fix(stage1-part2): give Claude B1-B5 workers localdocs tool (refs #2)

The Claude Part_2 domain workers (Stage_B_B1..B5) had use_tools: [] and
relied entirely on preflight injecting stage1_tmp/task_c_bo/domain_slices/
B{n}.json. In the failing run the executed A0 wrote full-name slices
(B1_Money_Successor.json ...) while preflight expected short names
(B1.json), so nothing was injected and the tool-less workers emitted
tool-call syntax as plain text (<mcp_tool_call>/<function=read_file>) and
produced FAILED/empty output.

The current v.7 A0 already writes short names matching preflight, so the
naming mismatch itself is resolved in this file. This change adds
use_tools: ['localdocs'] (already declared on the stage) so the workers can
read their slice directly if preflight ever misses again — matching the
proven Codex worker design and removing the single point of failure.

Note: domain slices are 255-300KB (~65-90K tokens); llm_bridge caps tool/
injected content at 50K tokens, so slice compaction in A0 is still needed
for full-fidelity output quality.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-07-22 10:37:08 +09:00
co-authored by Claude Opus 4.8
parent d96d6edfd1
commit 4279fc70ab
@@ -1505,7 +1505,7 @@ Agent:
llm_reasoning: high llm_reasoning: high
llm_verbosity: low llm_verbosity: low
max_iterations: 2 max_iterations: 2
use_tools: [] use_tools: ["localdocs"]
cache_control: cache_control:
mode: auto mode: auto
ttl: 1h ttl: 1h
@@ -1758,7 +1758,7 @@ Agent:
llm_reasoning: high llm_reasoning: high
llm_verbosity: low llm_verbosity: low
max_iterations: 2 max_iterations: 2
use_tools: [] use_tools: ["localdocs"]
cache_control: cache_control:
mode: auto mode: auto
ttl: 1h ttl: 1h
@@ -2017,7 +2017,7 @@ Agent:
llm_reasoning: high llm_reasoning: high
llm_verbosity: low llm_verbosity: low
max_iterations: 2 max_iterations: 2
use_tools: [] use_tools: ["localdocs"]
cache_control: cache_control:
mode: auto mode: auto
ttl: 1h ttl: 1h
@@ -2279,7 +2279,7 @@ Agent:
llm_reasoning: high llm_reasoning: high
llm_verbosity: low llm_verbosity: low
max_iterations: 2 max_iterations: 2
use_tools: [] use_tools: ["localdocs"]
cache_control: cache_control:
mode: auto mode: auto
ttl: 1h ttl: 1h
@@ -2536,7 +2536,7 @@ Agent:
llm_reasoning: high llm_reasoning: high
llm_verbosity: low llm_verbosity: low
max_iterations: 2 max_iterations: 2
use_tools: [] use_tools: ["localdocs"]
cache_control: cache_control:
mode: auto mode: auto
ttl: 1h ttl: 1h