prepare_context
Generates a token-budgeted context for coding tasks by analyzing the task description to extract key files, symbols, and hotspots in one call.
Instructions
The recommended tool for coding tasks. Give it your task and get back a token-budgeted context with the right files, symbols, and hotspots — all in one call. Proven +18.6% file prediction improvement (p=0.049*, n=45). 95% helpful rate. Use this instead of calling index_repo → focus → blast_radius manually.
task: describe what you're working on. Two modes are auto-selected:
- PR/commit titles ("Merge pull request #123 from org/fix-auth-bug",
"fix: prevent null pointer in handler", "Fix teardown callbacks (#5928)")
→ keyword extraction from branch name → per-keyword symbol focus → KEY FILES list
→ proven +7% file prediction improvement on real PRs (canonical n=159, p=0.035*)
- General coding tasks ("add pagination to user list", "refactor database layer")
→ fuzzy symbol search → overview fallback if no match
task_type: optional hint — "changelocal" forces keyword-extraction path regardless
of task format; also accepts "debug", "feature", "refactor", "review"
max_tokens: total token budget for the response (default 6000)
exclude_dirs: comma-separated directory prefixes to skip
baseline_predicted_files: optional list of files already predicted by the model
(for adaptive injection). Two skip conditions:
1. If len(baseline) ≥ 3 → returns "" (model is highly confident with 3+ predictions;
any context disagrees more than it helps). Evidence: falcon bl=1.000, 3 correct preds
→ av2 without this guard injected anyway → F1 1.0→0.5 (commit 988960b/d4eb3c8).
2. If overlap(baseline ∩ KEY FILES) ≥ 50% → returns "" (model already knows the files).
Otherwise: returns full context (model needs the structural graph bridge).
Bench (canonical): python3 -m bench.changelocal.analyze --canonical --conditions baseline,tempograph_adaptive
Canonical result (n=159 Python+JS): +6.9% F1 (p=0.035*). Cost: 2× inference for ~37% of tasks.
precision_filter: if True, skip context when >4 key files are found (topic too broad).
Canonical bench: python3 -m bench.changelocal.analyze --canonical --conditions baseline,tempograph_precision
Canonical result (n=159 Python+JS): +3.7% F1 (p=0.21, ns). Default False (plain tempograph = +6.0%
outperforms precision_filter on canonical corpus). Enable only for high-baseline repos.
definition_first: if True, when a keyword produces too-broad focus (>10 files) and no path match,
fall back to the *defining file* of the top-ranked symbol (requires score≥10 and ≤2 defining files).
Handles "redirect" → flask/helpers.py instead of injecting nothing.
Default True (enabled).
output_format: "text" (default) or "json" for structured response
Returns: overview summary + focused context + KEY FILES + hotspot warnings,
all within the token budget. JSON format adds `key_files` (parsed list) and `injected` (bool).Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| repo_path | No | /demo | |
| task | No | ||
| task_type | No | ||
| max_tokens | No | ||
| exclude_dirs | No | ||
| baseline_predicted_files | No | ||
| precision_filter | No | ||
| definition_first | No | ||
| output_format | No | text |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |