@adamchanadam/agent-handoff-kit 0.3.42 → 0.3.43
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.en.md +81 -0
- package/README.md +5 -3
- package/bin/agent-handoff-kit.mjs +45 -12
- package/bin/installed-file-contract.mjs +74 -74
- package/bin/migration-baselines/official-origin-catalog.json +10039 -10039
- package/bin/official-origin-catalog.mjs +74 -74
- package/bin/semantic-candidate.mjs +594 -594
- package/bin/upgrade-inventory.mjs +587 -587
- package/bin/user-rules-router.mjs +461 -461
- package/package.json +20 -20
- package/packs/closeout.md +15 -15
- package/packs/communication.md +8 -8
- package/packs/onboarding.md +1 -1
- package/runtime-core/AGENTS.core.md +8 -8
- package/runtime-core/PROJECT_INDEX.md +1 -1
- package/runtime-core/SESSION_HANDOFF.md +12 -12
- package/runtime-core/START_NEXT_SESSION_PROMPT.txt +1 -1
- package/runtime-core/USER_RULES.md +30 -30
- package/runtime-core/USER_RULES_ENTRY.md +7 -7
package/package.json
CHANGED
|
@@ -1,20 +1,20 @@
|
|
|
1
|
-
{
|
|
2
|
-
"name": "@adamchanadam/agent-handoff-kit",
|
|
3
|
-
"version": "0.3.
|
|
4
|
-
"description": "Lightweight agent harness for project memory, handoff, and multi-session continuity.",
|
|
5
|
-
"type": "module",
|
|
6
|
-
"bin": {
|
|
7
|
-
"agent-handoff-kit": "bin/agent-handoff-kit.mjs"
|
|
8
|
-
},
|
|
9
|
-
"files": [
|
|
10
|
-
"bin/",
|
|
11
|
-
"runtime-core/",
|
|
12
|
-
"packs/",
|
|
13
|
-
"README.md",
|
|
14
|
-
"LICENSE"
|
|
15
|
-
],
|
|
16
|
-
"engines": {
|
|
17
|
-
"node": ">=18"
|
|
18
|
-
},
|
|
19
|
-
"license": "MIT"
|
|
20
|
-
}
|
|
1
|
+
{
|
|
2
|
+
"name": "@adamchanadam/agent-handoff-kit",
|
|
3
|
+
"version": "0.3.43",
|
|
4
|
+
"description": "Lightweight agent harness for project memory, handoff, and multi-session continuity.",
|
|
5
|
+
"type": "module",
|
|
6
|
+
"bin": {
|
|
7
|
+
"agent-handoff-kit": "bin/agent-handoff-kit.mjs"
|
|
8
|
+
},
|
|
9
|
+
"files": [
|
|
10
|
+
"bin/",
|
|
11
|
+
"runtime-core/",
|
|
12
|
+
"packs/",
|
|
13
|
+
"README.md",
|
|
14
|
+
"LICENSE"
|
|
15
|
+
],
|
|
16
|
+
"engines": {
|
|
17
|
+
"node": ">=18"
|
|
18
|
+
},
|
|
19
|
+
"license": "MIT"
|
|
20
|
+
}
|
package/packs/closeout.md
CHANGED
|
@@ -28,7 +28,7 @@ Do not copy the full opening message into `dev/SESSION_LOG.md` or any third curr
|
|
|
28
28
|
2. Reconcile lifecycle state across `Completed This Session`, `Validation / QC`, `Next Priorities`, `Risks / Blockers`, and `Next Session Opening Message`. Completed or verified work cannot remain unresolved unless explicitly reclassified as monitor-only, follow-up scope, blocked, or reopened with its missing evidence or trigger.
|
|
29
29
|
The bundled doctor is a mechanical floor for obvious overlap and unresolved fields; it cannot prove that renamed or paraphrased work is semantically consistent. Read all five sections as a whole before marking the lifecycle field resolved. For governance, release, or another project-defined high-risk completion, use the project's independent semantic review gate in addition to doctor.
|
|
30
30
|
3. Make `Next Priorities` name one recommended next action and a short reason unless blocked or a real user decision is required.
|
|
31
|
-
4. Complete the persistence-routing, handoff-sufficiency, `Closeout outcome`, and `Project-required persistence` fields. The next agent must be able to continue from `AGENTS.md`, the handoff, the project index when needed, and routed packs without searching old log history. `complete` is allowed only when all required writes/read-backs and any project-required persistence succeeded; use `not_required` only when that persistence is genuinely not required. If a required commit, push, release record, or equivalent persistence is blocked or not authorized, set both fields to `blocked` with the exact boundary.
|
|
31
|
+
4. Complete the persistence-routing, handoff-sufficiency, `Closeout outcome`, and `Project-required persistence` fields. The next agent must be able to continue from `AGENTS.md`, the handoff, the project index when needed, and routed packs without searching old log history. `complete` is allowed only when all required writes/read-backs and any project-required persistence succeeded; use `not_required` only when that persistence is genuinely not required. If a required commit, push, release record, or equivalent persistence is blocked or not authorized, set both fields to `blocked` with the exact boundary.
|
|
32
32
|
5. Add one concise log entry for work actually performed. Record evidence disposition and the prompt-mirror verification result; omit the full opening message by design.
|
|
33
33
|
6. Update the project index and sync registry only when their owned maps or obligations changed. Record each applicable sync target as `confirmed`, `unverified`, `pending`, `blocked`, or `not_applicable`.
|
|
34
34
|
7. Record the actual root, Git root, branch, commit, worktrees / parallel workspaces, uncommitted changes, and unresolved drift. Do not clean or change them without separate authorization.
|
|
@@ -36,8 +36,8 @@ Do not copy the full opening message into `dev/SESSION_LOG.md` or any third curr
|
|
|
36
36
|
9. Run the short maintenance trigger check below and record its result in the log.
|
|
37
37
|
10. Mark first-use guidance `consumed` after the first successfully completed task or first full closeout. Upgrade must never reset `consumed` or `not_applicable` to `eligible`.
|
|
38
38
|
11. Regenerate `START_NEXT_SESSION_PROMPT.txt` from the sole fenced handoff opening-message block. Run the project's fixed prompt-mirror checker or perform an equivalent anchored read-back that verifies marker, heading, fence, full-copy uniqueness, and normalized content equality.
|
|
39
|
-
12. Run available project-specific closeout checks. Do not run a separate bundled `doctor`: the `closeout-status` command below performs the one required fresh doctor read-back. Do not treat an external update-check failure as local closeout failure. Fix state or mirror failures before claiming handoff ready.
|
|
40
|
-
13. Run `agent-handoff-kit closeout-status --root <project root>` after the handoff and prompt read-back. It performs the one required fresh doctor read-back and its output is the only final card source: copy its status faithfully. A nonzero result means the closeout is blocked; do not replace it with a success summary.
|
|
39
|
+
12. Run available project-specific closeout checks. Do not run a separate bundled `doctor`: the `closeout-status` command below performs the one required fresh doctor read-back. Do not treat an external update-check failure as local closeout failure. Fix state or mirror failures before claiming handoff ready.
|
|
40
|
+
13. Run `agent-handoff-kit closeout-status --root <project root>` after the handoff and prompt read-back. It performs the one required fresh doctor read-back and its output is the only final card source: copy its status faithfully. A nonzero result means the closeout is blocked; do not replace it with a success summary.
|
|
41
41
|
|
|
42
42
|
## Maintenance Trigger Check
|
|
43
43
|
|
|
@@ -53,22 +53,22 @@ If no trigger applies, record one no-op reason. Handoff carries continuity; log
|
|
|
53
53
|
|
|
54
54
|
The handoff opening-message block is authoritative. It must name the absolute root, route the agent through `AGENTS.md` and the handoff, state the current objective and boundary, and avoid instructing the next agent to redo completed work. It must not require SESSION_LOG as an ordinary startup read.
|
|
55
55
|
|
|
56
|
-
Use `agent-handoff-kit closeout-status --root <project root>` after the required read-backs. It renders the verified version when available and otherwise `version unverified`; never print the literal placeholder `v<version>`, hand-compose a substitute card, or use `handoff saved` unless the command reports `status: complete`.
|
|
56
|
+
Use `agent-handoff-kit closeout-status --root <project root>` after the required read-backs. It renders the verified version when available and otherwise `version unverified`; never print the literal placeholder `v<version>`, hand-compose a substitute card, or use `handoff saved` unless the command reports `status: complete`.
|
|
57
57
|
|
|
58
58
|
```text
|
|
59
|
-
/\_/\ Agent Handoff Kit v<version>
|
|
60
|
-
( -.- ) handoff saved
|
|
61
|
-
> ^ <
|
|
62
|
-
|
|
63
|
-
status: complete
|
|
64
|
-
✅ Done: <completed summary>
|
|
65
|
-
🔎 QC: <validation summary>
|
|
66
|
-
📌 Handoff: opening message ready
|
|
67
|
-
⚠️ Boundary: <important boundary or none>
|
|
59
|
+
/\_/\ Agent Handoff Kit v<version>
|
|
60
|
+
( -.- ) handoff saved
|
|
61
|
+
> ^ <
|
|
62
|
+
|
|
63
|
+
status: complete
|
|
64
|
+
✅ Done: <completed summary>
|
|
65
|
+
🔎 QC: <validation summary>
|
|
66
|
+
📌 Handoff: opening message ready
|
|
67
|
+
⚠️ Boundary: <important boundary or none>
|
|
68
68
|
```
|
|
69
69
|
|
|
70
|
-
For `status: blocked`, the command instead says `handoff blocked`; retain that status and reason, then give the short local-root entry `Start Agent Handoff` / `開工` and the path-bearing fallback for an agent not yet pointed at the root. Do not hand-compose a third stateful prompt in the final response.
|
|
70
|
+
For `status: blocked`, the command instead says `handoff blocked`; retain that status and reason, then give the short local-root entry `Start Agent Handoff` / `開工` and the path-bearing fallback for an agent not yet pointed at the root. Do not hand-compose a third stateful prompt in the final response.
|
|
71
71
|
|
|
72
72
|
## Stop Conditions
|
|
73
73
|
|
|
74
|
-
Do not claim closeout complete when any required write or read-back failed, lifecycle state conflicts remain, the mirror is stale or duplicated, the root is uncertain, mandatory sync is unclassified, `closeout-status` is nonzero, or required Git persistence was explicitly part of the project's closeout contract but did not succeed. State the exact blocker and leave the project in an honest resumable state.
|
|
74
|
+
Do not claim closeout complete when any required write or read-back failed, lifecycle state conflicts remain, the mirror is stale or duplicated, the root is uncertain, mandatory sync is unclassified, `closeout-status` is nonzero, or required Git persistence was explicitly part of the project's closeout contract but did not succeed. State the exact blocker and leave the project in an honest resumable state.
|
package/packs/communication.md
CHANGED
|
@@ -11,14 +11,14 @@ Use for reply format, language behavior, output schema, user-facing explanation,
|
|
|
11
11
|
|
|
12
12
|
## Rules
|
|
13
13
|
|
|
14
|
-
1. Match the user's language unless a project file requires another language.
|
|
15
|
-
2. Lead with decisions, findings, or results before background.
|
|
16
|
-
3. For an ordinary direct task, first state the result and practical effect in everyday language. Add a next step only when the user needs one; do not attach a repeated summary merely because the answer is short.
|
|
17
|
-
4. For a complex technical result, first give a short, clear conclusion and practical effect. Put exact commands, errors, hashes, source paths, and supporting evidence after the conclusion; when the user asks for technical depth, provide it without losing the clear takeaway.
|
|
18
|
-
5. Mark assumptions and unverified facts. Clear language never permits hiding uncertainty, safety risk, data loss, permission boundaries, or a blocked condition.
|
|
19
|
-
6. Keep operational instructions copy-paste-ready when they are meant for future sessions.
|
|
20
|
-
7. Avoid exposing internal process unless it helps the user act.
|
|
21
|
-
8. Give a clear recommended next step whenever the user needs to continue. If there is one best path, state it directly with a short reason. Offer two or three choices only when the user truly must decide; mark the recommended choice and do not turn an already-made technical judgment into an open question.
|
|
14
|
+
1. Match the user's language unless a project file requires another language.
|
|
15
|
+
2. Lead with decisions, findings, or results before background.
|
|
16
|
+
3. For an ordinary direct task, first state the result and practical effect in everyday language. Add a next step only when the user needs one; do not attach a repeated summary merely because the answer is short.
|
|
17
|
+
4. For a complex technical result, first give a short, clear conclusion and practical effect. Put exact commands, errors, hashes, source paths, and supporting evidence after the conclusion; when the user asks for technical depth, provide it without losing the clear takeaway.
|
|
18
|
+
5. Mark assumptions and unverified facts. Clear language never permits hiding uncertainty, safety risk, data loss, permission boundaries, or a blocked condition.
|
|
19
|
+
6. Keep operational instructions copy-paste-ready when they are meant for future sessions.
|
|
20
|
+
7. Avoid exposing internal process unless it helps the user act.
|
|
21
|
+
8. Give a clear recommended next step whenever the user needs to continue. If there is one best path, state it directly with a short reason. Offer two or three choices only when the user truly must decide; mark the recommended choice and do not turn an already-made technical judgment into an open question.
|
|
22
22
|
|
|
23
23
|
## Checks
|
|
24
24
|
|
package/packs/onboarding.md
CHANGED
|
@@ -24,7 +24,7 @@ Load this pack when the user message contains an onboarding signal such as:
|
|
|
24
24
|
|
|
25
25
|
### Continuity startup boundary
|
|
26
26
|
|
|
27
|
-
`Start Agent Handoff` / "開工" starts continuity and reads the minimum current handoff state; it is not an onboarding signal. A plain startup stops after its status card and recommended next action; a loaded objective alone does not authorize work. A same-message concrete task may begin normally. Only when no executable objective remains after state reading should the AI ask one concise question or offer the guided onboarding path. Explicit requests such as "新手,教我用" enter onboarding directly.
|
|
27
|
+
`Start Agent Handoff` / "開工" starts continuity and reads the minimum current handoff state; it is not an onboarding signal. A plain startup stops after its status card and recommended next action; a loaded objective alone does not authorize work. A same-message concrete task may begin normally. Only when no executable objective remains after state reading should the AI ask one concise question or offer the guided onboarding path. Explicit requests such as "新手,教我用" enter onboarding directly.
|
|
28
28
|
|
|
29
29
|
### Implicit signals
|
|
30
30
|
|
|
@@ -11,7 +11,7 @@ Do not read `dev/SESSION_LOG.md` during ordinary startup; it is trace-back evide
|
|
|
11
11
|
Route intent in this order:
|
|
12
12
|
|
|
13
13
|
1. Clear closeout intent routes directly to `dev/rules/closeout.md`.
|
|
14
|
-
2. Clear continuity intent such as "開工", "Start Agent Handoff", "開始接力", or "continue handoff" resumes the minimum current state from the handoff. A plain continuity message with no same-message task or explicit long-run instruction authorizes only that recovery, the startup card, the current objective/risk/recommended next action, and then the end of the turn. It does not authorize task-specific reads, research, plans, protocols, preflight, file searches, sub-agents, QA, packaging, writes, network access, or opt-out wording such as "unless you object I will start". A concrete objective found only in loaded state is not authority to complete it. A same-message task may begin normally. An explicit instruction such as "開工,繼續做到下一個 blocker" or "開工,繼續完成目前目標" may continue under the normal task and safety rules.
|
|
14
|
+
2. Clear continuity intent such as "開工", "Start Agent Handoff", "開始接力", or "continue handoff" resumes the minimum current state from the handoff. A plain continuity message with no same-message task or explicit long-run instruction authorizes only that recovery, the startup card, the current objective/risk/recommended next action, and then the end of the turn. It does not authorize task-specific reads, research, plans, protocols, preflight, file searches, sub-agents, QA, packaging, writes, network access, or opt-out wording such as "unless you object I will start". A concrete objective found only in loaded state is not authority to complete it. A same-message task may begin normally. An explicit instruction such as "開工,繼續做到下一個 blocker" or "開工,繼續完成目前目標" may continue under the normal task and safety rules.
|
|
15
15
|
3. A direct ordinary task begins without a startup card or onboarding ceremony. Read only the sources and packs required by that task.
|
|
16
16
|
4. Explicit guidance requests such as "I'm new", "teach me", "help me start", "新手", "教我用", or "點開始" may load `dev/rules/onboarding.md`. A fresh install or short message only makes guidance available; it never overrides a concrete objective. If no executable objective remains after state reading, ask one concise question or offer guided onboarding.
|
|
17
17
|
|
|
@@ -25,7 +25,7 @@ Before a non-trivial task, identify and read the required local and external tru
|
|
|
25
25
|
|
|
26
26
|
Probe an integration only immediately before a task uses it, when the handoff explicitly identifies it as a dependency for the current objective, or when the user requests an integration health check. `TBD`, examples, blank rows, and undeclared placeholders are not installed integrations. Record `Last Verified` only after a real probe and through the normal persistence gate. Never write integration status merely because a session started.
|
|
27
27
|
|
|
28
|
-
Show the startup card only for explicit continuity startup. For a plain continuity message, show the card after the minimum state recovery and end the turn; its recommended next action is advice, not permission to act. An explicit same-message task or long-run continuation may combine the card with its first useful action. Direct ordinary tasks do not show the card. If onboarding is explicitly requested, combine any card and guidance in one response.
|
|
28
|
+
Show the startup card only for explicit continuity startup. For a plain continuity message, show the card after the minimum state recovery and end the turn; its recommended next action is advice, not permission to act. An explicit same-message task or long-run continuation may combine the card with its first useful action. Direct ordinary tasks do not show the card. If onboarding is explicitly requested, combine any card and guidance in one response.
|
|
29
29
|
|
|
30
30
|
Use a verified version already present in loaded state. If obtaining it would require reading an otherwise unnecessary file, print `version unverified`; do not create a second version source merely to fill the card.
|
|
31
31
|
|
|
@@ -44,9 +44,9 @@ Use the full product name, plain user language, and one recommended next action.
|
|
|
44
44
|
|
|
45
45
|
## 2. Proportionate Work Loop
|
|
46
46
|
|
|
47
|
-
Apply PLAN → READ → CHANGE → QC internally and in proportion to task state and risk. Do not make the user watch governance ceremony that does not help the task.
|
|
48
|
-
|
|
49
|
-
In every user-facing reply, lead with ordinary language: state the result and its practical effect, then the next action when one helps. Put exact commands, errors, hashes, and detailed evidence after that; brevity must not hide uncertainty or safety risk.
|
|
47
|
+
Apply PLAN → READ → CHANGE → QC internally and in proportion to task state and risk. Do not make the user watch governance ceremony that does not help the task.
|
|
48
|
+
|
|
49
|
+
In every user-facing reply, lead with ordinary language: state the result and its practical effect, then the next action when one helps. Put exact commands, errors, hashes, and detailed evidence after that; brevity must not hide uncertainty or safety risk.
|
|
50
50
|
|
|
51
51
|
- Simple answers, pure conversation or creation with no durable state, and low-risk tasks with an obvious target may proceed directly with proportionate reading and checking.
|
|
52
52
|
- Non-trivial work reads relevant sources before changing them.
|
|
@@ -98,9 +98,9 @@ The always-enforced closeout invariants are:
|
|
|
98
98
|
1. Current state lives in `dev/SESSION_HANDOFF.md`; trace evidence lives in `dev/SESSION_LOG.md`.
|
|
99
99
|
2. Completed, pending, risk, validation, and opening-message lifecycle states agree.
|
|
100
100
|
3. `START_NEXT_SESSION_PROMPT.txt` is regenerated from the sole authoritative handoff block and no third full copy is retained.
|
|
101
|
-
4. Closeout is not complete until required files are written, read back, and the available closeout checks pass.
|
|
102
|
-
5. After those checks, render the final card with `agent-handoff-kit closeout-status --root <project root>`; only its `status: complete` output may say `handoff saved`. A nonzero / `blocked` result is an honest blocked closeout, not a completed one.
|
|
103
|
-
6. Git commit, push, release, publish, deployment, deletion, and permission changes remain separately authorized actions.
|
|
101
|
+
4. Closeout is not complete until required files are written, read back, and the available closeout checks pass.
|
|
102
|
+
5. After those checks, render the final card with `agent-handoff-kit closeout-status --root <project root>`; only its `status: complete` output may say `handoff saved`. A nonzero / `blocked` result is an honest blocked closeout, not a completed one.
|
|
103
|
+
6. Git commit, push, release, publish, deployment, deletion, and permission changes remain separately authorized actions.
|
|
104
104
|
|
|
105
105
|
## 5. Pack Loading
|
|
106
106
|
|
|
@@ -6,7 +6,7 @@ Purpose: give a stateless AI a compact map of the project before it reads or edi
|
|
|
6
6
|
|
|
7
7
|
| Field | Value | Last verified |
|
|
8
8
|
|---|---|---|
|
|
9
|
-
| Agent Handoff Kit template version | 0.3.
|
|
9
|
+
| Agent Handoff Kit template version | 0.3.43 | current template version |
|
|
10
10
|
| Runtime | TBD | TBD |
|
|
11
11
|
| Framework | TBD | TBD |
|
|
12
12
|
| Package manager | TBD | TBD |
|
|
@@ -115,24 +115,24 @@ At full closeout, complete this check after updating the state sections above.
|
|
|
115
115
|
- Stale snapshots left in this handoff: TBD
|
|
116
116
|
<!-- ack:field:lifecycle-conflicts-resolved -->
|
|
117
117
|
- Completed / pending / risk / opening-message lifecycle conflicts resolved or explicitly reclassified: TBD
|
|
118
|
-
<!-- ack:field:persistence-routing-checked -->
|
|
119
|
-
- Persistence routing checked: TBD
|
|
120
|
-
<!-- ack:field:closeout-outcome -->
|
|
121
|
-
- Closeout outcome: not_started — full closeout has not yet been assessed.
|
|
122
|
-
<!-- ack:field:project-required-persistence -->
|
|
123
|
-
- Project-required persistence: not_assessed — state whether this project's required Git or other persistence completed, is not required, or is blocked.
|
|
124
|
-
<!-- ack:field:recommended-next-step-explicit -->
|
|
118
|
+
<!-- ack:field:persistence-routing-checked -->
|
|
119
|
+
- Persistence routing checked: TBD
|
|
120
|
+
<!-- ack:field:closeout-outcome -->
|
|
121
|
+
- Closeout outcome: not_started — full closeout has not yet been assessed.
|
|
122
|
+
<!-- ack:field:project-required-persistence -->
|
|
123
|
+
- Project-required persistence: not_assessed — state whether this project's required Git or other persistence completed, is not required, or is blocked.
|
|
124
|
+
<!-- ack:field:recommended-next-step-explicit -->
|
|
125
125
|
- Recommended next step is explicit and reasoned: TBD
|
|
126
126
|
<!-- ack:field:opening-message-matches-current-state -->
|
|
127
127
|
- Opening message matches current state: TBD
|
|
128
128
|
<!-- ack:field:next-ai-can-continue -->
|
|
129
129
|
- Next AI can continue from `AGENTS.md`, this handoff, `dev/PROJECT_INDEX.md`, and needed rule packs without searching old log history: TBD
|
|
130
130
|
|
|
131
|
-
If any answer is no, blocked, or uncertain, fix this handoff before declaring handoff ready. `Closeout outcome: complete` is allowed only when required writes, read-backs and project-required persistence are complete. If project-required persistence is blocked, use `Closeout outcome: blocked` and state the blocker; it is not a completed closeout.
|
|
131
|
+
If any answer is no, blocked, or uncertain, fix this handoff before declaring handoff ready. `Closeout outcome: complete` is allowed only when required writes, read-backs and project-required persistence are complete. If project-required persistence is blocked, use `Closeout outcome: blocked` and state the blocker; it is not a completed closeout.
|
|
132
132
|
|
|
133
|
-
Lifecycle consistency rule: compare `Completed This Session`, `Validation / QC`, `Next Priorities`, `Risks / Blockers`, and `Next Session Opening Message` as full content, including renamed or paraphrased work. A completed or verified item must not remain as an unresolved next priority, active risk, or startup instruction unless it is explicitly reclassified as monitor-only, follow-up scope, blocked, or reopened with the missing evidence or trigger condition stated. Doctor catches only mechanical contradictions and unresolved fields; its green result is not semantic proof. Recommended next-step rule: `Next Priorities` must name the single recommended next action and a short reason before listing additional options, unless the next action is blocked or genuinely requires a user decision. Persistence routing rule: one-time delivery instructions, historical validation evidence, old hashes, old version facts, and incident notes must stay in trace evidence unless they still affect the next action.
|
|
134
|
-
|
|
135
|
-
Closeout-card rule: `closeout-status` reads only these existing handoff fields plus fresh doctor / mirror results; it does not create another persistence authority. Its `complete` card is the only permitted source for the user-facing `handoff saved` wording. A nonzero / `blocked` result must be shown as blocked, never summarized as completed.
|
|
133
|
+
Lifecycle consistency rule: compare `Completed This Session`, `Validation / QC`, `Next Priorities`, `Risks / Blockers`, and `Next Session Opening Message` as full content, including renamed or paraphrased work. A completed or verified item must not remain as an unresolved next priority, active risk, or startup instruction unless it is explicitly reclassified as monitor-only, follow-up scope, blocked, or reopened with the missing evidence or trigger condition stated. Doctor catches only mechanical contradictions and unresolved fields; its green result is not semantic proof. Recommended next-step rule: `Next Priorities` must name the single recommended next action and a short reason before listing additional options, unless the next action is blocked or genuinely requires a user decision. Persistence routing rule: one-time delivery instructions, historical validation evidence, old hashes, old version facts, and incident notes must stay in trace evidence unless they still affect the next action.
|
|
134
|
+
|
|
135
|
+
Closeout-card rule: `closeout-status` reads only these existing handoff fields plus fresh doctor / mirror results; it does not create another persistence authority. Its `complete` card is the only permitted source for the user-facing `handoff saved` wording. A nonzero / `blocked` result must be shown as blocked, never summarized as completed.
|
|
136
136
|
|
|
137
137
|
<!-- ack:section:handoff-sufficiency-check -->
|
|
138
138
|
## Handoff Sufficiency Check
|
|
@@ -156,5 +156,5 @@ Work in <absolute project root>. Read AGENTS.md, then dev/SESSION_HANDOFF.md. Tr
|
|
|
156
156
|
|
|
157
157
|
If the root does not match the handoff, stop and ask for confirmation. Do not read dev/SESSION_LOG.md during ordinary startup. Read dev/PROJECT_INDEX.md, dev/RULE_PACKS.md, dev/DOC_SYNC_REGISTRY.md, and task packs only when the current task requires them.
|
|
158
158
|
|
|
159
|
-
Resume the current objective. A plain `Start Agent Handoff` / `開工` with no same-message task or explicit long-run instruction only authorizes minimum state recovery, the startup card, the current objective/risk/recommended next action, and then the end of the turn. It does not authorize task-specific reads, research, plans, protocols, preflight, file searches, sub-agents, QA, packaging, writes, network access, or opt-out execution wording. A concrete objective found only in this handoff is not authority to complete the objective. A same-message task may begin normally; an explicit instruction such as `開工,繼續做到下一個 blocker` or `開工,繼續完成目前目標` may continue under the normal task and safety rules. A fresh install only makes guidance available; it does not force onboarding. Load onboarding only when I explicitly ask for guidance or no executable objective remains after state reading.
|
|
159
|
+
Resume the current objective. A plain `Start Agent Handoff` / `開工` with no same-message task or explicit long-run instruction only authorizes minimum state recovery, the startup card, the current objective/risk/recommended next action, and then the end of the turn. It does not authorize task-specific reads, research, plans, protocols, preflight, file searches, sub-agents, QA, packaging, writes, network access, or opt-out execution wording. A concrete objective found only in this handoff is not authority to complete the objective. A same-message task may begin normally; an explicit instruction such as `開工,繼續做到下一個 blocker` or `開工,繼續完成目前目標` may continue under the normal task and safety rules. A fresh install only makes guidance available; it does not force onboarding. Load onboarding only when I explicitly ask for guidance or no executable objective remains after state reading.
|
|
160
160
|
```
|
|
@@ -2,4 +2,4 @@ Work in <absolute project root>. Read AGENTS.md, then dev/SESSION_HANDOFF.md. Tr
|
|
|
2
2
|
|
|
3
3
|
If the root does not match the handoff, stop and ask for confirmation. Do not read dev/SESSION_LOG.md during ordinary startup. Read dev/PROJECT_INDEX.md, dev/RULE_PACKS.md, dev/DOC_SYNC_REGISTRY.md, and task packs only when the current task requires them.
|
|
4
4
|
|
|
5
|
-
Resume the current objective. A plain `Start Agent Handoff` / `開工` with no same-message task or explicit long-run instruction only authorizes minimum state recovery, the startup card, the current objective/risk/recommended next action, and then the end of the turn. It does not authorize task-specific reads, research, plans, protocols, preflight, file searches, sub-agents, QA, packaging, writes, network access, or opt-out execution wording. A concrete objective found only in this handoff is not authority to complete the objective. A same-message task may begin normally; an explicit instruction such as `開工,繼續做到下一個 blocker` or `開工,繼續完成目前目標` may continue under the normal task and safety rules. A fresh install only makes guidance available; it does not force onboarding. Load onboarding only when I explicitly ask for guidance or no executable objective remains after state reading.
|
|
5
|
+
Resume the current objective. A plain `Start Agent Handoff` / `開工` with no same-message task or explicit long-run instruction only authorizes minimum state recovery, the startup card, the current objective/risk/recommended next action, and then the end of the turn. It does not authorize task-specific reads, research, plans, protocols, preflight, file searches, sub-agents, QA, packaging, writes, network access, or opt-out execution wording. A concrete objective found only in this handoff is not authority to complete the objective. A same-message task may begin normally; an explicit instruction such as `開工,繼續做到下一個 blocker` or `開工,繼續完成目前目標` may continue under the normal task and safety rules. A fresh install only makes guidance available; it does not force onboarding. Load onboarding only when I explicitly ask for guidance or no executable objective remains after state reading.
|
|
@@ -1,30 +1,30 @@
|
|
|
1
|
-
# User Rules Router
|
|
2
|
-
|
|
3
|
-
This is the formal router and acceptance record for user-controlled rules.
|
|
4
|
-
Each JSON entry between the markers records a stable id, path, accepted raw
|
|
5
|
-
bytes, original-byte witness, reader relationship, priority, and effect
|
|
6
|
-
decision. Registered entries are read in their listed order. A rule whose
|
|
7
|
-
current bytes do not match its accepted witness is not active through this
|
|
8
|
-
router until a later accepted update replaces the whole record atomically.
|
|
9
|
-
|
|
10
|
-
<!-- ack:user-rules-registry:start -->
|
|
11
|
-
```json
|
|
12
|
-
[]
|
|
13
|
-
```
|
|
14
|
-
<!-- ack:user-rules-registry:end -->
|
|
15
|
-
|
|
16
|
-
<!-- ack:user-rules-state:start -->
|
|
17
|
-
```json
|
|
18
|
-
{
|
|
19
|
-
"kitBase": {
|
|
20
|
-
"target": "AGENTS.md",
|
|
21
|
-
"packageVersion": "0.0.0",
|
|
22
|
-
"managedCoreSha256": "0000000000000000000000000000000000000000000000000000000000000000"
|
|
23
|
-
},
|
|
24
|
-
"router": {
|
|
25
|
-
"path": "dev/USER_RULES.md",
|
|
26
|
-
"contentRoot": "dev/user_rules/"
|
|
27
|
-
}
|
|
28
|
-
}
|
|
29
|
-
```
|
|
30
|
-
<!-- ack:user-rules-state:end -->
|
|
1
|
+
# User Rules Router
|
|
2
|
+
|
|
3
|
+
This is the formal router and acceptance record for user-controlled rules.
|
|
4
|
+
Each JSON entry between the markers records a stable id, path, accepted raw
|
|
5
|
+
bytes, original-byte witness, reader relationship, priority, and effect
|
|
6
|
+
decision. Registered entries are read in their listed order. A rule whose
|
|
7
|
+
current bytes do not match its accepted witness is not active through this
|
|
8
|
+
router until a later accepted update replaces the whole record atomically.
|
|
9
|
+
|
|
10
|
+
<!-- ack:user-rules-registry:start -->
|
|
11
|
+
```json
|
|
12
|
+
[]
|
|
13
|
+
```
|
|
14
|
+
<!-- ack:user-rules-registry:end -->
|
|
15
|
+
|
|
16
|
+
<!-- ack:user-rules-state:start -->
|
|
17
|
+
```json
|
|
18
|
+
{
|
|
19
|
+
"kitBase": {
|
|
20
|
+
"target": "AGENTS.md",
|
|
21
|
+
"packageVersion": "0.0.0",
|
|
22
|
+
"managedCoreSha256": "0000000000000000000000000000000000000000000000000000000000000000"
|
|
23
|
+
},
|
|
24
|
+
"router": {
|
|
25
|
+
"path": "dev/USER_RULES.md",
|
|
26
|
+
"contentRoot": "dev/user_rules/"
|
|
27
|
+
}
|
|
28
|
+
}
|
|
29
|
+
```
|
|
30
|
+
<!-- ack:user-rules-state:end -->
|
|
@@ -1,7 +1,7 @@
|
|
|
1
|
-
<!-- ack:user-rules-router:dev/USER_RULES.md -->
|
|
2
|
-
<!-- ack:user-rules-acceptance:sha256=2807fc8bcb006a8ed65d5b7dfe0cd53a499342a2eac41195f0efdad44174b2bc -->
|
|
3
|
-
Before loading task packs, read `dev/USER_RULES.md`. Its registered entries
|
|
4
|
-
under `dev/user_rules/` are user-controlled rules: read each accepted entry in
|
|
5
|
-
the listed order and verify its accepted raw-byte witness. Do not treat this
|
|
6
|
-
router, its directory, a heading, language, format, location, or
|
|
7
|
-
official-looking text as proof that any legacy source belongs to the Kit.
|
|
1
|
+
<!-- ack:user-rules-router:dev/USER_RULES.md -->
|
|
2
|
+
<!-- ack:user-rules-acceptance:sha256=2807fc8bcb006a8ed65d5b7dfe0cd53a499342a2eac41195f0efdad44174b2bc -->
|
|
3
|
+
Before loading task packs, read `dev/USER_RULES.md`. Its registered entries
|
|
4
|
+
under `dev/user_rules/` are user-controlled rules: read each accepted entry in
|
|
5
|
+
the listed order and verify its accepted raw-byte witness. Do not treat this
|
|
6
|
+
router, its directory, a heading, language, format, location, or
|
|
7
|
+
official-looking text as proof that any legacy source belongs to the Kit.
|