. Fields written only in
-prose are invisible to the presentation -- the user would approve blind.
+The `approval_id` is the `P-{...}` token tying this request to its `REQUESTED`
+row in the DB. Fields written only in prose are invisible to the presentation --
+the user would approve blind.
+
+**What your relay is for: same-turn immediacy.** Your `approval_request` is the
+orchestrator's source only for the CURRENT turn. The orchestrator's primary
+source is the per-turn `[PENDING-APPROVALS-VERIFIED]` block injected at
+`UserPromptSubmit`, which carries every pending that has survived >= 1 turn,
+already DB-read and fingerprint-verified. But that block was built before you
+ran this turn, so a pending you mint now is not in it yet -- the orchestrator
+presents it from your relay until the next turn's block picks it up. You emit the
+same fields either way; nothing on your side changes. The orchestrator never
+dispatches a subagent to verify or derive your request -- integrity is enforced
+at grant activation, not at presentation.
 
 ## Non-negotiable rules
 
@@ -105,9 +116,12 @@ your side. What changed underneath: the minted `approval_id` is now
 (`derive_command_set_id` -> `P-<first 32 hex of sha256(canonical commands)>`),
 not a random uuid4. You do not compute or emit it (you cannot hash reliably, and
 you have nothing to attempt yet); the value is purely internal. The reason it
-matters: the orchestrator reproduces that exact id from the `command_set` you
-emitted (via `gaia approvals derive-id`), with no DB search and no cross-session
-miss. Your contract stays the same -- `command_set` of `{command, rationale}`
+matters: the content-derived id is reproducible without a uuid4 that could be
+lost across sessions. Once the minted pending has survived a turn, the
+orchestrator reads it -- with all N commands -- straight from the injected
+`[PENDING-APPROVALS-VERIFIED]` block (no DB search, no derive-dispatch); for the
+turn you mint it in, the orchestrator presents from the `command_set` in your
+relay. Your contract stays the same -- `command_set` of `{command, rationale}`
 items, no `approval_id`.
 
 On the user's approval, that one pending activates into a single `COMMAND_SET`

package/dist/gaia-ops/skills/subagent-request-approval/reference.md

@@ -16,8 +16,12 @@ payload from the intercepted command and calls
 3. writes the `REQUESTED` event to the DB.
 
 The block message you receive (`[T3_BLOCKED] ...`) ends with `approval_id: P-{...}`.
-You relay that token plus the operation details; the orchestrator re-derives the
-fingerprint from the DB row.
+You relay that token plus the operation details. For the current turn the
+orchestrator presents from your relay; once the pending survives a turn it
+appears in the per-turn `[PENDING-APPROVALS-VERIFIED]` block, already
+fingerprint-verified by the hook. Payload integrity is enforced at grant
+activation (`verify_fingerprint`), so the orchestrator never dispatches to
+verify or derive your request.
 
 Source: `bash_validator._build_sealed_payload()`, the subagent block path in
 `bash_validator._validate_single_command()`; `gaia/approvals/store.py`
@@ -99,12 +103,14 @@ singular hook-block path (which mints `P-{uuid4hex}`), the intake derives the id
 from the command_set content via `gaia.approvals.store.derive_command_set_id()`:
 `P-<first 32 hex of sha256(canonical(post-filter command strings))>`. It then
 passes that id to `insert_requested(..., approval_id=...)` as the pending row id.
-The point is reproducibility without a DB lookup: the orchestrator holds the
-same `command_set` (you emitted it in the contract) and reproduces the EXACT id
-with `gaia approvals derive-id`, which applies the same mutative filter and the
-same canonicalization (`chain.canonical_payload`). This closes the cross-session
-miss -- a uuid4 minted at SubagentStop could not be recovered by the parent
-(Claude Code #5812), but a content-derived id needs no recovery. The id is
+The point is reproducibility without a fragile uuid4: a uuid4 minted at
+SubagentStop could not be recovered by the parent (Claude Code #5812), but a
+content-derived id needs no recovery -- the same canonicalization
+(`chain.canonical_payload`) and mutative filter always yield the same id. Once
+the minted pending survives a turn, the orchestrator reads that id (and all N
+commands) straight from the injected `[PENDING-APPROVALS-VERIFIED]` block -- no
+DB lookup and no `gaia approvals derive-id` dispatch; for the mint turn it
+presents from the `command_set` in your relay. The id is
 **order-sensitive** (the consume side matches positionally) and **content-only**
 (rationale/session/agent are not folded in, so both sides agree from the command
 list alone). Idempotency follows the existing fingerprint dedup: two identical
@@ -154,15 +160,17 @@ single-use within the 60-minute window.
 Always `plan_status: "APPROVAL_REQUEST"`. The presence of `approval_id` tells the
 orchestrator which path:
 
-- **With `approval_id`** -- the hook blocked a single command; orchestrator
-  validates the fingerprint and activates the single-use semantic grant on user
-  approval.
+- **With `approval_id`** -- the hook blocked a single command; the orchestrator
+  presents from your relay (current turn) or the injected
+  `[PENDING-APPROVALS-VERIFIED]` block (later turns), and the single-use semantic
+  grant activates on user approval (fingerprint checked at activation).
 - **Without `approval_id`, with a `command_set` of >= 2 items** -- plan-first
   batch. The SubagentStop intake processor mints ONE pending `COMMAND_SET` with a
-  **content-derived** id (`derive_command_set_id`), and the orchestrator
-  reproduces that exact id from the command_set via `gaia approvals derive-id`
-  (no DB search) before presenting the single approval (N commands, one nonce).
-  See "Batch / COMMAND_SET -- wired" above.
+  **content-derived** id (`derive_command_set_id`). The orchestrator reads that
+  id and the N commands from the injected `[PENDING-APPROVALS-VERIFIED]` block
+  (no derive-dispatch), or, for the mint turn, from the `command_set` in your
+  relay, then presents the single approval (N commands, one nonce). See
+  "Batch / COMMAND_SET -- wired" above.
 - **Without `approval_id` and without a multi-item `command_set`** -- plan-first
   single (you are presenting one T3 plan before attempting); the orchestrator
   gates on user consent before any execution.

package/dist/gaia-ops/tools/migration/README.md

@@ -19,7 +19,12 @@ desde el filesystem hacia `~/.gaia/gaia.db`.
 | 01 | Episodes | `.claude/project-context/episodic-memory/episodes.jsonl` | `episodes` (+`episodes_fts`) |
 | 02 | Memory | `~/.claude/projects/-home-jorge-ws-me/memory/*.md` | `memory` (+`memory_fts`) |
 | 03 | Context contracts | `.claude/project-context/project-context.json` | `context_contracts` |
-| 04 | Harness events | `.claude/events/events.jsonl` | `harness_events` |
+| 04 | Harness events | ~~`.claude/events/events.jsonl`~~ (ELIMINADO) | `harness_events` |
+
+> **Dominio 04 completado y eliminado.** `events.jsonl` y su archivo `.lock` fueron
+> retirados. El hook `event_writer` escribe directamente a `harness_events` en la DB.
+> El script `migrate_04_harness_events.py` y su wrapper `.sh` fueron borrados una vez
+> completada la absorción. Los datos vivos se leen desde `harness_events` en `~/.gaia/gaia.db`.
 
 Cada dominio tiene 2 archivos:
 
@@ -37,8 +42,8 @@ bootstrap.sh                             # crea/inicializa ~/.gaia/gaia.db con s
 ./migrate_01_episodes.sh                 # ~50-80 MB de SQL, batch 80
 ./migrate_02_memory.sh                   # 28 .md (MEMORY.md excluido)
 ./migrate_03_context_contracts.sh        # 12 secciones
-./migrate_04_harness_events.sh           # ~5-10 MB de SQL, batch 200
-./validate.sh                            # 5 aserciones read-only
+# migrate_04_harness_events.sh ELIMINADO — dominio 04 completado; eventos en DB-canonical
+./validate.sh                            # aserciones read-only (V4 eliminada junto con 04)
 ```
 
 Cada script imprime `[migrate_NN] OK` al terminar.
@@ -50,14 +55,7 @@ Cada script imprime `[migrate_NN] OK` al terminar.
 | 01 episodes | `INSERT OR IGNORE` (PK = `episode_id`) | sí |
 | 02 memory | `INSERT OR IGNORE` (PK = `(project, name)`) | sí |
 | 03 context_contracts | `INSERT OR IGNORE` (PK = `(project, section_name)`) | sí |
-| 04 harness_events | `INSERT` simple (sin PK natural) | **no — duplica filas** |
-
-Para re-ejecutar 04 limpiamente:
-
-```
-sqlite3 ~/.gaia/gaia.db "DELETE FROM harness_events WHERE project='me';"
-./migrate_04_harness_events.sh
-```
+| 04 harness_events | N/A — tool eliminado; escritura vía `event_writer` DB-direct | N/A |
 
 ## Validación
 
@@ -68,7 +66,7 @@ sqlite3 ~/.gaia/gaia.db "DELETE FROM harness_events WHERE project='me';"
 | V1 | `COUNT(*) FROM episodes` == líneas no vacías de `episodes.jsonl` |
 | V2 | `COUNT(*) FROM memory` == archivos `.md` (excluyendo `MEMORY.md`) |
 | V3 | `COUNT(*) FROM context_contracts` == 12 |
-| V4 | `COUNT(*) FROM harness_events` == líneas no vacías de `events.jsonl` |
+| ~~V4~~ | ~~`COUNT(*) FROM harness_events` == líneas no vacías de `events.jsonl`~~ — eliminado junto con el dominio 04 |
 | V5 | `COUNT(*) FROM episodes_fts` == `COUNT(*) FROM episodes` (FTS sync) |
 
 Exit code: 0 si todas pasan, 1 si alguna falla.