Merge pull request #1132 from trek-e/feat/1m-context-awareness-1086
This commit is contained in:
@@ -65,6 +65,7 @@ function loadConfig(cwd) {
|
|||||||
parallelization: true,
|
parallelization: true,
|
||||||
brave_search: false,
|
brave_search: false,
|
||||||
resolve_model_ids: false, // when true, resolve aliases (opus/sonnet/haiku) to full model IDs
|
resolve_model_ids: false, // when true, resolve aliases (opus/sonnet/haiku) to full model IDs
|
||||||
|
context_window: 200000, // default 200k; set to 1000000 for Opus/Sonnet 4.6 1M models
|
||||||
};
|
};
|
||||||
|
|
||||||
try {
|
try {
|
||||||
@@ -108,6 +109,7 @@ function loadConfig(cwd) {
|
|||||||
parallelization,
|
parallelization,
|
||||||
brave_search: get('brave_search') ?? defaults.brave_search,
|
brave_search: get('brave_search') ?? defaults.brave_search,
|
||||||
resolve_model_ids: get('resolve_model_ids') ?? defaults.resolve_model_ids,
|
resolve_model_ids: get('resolve_model_ids') ?? defaults.resolve_model_ids,
|
||||||
|
context_window: get('context_window') ?? defaults.context_window,
|
||||||
model_overrides: parsed.model_overrides || null,
|
model_overrides: parsed.model_overrides || null,
|
||||||
};
|
};
|
||||||
} catch {
|
} catch {
|
||||||
|
|||||||
@@ -31,6 +31,7 @@ function cmdInitExecutePhase(cwd, phase, raw) {
|
|||||||
// Config flags
|
// Config flags
|
||||||
commit_docs: config.commit_docs,
|
commit_docs: config.commit_docs,
|
||||||
parallelization: config.parallelization,
|
parallelization: config.parallelization,
|
||||||
|
context_window: config.context_window,
|
||||||
branching_strategy: config.branching_strategy,
|
branching_strategy: config.branching_strategy,
|
||||||
phase_branch_template: config.phase_branch_template,
|
phase_branch_template: config.phase_branch_template,
|
||||||
milestone_branch_template: config.milestone_branch_template,
|
milestone_branch_template: config.milestone_branch_template,
|
||||||
|
|||||||
@@ -191,8 +191,9 @@ Execute each wave in sequence. Within a wave: parallel if `PARALLELIZATION=true`
|
|||||||
|
|
||||||
2. **Spawn executor agents:**
|
2. **Spawn executor agents:**
|
||||||
|
|
||||||
Pass paths only — executors read files themselves with their fresh 200k context.
|
Pass paths only — executors read files themselves with their fresh context window.
|
||||||
This keeps orchestrator context lean (~10-15%).
|
For 200k models, this keeps orchestrator context lean (~10-15%).
|
||||||
|
For 1M+ models (Opus 4.6, Sonnet 4.6), richer context can be passed directly.
|
||||||
|
|
||||||
```
|
```
|
||||||
Task(
|
Task(
|
||||||
@@ -652,7 +653,13 @@ Only suggest the commands listed above. Do not invent or hallucinate command nam
|
|||||||
</process>
|
</process>
|
||||||
|
|
||||||
<context_efficiency>
|
<context_efficiency>
|
||||||
Orchestrator: ~10-15% context. Subagents: fresh 200k each. No polling (Task blocks). No context bleed.
|
Orchestrator: ~10-15% context for 200k windows, can use more for 1M+ windows.
|
||||||
|
Subagents: fresh context each (200k-1M depending on model). No polling (Task blocks). No context bleed.
|
||||||
|
|
||||||
|
For 1M+ context models, consider:
|
||||||
|
- Passing richer context (code snippets, dependency outputs) directly to executors instead of just file paths
|
||||||
|
- Running small phases (≤3 plans, no dependencies) inline without subagent spawning overhead
|
||||||
|
- Relaxing /clear recommendations — context rot onset is much further out with 5x window
|
||||||
</context_efficiency>
|
</context_efficiency>
|
||||||
|
|
||||||
<failure_handling>
|
<failure_handling>
|
||||||
|
|||||||
Reference in New Issue
Block a user