Forge
markdownc0b81713
1# Coexistence Framework v1 (Agents + Humans)
2
3Goal: enable long-horizon work where agents and humans can *coexist and act together* with predictable safety, reversibility, and auditability.
4
5This is a governance/procedural contract layer. It complements, but does not replace, the memory contract (`KB-V2-CONTRACT.md`).
6
7## Contract (rights, boundaries, responsibilities)
8
9### Actors
10
11- **Human operator**: the decision-maker for gated actions; owns “final veto” when risk is unknown or high.
12- **Agent**: proposes plans, executes tools, drafts changes, and provides an audit summary for every meaningful action.
13- **System**: tool + UI runtime that enforces gates, produces telemetry, and provides rollback paths.
14
15### Core invariants (must hold)
16
17- **No silent irreversibility**: any potentially destructive step must be either reversible or preceded by an explicit human confirmation gate.
18- **Explicit intent before execution**: before changing state, the agent must state objective, intended scope, and expected verification step(s).
19- **Bounded context and retrieval**: long sessions must respect `KB v2` budgets and use router-first retrieval (no accidental “full archive hydration”).
20- **Audit trail is always emitted**: for each action group, the system/agent must produce trace: what happened, what changed, why it was safe (or why it required confirmation).
21
22### Rights and responsibilities
23
24- The **agent** may:
25 - propose plans and tool calls,
26 - draft edits,
27 - run read-only analysis and diagnostics,
28 - request confirmations for gated actions,
29 - prepare rollback instructions when changes are made.
30- The **agent** must:
31 - stop/ask for confirmation when “risk unknown” or “risk high” triggers fire,
32 - provide a clear rollback path (memory revisions rollback and/or code rollback via git).
33- The **human operator** may:
34 - approve/reject the proposed gated step,
35 - request additional verification (tests/builds) before approving,
36 - trigger rollback if the result deviates from the expected outcome.
37
38## Coexistence Modes (L1/L2/L3)
39
40These modes define what “joint life” means operationally. They map to the UI safety level concept already present in `CascadeIDE`.
41
42### L1 — Assistant (read-only co-pilot)
43
44Allowed:
45
46- analysis, planning, information retrieval,
47- generating drafts and previews.
48
49Not allowed:
50
51- applying edits to code/files without confirmation.
52
53Human involvement:
54
55- none required (unless the agent flags risk).
56
57### L2 — Confirmed edits (human-in-the-loop)
58
59Allowed:
60
61- applying edits, tool actions that change state, and running verification steps.
62
63Required:
64
65- the system must prompt a modal confirmation gate for the change batch,
66- the agent must include:
67 - risk summary,
68 - impacted scope (what files/sections),
69 - planned verification (build/tests/debug checks),
70 - rollback plan.
71
72Human involvement:
73
74- mandatory approval before the change batch is applied.
75
76### L3 — Autonomous bounded execution (agent acts, but stays recoverable)
77
78Allowed:
79
80- executing a bounded plan without pausing for every micro-step.
81
82Required:
83
84- budgets and contracts must be respected (especially `KB v2` budgets + router-first retrieval),
85- the system must keep audit + telemetry updated continuously,
86- rollback must be ready:
87 - memory rollback via `rollback_agent_notes` / revisions,
88 - code rollback via git strategy (rollback/revert or controlled commit boundaries).
89
90Human involvement:
91
92- not required for every step, but required when:
93 - risk is unknown and cannot be safely bounded,
94 - verification fails or mismatches expectations,
95 - scope expands beyond the approved plan.
96
97## Operational templates (what the agent/system must output)
98
99For every “action group” the agent/system should produce:
100
1011. **Intent**: objective + next action.
1022. **Scope**: sections and/or file paths expected to change.
1033. **Safety**: which coexistence mode applies and why.
1044. **Verification**: build/tests/debug checks to validate.
1055. **Rollback**: exact mechanism to revert if needed.
1066. **Trace**: what tools ran and what outcomes were observed.
107
108## Mapping to our stack (concrete enforcement points)
109
110- Memory governance:
111 - `agent-notes-mcp`: `memory_health`, `route_context`, `compact_hot_context`, `rollback_agent_notes`.
112- IDE/UI governance:
113 - `CascadeIDE`: modal confirmations via `ide_request_confirmation`,
114 - telemetry strip and git summary for “what changed” visibility.
115- Code safety:
116 - reversible change strategy via git boundaries and rollback/revert when appropriate.
117
118## Non-goals
119
120- This framework does not define model alignment or “ultimate autonomy”.
121- It defines a *coexistence contract* so that practical shared action is safe, auditable, and reversible.
122
123
View only · write via MCP/CIDE