You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit cc14c98
Browse filesBrowse the repository at this point in the historyBrowse files
Copy file name to clipboardExpand all lines: README.md
+85-22Lines changed: 85 additions & 22 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -12,19 +12,20 @@ It is **library-first** (the CLI is a thin shell over the same `Council` you imp
12
12
returns **structured results** (per-model latency, token usage, and error capture), and is
13
13
**partial-failure resilient** — one provider erroring never aborts the run. Keys are
14
14
**bring-your-own**, referenced by environment-variable *name* only — never stored or
15
-
logged. It ships four modes: **synthesize** (merge answers into one), **raw** (no merge),
15
+
logged. Published v1.1 ships five modes: **synthesize** (merge answers into one), **raw** (no merge),
16
16
**debate** (multi-round, members revise after seeing peers' anonymized answers), and
17
-
**adversarial** (propose → refute → verdict). conclave is intentionally lightweight — a
18
-
small council primitive, not an agent framework.
17
+
**adversarial** (propose → refute → verdict), and **vote** (fixed-choice tally). This source
18
+
branch also implements the unreleased **elite** quality-first claim-audit and revision mode.
19
+
conclave is intentionally lightweight — a small council primitive, not an agent framework.
19
20
20
-
**The v1.1 wedge — the auditable council.** Every run also yields **a multi-model council
21
-
verdict you can act on — structured, scored for agreement, fully auditable**: a
21
+
**The v1.1 wedge — the execution-traceable council.** Decision/review synthesis runs can yield
22
+
**a multi-model council verdict you can inspect — structured, scored for agreement, and
23
+
execution-traceable**: a
22
24
`CouncilVerdict` exposing agreement, `conflicts`, `minority_reports`, and `provider_votes`;
23
25
a deterministic `consensus_score` (arithmetic over the model's clustering, *never* an
24
26
LLM-emitted number); and a redacted `ModelHarnessManifest` recording how the run executed and
25
27
which model produced the disagreement analysis. The verdict is **default-on**, and the manifest
26
-
rides on **every** result — for all five modes (`synthesize`, `raw`, `debate`, `adversarial`,
27
-
`vote`), not just `ask`. A constrained-choice **`vote` mode** (`--mode vote --choices ...`) also
28
+
rides on **every** released-mode result; source-only Elite results carry it too. A constrained-choice **`vote` mode** (`--mode vote --choices ...`) also
28
29
shipped in v1.1 (CAC-09 / #3) — distinct from the verdict's `provider_votes`, which score
29
30
free-form agreement rather than tally a fixed ballot.
30
31
@@ -125,17 +126,25 @@ conclave ask "Defend event sourcing for this ledger." \
125
126
conclave ask "Which datastore for this workload?" \
0 commit comments